From 0ca3b1b7b9652875861eaa24ae2c514771c2750e Mon Sep 17 00:00:00 2001 From: Igor Grinberg Date: Sun, 24 Feb 2019 11:20:02 +0200 Subject: [PATCH 001/255] habanalabs: add new device CPU boot status This patch adds a definition of a new status in the device CPU boot stages and add the handling of the new status. Signed-off-by: Igor Grinberg Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 5 +++++ drivers/misc/habanalabs/include/hl_boot_if.h | 3 ++- 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index ea979ebd62fb..0185f11c5577 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2550,6 +2550,11 @@ static int goya_init_cpu(struct hl_device *hdev, u32 cpu_timeout) "ARM status %d - DDR initialization failed\n", status); break; + case CPU_BOOT_STATUS_UBOOT_NOT_READY: + dev_err(hdev->dev, + "ARM status %d - u-boot stopped by user\n", + status); + break; default: dev_err(hdev->dev, "ARM status %d - Invalid status code\n", diff --git a/drivers/misc/habanalabs/include/hl_boot_if.h b/drivers/misc/habanalabs/include/hl_boot_if.h index 7475732b9996..4cd04c090285 100644 --- a/drivers/misc/habanalabs/include/hl_boot_if.h +++ b/drivers/misc/habanalabs/include/hl_boot_if.h @@ -18,7 +18,8 @@ enum cpu_boot_status { CPU_BOOT_STATUS_IN_SPL, CPU_BOOT_STATUS_IN_UBOOT, CPU_BOOT_STATUS_DRAM_INIT_FAIL, - CPU_BOOT_STATUS_FIT_CORRUPTED + CPU_BOOT_STATUS_FIT_CORRUPTED, + CPU_BOOT_STATUS_UBOOT_NOT_READY, }; enum kmd_msg { From b24ca4587e2b940b22de4490209b8d785bf487a5 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sun, 24 Feb 2019 15:50:53 +0200 Subject: [PATCH 002/255] habanalabs: rename goya_non_fatal_events array to all events The goya_non_fatal_events array actually contains all the possible events the driver can receive from the F/W. Therefore, use a proper name for the array. The patch also adds missing event Ids to the goya_async_event_id enum. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 8 +++----- drivers/misc/habanalabs/include/goya/goya_async_events.h | 9 +++++++++ 2 files changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 0185f11c5577..3dfac5393269 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -176,9 +176,7 @@ static u64 goya_mmu_regs[GOYA_MMU_REGS_NUM] = { mmMME_WBC_CONTROL_DATA }; -#define GOYA_ASYC_EVENT_GROUP_NON_FATAL_SIZE 121 - -static u32 goya_non_fatal_events[GOYA_ASYC_EVENT_GROUP_NON_FATAL_SIZE] = { +static u32 goya_all_events[] = { GOYA_ASYNC_EVENT_ID_PCIE_IF, GOYA_ASYNC_EVENT_ID_TPC0_ECC, GOYA_ASYNC_EVENT_ID_TPC1_ECC, @@ -4627,8 +4625,8 @@ static int goya_soft_reset_late_init(struct hl_device *hdev) * Unmask all IRQs since some could have been received * during the soft reset */ - return goya_unmask_irq_arr(hdev, goya_non_fatal_events, - sizeof(goya_non_fatal_events)); + return goya_unmask_irq_arr(hdev, goya_all_events, + sizeof(goya_all_events)); } static int goya_unmask_irq(struct hl_device *hdev, u16 event_type) diff --git a/drivers/misc/habanalabs/include/goya/goya_async_events.h b/drivers/misc/habanalabs/include/goya/goya_async_events.h index 497937a17ee9..bb7a1aa3279e 100644 --- a/drivers/misc/habanalabs/include/goya/goya_async_events.h +++ b/drivers/misc/habanalabs/include/goya/goya_async_events.h @@ -9,7 +9,9 @@ #define __GOYA_ASYNC_EVENTS_H_ enum goya_async_event_id { + GOYA_ASYNC_EVENT_ID_PCIE_CORE = 32, GOYA_ASYNC_EVENT_ID_PCIE_IF = 33, + GOYA_ASYNC_EVENT_ID_PCIE_PHY = 34, GOYA_ASYNC_EVENT_ID_TPC0_ECC = 36, GOYA_ASYNC_EVENT_ID_TPC1_ECC = 39, GOYA_ASYNC_EVENT_ID_TPC2_ECC = 42, @@ -23,6 +25,8 @@ enum goya_async_event_id { GOYA_ASYNC_EVENT_ID_MMU_ECC = 63, GOYA_ASYNC_EVENT_ID_DMA_MACRO = 64, GOYA_ASYNC_EVENT_ID_DMA_ECC = 66, + GOYA_ASYNC_EVENT_ID_DDR0_PARITY = 69, + GOYA_ASYNC_EVENT_ID_DDR1_PARITY = 72, GOYA_ASYNC_EVENT_ID_CPU_IF_ECC = 75, GOYA_ASYNC_EVENT_ID_PSOC_MEM = 78, GOYA_ASYNC_EVENT_ID_PSOC_CORESIGHT = 79, @@ -72,6 +76,7 @@ enum goya_async_event_id { GOYA_ASYNC_EVENT_ID_MME_WACSD = 142, GOYA_ASYNC_EVENT_ID_PLL0 = 143, GOYA_ASYNC_EVENT_ID_PLL1 = 144, + GOYA_ASYNC_EVENT_ID_PLL2 = 145, GOYA_ASYNC_EVENT_ID_PLL3 = 146, GOYA_ASYNC_EVENT_ID_PLL4 = 147, GOYA_ASYNC_EVENT_ID_PLL5 = 148, @@ -81,6 +86,7 @@ enum goya_async_event_id { GOYA_ASYNC_EVENT_ID_PSOC = 160, GOYA_ASYNC_EVENT_ID_PCIE_FLR = 171, GOYA_ASYNC_EVENT_ID_PCIE_HOT_RESET = 172, + GOYA_ASYNC_EVENT_ID_PCIE_PERST = 173, GOYA_ASYNC_EVENT_ID_PCIE_QID0_ENG0 = 174, GOYA_ASYNC_EVENT_ID_PCIE_QID0_ENG1 = 175, GOYA_ASYNC_EVENT_ID_PCIE_QID0_ENG2 = 176, @@ -144,8 +150,11 @@ enum goya_async_event_id { GOYA_ASYNC_EVENT_ID_PSOC_GPIO_U16_0 = 330, GOYA_ASYNC_EVENT_ID_PSOC_GPIO_U16_1 = 331, GOYA_ASYNC_EVENT_ID_PSOC_GPIO_U16_2 = 332, + GOYA_ASYNC_EVENT_ID_PSOC_GPIO_U16_3 = 333, + GOYA_ASYNC_EVENT_ID_PSOC_GPIO_U16_4 = 334, GOYA_ASYNC_EVENT_ID_PSOC_GPIO_05_SW_RESET = 356, GOYA_ASYNC_EVENT_ID_PSOC_GPIO_10_VRHOT_ICRIT = 361, + GOYA_ASYNC_EVENT_ID_FAN = 425, GOYA_ASYNC_EVENT_ID_TPC0_CMDQ = 430, GOYA_ASYNC_EVENT_ID_TPC1_CMDQ = 431, GOYA_ASYNC_EVENT_ID_TPC2_CMDQ = 432, From 5eb420446a595ee111828641bff1f3a125fc5c0d Mon Sep 17 00:00:00 2001 From: Dotan Barak Date: Wed, 27 Feb 2019 09:55:57 +0200 Subject: [PATCH 003/255] habanalabs: remove implicit include from header files This will prevent unneeded include of header files, which may increase compilation time. Signed-off-by: Dotan Barak Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya_security.c | 1 + drivers/misc/habanalabs/include/goya/goya.h | 4 ---- 2 files changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya_security.c b/drivers/misc/habanalabs/goya/goya_security.c index 575003238401..9d2dee67e46f 100644 --- a/drivers/misc/habanalabs/goya/goya_security.c +++ b/drivers/misc/habanalabs/goya/goya_security.c @@ -6,6 +6,7 @@ */ #include "goyaP.h" +#include "include/goya/asic_reg/goya_regs.h" /* * goya_set_block_as_protected - set the given block as protected diff --git a/drivers/misc/habanalabs/include/goya/goya.h b/drivers/misc/habanalabs/include/goya/goya.h index 614149efa412..3f02a52ba4ce 100644 --- a/drivers/misc/habanalabs/include/goya/goya.h +++ b/drivers/misc/habanalabs/include/goya/goya.h @@ -8,10 +8,6 @@ #ifndef GOYA_H #define GOYA_H -#include "asic_reg/goya_regs.h" - -#include - #define SRAM_CFG_BAR_ID 0 #define MSIX_BAR_ID 2 #define DDR_BAR_ID 4 From 3110c60fdc7a5a7626b7cd401c4918751d7c19db Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Mon, 4 Mar 2019 10:22:09 +0200 Subject: [PATCH 004/255] habanalabs: Move device CPU code into common file This patch moves the code that is responsible of the communication vs. the F/W to a dedicated file. This will allow us to share the code between different ASICs. Signed-off-by: Tomer Tayar Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/Makefile | 2 +- drivers/misc/habanalabs/firmware_if.c | 325 +++++++++++++++++++ drivers/misc/habanalabs/goya/goya.c | 361 ++++----------------- drivers/misc/habanalabs/goya/goyaP.h | 11 - drivers/misc/habanalabs/habanalabs.h | 17 + drivers/misc/habanalabs/include/armcp_if.h | 8 + 6 files changed, 408 insertions(+), 316 deletions(-) create mode 100644 drivers/misc/habanalabs/firmware_if.c diff --git a/drivers/misc/habanalabs/Makefile b/drivers/misc/habanalabs/Makefile index c6592db59b25..598740d235f8 100644 --- a/drivers/misc/habanalabs/Makefile +++ b/drivers/misc/habanalabs/Makefile @@ -6,7 +6,7 @@ obj-m := habanalabs.o habanalabs-y := habanalabs_drv.o device.o context.o asid.o habanalabs_ioctl.o \ command_buffer.o hw_queue.o irq.o sysfs.o hwmon.o memory.o \ - command_submission.o mmu.o + command_submission.o mmu.o firmware_if.o habanalabs-$(CONFIG_DEBUG_FS) += debugfs.o diff --git a/drivers/misc/habanalabs/firmware_if.c b/drivers/misc/habanalabs/firmware_if.c new file mode 100644 index 000000000000..1acf82650b20 --- /dev/null +++ b/drivers/misc/habanalabs/firmware_if.c @@ -0,0 +1,325 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2016-2019 HabanaLabs, Ltd. + * All Rights Reserved. + */ + +#include "habanalabs.h" + +#include +#include +#include + +/** + * hl_fw_push_fw_to_device() - Push FW code to device. + * @hdev: pointer to hl_device structure. + * + * Copy fw code from firmware file to device memory. + * + * Return: 0 on success, non-zero for failure. + */ +int hl_fw_push_fw_to_device(struct hl_device *hdev, const char *fw_name, + void __iomem *dst) +{ + const struct firmware *fw; + const u64 *fw_data; + size_t fw_size, i; + int rc; + + rc = request_firmware(&fw, fw_name, hdev->dev); + if (rc) { + dev_err(hdev->dev, "Failed to request %s\n", fw_name); + goto out; + } + + fw_size = fw->size; + if ((fw_size % 4) != 0) { + dev_err(hdev->dev, "illegal %s firmware size %zu\n", + fw_name, fw_size); + rc = -EINVAL; + goto out; + } + + dev_dbg(hdev->dev, "%s firmware size == %zu\n", fw_name, fw_size); + + fw_data = (const u64 *) fw->data; + + if ((fw->size % 8) != 0) + fw_size -= 8; + + for (i = 0 ; i < fw_size ; i += 8, fw_data++, dst += 8) { + if (!(i & (0x80000 - 1))) { + dev_dbg(hdev->dev, + "copied so far %zu out of %zu for %s firmware", + i, fw_size, fw_name); + usleep_range(20, 100); + } + + writeq(*fw_data, dst); + } + + if ((fw->size % 8) != 0) + writel(*(const u32 *) fw_data, dst); + +out: + release_firmware(fw); + return rc; +} + +int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode) +{ + struct armcp_packet pkt = {}; + + pkt.ctl = cpu_to_le32(opcode << ARMCP_PKT_CTL_OPCODE_SHIFT); + + return hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, + sizeof(pkt), HL_DEVICE_TIMEOUT_USEC, NULL); +} + +int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg, + u16 len, u32 timeout, long *result) +{ + struct armcp_packet *pkt; + dma_addr_t pkt_dma_addr; + u32 tmp; + int rc = 0; + + if (len > HL_CPU_CB_SIZE) { + dev_err(hdev->dev, "Invalid CPU message size of %d bytes\n", + len); + return -ENOMEM; + } + + pkt = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, len, + &pkt_dma_addr); + if (!pkt) { + dev_err(hdev->dev, + "Failed to allocate DMA memory for packet to CPU\n"); + return -ENOMEM; + } + + memcpy(pkt, msg, len); + + mutex_lock(&hdev->send_cpu_message_lock); + + if (hdev->disabled) + goto out; + + if (hdev->device_cpu_disabled) { + rc = -EIO; + goto out; + } + + rc = hl_hw_queue_send_cb_no_cmpl(hdev, hw_queue_id, len, pkt_dma_addr); + if (rc) { + dev_err(hdev->dev, "Failed to send CB on CPU PQ (%d)\n", rc); + goto out; + } + + rc = hl_poll_timeout_memory(hdev, (u64) (uintptr_t) &pkt->fence, + timeout, &tmp); + + hl_hw_queue_inc_ci_kernel(hdev, hw_queue_id); + + if (rc == -ETIMEDOUT) { + dev_err(hdev->dev, "Timeout while waiting for device CPU\n"); + hdev->device_cpu_disabled = true; + goto out; + } + + if (tmp == ARMCP_PACKET_FENCE_VAL) { + u32 ctl = le32_to_cpu(pkt->ctl); + + rc = (ctl & ARMCP_PKT_CTL_RC_MASK) >> ARMCP_PKT_CTL_RC_SHIFT; + if (rc) { + dev_err(hdev->dev, + "F/W ERROR %d for CPU packet %d\n", + rc, (ctl & ARMCP_PKT_CTL_OPCODE_MASK) + >> ARMCP_PKT_CTL_OPCODE_SHIFT); + rc = -EINVAL; + } else if (result) { + *result = (long) le64_to_cpu(pkt->result); + } + } else { + dev_err(hdev->dev, "CPU packet wrong fence value\n"); + rc = -EINVAL; + } + +out: + mutex_unlock(&hdev->send_cpu_message_lock); + + hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, len, pkt); + + return rc; +} + +int hl_fw_test_cpu_queue(struct hl_device *hdev) +{ + struct armcp_packet test_pkt = {}; + long result; + int rc; + + test_pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEST << + ARMCP_PKT_CTL_OPCODE_SHIFT); + test_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL); + + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &test_pkt, + sizeof(test_pkt), HL_DEVICE_TIMEOUT_USEC, &result); + + if (!rc) { + if (result == ARMCP_PACKET_FENCE_VAL) + dev_info(hdev->dev, + "queue test on CPU queue succeeded\n"); + else + dev_err(hdev->dev, + "CPU queue test failed (0x%08lX)\n", result); + } else { + dev_err(hdev->dev, "CPU queue test failed, error %d\n", rc); + } + + return rc; +} + +void *hl_fw_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size, + dma_addr_t *dma_handle) +{ + u64 kernel_addr; + + /* roundup to HL_CPU_PKT_SIZE */ + size = (size + (HL_CPU_PKT_SIZE - 1)) & HL_CPU_PKT_MASK; + + kernel_addr = gen_pool_alloc(hdev->cpu_accessible_dma_pool, size); + + *dma_handle = hdev->cpu_accessible_dma_address + + (kernel_addr - (u64) (uintptr_t) hdev->cpu_accessible_dma_mem); + + return (void *) (uintptr_t) kernel_addr; +} + +void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size, + void *vaddr) +{ + /* roundup to HL_CPU_PKT_SIZE */ + size = (size + (HL_CPU_PKT_SIZE - 1)) & HL_CPU_PKT_MASK; + + gen_pool_free(hdev->cpu_accessible_dma_pool, (u64) (uintptr_t) vaddr, + size); +} + +int hl_fw_send_heartbeat(struct hl_device *hdev) +{ + struct armcp_packet hb_pkt = {}; + long result; + int rc; + + hb_pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEST << + ARMCP_PKT_CTL_OPCODE_SHIFT); + hb_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL); + + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &hb_pkt, + sizeof(hb_pkt), HL_DEVICE_TIMEOUT_USEC, &result); + + if ((rc) || (result != ARMCP_PACKET_FENCE_VAL)) + rc = -EIO; + + return rc; +} + +int hl_fw_armcp_info_get(struct hl_device *hdev) +{ + struct asic_fixed_properties *prop = &hdev->asic_prop; + struct armcp_packet pkt = {}; + void *armcp_info_cpu_addr; + dma_addr_t armcp_info_dma_addr; + long result; + int rc; + + armcp_info_cpu_addr = + hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, + sizeof(struct armcp_info), + &armcp_info_dma_addr); + if (!armcp_info_cpu_addr) { + dev_err(hdev->dev, + "Failed to allocate DMA memory for ArmCP info packet\n"); + return -ENOMEM; + } + + memset(armcp_info_cpu_addr, 0, sizeof(struct armcp_info)); + + pkt.ctl = cpu_to_le32(ARMCP_PACKET_INFO_GET << + ARMCP_PKT_CTL_OPCODE_SHIFT); + pkt.addr = cpu_to_le64(armcp_info_dma_addr + + prop->host_phys_base_address); + pkt.data_max_size = cpu_to_le32(sizeof(struct armcp_info)); + + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), + HL_ARMCP_INFO_TIMEOUT_USEC, &result); + if (rc) { + dev_err(hdev->dev, + "Failed to send armcp info pkt, error %d\n", rc); + goto out; + } + + memcpy(&prop->armcp_info, armcp_info_cpu_addr, + sizeof(prop->armcp_info)); + + rc = hl_build_hwmon_channel_info(hdev, prop->armcp_info.sensors); + if (rc) { + dev_err(hdev->dev, + "Failed to build hwmon channel info, error %d\n", rc); + rc = -EFAULT; + goto out; + } + +out: + hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, + sizeof(struct armcp_info), armcp_info_cpu_addr); + + return rc; +} + +int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size) +{ + struct asic_fixed_properties *prop = &hdev->asic_prop; + struct armcp_packet pkt = {}; + void *eeprom_info_cpu_addr; + dma_addr_t eeprom_info_dma_addr; + long result; + int rc; + + eeprom_info_cpu_addr = + hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, + max_size, &eeprom_info_dma_addr); + if (!eeprom_info_cpu_addr) { + dev_err(hdev->dev, + "Failed to allocate DMA memory for EEPROM info packet\n"); + return -ENOMEM; + } + + memset(eeprom_info_cpu_addr, 0, max_size); + + pkt.ctl = cpu_to_le32(ARMCP_PACKET_EEPROM_DATA_GET << + ARMCP_PKT_CTL_OPCODE_SHIFT); + pkt.addr = cpu_to_le64(eeprom_info_dma_addr + + prop->host_phys_base_address); + pkt.data_max_size = cpu_to_le32(max_size); + + rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), + HL_ARMCP_EEPROM_TIMEOUT_USEC, &result); + + if (rc) { + dev_err(hdev->dev, + "Failed to send armcp EEPROM pkt, error %d\n", rc); + goto out; + } + + /* result contains the actual size */ + memcpy(data, eeprom_info_cpu_addr, min((size_t)result, max_size)); + +out: + hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, max_size, + eeprom_info_cpu_addr); + + return rc; +} diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 3dfac5393269..30f83521de90 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -12,10 +12,8 @@ #include #include -#include #include #include -#include /* * GOYA security scheme: @@ -373,18 +371,6 @@ static void goya_get_fixed_properties(struct hl_device *hdev) prop->high_pll = PLL_HIGH_DEFAULT; } -int goya_send_pci_access_msg(struct hl_device *hdev, u32 opcode) -{ - struct armcp_packet pkt; - - memset(&pkt, 0, sizeof(pkt)); - - pkt.ctl = cpu_to_le32(opcode << ARMCP_PKT_CTL_OPCODE_SHIFT); - - return hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, - sizeof(pkt), HL_DEVICE_TIMEOUT_USEC, NULL); -} - /* * goya_pci_bars_map - Map PCI BARS of Goya device * @@ -802,7 +788,7 @@ static int goya_late_init(struct hl_device *hdev) */ WREG32(mmMMU_LOG2_DDR_SIZE, ilog2(prop->dram_size)); - rc = goya_send_pci_access_msg(hdev, ARMCP_PACKET_ENABLE_PCI_ACCESS); + rc = hl_fw_send_pci_access_msg(hdev, ARMCP_PACKET_ENABLE_PCI_ACCESS); if (rc) { dev_err(hdev->dev, "Failed to enable PCI access from CPU\n"); return rc; @@ -828,7 +814,7 @@ static int goya_late_init(struct hl_device *hdev) return 0; disable_pci_access: - goya_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS); + hl_fw_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS); return rc; } @@ -900,19 +886,16 @@ static int goya_sw_init(struct hl_device *hdev) hdev->cpu_accessible_dma_mem = hdev->asic_funcs->dma_alloc_coherent(hdev, - CPU_ACCESSIBLE_MEM_SIZE, + HL_CPU_ACCESSIBLE_MEM_SIZE, &hdev->cpu_accessible_dma_address, GFP_KERNEL | __GFP_ZERO); if (!hdev->cpu_accessible_dma_mem) { - dev_err(hdev->dev, - "failed to allocate %d of dma memory for CPU accessible memory space\n", - CPU_ACCESSIBLE_MEM_SIZE); rc = -ENOMEM; goto free_dma_pool; } - hdev->cpu_accessible_dma_pool = gen_pool_create(CPU_PKT_SHIFT, -1); + hdev->cpu_accessible_dma_pool = gen_pool_create(HL_CPU_PKT_SHIFT, -1); if (!hdev->cpu_accessible_dma_pool) { dev_err(hdev->dev, "Failed to create CPU accessible DMA pool\n"); @@ -922,7 +905,7 @@ static int goya_sw_init(struct hl_device *hdev) rc = gen_pool_add(hdev->cpu_accessible_dma_pool, (uintptr_t) hdev->cpu_accessible_dma_mem, - CPU_ACCESSIBLE_MEM_SIZE, -1); + HL_CPU_ACCESSIBLE_MEM_SIZE, -1); if (rc) { dev_err(hdev->dev, "Failed to add memory to CPU accessible DMA pool\n"); @@ -937,7 +920,7 @@ static int goya_sw_init(struct hl_device *hdev) free_cpu_pq_pool: gen_pool_destroy(hdev->cpu_accessible_dma_pool); free_cpu_pq_dma_mem: - hdev->asic_funcs->dma_free_coherent(hdev, CPU_ACCESSIBLE_MEM_SIZE, + hdev->asic_funcs->dma_free_coherent(hdev, HL_CPU_ACCESSIBLE_MEM_SIZE, hdev->cpu_accessible_dma_mem, hdev->cpu_accessible_dma_address); free_dma_pool: @@ -960,7 +943,7 @@ static int goya_sw_fini(struct hl_device *hdev) gen_pool_destroy(hdev->cpu_accessible_dma_pool); - hdev->asic_funcs->dma_free_coherent(hdev, CPU_ACCESSIBLE_MEM_SIZE, + hdev->asic_funcs->dma_free_coherent(hdev, HL_CPU_ACCESSIBLE_MEM_SIZE, hdev->cpu_accessible_dma_mem, hdev->cpu_accessible_dma_address); @@ -1240,7 +1223,7 @@ static int goya_init_cpu_queues(struct hl_device *hdev) WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_5, HL_QUEUE_SIZE_IN_BYTES); WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_4, HL_EQ_SIZE_IN_BYTES); - WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_10, CPU_ACCESSIBLE_MEM_SIZE); + WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_10, HL_CPU_ACCESSIBLE_MEM_SIZE); /* Used for EQ CI */ WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_6, 0); @@ -2328,67 +2311,45 @@ static void goya_halt_engines(struct hl_device *hdev, bool hard_reset) } /* - * goya_push_fw_to_device - Push FW code to device + * goya_push_uboot_to_device() - Push u-boot FW code to device. + * @hdev: Pointer to hl_device structure. * - * @hdev: pointer to hl_device structure - * - * Copy fw code from firmware file to device memory. - * Returns 0 on success + * Copy u-boot fw code from firmware file to SRAM BAR. * + * Return: 0 on success, non-zero for failure. */ -static int goya_push_fw_to_device(struct hl_device *hdev, const char *fw_name, - void __iomem *dst) +static int goya_push_uboot_to_device(struct hl_device *hdev) { - const struct firmware *fw; - const u64 *fw_data; - size_t fw_size, i; - int rc; + char fw_name[200]; + void __iomem *dst; - rc = request_firmware(&fw, fw_name, hdev->dev); + snprintf(fw_name, sizeof(fw_name), "habanalabs/goya/goya-u-boot.bin"); + dst = hdev->pcie_bar[SRAM_CFG_BAR_ID] + UBOOT_FW_OFFSET; - if (rc) { - dev_err(hdev->dev, "Failed to request %s\n", fw_name); - goto out; - } + return hl_fw_push_fw_to_device(hdev, fw_name, dst); +} - fw_size = fw->size; - if ((fw_size % 4) != 0) { - dev_err(hdev->dev, "illegal %s firmware size %zu\n", - fw_name, fw_size); - rc = -EINVAL; - goto out; - } +/* + * goya_push_linux_to_device() - Push LINUX FW code to device. + * @hdev: Pointer to hl_device structure. + * + * Copy LINUX fw code from firmware file to HBM BAR. + * + * Return: 0 on success, non-zero for failure. + */ +static int goya_push_linux_to_device(struct hl_device *hdev) +{ + char fw_name[200]; + void __iomem *dst; - dev_dbg(hdev->dev, "%s firmware size == %zu\n", fw_name, fw_size); + snprintf(fw_name, sizeof(fw_name), "habanalabs/goya/goya-fit.itb"); + dst = hdev->pcie_bar[DDR_BAR_ID] + LINUX_FW_OFFSET; - fw_data = (const u64 *) fw->data; - - if ((fw->size % 8) != 0) - fw_size -= 8; - - for (i = 0 ; i < fw_size ; i += 8, fw_data++, dst += 8) { - if (!(i & (0x80000 - 1))) { - dev_dbg(hdev->dev, - "copied so far %zu out of %zu for %s firmware", - i, fw_size, fw_name); - usleep_range(20, 100); - } - - writeq(*fw_data, dst); - } - - if ((fw->size % 8) != 0) - writel(*(const u32 *) fw_data, dst); - -out: - release_firmware(fw); - return rc; + return hl_fw_push_fw_to_device(hdev, fw_name, dst); } static int goya_pldm_init_cpu(struct hl_device *hdev) { - char fw_name[200]; - void __iomem *dst; u32 val, unit_rst_val; int rc; @@ -2406,15 +2367,11 @@ static int goya_pldm_init_cpu(struct hl_device *hdev) WREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N, unit_rst_val); val = RREG32(mmPSOC_GLOBAL_CONF_UNIT_RST_N); - snprintf(fw_name, sizeof(fw_name), "habanalabs/goya/goya-u-boot.bin"); - dst = hdev->pcie_bar[SRAM_CFG_BAR_ID] + UBOOT_FW_OFFSET; - rc = goya_push_fw_to_device(hdev, fw_name, dst); + rc = goya_push_uboot_to_device(hdev); if (rc) return rc; - snprintf(fw_name, sizeof(fw_name), "habanalabs/goya/goya-fit.itb"); - dst = hdev->pcie_bar[DDR_BAR_ID] + LINUX_FW_OFFSET; - rc = goya_push_fw_to_device(hdev, fw_name, dst); + rc = goya_push_linux_to_device(hdev); if (rc) return rc; @@ -2476,8 +2433,6 @@ static void goya_read_device_fw_version(struct hl_device *hdev, static int goya_init_cpu(struct hl_device *hdev, u32 cpu_timeout) { struct goya_device *goya = hdev->asic_specific; - char fw_name[200]; - void __iomem *dst; u32 status; int rc; @@ -2574,9 +2529,7 @@ static int goya_init_cpu(struct hl_device *hdev, u32 cpu_timeout) goto out; } - snprintf(fw_name, sizeof(fw_name), "habanalabs/goya/goya-fit.itb"); - dst = hdev->pcie_bar[DDR_BAR_ID] + LINUX_FW_OFFSET; - rc = goya_push_fw_to_device(hdev, fw_name, dst); + rc = goya_push_linux_to_device(hdev); if (rc) return rc; @@ -2762,7 +2715,7 @@ static int goya_hw_init(struct hl_device *hdev) return 0; disable_pci_access: - goya_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS); + hl_fw_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS); disable_msix: goya_disable_msix(hdev); disable_queues: @@ -2869,7 +2822,7 @@ int goya_suspend(struct hl_device *hdev) { int rc; - rc = goya_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS); + rc = hl_fw_send_pci_access_msg(hdev, ARMCP_PACKET_DISABLE_PCI_ACCESS); if (rc) dev_err(hdev->dev, "Failed to disable PCI access from CPU\n"); @@ -3150,10 +3103,6 @@ int goya_send_cpu_message(struct hl_device *hdev, u32 *msg, u16 len, u32 timeout, long *result) { struct goya_device *goya = hdev->asic_specific; - struct armcp_packet *pkt; - dma_addr_t pkt_dma_addr; - u32 tmp; - int rc = 0; if (!(goya->hw_cap_initialized & HW_CAP_CPU_Q)) { if (result) @@ -3161,74 +3110,8 @@ int goya_send_cpu_message(struct hl_device *hdev, u32 *msg, u16 len, return 0; } - if (len > CPU_CB_SIZE) { - dev_err(hdev->dev, "Invalid CPU message size of %d bytes\n", - len); - return -ENOMEM; - } - - pkt = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, len, - &pkt_dma_addr); - if (!pkt) { - dev_err(hdev->dev, - "Failed to allocate DMA memory for packet to CPU\n"); - return -ENOMEM; - } - - memcpy(pkt, msg, len); - - mutex_lock(&hdev->send_cpu_message_lock); - - if (hdev->disabled) - goto out; - - if (hdev->device_cpu_disabled) { - rc = -EIO; - goto out; - } - - rc = hl_hw_queue_send_cb_no_cmpl(hdev, GOYA_QUEUE_ID_CPU_PQ, len, - pkt_dma_addr); - if (rc) { - dev_err(hdev->dev, "Failed to send CB on CPU PQ (%d)\n", rc); - goto out; - } - - rc = hl_poll_timeout_memory(hdev, (u64) (uintptr_t) &pkt->fence, - timeout, &tmp); - - hl_hw_queue_inc_ci_kernel(hdev, GOYA_QUEUE_ID_CPU_PQ); - - if (rc == -ETIMEDOUT) { - dev_err(hdev->dev, "Timeout while waiting for device CPU\n"); - hdev->device_cpu_disabled = true; - goto out; - } - - if (tmp == ARMCP_PACKET_FENCE_VAL) { - u32 ctl = le32_to_cpu(pkt->ctl); - - rc = (ctl & ARMCP_PKT_CTL_RC_MASK) >> ARMCP_PKT_CTL_RC_SHIFT; - if (rc) { - dev_err(hdev->dev, - "F/W ERROR %d for CPU packet %d\n", - rc, (ctl & ARMCP_PKT_CTL_OPCODE_MASK) - >> ARMCP_PKT_CTL_OPCODE_SHIFT); - rc = -EINVAL; - } else if (result) { - *result = (long) le64_to_cpu(pkt->result); - } - } else { - dev_err(hdev->dev, "CPU packet wrong fence value\n"); - rc = -EINVAL; - } - -out: - mutex_unlock(&hdev->send_cpu_message_lock); - - hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, len, pkt); - - return rc; + return hl_fw_send_cpu_message(hdev, GOYA_QUEUE_ID_CPU_PQ, msg, len, + timeout, result); } int goya_test_queue(struct hl_device *hdev, u32 hw_queue_id) @@ -3306,33 +3189,16 @@ int goya_test_queue(struct hl_device *hdev, u32 hw_queue_id) int goya_test_cpu_queue(struct hl_device *hdev) { - struct armcp_packet test_pkt; - long result; - int rc; + struct goya_device *goya = hdev->asic_specific; - /* cpu_queues_enable flag is always checked in send cpu message */ + /* + * check capability here as send_cpu_message() won't update the result + * value if no capability + */ + if (!(goya->hw_cap_initialized & HW_CAP_CPU_Q)) + return 0; - memset(&test_pkt, 0, sizeof(test_pkt)); - - test_pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEST << - ARMCP_PKT_CTL_OPCODE_SHIFT); - test_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL); - - rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &test_pkt, - sizeof(test_pkt), HL_DEVICE_TIMEOUT_USEC, &result); - - if (!rc) { - if (result == ARMCP_PACKET_FENCE_VAL) - dev_info(hdev->dev, - "queue test on CPU queue succeeded\n"); - else - dev_err(hdev->dev, - "CPU queue test failed (0x%08lX)\n", result); - } else { - dev_err(hdev->dev, "CPU queue test failed, error %d\n", rc); - } - - return rc; + return hl_fw_test_cpu_queue(hdev); } static int goya_test_queues(struct hl_device *hdev) @@ -3373,27 +3239,13 @@ static void goya_dma_pool_free(struct hl_device *hdev, void *vaddr, static void *goya_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size, dma_addr_t *dma_handle) { - u64 kernel_addr; - - /* roundup to CPU_PKT_SIZE */ - size = (size + (CPU_PKT_SIZE - 1)) & CPU_PKT_MASK; - - kernel_addr = gen_pool_alloc(hdev->cpu_accessible_dma_pool, size); - - *dma_handle = hdev->cpu_accessible_dma_address + - (kernel_addr - (u64) (uintptr_t) hdev->cpu_accessible_dma_mem); - - return (void *) (uintptr_t) kernel_addr; + return hl_fw_cpu_accessible_dma_pool_alloc(hdev, size, dma_handle); } static void goya_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size, void *vaddr) { - /* roundup to CPU_PKT_SIZE */ - size = (size + (CPU_PKT_SIZE - 1)) & CPU_PKT_MASK; - - gen_pool_free(hdev->cpu_accessible_dma_pool, (u64) (uintptr_t) vaddr, - size); + hl_fw_cpu_accessible_dma_pool_free(hdev, size, vaddr); } static int goya_dma_map_sg(struct hl_device *hdev, struct scatterlist *sg, @@ -5032,72 +4884,26 @@ static int goya_mmu_update_asid_hop0_addr(struct hl_device *hdev, u32 asid, int goya_send_heartbeat(struct hl_device *hdev) { struct goya_device *goya = hdev->asic_specific; - struct armcp_packet hb_pkt; - long result; - int rc; if (!(goya->hw_cap_initialized & HW_CAP_CPU_Q)) return 0; - memset(&hb_pkt, 0, sizeof(hb_pkt)); - - hb_pkt.ctl = cpu_to_le32(ARMCP_PACKET_TEST << - ARMCP_PKT_CTL_OPCODE_SHIFT); - hb_pkt.value = cpu_to_le64(ARMCP_PACKET_FENCE_VAL); - - rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &hb_pkt, - sizeof(hb_pkt), HL_DEVICE_TIMEOUT_USEC, &result); - - if ((rc) || (result != ARMCP_PACKET_FENCE_VAL)) - rc = -EIO; - - return rc; + return hl_fw_send_heartbeat(hdev); } static int goya_armcp_info_get(struct hl_device *hdev) { struct goya_device *goya = hdev->asic_specific; struct asic_fixed_properties *prop = &hdev->asic_prop; - struct armcp_packet pkt; - void *armcp_info_cpu_addr; - dma_addr_t armcp_info_dma_addr; u64 dram_size; - long result; int rc; if (!(goya->hw_cap_initialized & HW_CAP_CPU_Q)) return 0; - armcp_info_cpu_addr = - hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, - sizeof(struct armcp_info), &armcp_info_dma_addr); - if (!armcp_info_cpu_addr) { - dev_err(hdev->dev, - "Failed to allocate DMA memory for ArmCP info packet\n"); - return -ENOMEM; - } - - memset(armcp_info_cpu_addr, 0, sizeof(struct armcp_info)); - - memset(&pkt, 0, sizeof(pkt)); - - pkt.ctl = cpu_to_le32(ARMCP_PACKET_INFO_GET << - ARMCP_PKT_CTL_OPCODE_SHIFT); - pkt.addr = cpu_to_le64(armcp_info_dma_addr + - prop->host_phys_base_address); - pkt.data_max_size = cpu_to_le32(sizeof(struct armcp_info)); - - rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - GOYA_ARMCP_INFO_TIMEOUT, &result); - - if (rc) { - dev_err(hdev->dev, - "Failed to send armcp info pkt, error %d\n", rc); - goto out; - } - - memcpy(&prop->armcp_info, armcp_info_cpu_addr, - sizeof(prop->armcp_info)); + rc = hl_fw_armcp_info_get(hdev); + if (rc) + return rc; dram_size = le64_to_cpu(prop->armcp_info.dram_size); if (dram_size) { @@ -5113,19 +4919,7 @@ static int goya_armcp_info_get(struct hl_device *hdev) prop->dram_end_address = prop->dram_base_address + dram_size; } - rc = hl_build_hwmon_channel_info(hdev, prop->armcp_info.sensors); - if (rc) { - dev_err(hdev->dev, - "Failed to build hwmon channel info, error %d\n", rc); - rc = -EFAULT; - goto out; - } - -out: - hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, - sizeof(struct armcp_info), armcp_info_cpu_addr); - - return rc; + return 0; } static void goya_init_clock_gating(struct hl_device *hdev) @@ -5214,52 +5008,11 @@ static int goya_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size) { struct goya_device *goya = hdev->asic_specific; - struct asic_fixed_properties *prop = &hdev->asic_prop; - struct armcp_packet pkt; - void *eeprom_info_cpu_addr; - dma_addr_t eeprom_info_dma_addr; - long result; - int rc; if (!(goya->hw_cap_initialized & HW_CAP_CPU_Q)) return 0; - eeprom_info_cpu_addr = - hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, - max_size, &eeprom_info_dma_addr); - if (!eeprom_info_cpu_addr) { - dev_err(hdev->dev, - "Failed to allocate DMA memory for EEPROM info packet\n"); - return -ENOMEM; - } - - memset(eeprom_info_cpu_addr, 0, max_size); - - memset(&pkt, 0, sizeof(pkt)); - - pkt.ctl = cpu_to_le32(ARMCP_PACKET_EEPROM_DATA_GET << - ARMCP_PKT_CTL_OPCODE_SHIFT); - pkt.addr = cpu_to_le64(eeprom_info_dma_addr + - prop->host_phys_base_address); - pkt.data_max_size = cpu_to_le32(max_size); - - rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), - GOYA_ARMCP_EEPROM_TIMEOUT, &result); - - if (rc) { - dev_err(hdev->dev, - "Failed to send armcp EEPROM pkt, error %d\n", rc); - goto out; - } - - /* result contains the actual size */ - memcpy(data, eeprom_info_cpu_addr, min((size_t)result, max_size)); - -out: - hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, max_size, - eeprom_info_cpu_addr); - - return rc; + return hl_fw_get_eeprom_data(hdev, data, max_size); } static enum hl_device_hw_state goya_get_hw_state(struct hl_device *hdev) diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h index 830551b6b062..6fdc76b5bde0 100644 --- a/drivers/misc/habanalabs/goya/goyaP.h +++ b/drivers/misc/habanalabs/goya/goyaP.h @@ -49,9 +49,6 @@ #define MAX_POWER_DEFAULT 200000 /* 200W */ -#define GOYA_ARMCP_INFO_TIMEOUT 10000000 /* 10s */ -#define GOYA_ARMCP_EEPROM_TIMEOUT 10000000 /* 10s */ - #define DRAM_PHYS_DEFAULT_SIZE 0x100000000ull /* 4GB */ /* DRAM Memory Map */ @@ -142,13 +139,6 @@ #define HW_CAP_GOLDEN 0x00000400 #define HW_CAP_TPC 0x00000800 -#define CPU_PKT_SHIFT 5 -#define CPU_PKT_SIZE (1 << CPU_PKT_SHIFT) -#define CPU_PKT_MASK (~((1 << CPU_PKT_SHIFT) - 1)) -#define CPU_MAX_PKTS_IN_CB 32 -#define CPU_CB_SIZE (CPU_PKT_SIZE * CPU_MAX_PKTS_IN_CB) -#define CPU_ACCESSIBLE_MEM_SIZE (HL_QUEUE_LENGTH * CPU_CB_SIZE) - enum goya_fw_component { FW_COMP_UBOOT, FW_COMP_PREBOOT @@ -192,7 +182,6 @@ void goya_init_security(struct hl_device *hdev); u64 goya_get_max_power(struct hl_device *hdev); void goya_set_max_power(struct hl_device *hdev, u64 value); -int goya_send_pci_access_msg(struct hl_device *hdev, u32 opcode); void goya_late_fini(struct hl_device *hdev); int goya_suspend(struct hl_device *hdev); int goya_resume(struct hl_device *hdev); diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index a8ee52c880cd..1445ba1cafd4 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -33,6 +33,9 @@ #define HL_PLL_LOW_JOB_FREQ_USEC 5000000 /* 5 s */ +#define HL_ARMCP_INFO_TIMEOUT_USEC 10000000 /* 10s */ +#define HL_ARMCP_EEPROM_TIMEOUT_USEC 10000000 /* 10s */ + #define HL_MAX_QUEUES 128 #define HL_MAX_JOBS_PER_CS 64 @@ -1351,6 +1354,20 @@ int hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr, u32 page_size); void hl_mmu_swap_out(struct hl_ctx *ctx); void hl_mmu_swap_in(struct hl_ctx *ctx); +int hl_fw_push_fw_to_device(struct hl_device *hdev, const char *fw_name, + void __iomem *dst); +int hl_fw_send_pci_access_msg(struct hl_device *hdev, u32 opcode); +int hl_fw_send_cpu_message(struct hl_device *hdev, u32 hw_queue_id, u32 *msg, + u16 len, u32 timeout, long *result); +int hl_fw_test_cpu_queue(struct hl_device *hdev); +void *hl_fw_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size, + dma_addr_t *dma_handle); +void hl_fw_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size, + void *vaddr); +int hl_fw_send_heartbeat(struct hl_device *hdev); +int hl_fw_armcp_info_get(struct hl_device *hdev); +int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size); + long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr); void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq); long hl_get_temperature(struct hl_device *hdev, int sensor_index, u32 attr); diff --git a/drivers/misc/habanalabs/include/armcp_if.h b/drivers/misc/habanalabs/include/armcp_if.h index 9dddb917e72c..ccb82390241e 100644 --- a/drivers/misc/habanalabs/include/armcp_if.h +++ b/drivers/misc/habanalabs/include/armcp_if.h @@ -302,6 +302,14 @@ enum armcp_pwm_attributes { armcp_pwm_enable }; +#define HL_CPU_PKT_SHIFT 5 +#define HL_CPU_PKT_SIZE (1 << HL_CPU_PKT_SHIFT) +#define HL_CPU_PKT_MASK (~((1 << HL_CPU_PKT_SHIFT) - 1)) +#define HL_CPU_MAX_PKTS_IN_CB 32 +#define HL_CPU_CB_SIZE (HL_CPU_PKT_SIZE * \ + HL_CPU_MAX_PKTS_IN_CB) +#define HL_CPU_ACCESSIBLE_MEM_SIZE (HL_QUEUE_LENGTH * HL_CPU_CB_SIZE) + /* Event Queue Packets */ struct eq_generic_event { From c535bfdd0f86aeed165d4f5aba187570f42d785f Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Mon, 4 Mar 2019 15:51:30 +0200 Subject: [PATCH 005/255] habanalabs: use EQ MSI/X ID per chip The Event Queue MSI/X ID is different per ASIC. This patch renames the current define to have the GOYA_ prefix to mark it only for Goya. It also moves it from the common armcp_if.h file to the ASIC specific goya_fw_if.h file. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 8 ++++---- drivers/misc/habanalabs/include/armcp_if.h | 2 -- drivers/misc/habanalabs/include/goya/goya_fw_if.h | 2 ++ 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 30f83521de90..78eacd14c9ac 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2204,10 +2204,10 @@ static int goya_enable_msix(struct hl_device *hdev) } } - irq = pci_irq_vector(hdev->pdev, EVENT_QUEUE_MSIX_IDX); + irq = pci_irq_vector(hdev->pdev, GOYA_EVENT_QUEUE_MSIX_IDX); rc = request_irq(irq, hl_irq_handler_eq, 0, - goya_irq_name[EVENT_QUEUE_MSIX_IDX], + goya_irq_name[GOYA_EVENT_QUEUE_MSIX_IDX], &hdev->event_queue); if (rc) { dev_err(hdev->dev, "Failed to request IRQ %d", irq); @@ -2238,7 +2238,7 @@ static void goya_sync_irqs(struct hl_device *hdev) for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++) synchronize_irq(pci_irq_vector(hdev->pdev, i)); - synchronize_irq(pci_irq_vector(hdev->pdev, EVENT_QUEUE_MSIX_IDX)); + synchronize_irq(pci_irq_vector(hdev->pdev, GOYA_EVENT_QUEUE_MSIX_IDX)); } static void goya_disable_msix(struct hl_device *hdev) @@ -2251,7 +2251,7 @@ static void goya_disable_msix(struct hl_device *hdev) goya_sync_irqs(hdev); - irq = pci_irq_vector(hdev->pdev, EVENT_QUEUE_MSIX_IDX); + irq = pci_irq_vector(hdev->pdev, GOYA_EVENT_QUEUE_MSIX_IDX); free_irq(irq, &hdev->event_queue); for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++) { diff --git a/drivers/misc/habanalabs/include/armcp_if.h b/drivers/misc/habanalabs/include/armcp_if.h index ccb82390241e..c8f28cadc335 100644 --- a/drivers/misc/habanalabs/include/armcp_if.h +++ b/drivers/misc/habanalabs/include/armcp_if.h @@ -32,8 +32,6 @@ struct hl_eq_entry { #define EQ_CTL_EVENT_TYPE_SHIFT 16 #define EQ_CTL_EVENT_TYPE_MASK 0x03FF0000 -#define EVENT_QUEUE_MSIX_IDX 5 - enum pq_init_status { PQ_INIT_STATUS_NA = 0, PQ_INIT_STATUS_READY_FOR_CP, diff --git a/drivers/misc/habanalabs/include/goya/goya_fw_if.h b/drivers/misc/habanalabs/include/goya/goya_fw_if.h index a9920cb4a07b..0fa80fe9f6cc 100644 --- a/drivers/misc/habanalabs/include/goya/goya_fw_if.h +++ b/drivers/misc/habanalabs/include/goya/goya_fw_if.h @@ -8,6 +8,8 @@ #ifndef GOYA_FW_IF_H #define GOYA_FW_IF_H +#define GOYA_EVENT_QUEUE_MSIX_IDX 5 + #define CPU_BOOT_ADDR 0x7FF8040000ull #define UBOOT_FW_OFFSET 0x100000 /* 1MB in SRAM */ From e0a29952c52787f8e4a4fc3046f3e47916ffa239 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Thu, 28 Feb 2019 10:19:41 +0200 Subject: [PATCH 006/255] habanalabs: remove unused defines This patch removes some old defines which are not in use anymore. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goyaP.h | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h index 6fdc76b5bde0..ae5e41bc8f7f 100644 --- a/drivers/misc/habanalabs/goya/goyaP.h +++ b/drivers/misc/habanalabs/goya/goyaP.h @@ -54,11 +54,9 @@ /* DRAM Memory Map */ #define CPU_FW_IMAGE_SIZE 0x10000000 /* 256MB */ -#define MMU_PAGE_TABLES_SIZE 0x0DE00000 /* 222MB */ +#define MMU_PAGE_TABLES_SIZE 0x0FC00000 /* 252MB */ #define MMU_DRAM_DEFAULT_PAGE_SIZE 0x00200000 /* 2MB */ #define MMU_CACHE_MNG_SIZE 0x00001000 /* 4KB */ -#define CPU_PQ_PKT_SIZE 0x00001000 /* 4KB */ -#define CPU_PQ_DATA_SIZE 0x01FFE000 /* 32MB - 8KB */ #define CPU_FW_IMAGE_ADDR DRAM_PHYS_BASE #define MMU_PAGE_TABLES_ADDR (CPU_FW_IMAGE_ADDR + CPU_FW_IMAGE_SIZE) @@ -66,13 +64,13 @@ MMU_PAGE_TABLES_SIZE) #define MMU_CACHE_MNG_ADDR (MMU_DRAM_DEFAULT_PAGE_ADDR + \ MMU_DRAM_DEFAULT_PAGE_SIZE) -#define CPU_PQ_PKT_ADDR (MMU_CACHE_MNG_ADDR + \ +#define DRAM_KMD_END_ADDR (MMU_CACHE_MNG_ADDR + \ MMU_CACHE_MNG_SIZE) -#define CPU_PQ_DATA_ADDR (CPU_PQ_PKT_ADDR + CPU_PQ_PKT_SIZE) -#define DRAM_BASE_ADDR_USER (CPU_PQ_DATA_ADDR + CPU_PQ_DATA_SIZE) -#if (DRAM_BASE_ADDR_USER != 0x20000000) -#error "KMD must reserve 512MB" +#define DRAM_BASE_ADDR_USER 0x20000000 + +#if (DRAM_KMD_END_ADDR > DRAM_BASE_ADDR_USER) +#error "KMD must reserve no more than 512MB" #endif /* From 680cb3991c9ed72cefffc49e222a8c8d34ff5e3e Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Tue, 5 Mar 2019 13:53:22 +0200 Subject: [PATCH 007/255] habanalabs: ratelimit warnings at start of IOCTLs At the start of some IOCTLs we check if the device is disabled or in reset. If it is, we return -EBUSY and print a message to kernel log. Because these IOCTLs can be called at very high frequency, use ratelimit to avoid spamming the kernel log. Also use the same type of message - dev_warn - in all the relevant IOCTLs. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/command_submission.c | 2 +- drivers/misc/habanalabs/habanalabs_ioctl.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index 19c84214a7ea..f908643f871f 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -604,7 +604,7 @@ int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data) bool need_soft_reset = false; if (hl_device_disabled_or_in_reset(hdev)) { - dev_warn(hdev->dev, + dev_warn_ratelimited(hdev->dev, "Device is %s. Can't submit new CS\n", atomic_read(&hdev->in_reset) ? "in_reset" : "disabled"); rc = -EBUSY; diff --git a/drivers/misc/habanalabs/habanalabs_ioctl.c b/drivers/misc/habanalabs/habanalabs_ioctl.c index 2c2739a3c5ec..19b96afc0308 100644 --- a/drivers/misc/habanalabs/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/habanalabs_ioctl.c @@ -106,7 +106,7 @@ static int hl_info_ioctl(struct hl_fpriv *hpriv, void *data) int rc; if (hl_device_disabled_or_in_reset(hdev)) { - dev_err(hdev->dev, + dev_warn_ratelimited(hdev->dev, "Device is disabled or in reset. Can't execute INFO IOCTL\n"); return -EBUSY; } From b6f897d75d651f86a3988a602e767696f9e08de6 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Tue, 5 Mar 2019 16:48:42 +0200 Subject: [PATCH 008/255] habanalabs: Move PCI code into common file Move duplicated PCI-related code from ASIC-specific files into the common pci.c file. Signed-off-by: Tomer Tayar Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/Makefile | 2 +- drivers/misc/habanalabs/goya/goya.c | 272 +------------ drivers/misc/habanalabs/habanalabs.h | 20 + .../include/goya/asic_reg/goya_masks.h | 12 - .../include/hw_ip/pci/pci_general.h | 23 ++ drivers/misc/habanalabs/pci.c | 370 ++++++++++++++++++ 6 files changed, 434 insertions(+), 265 deletions(-) create mode 100644 drivers/misc/habanalabs/include/hw_ip/pci/pci_general.h create mode 100644 drivers/misc/habanalabs/pci.c diff --git a/drivers/misc/habanalabs/Makefile b/drivers/misc/habanalabs/Makefile index 598740d235f8..f8e85243d672 100644 --- a/drivers/misc/habanalabs/Makefile +++ b/drivers/misc/habanalabs/Makefile @@ -6,7 +6,7 @@ obj-m := habanalabs.o habanalabs-y := habanalabs_drv.o device.o context.o asid.o habanalabs_ioctl.o \ command_buffer.o hw_queue.o irq.o sysfs.o hwmon.o memory.o \ - command_submission.o mmu.o firmware_if.o + command_submission.o mmu.o firmware_if.o pci.o habanalabs-$(CONFIG_DEBUG_FS) += debugfs.o diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 78eacd14c9ac..5ce3a341ba5f 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -363,12 +363,13 @@ static void goya_get_fixed_properties(struct hl_device *hdev) prop->cfg_size = CFG_SIZE; prop->max_asid = MAX_ASID; prop->num_of_events = GOYA_ASYNC_EVENT_ID_SIZE; + prop->high_pll = PLL_HIGH_DEFAULT; prop->cb_pool_cb_cnt = GOYA_CB_POOL_CB_CNT; prop->cb_pool_cb_size = GOYA_CB_POOL_CB_SIZE; prop->max_power_default = MAX_POWER_DEFAULT; prop->tpc_enabled_mask = TPC_ENABLED_MASK; - - prop->high_pll = PLL_HIGH_DEFAULT; + prop->pcie_dbi_base_address = mmPCIE_DBI_BASE; + prop->pcie_aux_dbi_reg_addr = CFG_BASE + mmPCIE_AUX_DBI; } /* @@ -382,159 +383,18 @@ static void goya_get_fixed_properties(struct hl_device *hdev) */ static int goya_pci_bars_map(struct hl_device *hdev) { - struct pci_dev *pdev = hdev->pdev; + static const char * const name[] = {"SRAM_CFG", "MSIX", "DDR"}; + bool is_wc[3] = {false, false, true}; int rc; - rc = pci_request_regions(pdev, HL_NAME); - if (rc) { - dev_err(hdev->dev, "Cannot obtain PCI resources\n"); + rc = hl_pci_bars_map(hdev, name, is_wc); + if (rc) return rc; - } - - hdev->pcie_bar[SRAM_CFG_BAR_ID] = - pci_ioremap_bar(pdev, SRAM_CFG_BAR_ID); - if (!hdev->pcie_bar[SRAM_CFG_BAR_ID]) { - dev_err(hdev->dev, "pci_ioremap_bar failed for CFG\n"); - rc = -ENODEV; - goto err_release_regions; - } - - hdev->pcie_bar[MSIX_BAR_ID] = pci_ioremap_bar(pdev, MSIX_BAR_ID); - if (!hdev->pcie_bar[MSIX_BAR_ID]) { - dev_err(hdev->dev, "pci_ioremap_bar failed for MSIX\n"); - rc = -ENODEV; - goto err_unmap_sram_cfg; - } - - hdev->pcie_bar[DDR_BAR_ID] = pci_ioremap_wc_bar(pdev, DDR_BAR_ID); - if (!hdev->pcie_bar[DDR_BAR_ID]) { - dev_err(hdev->dev, "pci_ioremap_bar failed for DDR\n"); - rc = -ENODEV; - goto err_unmap_msix; - } hdev->rmmio = hdev->pcie_bar[SRAM_CFG_BAR_ID] + - (CFG_BASE - SRAM_BASE_ADDR); + (CFG_BASE - SRAM_BASE_ADDR); return 0; - -err_unmap_msix: - iounmap(hdev->pcie_bar[MSIX_BAR_ID]); -err_unmap_sram_cfg: - iounmap(hdev->pcie_bar[SRAM_CFG_BAR_ID]); -err_release_regions: - pci_release_regions(pdev); - - return rc; -} - -/* - * goya_pci_bars_unmap - Unmap PCI BARS of Goya device - * - * @hdev: pointer to hl_device structure - * - * Release all PCI BARS and unmap their virtual addresses - * - */ -static void goya_pci_bars_unmap(struct hl_device *hdev) -{ - struct pci_dev *pdev = hdev->pdev; - - iounmap(hdev->pcie_bar[DDR_BAR_ID]); - iounmap(hdev->pcie_bar[MSIX_BAR_ID]); - iounmap(hdev->pcie_bar[SRAM_CFG_BAR_ID]); - pci_release_regions(pdev); -} - -/* - * goya_elbi_write - Write through the ELBI interface - * - * @hdev: pointer to hl_device structure - * - * return 0 on success, -1 on failure - * - */ -static int goya_elbi_write(struct hl_device *hdev, u64 addr, u32 data) -{ - struct pci_dev *pdev = hdev->pdev; - ktime_t timeout; - u32 val; - - /* Clear previous status */ - pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, 0); - - pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_ADDR, (u32) addr); - pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_DATA, data); - pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_CTRL, - PCI_CONFIG_ELBI_CTRL_WRITE); - - timeout = ktime_add_ms(ktime_get(), 10); - for (;;) { - pci_read_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, &val); - if (val & PCI_CONFIG_ELBI_STS_MASK) - break; - if (ktime_compare(ktime_get(), timeout) > 0) { - pci_read_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, - &val); - break; - } - usleep_range(300, 500); - } - - if ((val & PCI_CONFIG_ELBI_STS_MASK) == PCI_CONFIG_ELBI_STS_DONE) - return 0; - - if (val & PCI_CONFIG_ELBI_STS_ERR) { - dev_err(hdev->dev, "Error writing to ELBI\n"); - return -EIO; - } - - if (!(val & PCI_CONFIG_ELBI_STS_MASK)) { - dev_err(hdev->dev, "ELBI write didn't finish in time\n"); - return -EIO; - } - - dev_err(hdev->dev, "ELBI write has undefined bits in status\n"); - return -EIO; -} - -/* - * goya_iatu_write - iatu write routine - * - * @hdev: pointer to hl_device structure - * - */ -static int goya_iatu_write(struct hl_device *hdev, u32 addr, u32 data) -{ - u32 dbi_offset; - int rc; - - dbi_offset = addr & 0xFFF; - - rc = goya_elbi_write(hdev, CFG_BASE + mmPCIE_AUX_DBI, 0x00300000); - rc |= goya_elbi_write(hdev, mmPCIE_DBI_BASE + dbi_offset, data); - - if (rc) - return -EIO; - - return 0; -} - -static void goya_reset_link_through_bridge(struct hl_device *hdev) -{ - struct pci_dev *pdev = hdev->pdev; - struct pci_dev *parent_port; - u16 val; - - parent_port = pdev->bus->self; - pci_read_config_word(parent_port, PCI_BRIDGE_CONTROL, &val); - val |= PCI_BRIDGE_CTL_BUS_RESET; - pci_write_config_word(parent_port, PCI_BRIDGE_CONTROL, val); - ssleep(1); - - val &= ~(PCI_BRIDGE_CTL_BUS_RESET); - pci_write_config_word(parent_port, PCI_BRIDGE_CONTROL, val); - ssleep(3); } /* @@ -556,20 +416,9 @@ static int goya_set_ddr_bar_base(struct hl_device *hdev, u64 addr) return 0; /* Inbound Region 1 - Bar 4 - Point to DDR */ - rc = goya_iatu_write(hdev, 0x314, lower_32_bits(addr)); - rc |= goya_iatu_write(hdev, 0x318, upper_32_bits(addr)); - rc |= goya_iatu_write(hdev, 0x300, 0); - /* Enable + Bar match + match enable + Bar 4 */ - rc |= goya_iatu_write(hdev, 0x304, 0xC0080400); - - /* Return the DBI window to the default location */ - rc |= goya_elbi_write(hdev, CFG_BASE + mmPCIE_AUX_DBI, 0); - rc |= goya_elbi_write(hdev, CFG_BASE + mmPCIE_AUX_DBI_32, 0); - - if (rc) { - dev_err(hdev->dev, "failed to map DDR bar to 0x%08llx\n", addr); - return -EIO; - } + rc = hl_pci_set_dram_bar_base(hdev, 1, 4, addr); + if (rc) + return rc; if (goya) goya->ddr_bar_cur_addr = addr; @@ -587,40 +436,8 @@ static int goya_set_ddr_bar_base(struct hl_device *hdev, u64 addr) */ static int goya_init_iatu(struct hl_device *hdev) { - int rc; - - /* Inbound Region 0 - Bar 0 - Point to SRAM_BASE_ADDR */ - rc = goya_iatu_write(hdev, 0x114, lower_32_bits(SRAM_BASE_ADDR)); - rc |= goya_iatu_write(hdev, 0x118, upper_32_bits(SRAM_BASE_ADDR)); - rc |= goya_iatu_write(hdev, 0x100, 0); - /* Enable + Bar match + match enable */ - rc |= goya_iatu_write(hdev, 0x104, 0xC0080000); - - /* Inbound Region 1 - Bar 4 - Point to DDR */ - rc |= goya_set_ddr_bar_base(hdev, DRAM_PHYS_BASE); - - /* Outbound Region 0 - Point to Host */ - rc |= goya_iatu_write(hdev, 0x008, lower_32_bits(HOST_PHYS_BASE)); - rc |= goya_iatu_write(hdev, 0x00C, upper_32_bits(HOST_PHYS_BASE)); - rc |= goya_iatu_write(hdev, 0x010, - lower_32_bits(HOST_PHYS_BASE + HOST_PHYS_SIZE - 1)); - rc |= goya_iatu_write(hdev, 0x014, 0); - rc |= goya_iatu_write(hdev, 0x018, 0); - rc |= goya_iatu_write(hdev, 0x020, - upper_32_bits(HOST_PHYS_BASE + HOST_PHYS_SIZE - 1)); - /* Increase region size */ - rc |= goya_iatu_write(hdev, 0x000, 0x00002000); - /* Enable */ - rc |= goya_iatu_write(hdev, 0x004, 0x80000000); - - /* Return the DBI window to the default location */ - rc |= goya_elbi_write(hdev, CFG_BASE + mmPCIE_AUX_DBI, 0); - rc |= goya_elbi_write(hdev, CFG_BASE + mmPCIE_AUX_DBI_32, 0); - - if (rc) - return -EIO; - - return 0; + return hl_pci_init_iatu(hdev, SRAM_BASE_ADDR, DRAM_PHYS_BASE, + HOST_PHYS_SIZE); } /* @@ -666,52 +483,9 @@ static int goya_early_init(struct hl_device *hdev) prop->dram_pci_bar_size = pci_resource_len(pdev, DDR_BAR_ID); - /* set DMA mask for GOYA */ - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(39)); - if (rc) { - dev_warn(hdev->dev, "Unable to set pci dma mask to 39 bits\n"); - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); - if (rc) { - dev_err(hdev->dev, - "Unable to set pci dma mask to 32 bits\n"); - return rc; - } - } - - rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39)); - if (rc) { - dev_warn(hdev->dev, - "Unable to set pci consistent dma mask to 39 bits\n"); - rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); - if (rc) { - dev_err(hdev->dev, - "Unable to set pci consistent dma mask to 32 bits\n"); - return rc; - } - } - - if (hdev->reset_pcilink) - goya_reset_link_through_bridge(hdev); - - rc = pci_enable_device_mem(pdev); - if (rc) { - dev_err(hdev->dev, "can't enable PCI device\n"); + rc = hl_pci_init(hdev); + if (rc) return rc; - } - - pci_set_master(pdev); - - rc = goya_init_iatu(hdev); - if (rc) { - dev_err(hdev->dev, "Failed to initialize iATU\n"); - goto disable_device; - } - - rc = goya_pci_bars_map(hdev); - if (rc) { - dev_err(hdev->dev, "Failed to initialize PCI BARS\n"); - goto disable_device; - } if (!hdev->pldm) { val = RREG32(mmPSOC_GLOBAL_CONF_BOOT_STRAP_PINS); @@ -721,12 +495,6 @@ static int goya_early_init(struct hl_device *hdev) } return 0; - -disable_device: - pci_clear_master(pdev); - pci_disable_device(pdev); - - return rc; } /* @@ -739,10 +507,7 @@ static int goya_early_init(struct hl_device *hdev) */ static int goya_early_fini(struct hl_device *hdev) { - goya_pci_bars_unmap(hdev); - - pci_clear_master(hdev->pdev); - pci_disable_device(hdev->pdev); + hl_pci_fini(hdev); return 0; } @@ -5071,7 +4836,10 @@ static const struct hl_asic_funcs goya_funcs = { .get_pci_id = goya_get_pci_id, .get_eeprom_data = goya_get_eeprom_data, .send_cpu_message = goya_send_cpu_message, - .get_hw_state = goya_get_hw_state + .get_hw_state = goya_get_hw_state, + .pci_bars_map = goya_pci_bars_map, + .set_dram_bar_base = goya_set_ddr_bar_base, + .init_iatu = goya_init_iatu }; /* diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 1445ba1cafd4..ed3649d38ff8 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -148,6 +148,8 @@ enum hl_device_hw_state { * mapping DRAM memory. * @dram_size_for_default_page_mapping: DRAM size needed to map to avoid page * fault. + * @pcie_dbi_base_address: Base address of the PCIE_DBI block. + * @pcie_aux_dbi_reg_addr: Address of the PCIE_AUX DBI register. * @mmu_pgt_addr: base physical address in DRAM of MMU page tables. * @mmu_dram_default_page_addr: DRAM default page physical address. * @mmu_pgt_size: MMU page tables total size. @@ -189,6 +191,8 @@ struct asic_fixed_properties { u64 va_space_dram_start_address; u64 va_space_dram_end_address; u64 dram_size_for_default_page_mapping; + u64 pcie_dbi_base_address; + u64 pcie_aux_dbi_reg_addr; u64 mmu_pgt_addr; u64 mmu_dram_default_page_addr; u32 mmu_pgt_size; @@ -485,6 +489,9 @@ enum hl_pll_frequency { * @get_eeprom_data: retrieve EEPROM data from F/W. * @send_cpu_message: send buffer to ArmCP. * @get_hw_state: retrieve the H/W state + * @pci_bars_map: Map PCI BARs. + * @set_dram_bar_base: Set DRAM BAR to map specific device address. + * @init_iatu: Initialize the iATU unit inside the PCI controller. */ struct hl_asic_funcs { int (*early_init)(struct hl_device *hdev); @@ -558,6 +565,9 @@ struct hl_asic_funcs { int (*send_cpu_message)(struct hl_device *hdev, u32 *msg, u16 len, u32 timeout, long *result); enum hl_device_hw_state (*get_hw_state)(struct hl_device *hdev); + int (*pci_bars_map)(struct hl_device *hdev); + int (*set_dram_bar_base)(struct hl_device *hdev, u64 addr); + int (*init_iatu)(struct hl_device *hdev); }; @@ -1368,6 +1378,16 @@ int hl_fw_send_heartbeat(struct hl_device *hdev); int hl_fw_armcp_info_get(struct hl_device *hdev); int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size); +int hl_pci_bars_map(struct hl_device *hdev, const char * const name[3], + bool is_wc[3]); +int hl_pci_iatu_write(struct hl_device *hdev, u32 addr, u32 data); +int hl_pci_set_dram_bar_base(struct hl_device *hdev, u8 inbound_region, u8 bar, + u64 addr); +int hl_pci_init_iatu(struct hl_device *hdev, u64 sram_base_address, + u64 dram_base_address, u64 host_phys_size); +int hl_pci_init(struct hl_device *hdev); +void hl_pci_fini(struct hl_device *hdev); + long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr); void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq); long hl_get_temperature(struct hl_device *hdev, int sensor_index, u32 attr); diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h index a161ecfe74de..8618891d5afa 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h @@ -189,18 +189,6 @@ 1 << CPU_CA53_CFG_ARM_RST_CONTROL_NL2RESET_SHIFT |\ 1 << CPU_CA53_CFG_ARM_RST_CONTROL_NMBISTRESET_SHIFT) -/* PCI CONFIGURATION SPACE */ -#define mmPCI_CONFIG_ELBI_ADDR 0xFF0 -#define mmPCI_CONFIG_ELBI_DATA 0xFF4 -#define mmPCI_CONFIG_ELBI_CTRL 0xFF8 -#define PCI_CONFIG_ELBI_CTRL_WRITE (1 << 31) - -#define mmPCI_CONFIG_ELBI_STS 0xFFC -#define PCI_CONFIG_ELBI_STS_ERR (1 << 30) -#define PCI_CONFIG_ELBI_STS_DONE (1 << 31) -#define PCI_CONFIG_ELBI_STS_MASK (PCI_CONFIG_ELBI_STS_ERR | \ - PCI_CONFIG_ELBI_STS_DONE) - #define GOYA_IRQ_HBW_ID_MASK 0x1FFF #define GOYA_IRQ_HBW_ID_SHIFT 0 #define GOYA_IRQ_HBW_INTERNAL_ID_MASK 0xE000 diff --git a/drivers/misc/habanalabs/include/hw_ip/pci/pci_general.h b/drivers/misc/habanalabs/include/hw_ip/pci/pci_general.h new file mode 100644 index 000000000000..d232081d4e0f --- /dev/null +++ b/drivers/misc/habanalabs/include/hw_ip/pci/pci_general.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright 2016-2019 HabanaLabs, Ltd. + * All Rights Reserved. + * + */ + +#ifndef INCLUDE_PCI_GENERAL_H_ +#define INCLUDE_PCI_GENERAL_H_ + +/* PCI CONFIGURATION SPACE */ +#define mmPCI_CONFIG_ELBI_ADDR 0xFF0 +#define mmPCI_CONFIG_ELBI_DATA 0xFF4 +#define mmPCI_CONFIG_ELBI_CTRL 0xFF8 +#define PCI_CONFIG_ELBI_CTRL_WRITE (1 << 31) + +#define mmPCI_CONFIG_ELBI_STS 0xFFC +#define PCI_CONFIG_ELBI_STS_ERR (1 << 30) +#define PCI_CONFIG_ELBI_STS_DONE (1 << 31) +#define PCI_CONFIG_ELBI_STS_MASK (PCI_CONFIG_ELBI_STS_ERR | \ + PCI_CONFIG_ELBI_STS_DONE) + +#endif /* INCLUDE_PCI_GENERAL_H_ */ diff --git a/drivers/misc/habanalabs/pci.c b/drivers/misc/habanalabs/pci.c new file mode 100644 index 000000000000..822ac110b997 --- /dev/null +++ b/drivers/misc/habanalabs/pci.c @@ -0,0 +1,370 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2016-2019 HabanaLabs, Ltd. + * All Rights Reserved. + */ + +#include "habanalabs.h" +#include "include/hw_ip/pci/pci_general.h" + +#include + +/** + * hl_pci_bars_map() - Map PCI BARs. + * @hdev: Pointer to hl_device structure. + * @bar_name: Array of BAR names. + * @is_wc: Array with flag per BAR whether a write-combined mapping is needed. + * + * Request PCI regions and map them to kernel virtual addresses. + * + * Return: 0 on success, non-zero for failure. + */ +int hl_pci_bars_map(struct hl_device *hdev, const char * const name[3], + bool is_wc[3]) +{ + struct pci_dev *pdev = hdev->pdev; + int rc, i, bar; + + rc = pci_request_regions(pdev, HL_NAME); + if (rc) { + dev_err(hdev->dev, "Cannot obtain PCI resources\n"); + return rc; + } + + for (i = 0 ; i < 3 ; i++) { + bar = i * 2; /* 64-bit BARs */ + hdev->pcie_bar[bar] = is_wc[i] ? + pci_ioremap_wc_bar(pdev, bar) : + pci_ioremap_bar(pdev, bar); + if (!hdev->pcie_bar[bar]) { + dev_err(hdev->dev, "pci_ioremap%s_bar failed for %s\n", + is_wc[i] ? "_wc" : "", name[i]); + rc = -ENODEV; + goto err; + } + } + + return 0; + +err: + for (i = 2 ; i >= 0 ; i--) { + bar = i * 2; /* 64-bit BARs */ + if (hdev->pcie_bar[bar]) + iounmap(hdev->pcie_bar[bar]); + } + + pci_release_regions(pdev); + + return rc; +} + +/* + * hl_pci_bars_unmap() - Unmap PCI BARS. + * @hdev: Pointer to hl_device structure. + * + * Release all PCI BARs and unmap their virtual addresses. + */ +static void hl_pci_bars_unmap(struct hl_device *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int i, bar; + + for (i = 2 ; i >= 0 ; i--) { + bar = i * 2; /* 64-bit BARs */ + iounmap(hdev->pcie_bar[bar]); + } + + pci_release_regions(pdev); +} + +/* + * hl_pci_elbi_write() - Write through the ELBI interface. + * @hdev: Pointer to hl_device structure. + * + * Return: 0 on success, negative value for failure. + */ +static int hl_pci_elbi_write(struct hl_device *hdev, u64 addr, u32 data) +{ + struct pci_dev *pdev = hdev->pdev; + ktime_t timeout; + u32 val; + + /* Clear previous status */ + pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, 0); + + pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_ADDR, (u32) addr); + pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_DATA, data); + pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_CTRL, + PCI_CONFIG_ELBI_CTRL_WRITE); + + timeout = ktime_add_ms(ktime_get(), 10); + for (;;) { + pci_read_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, &val); + if (val & PCI_CONFIG_ELBI_STS_MASK) + break; + if (ktime_compare(ktime_get(), timeout) > 0) { + pci_read_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, + &val); + break; + } + + usleep_range(300, 500); + } + + if ((val & PCI_CONFIG_ELBI_STS_MASK) == PCI_CONFIG_ELBI_STS_DONE) + return 0; + + if (val & PCI_CONFIG_ELBI_STS_ERR) { + dev_err(hdev->dev, "Error writing to ELBI\n"); + return -EIO; + } + + if (!(val & PCI_CONFIG_ELBI_STS_MASK)) { + dev_err(hdev->dev, "ELBI write didn't finish in time\n"); + return -EIO; + } + + dev_err(hdev->dev, "ELBI write has undefined bits in status\n"); + return -EIO; +} + +/** + * hl_pci_iatu_write() - iatu write routine. + * @hdev: Pointer to hl_device structure. + * + * Return: 0 on success, negative value for failure. + */ +int hl_pci_iatu_write(struct hl_device *hdev, u32 addr, u32 data) +{ + struct asic_fixed_properties *prop = &hdev->asic_prop; + u32 dbi_offset; + int rc; + + dbi_offset = addr & 0xFFF; + + rc = hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0x00300000); + rc |= hl_pci_elbi_write(hdev, prop->pcie_dbi_base_address + dbi_offset, + data); + + if (rc) + return -EIO; + + return 0; +} + +/* + * hl_pci_reset_link_through_bridge() - Reset PCI link. + * @hdev: Pointer to hl_device structure. + */ +static void hl_pci_reset_link_through_bridge(struct hl_device *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + struct pci_dev *parent_port; + u16 val; + + parent_port = pdev->bus->self; + pci_read_config_word(parent_port, PCI_BRIDGE_CONTROL, &val); + val |= PCI_BRIDGE_CTL_BUS_RESET; + pci_write_config_word(parent_port, PCI_BRIDGE_CONTROL, val); + ssleep(1); + + val &= ~(PCI_BRIDGE_CTL_BUS_RESET); + pci_write_config_word(parent_port, PCI_BRIDGE_CONTROL, val); + ssleep(3); +} + +/** + * hl_pci_set_dram_bar_base() - Set DDR BAR to map specific device address. + * @hdev: Pointer to hl_device structure. + * @inbound_region: Inbound region number. + * @bar: PCI BAR number. + * @addr: Address in DRAM. Must be aligned to DRAM bar size. + * + * Configure the iATU so that the DRAM bar will start at the specified address. + * + * Return: 0 on success, negative value for failure. + */ +int hl_pci_set_dram_bar_base(struct hl_device *hdev, u8 inbound_region, u8 bar, + u64 addr) +{ + struct asic_fixed_properties *prop = &hdev->asic_prop; + u32 offset; + int rc; + + switch (inbound_region) { + case 0: + offset = 0x100; + break; + case 1: + offset = 0x300; + break; + case 2: + offset = 0x500; + break; + default: + dev_err(hdev->dev, "Invalid inbound region %d\n", + inbound_region); + return -EINVAL; + } + + if (bar != 0 && bar != 2 && bar != 4) { + dev_err(hdev->dev, "Invalid PCI BAR %d\n", bar); + return -EINVAL; + } + + /* Point to the specified address */ + rc = hl_pci_iatu_write(hdev, offset + 0x14, lower_32_bits(addr)); + rc |= hl_pci_iatu_write(hdev, offset + 0x18, upper_32_bits(addr)); + rc |= hl_pci_iatu_write(hdev, offset + 0x0, 0); + /* Enable + BAR match + match enable + BAR number */ + rc |= hl_pci_iatu_write(hdev, offset + 0x4, 0xC0080000 | (bar << 8)); + + /* Return the DBI window to the default location */ + rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0); + rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr + 4, 0); + + if (rc) + dev_err(hdev->dev, "failed to map DRAM bar to 0x%08llx\n", + addr); + + return rc; +} + +/** + * hl_pci_init_iatu() - Initialize the iATU unit inside the PCI controller. + * @hdev: Pointer to hl_device structure. + * @sram_base_address: SRAM base address. + * @dram_base_address: DRAM base address. + * @host_phys_size: Size of host memory for device transactions. + * + * This is needed in case the firmware doesn't initialize the iATU. + * + * Return: 0 on success, negative value for failure. + */ +int hl_pci_init_iatu(struct hl_device *hdev, u64 sram_base_address, + u64 dram_base_address, u64 host_phys_size) +{ + struct asic_fixed_properties *prop = &hdev->asic_prop; + u64 host_phys_end_addr; + int rc = 0; + + /* Inbound Region 0 - Bar 0 - Point to SRAM base address */ + rc = hl_pci_iatu_write(hdev, 0x114, lower_32_bits(sram_base_address)); + rc |= hl_pci_iatu_write(hdev, 0x118, upper_32_bits(sram_base_address)); + rc |= hl_pci_iatu_write(hdev, 0x100, 0); + /* Enable + Bar match + match enable */ + rc |= hl_pci_iatu_write(hdev, 0x104, 0xC0080000); + + /* Point to DRAM */ + if (!hdev->asic_funcs->set_dram_bar_base) + return -EINVAL; + rc |= hdev->asic_funcs->set_dram_bar_base(hdev, dram_base_address); + + /* Outbound Region 0 - Point to Host */ + host_phys_end_addr = prop->host_phys_base_address + host_phys_size - 1; + rc |= hl_pci_iatu_write(hdev, 0x008, + lower_32_bits(prop->host_phys_base_address)); + rc |= hl_pci_iatu_write(hdev, 0x00C, + upper_32_bits(prop->host_phys_base_address)); + rc |= hl_pci_iatu_write(hdev, 0x010, lower_32_bits(host_phys_end_addr)); + rc |= hl_pci_iatu_write(hdev, 0x014, 0); + rc |= hl_pci_iatu_write(hdev, 0x018, 0); + rc |= hl_pci_iatu_write(hdev, 0x020, upper_32_bits(host_phys_end_addr)); + /* Increase region size */ + rc |= hl_pci_iatu_write(hdev, 0x000, 0x00002000); + /* Enable */ + rc |= hl_pci_iatu_write(hdev, 0x004, 0x80000000); + + /* Return the DBI window to the default location */ + rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0); + rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr + 4, 0); + + if (rc) + return -EIO; + + return 0; +} + +/** + * hl_pci_init() - PCI initialization code. + * @hdev: Pointer to hl_device structure. + * + * Set DMA masks, initialize the PCI controller and map the PCI BARs. + * + * Return: 0 on success, non-zero for failure. + */ +int hl_pci_init(struct hl_device *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int rc; + + /* set DMA mask */ + rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(39)); + if (rc) { + dev_warn(hdev->dev, "Unable to set pci dma mask to 39 bits\n"); + rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + if (rc) { + dev_err(hdev->dev, + "Unable to set pci dma mask to 32 bits\n"); + return rc; + } + } + + rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39)); + if (rc) { + dev_warn(hdev->dev, + "Unable to set pci consistent dma mask to 39 bits\n"); + rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + if (rc) { + dev_err(hdev->dev, + "Unable to set pci consistent dma mask to 32 bits\n"); + return rc; + } + } + + if (hdev->reset_pcilink) + hl_pci_reset_link_through_bridge(hdev); + + rc = pci_enable_device_mem(pdev); + if (rc) { + dev_err(hdev->dev, "can't enable PCI device\n"); + return rc; + } + + pci_set_master(pdev); + + rc = hdev->asic_funcs->init_iatu(hdev); + if (rc) { + dev_err(hdev->dev, "Failed to initialize iATU\n"); + goto disable_device; + } + + rc = hdev->asic_funcs->pci_bars_map(hdev); + if (rc) { + dev_err(hdev->dev, "Failed to initialize PCI BARs\n"); + goto disable_device; + } + + return 0; + +disable_device: + pci_clear_master(pdev); + pci_disable_device(pdev); + + return rc; +} + +/** + * hl_fw_fini() - PCI finalization code. + * @hdev: Pointer to hl_device structure + * + * Unmap PCI bars and disable PCI device. + */ +void hl_pci_fini(struct hl_device *hdev) +{ + hl_pci_bars_unmap(hdev); + + pci_clear_master(hdev->pdev); + pci_disable_device(hdev->pdev); +} From 393e5b55e2228fdb8382cca78b2b1dcae2b17590 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Wed, 6 Mar 2019 14:30:26 +0200 Subject: [PATCH 009/255] habanalabs: Remove unneeded function pointers Remove pointers to ASIC-specific functions and instead call the functions explicitly as they are not accessed from outside the ASIC-specific files. Signed-off-by: Tomer Tayar Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 12 +++--------- drivers/misc/habanalabs/goya/goyaP.h | 4 +--- 2 files changed, 4 insertions(+), 12 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 5ce3a341ba5f..3b34627500a2 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -298,7 +298,6 @@ static u32 goya_all_events[] = { GOYA_ASYNC_EVENT_ID_DMA_BM_CH4 }; -static int goya_armcp_info_get(struct hl_device *hdev); static void goya_mmu_prepare(struct hl_device *hdev, u32 asid); static int goya_mmu_clear_pgt_range(struct hl_device *hdev); static int goya_mmu_set_dram_default_page(struct hl_device *hdev); @@ -538,10 +537,9 @@ static void goya_fetch_psoc_frequency(struct hl_device *hdev) static int goya_late_init(struct hl_device *hdev) { struct asic_fixed_properties *prop = &hdev->asic_prop; - struct goya_device *goya = hdev->asic_specific; int rc; - rc = goya->armcp_info_get(hdev); + rc = goya_armcp_info_get(hdev); if (rc) { dev_err(hdev->dev, "Failed to get armcp info\n"); return rc; @@ -628,9 +626,6 @@ static int goya_sw_init(struct hl_device *hdev) if (!goya) return -ENOMEM; - goya->test_cpu_queue = goya_test_cpu_queue; - goya->armcp_info_get = goya_armcp_info_get; - /* according to goya_init_iatu */ goya->ddr_bar_cur_addr = DRAM_PHYS_BASE; @@ -2968,7 +2963,6 @@ int goya_test_cpu_queue(struct hl_device *hdev) static int goya_test_queues(struct hl_device *hdev) { - struct goya_device *goya = hdev->asic_specific; int i, rc, ret_val = 0; for (i = 0 ; i < NUMBER_OF_EXT_HW_QUEUES ; i++) { @@ -2978,7 +2972,7 @@ static int goya_test_queues(struct hl_device *hdev) } if (hdev->cpu_queues_enable) { - rc = goya->test_cpu_queue(hdev); + rc = goya_test_cpu_queue(hdev); if (rc) ret_val = -EINVAL; } @@ -4656,7 +4650,7 @@ int goya_send_heartbeat(struct hl_device *hdev) return hl_fw_send_heartbeat(hdev); } -static int goya_armcp_info_get(struct hl_device *hdev) +int goya_armcp_info_get(struct hl_device *hdev) { struct goya_device *goya = hdev->asic_specific; struct asic_fixed_properties *prop = &hdev->asic_prop; diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h index ae5e41bc8f7f..b99d92f197eb 100644 --- a/drivers/misc/habanalabs/goya/goyaP.h +++ b/drivers/misc/habanalabs/goya/goyaP.h @@ -143,9 +143,6 @@ enum goya_fw_component { }; struct goya_device { - int (*test_cpu_queue)(struct hl_device *hdev); - int (*armcp_info_get)(struct hl_device *hdev); - /* TODO: remove hw_queues_lock after moving to scheduler code */ spinlock_t hw_queues_lock; @@ -176,6 +173,7 @@ void goya_debugfs_led_set(struct hl_device *hdev, u8 led, u8 state); void goya_set_pll_profile(struct hl_device *hdev, enum hl_pll_frequency freq); void goya_add_device_attr(struct hl_device *hdev, struct attribute_group *dev_attr_grp); +int goya_armcp_info_get(struct hl_device *hdev); void goya_init_security(struct hl_device *hdev); u64 goya_get_max_power(struct hl_device *hdev); void goya_set_max_power(struct hl_device *hdev, u64 value); From e1266004872c837db4ed8a72f066820ebb5d5353 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Thu, 7 Mar 2019 14:20:05 +0200 Subject: [PATCH 010/255] uapi/habanalabs: add some comments in habanalabs.h This patch adds two comments in uapi/habanalabs.h: - From which queue id the internal queues begin - Invalid values that can be returned in the seq field from the CS IOCTL Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 7fd6f633534c..ab1957e31077 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -33,7 +33,7 @@ enum goya_queue_id { GOYA_QUEUE_ID_DMA_3, GOYA_QUEUE_ID_DMA_4, GOYA_QUEUE_ID_CPU_PQ, - GOYA_QUEUE_ID_MME, + GOYA_QUEUE_ID_MME, /* Internal queues start here */ GOYA_QUEUE_ID_TPC0, GOYA_QUEUE_ID_TPC1, GOYA_QUEUE_ID_TPC2, @@ -181,7 +181,10 @@ struct hl_cs_in { }; struct hl_cs_out { - /* this holds the sequence number of the CS to pass to wait ioctl */ + /* + * seq holds the sequence number of the CS to pass to wait ioctl. All + * values are valid except for 0 and ULLONG_MAX + */ __u64 seq; /* HL_CS_STATUS_* */ __u32 status; From c811f7bc771f1cc3b1d932d5439757802806a789 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Thu, 7 Mar 2019 14:26:02 +0200 Subject: [PATCH 011/255] habanalabs: Add a printout with the name of a busy engine Print the name of a busy engine when checking if a device is idle. The change is done mainly to help a user to pinpoint problems in his topology's recipe. Signed-off-by: Tomer Tayar Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 24 ++++++++++++---------- drivers/misc/habanalabs/habanalabs.h | 8 +++++++- drivers/misc/habanalabs/habanalabs_ioctl.c | 2 +- 3 files changed, 21 insertions(+), 13 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 3b34627500a2..630979422390 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -2783,6 +2783,7 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) dma_addr_t fence_dma_addr; struct hl_cb *cb; u32 tmp, timeout; + char buf[16] = {}; int rc; if (hdev->pldm) @@ -2790,9 +2791,10 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) else timeout = HL_DEVICE_TIMEOUT_USEC; - if (!hdev->asic_funcs->is_device_idle(hdev)) { + if (!hdev->asic_funcs->is_device_idle(hdev, buf, sizeof(buf))) { dev_err_ratelimited(hdev->dev, - "Can't send KMD job on QMAN0 if device is not idle\n"); + "Can't send KMD job on QMAN0 because %s is busy\n", + buf); return -EBUSY; } @@ -4691,7 +4693,7 @@ static void goya_disable_clock_gating(struct hl_device *hdev) } -static bool goya_is_device_idle(struct hl_device *hdev) +static bool goya_is_device_idle(struct hl_device *hdev, char *buf, size_t size) { u64 offset, dma_qm_reg, tpc_qm_reg, tpc_cmdq_reg, tpc_cfg_reg; int i; @@ -4703,7 +4705,7 @@ static bool goya_is_device_idle(struct hl_device *hdev) if ((RREG32(dma_qm_reg) & DMA_QM_IDLE_MASK) != DMA_QM_IDLE_MASK) - return false; + return HL_ENG_BUSY(buf, size, "DMA%d_QM", i); } offset = mmTPC1_QM_GLBL_STS0 - mmTPC0_QM_GLBL_STS0; @@ -4715,31 +4717,31 @@ static bool goya_is_device_idle(struct hl_device *hdev) if ((RREG32(tpc_qm_reg) & TPC_QM_IDLE_MASK) != TPC_QM_IDLE_MASK) - return false; + return HL_ENG_BUSY(buf, size, "TPC%d_QM", i); if ((RREG32(tpc_cmdq_reg) & TPC_CMDQ_IDLE_MASK) != TPC_CMDQ_IDLE_MASK) - return false; + return HL_ENG_BUSY(buf, size, "TPC%d_CMDQ", i); if ((RREG32(tpc_cfg_reg) & TPC_CFG_IDLE_MASK) != TPC_CFG_IDLE_MASK) - return false; + return HL_ENG_BUSY(buf, size, "TPC%d_CFG", i); } if ((RREG32(mmMME_QM_GLBL_STS0) & MME_QM_IDLE_MASK) != MME_QM_IDLE_MASK) - return false; + return HL_ENG_BUSY(buf, size, "MME_QM"); if ((RREG32(mmMME_CMDQ_GLBL_STS0) & MME_CMDQ_IDLE_MASK) != MME_CMDQ_IDLE_MASK) - return false; + return HL_ENG_BUSY(buf, size, "MME_CMDQ"); if ((RREG32(mmMME_ARCH_STATUS) & MME_ARCH_IDLE_MASK) != MME_ARCH_IDLE_MASK) - return false; + return HL_ENG_BUSY(buf, size, "MME_ARCH"); if (RREG32(mmMME_SHADOW_0_STATUS) & MME_SHADOW_IDLE_MASK) - return false; + return HL_ENG_BUSY(buf, size, "MME"); return true; } diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index ed3649d38ff8..9cc841777d81 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -555,7 +555,7 @@ struct hl_asic_funcs { int (*send_heartbeat)(struct hl_device *hdev); void (*enable_clock_gating)(struct hl_device *hdev); void (*disable_clock_gating)(struct hl_device *hdev); - bool (*is_device_idle)(struct hl_device *hdev); + bool (*is_device_idle)(struct hl_device *hdev, char *buf, size_t size); int (*soft_reset_late_init)(struct hl_device *hdev); void (*hw_queues_lock)(struct hl_device *hdev); void (*hw_queues_unlock)(struct hl_device *hdev); @@ -1010,6 +1010,12 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val); WREG32(mm##reg, (RREG32(mm##reg) & ~REG_FIELD_MASK(reg, field)) | \ (val) << REG_FIELD_SHIFT(reg, field)) +#define HL_ENG_BUSY(buf, size, fmt, ...) ({ \ + if (buf) \ + snprintf(buf, size, fmt, ##__VA_ARGS__); \ + false; \ + }) + struct hwmon_chip_info; /** diff --git a/drivers/misc/habanalabs/habanalabs_ioctl.c b/drivers/misc/habanalabs/habanalabs_ioctl.c index 19b96afc0308..37f9de8e7404 100644 --- a/drivers/misc/habanalabs/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/habanalabs_ioctl.c @@ -93,7 +93,7 @@ static int hw_idle(struct hl_device *hdev, struct hl_info_args *args) if ((!max_size) || (!out)) return -EINVAL; - hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev); + hw_idle.is_idle = hdev->asic_funcs->is_device_idle(hdev, NULL, 0); return copy_to_user(out, &hw_idle, min((size_t) max_size, sizeof(hw_idle))) ? -EFAULT : 0; From d75bcf3e5d60d4e586f3fb20f2cc9041667497a7 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Tue, 12 Mar 2019 13:53:17 +0200 Subject: [PATCH 012/255] habanalabs: Allow accessing DRAM virtual addresses via debugfs The addr/data32 debugfs nodes currently permit the access to only physical addresses of a device. This patch extends it and allows accessing also device's DRAM virtual addresses. Signed-off-by: Tomer Tayar Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/debugfs.c | 96 +++++++++++++++++++++++++++++-- 1 file changed, 91 insertions(+), 5 deletions(-) diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c index 974a87789bd8..a4447699ff4e 100644 --- a/drivers/misc/habanalabs/debugfs.c +++ b/drivers/misc/habanalabs/debugfs.c @@ -505,22 +505,97 @@ static ssize_t mmu_write(struct file *file, const char __user *buf, return -EINVAL; } +static int device_va_to_pa(struct hl_device *hdev, u64 virt_addr, + u64 *phys_addr) +{ + struct hl_ctx *ctx = hdev->user_ctx; + u64 hop_addr, hop_pte_addr, hop_pte; + int rc = 0; + + if (!ctx) { + dev_err(hdev->dev, "no ctx available\n"); + return -EINVAL; + } + + mutex_lock(&ctx->mmu_lock); + + /* hop 0 */ + hop_addr = get_hop0_addr(ctx); + hop_pte_addr = get_hop0_pte_addr(ctx, hop_addr, virt_addr); + hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr); + + /* hop 1 */ + hop_addr = get_next_hop_addr(hop_pte); + if (hop_addr == ULLONG_MAX) + goto not_mapped; + hop_pte_addr = get_hop1_pte_addr(ctx, hop_addr, virt_addr); + hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr); + + /* hop 2 */ + hop_addr = get_next_hop_addr(hop_pte); + if (hop_addr == ULLONG_MAX) + goto not_mapped; + hop_pte_addr = get_hop2_pte_addr(ctx, hop_addr, virt_addr); + hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr); + + /* hop 3 */ + hop_addr = get_next_hop_addr(hop_pte); + if (hop_addr == ULLONG_MAX) + goto not_mapped; + hop_pte_addr = get_hop3_pte_addr(ctx, hop_addr, virt_addr); + hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr); + + if (!(hop_pte & LAST_MASK)) { + /* hop 4 */ + hop_addr = get_next_hop_addr(hop_pte); + if (hop_addr == ULLONG_MAX) + goto not_mapped; + hop_pte_addr = get_hop4_pte_addr(ctx, hop_addr, virt_addr); + hop_pte = hdev->asic_funcs->read_pte(hdev, hop_pte_addr); + } + + if (!(hop_pte & PAGE_PRESENT_MASK)) + goto not_mapped; + + *phys_addr = (hop_pte & PTE_PHYS_ADDR_MASK) | (virt_addr & OFFSET_MASK); + + goto out; + +not_mapped: + dev_err(hdev->dev, "virt addr 0x%llx is not mapped to phys addr\n", + virt_addr); + rc = -EINVAL; +out: + mutex_unlock(&ctx->mmu_lock); + return rc; +} + static ssize_t hl_data_read32(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; + struct asic_fixed_properties *prop = &hdev->asic_prop; char tmp_buf[32]; + u64 addr = entry->addr; u32 val; ssize_t rc; if (*ppos) return 0; - rc = hdev->asic_funcs->debugfs_read32(hdev, entry->addr, &val); + if (addr >= prop->va_space_dram_start_address && + addr < prop->va_space_dram_end_address && + hdev->mmu_enable && + hdev->dram_supports_virtual_memory) { + rc = device_va_to_pa(hdev, entry->addr, &addr); + if (rc) + return rc; + } + + rc = hdev->asic_funcs->debugfs_read32(hdev, addr, &val); if (rc) { - dev_err(hdev->dev, "Failed to read from 0x%010llx\n", - entry->addr); + dev_err(hdev->dev, "Failed to read from 0x%010llx\n", addr); return rc; } @@ -536,6 +611,8 @@ static ssize_t hl_data_write32(struct file *f, const char __user *buf, { struct hl_dbg_device_entry *entry = file_inode(f)->i_private; struct hl_device *hdev = entry->hdev; + struct asic_fixed_properties *prop = &hdev->asic_prop; + u64 addr = entry->addr; u32 value; ssize_t rc; @@ -543,10 +620,19 @@ static ssize_t hl_data_write32(struct file *f, const char __user *buf, if (rc) return rc; - rc = hdev->asic_funcs->debugfs_write32(hdev, entry->addr, value); + if (addr >= prop->va_space_dram_start_address && + addr < prop->va_space_dram_end_address && + hdev->mmu_enable && + hdev->dram_supports_virtual_memory) { + rc = device_va_to_pa(hdev, entry->addr, &addr); + if (rc) + return rc; + } + + rc = hdev->asic_funcs->debugfs_write32(hdev, addr, value); if (rc) { dev_err(hdev->dev, "Failed to write 0x%08x to 0x%010llx\n", - value, entry->addr); + value, addr); return rc; } From 66542c3b9d2fe179f7392f01aaf49a5b432426a7 Mon Sep 17 00:00:00 2001 From: Omer Shpigelman Date: Sun, 24 Feb 2019 09:17:55 +0200 Subject: [PATCH 013/255] habanalabs: add MMU shadow mapping This patch adds shadow mapping to the MMU module. The shadow mapping allows traversing the page table in host memory rather reading each PTE from the device memory. It brings better performance and avoids reading from invalid device address upon PCI errors. Only at the end of map/unmap flow, writings to the device are performed in order to sync the H/W page tables with the shadow ones. Signed-off-by: Omer Shpigelman Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/habanalabs.h | 24 +- .../include/hw_ip/mmu/mmu_general.h | 16 +- drivers/misc/habanalabs/mmu.c | 600 ++++++++++-------- 3 files changed, 356 insertions(+), 284 deletions(-) diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 9cc841777d81..6991a7f260e8 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -51,8 +51,9 @@ /** * struct pgt_info - MMU hop page info. - * @node: hash linked-list node for the pgts hash of pgts. - * @addr: physical address of the pgt. + * @node: hash linked-list node for the pgts shadow hash of pgts. + * @phys_addr: physical address of the pgt. + * @shadow_addr: shadow hop in the host. * @ctx: pointer to the owner ctx. * @num_of_ptes: indicates how many ptes are used in the pgt. * @@ -62,10 +63,11 @@ * page, it is freed with its pgt_info structure. */ struct pgt_info { - struct hlist_node node; - u64 addr; - struct hl_ctx *ctx; - int num_of_ptes; + struct hlist_node node; + u64 phys_addr; + u64 shadow_addr; + struct hl_ctx *ctx; + int num_of_ptes; }; struct hl_device; @@ -595,7 +597,8 @@ struct hl_va_range { * struct hl_ctx - user/kernel context. * @mem_hash: holds mapping from virtual address to virtual memory area * descriptor (hl_vm_phys_pg_list or hl_userptr). - * @mmu_hash: holds a mapping from virtual address to pgt_info structure. + * @mmu_phys_hash: holds a mapping from physical address to pgt_info structure. + * @mmu_shadow_hash: holds a mapping from shadow address to pgt_info structure. * @hpriv: pointer to the private (KMD) data of the process (fd). * @hdev: pointer to the device structure. * @refcount: reference counter for the context. Context is released only when @@ -624,7 +627,8 @@ struct hl_va_range { */ struct hl_ctx { DECLARE_HASHTABLE(mem_hash, MEM_HASH_TABLE_BITS); - DECLARE_HASHTABLE(mmu_hash, MMU_HASH_TABLE_BITS); + DECLARE_HASHTABLE(mmu_phys_hash, MMU_HASH_TABLE_BITS); + DECLARE_HASHTABLE(mmu_shadow_hash, MMU_HASH_TABLE_BITS); struct hl_fpriv *hpriv; struct hl_device *hdev; struct kref refcount; @@ -1066,7 +1070,8 @@ struct hl_device_reset_work { * @asic_specific: ASIC specific information to use only from ASIC files. * @mmu_pgt_pool: pool of available MMU hops. * @vm: virtual memory manager for MMU. - * @mmu_cache_lock: protects MMU cache invalidation as it can serve one context + * @mmu_cache_lock: protects MMU cache invalidation as it can serve one context. + * @mmu_shadow_hop0: shadow mapping of the MMU hop 0 zone. * @hwmon_dev: H/W monitor device. * @pm_mng_profile: current power management profile. * @hl_chip_info: ASIC's sensors information. @@ -1136,6 +1141,7 @@ struct hl_device { struct gen_pool *mmu_pgt_pool; struct hl_vm vm; struct mutex mmu_cache_lock; + void *mmu_shadow_hop0; struct device *hwmon_dev; enum hl_pm_mng_profile pm_mng_profile; struct hwmon_chip_info *hl_chip_info; diff --git a/drivers/misc/habanalabs/include/hw_ip/mmu/mmu_general.h b/drivers/misc/habanalabs/include/hw_ip/mmu/mmu_general.h index b680052ee3f0..71ea3c3e8ba3 100644 --- a/drivers/misc/habanalabs/include/hw_ip/mmu/mmu_general.h +++ b/drivers/misc/habanalabs/include/hw_ip/mmu/mmu_general.h @@ -14,16 +14,16 @@ #define PAGE_SIZE_4KB (_AC(1, UL) << PAGE_SHIFT_4KB) #define PAGE_MASK_2MB (~(PAGE_SIZE_2MB - 1)) -#define PAGE_PRESENT_MASK 0x0000000000001 -#define SWAP_OUT_MASK 0x0000000000004 -#define LAST_MASK 0x0000000000800 -#define PHYS_ADDR_MASK 0x3FFFFFFFFF000ull +#define PAGE_PRESENT_MASK 0x0000000000001ull +#define SWAP_OUT_MASK 0x0000000000004ull +#define LAST_MASK 0x0000000000800ull +#define PHYS_ADDR_MASK 0xFFFFFFFFFFFFF000ull #define HOP0_MASK 0x3000000000000ull #define HOP1_MASK 0x0FF8000000000ull #define HOP2_MASK 0x0007FC0000000ull -#define HOP3_MASK 0x000003FE00000 -#define HOP4_MASK 0x00000001FF000 -#define OFFSET_MASK 0x0000000000FFF +#define HOP3_MASK 0x000003FE00000ull +#define HOP4_MASK 0x00000001FF000ull +#define OFFSET_MASK 0x0000000000FFFull #define HOP0_SHIFT 48 #define HOP1_SHIFT 39 @@ -32,7 +32,7 @@ #define HOP4_SHIFT 12 #define PTE_PHYS_ADDR_SHIFT 12 -#define PTE_PHYS_ADDR_MASK ~0xFFF +#define PTE_PHYS_ADDR_MASK ~OFFSET_MASK #define HL_PTE_SIZE sizeof(u64) #define HOP_TABLE_SIZE PAGE_SIZE_4KB diff --git a/drivers/misc/habanalabs/mmu.c b/drivers/misc/habanalabs/mmu.c index 3a5a2cec8305..533d9315b6fb 100644 --- a/drivers/misc/habanalabs/mmu.c +++ b/drivers/misc/habanalabs/mmu.c @@ -11,13 +11,15 @@ #include #include -static struct pgt_info *get_pgt_info(struct hl_ctx *ctx, u64 addr) +static inline u64 get_phys_addr(struct hl_ctx *ctx, u64 shadow_addr); + +static struct pgt_info *get_pgt_info(struct hl_ctx *ctx, u64 hop_addr) { struct pgt_info *pgt_info = NULL; - hash_for_each_possible(ctx->mmu_hash, pgt_info, node, - (unsigned long) addr) - if (addr == pgt_info->addr) + hash_for_each_possible(ctx->mmu_shadow_hash, pgt_info, node, + (unsigned long) hop_addr) + if (hop_addr == pgt_info->shadow_addr) break; return pgt_info; @@ -25,45 +27,109 @@ static struct pgt_info *get_pgt_info(struct hl_ctx *ctx, u64 addr) static void free_hop(struct hl_ctx *ctx, u64 hop_addr) { + struct hl_device *hdev = ctx->hdev; struct pgt_info *pgt_info = get_pgt_info(ctx, hop_addr); - gen_pool_free(pgt_info->ctx->hdev->mmu_pgt_pool, pgt_info->addr, - ctx->hdev->asic_prop.mmu_hop_table_size); + gen_pool_free(hdev->mmu_pgt_pool, pgt_info->phys_addr, + hdev->asic_prop.mmu_hop_table_size); hash_del(&pgt_info->node); - + kfree((u64 *) (uintptr_t) pgt_info->shadow_addr); kfree(pgt_info); } static u64 alloc_hop(struct hl_ctx *ctx) { struct hl_device *hdev = ctx->hdev; + struct asic_fixed_properties *prop = &hdev->asic_prop; struct pgt_info *pgt_info; - u64 addr; + u64 phys_addr, shadow_addr; pgt_info = kmalloc(sizeof(*pgt_info), GFP_KERNEL); if (!pgt_info) return ULLONG_MAX; - addr = (u64) gen_pool_alloc(hdev->mmu_pgt_pool, - hdev->asic_prop.mmu_hop_table_size); - if (!addr) { + phys_addr = (u64) gen_pool_alloc(hdev->mmu_pgt_pool, + prop->mmu_hop_table_size); + if (!phys_addr) { dev_err(hdev->dev, "failed to allocate page\n"); - kfree(pgt_info); - return ULLONG_MAX; + goto pool_add_err; } - pgt_info->addr = addr; + shadow_addr = (u64) (uintptr_t) kzalloc(prop->mmu_hop_table_size, + GFP_KERNEL); + if (!shadow_addr) + goto shadow_err; + + pgt_info->phys_addr = phys_addr; + pgt_info->shadow_addr = shadow_addr; pgt_info->ctx = ctx; pgt_info->num_of_ptes = 0; - hash_add(ctx->mmu_hash, &pgt_info->node, addr); + hash_add(ctx->mmu_shadow_hash, &pgt_info->node, shadow_addr); - return addr; + return shadow_addr; + +shadow_err: + gen_pool_free(hdev->mmu_pgt_pool, phys_addr, prop->mmu_hop_table_size); +pool_add_err: + kfree(pgt_info); + + return ULLONG_MAX; } -static inline void clear_pte(struct hl_device *hdev, u64 pte_addr) +static inline u64 get_phys_hop0_addr(struct hl_ctx *ctx) { - /* clear the last and present bits */ - hdev->asic_funcs->write_pte(hdev, pte_addr, 0); + return ctx->hdev->asic_prop.mmu_pgt_addr + + (ctx->asid * ctx->hdev->asic_prop.mmu_hop_table_size); +} + +static inline u64 get_hop0_addr(struct hl_ctx *ctx) +{ + return (u64) (uintptr_t) ctx->hdev->mmu_shadow_hop0 + + (ctx->asid * ctx->hdev->asic_prop.mmu_hop_table_size); +} + +static inline void flush(struct hl_ctx *ctx) +{ + /* flush all writes from all cores to reach PCI */ + mb(); + ctx->hdev->asic_funcs->read_pte(ctx->hdev, get_phys_hop0_addr(ctx)); +} + +/* transform the value to physical address when writing to H/W */ +static inline void write_pte(struct hl_ctx *ctx, u64 shadow_pte_addr, u64 val) +{ + /* + * The value to write is actually the address of the next shadow hop + + * flags at the 12 LSBs. + * Hence in order to get the value to write to the physical PTE, we + * clear the 12 LSBs and translate the shadow hop to its associated + * physical hop, and add back the original 12 LSBs. + */ + u64 phys_val = get_phys_addr(ctx, val & PTE_PHYS_ADDR_MASK) | + (val & OFFSET_MASK); + + ctx->hdev->asic_funcs->write_pte(ctx->hdev, + get_phys_addr(ctx, shadow_pte_addr), + phys_val); + + *(u64 *) (uintptr_t) shadow_pte_addr = val; +} + +/* do not transform the value to physical address when writing to H/W */ +static inline void write_final_pte(struct hl_ctx *ctx, u64 shadow_pte_addr, + u64 val) +{ + ctx->hdev->asic_funcs->write_pte(ctx->hdev, + get_phys_addr(ctx, shadow_pte_addr), + val); + *(u64 *) (uintptr_t) shadow_pte_addr = val; +} + +/* clear the last and present bits */ +static inline void clear_pte(struct hl_ctx *ctx, u64 pte_addr) +{ + /* no need to transform the value to physical address */ + write_final_pte(ctx, pte_addr, 0); } static inline void get_pte(struct hl_ctx *ctx, u64 hop_addr) @@ -98,12 +164,6 @@ static inline int put_pte(struct hl_ctx *ctx, u64 hop_addr) return num_of_ptes_left; } -static inline u64 get_hop0_addr(struct hl_ctx *ctx) -{ - return ctx->hdev->asic_prop.mmu_pgt_addr + - (ctx->asid * ctx->hdev->asic_prop.mmu_hop_table_size); -} - static inline u64 get_hopN_pte_addr(struct hl_ctx *ctx, u64 hop_addr, u64 virt_addr, u64 mask, u64 shift) { @@ -136,7 +196,7 @@ static inline u64 get_hop4_pte_addr(struct hl_ctx *ctx, u64 hop_addr, u64 vaddr) return get_hopN_pte_addr(ctx, hop_addr, vaddr, HOP4_MASK, HOP4_SHIFT); } -static inline u64 get_next_hop_addr(u64 curr_pte) +static inline u64 get_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte) { if (curr_pte & PAGE_PRESENT_MASK) return curr_pte & PHYS_ADDR_MASK; @@ -147,7 +207,7 @@ static inline u64 get_next_hop_addr(u64 curr_pte) static inline u64 get_alloc_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte, bool *is_new_hop) { - u64 hop_addr = get_next_hop_addr(curr_pte); + u64 hop_addr = get_next_hop_addr(ctx, curr_pte); if (hop_addr == ULLONG_MAX) { hop_addr = alloc_hop(ctx); @@ -157,106 +217,30 @@ static inline u64 get_alloc_next_hop_addr(struct hl_ctx *ctx, u64 curr_pte, return hop_addr; } -/* - * hl_mmu_init - init the mmu module - * - * @hdev: pointer to the habanalabs device structure - * - * This function does the following: - * - Allocate max_asid zeroed hop0 pgts so no mapping is available - * - Enable mmu in hw - * - Invalidate the mmu cache - * - Create a pool of pages for pgts - * - Returns 0 on success - * - * This function depends on DMA QMAN to be working! - */ -int hl_mmu_init(struct hl_device *hdev) +/* translates shadow address inside hop to a physical address */ +static inline u64 get_phys_addr(struct hl_ctx *ctx, u64 shadow_addr) { - struct asic_fixed_properties *prop = &hdev->asic_prop; - int rc; + u64 page_mask = (ctx->hdev->asic_prop.mmu_hop_table_size - 1); + u64 shadow_hop_addr = shadow_addr & ~page_mask; + u64 pte_offset = shadow_addr & page_mask; + u64 phys_hop_addr; - if (!hdev->mmu_enable) - return 0; + if (shadow_hop_addr != get_hop0_addr(ctx)) + phys_hop_addr = get_pgt_info(ctx, shadow_hop_addr)->phys_addr; + else + phys_hop_addr = get_phys_hop0_addr(ctx); - /* MMU HW init was already done in device hw_init() */ - - mutex_init(&hdev->mmu_cache_lock); - - hdev->mmu_pgt_pool = - gen_pool_create(__ffs(prop->mmu_hop_table_size), -1); - - if (!hdev->mmu_pgt_pool) { - dev_err(hdev->dev, "Failed to create page gen pool\n"); - rc = -ENOMEM; - goto err_pool_create; - } - - rc = gen_pool_add(hdev->mmu_pgt_pool, prop->mmu_pgt_addr + - prop->mmu_hop0_tables_total_size, - prop->mmu_pgt_size - prop->mmu_hop0_tables_total_size, - -1); - if (rc) { - dev_err(hdev->dev, "Failed to add memory to page gen pool\n"); - goto err_pool_add; - } - - return 0; - -err_pool_add: - gen_pool_destroy(hdev->mmu_pgt_pool); -err_pool_create: - mutex_destroy(&hdev->mmu_cache_lock); - - return rc; + return phys_hop_addr + pte_offset; } -/* - * hl_mmu_fini - release the mmu module. - * - * @hdev: pointer to the habanalabs device structure - * - * This function does the following: - * - Disable mmu in hw - * - free the pgts pool - * - * All ctxs should be freed before calling this func - */ -void hl_mmu_fini(struct hl_device *hdev) -{ - if (!hdev->mmu_enable) - return; - - gen_pool_destroy(hdev->mmu_pgt_pool); - - mutex_destroy(&hdev->mmu_cache_lock); - - /* MMU HW fini will be done in device hw_fini() */ -} - -/** - * hl_mmu_ctx_init() - initialize a context for using the MMU module. - * @ctx: pointer to the context structure to initialize. - * - * Initialize a mutex to protect the concurrent mapping flow, a hash to hold all - * page tables hops related to this context and an optional DRAM default page - * mapping. - * Return: 0 on success, non-zero otherwise. - */ -int hl_mmu_ctx_init(struct hl_ctx *ctx) +static int dram_default_mapping_init(struct hl_ctx *ctx) { struct hl_device *hdev = ctx->hdev; struct asic_fixed_properties *prop = &hdev->asic_prop; - u64 num_of_hop3, total_hops, hop1_addr, hop2_addr, hop2_pte_addr, - hop3_pte_addr, pte_val; + u64 num_of_hop3, total_hops, hop0_addr, hop1_addr, hop2_addr, + hop2_pte_addr, hop3_pte_addr, pte_val; int rc, i, j, hop3_allocated = 0; - if (!hdev->mmu_enable) - return 0; - - mutex_init(&ctx->mmu_lock); - hash_init(ctx->mmu_hash); - if (!hdev->dram_supports_virtual_memory || !hdev->dram_default_page_mapping) return 0; @@ -269,10 +253,10 @@ int hl_mmu_ctx_init(struct hl_ctx *ctx) total_hops = num_of_hop3 + 2; ctx->dram_default_hops = kzalloc(HL_PTE_SIZE * total_hops, GFP_KERNEL); - if (!ctx->dram_default_hops) { - rc = -ENOMEM; - goto alloc_err; - } + if (!ctx->dram_default_hops) + return -ENOMEM; + + hop0_addr = get_hop0_addr(ctx); hop1_addr = alloc_hop(ctx); if (hop1_addr == ULLONG_MAX) { @@ -304,17 +288,17 @@ int hl_mmu_ctx_init(struct hl_ctx *ctx) /* need only pte 0 in hops 0 and 1 */ pte_val = (hop1_addr & PTE_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK; - hdev->asic_funcs->write_pte(hdev, get_hop0_addr(ctx), pte_val); + write_pte(ctx, hop0_addr, pte_val); pte_val = (hop2_addr & PTE_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK; - hdev->asic_funcs->write_pte(hdev, hop1_addr, pte_val); + write_pte(ctx, hop1_addr, pte_val); get_pte(ctx, hop1_addr); hop2_pte_addr = hop2_addr; for (i = 0 ; i < num_of_hop3 ; i++) { pte_val = (ctx->dram_default_hops[i] & PTE_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK; - hdev->asic_funcs->write_pte(hdev, hop2_pte_addr, pte_val); + write_pte(ctx, hop2_pte_addr, pte_val); get_pte(ctx, hop2_addr); hop2_pte_addr += HL_PTE_SIZE; } @@ -325,33 +309,183 @@ int hl_mmu_ctx_init(struct hl_ctx *ctx) for (i = 0 ; i < num_of_hop3 ; i++) { hop3_pte_addr = ctx->dram_default_hops[i]; for (j = 0 ; j < PTE_ENTRIES_IN_HOP ; j++) { - hdev->asic_funcs->write_pte(hdev, hop3_pte_addr, - pte_val); + write_final_pte(ctx, hop3_pte_addr, pte_val); get_pte(ctx, ctx->dram_default_hops[i]); hop3_pte_addr += HL_PTE_SIZE; } } - /* flush all writes to reach PCI */ - mb(); - hdev->asic_funcs->read_pte(hdev, hop2_addr); + flush(ctx); return 0; hop3_err: for (i = 0 ; i < hop3_allocated ; i++) free_hop(ctx, ctx->dram_default_hops[i]); + free_hop(ctx, hop2_addr); hop2_err: free_hop(ctx, hop1_addr); hop1_err: kfree(ctx->dram_default_hops); -alloc_err: - mutex_destroy(&ctx->mmu_lock); return rc; } +static void dram_default_mapping_fini(struct hl_ctx *ctx) +{ + struct hl_device *hdev = ctx->hdev; + struct asic_fixed_properties *prop = &hdev->asic_prop; + u64 num_of_hop3, total_hops, hop0_addr, hop1_addr, hop2_addr, + hop2_pte_addr, hop3_pte_addr; + int i, j; + + if (!hdev->dram_supports_virtual_memory || + !hdev->dram_default_page_mapping) + return; + + num_of_hop3 = prop->dram_size_for_default_page_mapping; + do_div(num_of_hop3, prop->dram_page_size); + do_div(num_of_hop3, PTE_ENTRIES_IN_HOP); + + hop0_addr = get_hop0_addr(ctx); + /* add hop1 and hop2 */ + total_hops = num_of_hop3 + 2; + hop1_addr = ctx->dram_default_hops[total_hops - 1]; + hop2_addr = ctx->dram_default_hops[total_hops - 2]; + + for (i = 0 ; i < num_of_hop3 ; i++) { + hop3_pte_addr = ctx->dram_default_hops[i]; + for (j = 0 ; j < PTE_ENTRIES_IN_HOP ; j++) { + clear_pte(ctx, hop3_pte_addr); + put_pte(ctx, ctx->dram_default_hops[i]); + hop3_pte_addr += HL_PTE_SIZE; + } + } + + hop2_pte_addr = hop2_addr; + hop2_pte_addr = hop2_addr; + for (i = 0 ; i < num_of_hop3 ; i++) { + clear_pte(ctx, hop2_pte_addr); + put_pte(ctx, hop2_addr); + hop2_pte_addr += HL_PTE_SIZE; + } + + clear_pte(ctx, hop1_addr); + put_pte(ctx, hop1_addr); + clear_pte(ctx, hop0_addr); + + kfree(ctx->dram_default_hops); + + flush(ctx); +} + +/** + * hl_mmu_init() - initialize the MMU module. + * @hdev: habanalabs device structure. + * + * This function does the following: + * - Allocate max_asid zeroed hop0 pgts so no mapping is available. + * - Enable MMU in H/W. + * - Invalidate the MMU cache. + * - Create a pool of pages for pgt_infos. + * + * This function depends on DMA QMAN to be working! + * + * Return: 0 for success, non-zero for failure. + */ +int hl_mmu_init(struct hl_device *hdev) +{ + struct asic_fixed_properties *prop = &hdev->asic_prop; + int rc; + + if (!hdev->mmu_enable) + return 0; + + /* MMU H/W init was already done in device hw_init() */ + + mutex_init(&hdev->mmu_cache_lock); + + hdev->mmu_pgt_pool = + gen_pool_create(__ffs(prop->mmu_hop_table_size), -1); + + if (!hdev->mmu_pgt_pool) { + dev_err(hdev->dev, "Failed to create page gen pool\n"); + rc = -ENOMEM; + goto err_pool_create; + } + + rc = gen_pool_add(hdev->mmu_pgt_pool, prop->mmu_pgt_addr + + prop->mmu_hop0_tables_total_size, + prop->mmu_pgt_size - prop->mmu_hop0_tables_total_size, + -1); + if (rc) { + dev_err(hdev->dev, "Failed to add memory to page gen pool\n"); + goto err_pool_add; + } + + hdev->mmu_shadow_hop0 = kvmalloc_array(prop->max_asid, + prop->mmu_hop_table_size, + GFP_KERNEL | __GFP_ZERO); + if (!hdev->mmu_shadow_hop0) { + rc = -ENOMEM; + goto err_pool_add; + } + + return 0; + +err_pool_add: + gen_pool_destroy(hdev->mmu_pgt_pool); +err_pool_create: + mutex_destroy(&hdev->mmu_cache_lock); + + return rc; +} + +/** + * hl_mmu_fini() - release the MMU module. + * @hdev: habanalabs device structure. + * + * This function does the following: + * - Disable MMU in H/W. + * - Free the pgt_infos pool. + * + * All contexts should be freed before calling this function. + */ +void hl_mmu_fini(struct hl_device *hdev) +{ + if (!hdev->mmu_enable) + return; + + kvfree(hdev->mmu_shadow_hop0); + gen_pool_destroy(hdev->mmu_pgt_pool); + mutex_destroy(&hdev->mmu_cache_lock); + + /* MMU H/W fini will be done in device hw_fini() */ +} + +/** + * hl_mmu_ctx_init() - initialize a context for using the MMU module. + * @ctx: pointer to the context structure to initialize. + * + * Initialize a mutex to protect the concurrent mapping flow, a hash to hold all + * page tables hops related to this context. + * Return: 0 on success, non-zero otherwise. + */ +int hl_mmu_ctx_init(struct hl_ctx *ctx) +{ + struct hl_device *hdev = ctx->hdev; + + if (!hdev->mmu_enable) + return 0; + + mutex_init(&ctx->mmu_lock); + hash_init(ctx->mmu_phys_hash); + hash_init(ctx->mmu_shadow_hash); + + return dram_default_mapping_init(ctx); +} + /* * hl_mmu_ctx_fini - disable a ctx from using the mmu module * @@ -365,63 +499,23 @@ int hl_mmu_ctx_init(struct hl_ctx *ctx) void hl_mmu_ctx_fini(struct hl_ctx *ctx) { struct hl_device *hdev = ctx->hdev; - struct asic_fixed_properties *prop = &hdev->asic_prop; struct pgt_info *pgt_info; struct hlist_node *tmp; - u64 num_of_hop3, total_hops, hop1_addr, hop2_addr, hop2_pte_addr, - hop3_pte_addr; - int i, j; + int i; - if (!ctx->hdev->mmu_enable) + if (!hdev->mmu_enable) return; - if (hdev->dram_supports_virtual_memory && - hdev->dram_default_page_mapping) { + dram_default_mapping_fini(ctx); - num_of_hop3 = prop->dram_size_for_default_page_mapping; - do_div(num_of_hop3, prop->dram_page_size); - do_div(num_of_hop3, PTE_ENTRIES_IN_HOP); - - /* add hop1 and hop2 */ - total_hops = num_of_hop3 + 2; - hop1_addr = ctx->dram_default_hops[total_hops - 1]; - hop2_addr = ctx->dram_default_hops[total_hops - 2]; - - for (i = 0 ; i < num_of_hop3 ; i++) { - hop3_pte_addr = ctx->dram_default_hops[i]; - for (j = 0 ; j < PTE_ENTRIES_IN_HOP ; j++) { - clear_pte(hdev, hop3_pte_addr); - put_pte(ctx, ctx->dram_default_hops[i]); - hop3_pte_addr += HL_PTE_SIZE; - } - } - - hop2_pte_addr = hop2_addr; - for (i = 0 ; i < num_of_hop3 ; i++) { - clear_pte(hdev, hop2_pte_addr); - put_pte(ctx, hop2_addr); - hop2_pte_addr += HL_PTE_SIZE; - } - - clear_pte(hdev, hop1_addr); - put_pte(ctx, hop1_addr); - clear_pte(hdev, get_hop0_addr(ctx)); - - kfree(ctx->dram_default_hops); - - /* flush all writes to reach PCI */ - mb(); - hdev->asic_funcs->read_pte(hdev, hop2_addr); - } - - if (!hash_empty(ctx->mmu_hash)) + if (!hash_empty(ctx->mmu_shadow_hash)) dev_err(hdev->dev, "ctx is freed while it has pgts in use\n"); - hash_for_each_safe(ctx->mmu_hash, i, tmp, pgt_info, node) { + hash_for_each_safe(ctx->mmu_shadow_hash, i, tmp, pgt_info, node) { dev_err(hdev->dev, "pgt_info of addr 0x%llx of asid %d was not destroyed, num_ptes: %d\n", - pgt_info->addr, ctx->asid, pgt_info->num_of_ptes); - free_hop(ctx, pgt_info->addr); + pgt_info->phys_addr, ctx->asid, pgt_info->num_of_ptes); + free_hop(ctx, pgt_info->shadow_addr); } mutex_destroy(&ctx->mmu_lock); @@ -437,45 +531,43 @@ static int _hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr) hop3_addr = 0, hop3_pte_addr = 0, hop4_addr = 0, hop4_pte_addr = 0, curr_pte; - int clear_hop3 = 1; - bool is_dram_addr, is_huge, is_dram_default_page_mapping; + bool is_dram_addr, is_huge, clear_hop3 = true; is_dram_addr = hl_mem_area_inside_range(virt_addr, PAGE_SIZE_2MB, prop->va_space_dram_start_address, prop->va_space_dram_end_address); hop0_addr = get_hop0_addr(ctx); - hop0_pte_addr = get_hop0_pte_addr(ctx, hop0_addr, virt_addr); - curr_pte = hdev->asic_funcs->read_pte(hdev, hop0_pte_addr); + curr_pte = *(u64 *) (uintptr_t) hop0_pte_addr; - hop1_addr = get_next_hop_addr(curr_pte); + hop1_addr = get_next_hop_addr(ctx, curr_pte); if (hop1_addr == ULLONG_MAX) goto not_mapped; hop1_pte_addr = get_hop1_pte_addr(ctx, hop1_addr, virt_addr); - curr_pte = hdev->asic_funcs->read_pte(hdev, hop1_pte_addr); + curr_pte = *(u64 *) (uintptr_t) hop1_pte_addr; - hop2_addr = get_next_hop_addr(curr_pte); + hop2_addr = get_next_hop_addr(ctx, curr_pte); if (hop2_addr == ULLONG_MAX) goto not_mapped; hop2_pte_addr = get_hop2_pte_addr(ctx, hop2_addr, virt_addr); - curr_pte = hdev->asic_funcs->read_pte(hdev, hop2_pte_addr); + curr_pte = *(u64 *) (uintptr_t) hop2_pte_addr; - hop3_addr = get_next_hop_addr(curr_pte); + hop3_addr = get_next_hop_addr(ctx, curr_pte); if (hop3_addr == ULLONG_MAX) goto not_mapped; hop3_pte_addr = get_hop3_pte_addr(ctx, hop3_addr, virt_addr); - curr_pte = hdev->asic_funcs->read_pte(hdev, hop3_pte_addr); + curr_pte = *(u64 *) (uintptr_t) hop3_pte_addr; is_huge = curr_pte & LAST_MASK; @@ -485,27 +577,24 @@ static int _hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr) return -EFAULT; } - is_dram_default_page_mapping = - hdev->dram_default_page_mapping && is_dram_addr; - if (!is_huge) { - hop4_addr = get_next_hop_addr(curr_pte); + hop4_addr = get_next_hop_addr(ctx, curr_pte); if (hop4_addr == ULLONG_MAX) goto not_mapped; hop4_pte_addr = get_hop4_pte_addr(ctx, hop4_addr, virt_addr); - curr_pte = hdev->asic_funcs->read_pte(hdev, hop4_pte_addr); + curr_pte = *(u64 *) (uintptr_t) hop4_pte_addr; - clear_hop3 = 0; + clear_hop3 = false; } - if (is_dram_default_page_mapping) { - u64 zero_pte = (prop->mmu_dram_default_page_addr & + if (hdev->dram_default_page_mapping && is_dram_addr) { + u64 default_pte = (prop->mmu_dram_default_page_addr & PTE_PHYS_ADDR_MASK) | LAST_MASK | PAGE_PRESENT_MASK; - if (curr_pte == zero_pte) { + if (curr_pte == default_pte) { dev_err(hdev->dev, "DRAM: hop3 PTE points to zero page, can't unmap, va: 0x%llx\n", virt_addr); @@ -519,40 +608,43 @@ static int _hl_mmu_unmap(struct hl_ctx *ctx, u64 virt_addr) goto not_mapped; } - hdev->asic_funcs->write_pte(hdev, hop3_pte_addr, zero_pte); + write_final_pte(ctx, hop3_pte_addr, default_pte); put_pte(ctx, hop3_addr); } else { if (!(curr_pte & PAGE_PRESENT_MASK)) goto not_mapped; - clear_pte(hdev, hop4_addr ? hop4_pte_addr : hop3_pte_addr); + if (hop4_addr) + clear_pte(ctx, hop4_pte_addr); + else + clear_pte(ctx, hop3_pte_addr); if (hop4_addr && !put_pte(ctx, hop4_addr)) - clear_hop3 = 1; + clear_hop3 = true; if (!clear_hop3) goto flush; - clear_pte(hdev, hop3_pte_addr); + + clear_pte(ctx, hop3_pte_addr); if (put_pte(ctx, hop3_addr)) goto flush; - clear_pte(hdev, hop2_pte_addr); + + clear_pte(ctx, hop2_pte_addr); if (put_pte(ctx, hop2_addr)) goto flush; - clear_pte(hdev, hop1_pte_addr); + + clear_pte(ctx, hop1_pte_addr); if (put_pte(ctx, hop1_addr)) goto flush; - clear_pte(hdev, hop0_pte_addr); + + clear_pte(ctx, hop0_pte_addr); } flush: - /* flush all writes from all cores to reach PCI */ - mb(); - - hdev->asic_funcs->read_pte(hdev, - hop4_addr ? hop4_pte_addr : hop3_pte_addr); + flush(ctx); return 0; @@ -632,8 +724,7 @@ static int _hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, hop4_addr = 0, hop4_pte_addr = 0, curr_pte = 0; bool hop1_new = false, hop2_new = false, hop3_new = false, - hop4_new = false, is_huge, is_dram_addr, - is_dram_default_page_mapping; + hop4_new = false, is_huge, is_dram_addr; int rc = -ENOMEM; /* @@ -654,59 +745,46 @@ static int _hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, return -EFAULT; } - is_dram_default_page_mapping = - hdev->dram_default_page_mapping && is_dram_addr; - hop0_addr = get_hop0_addr(ctx); - hop0_pte_addr = get_hop0_pte_addr(ctx, hop0_addr, virt_addr); - - curr_pte = hdev->asic_funcs->read_pte(hdev, hop0_pte_addr); + curr_pte = *(u64 *) (uintptr_t) hop0_pte_addr; hop1_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop1_new); - if (hop1_addr == ULLONG_MAX) goto err; hop1_pte_addr = get_hop1_pte_addr(ctx, hop1_addr, virt_addr); - - curr_pte = hdev->asic_funcs->read_pte(hdev, hop1_pte_addr); + curr_pte = *(u64 *) (uintptr_t) hop1_pte_addr; hop2_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop2_new); - if (hop2_addr == ULLONG_MAX) goto err; hop2_pte_addr = get_hop2_pte_addr(ctx, hop2_addr, virt_addr); - - curr_pte = hdev->asic_funcs->read_pte(hdev, hop2_pte_addr); + curr_pte = *(u64 *) (uintptr_t) hop2_pte_addr; hop3_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop3_new); - if (hop3_addr == ULLONG_MAX) goto err; hop3_pte_addr = get_hop3_pte_addr(ctx, hop3_addr, virt_addr); - - curr_pte = hdev->asic_funcs->read_pte(hdev, hop3_pte_addr); + curr_pte = *(u64 *) (uintptr_t) hop3_pte_addr; if (!is_huge) { hop4_addr = get_alloc_next_hop_addr(ctx, curr_pte, &hop4_new); - if (hop4_addr == ULLONG_MAX) goto err; hop4_pte_addr = get_hop4_pte_addr(ctx, hop4_addr, virt_addr); - - curr_pte = hdev->asic_funcs->read_pte(hdev, hop4_pte_addr); + curr_pte = *(u64 *) (uintptr_t) hop4_pte_addr; } - if (is_dram_default_page_mapping) { - u64 zero_pte = (prop->mmu_dram_default_page_addr & + if (hdev->dram_default_page_mapping && is_dram_addr) { + u64 default_pte = (prop->mmu_dram_default_page_addr & PTE_PHYS_ADDR_MASK) | LAST_MASK | PAGE_PRESENT_MASK; - if (curr_pte != zero_pte) { + if (curr_pte != default_pte) { dev_err(hdev->dev, "DRAM: mapping already exists for virt_addr 0x%llx\n", virt_addr); @@ -722,27 +800,22 @@ static int _hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, } } else if (curr_pte & PAGE_PRESENT_MASK) { dev_err(hdev->dev, - "mapping already exists for virt_addr 0x%llx\n", - virt_addr); + "mapping already exists for virt_addr 0x%llx\n", + virt_addr); dev_dbg(hdev->dev, "hop0 pte: 0x%llx (0x%llx)\n", - hdev->asic_funcs->read_pte(hdev, hop0_pte_addr), - hop0_pte_addr); + *(u64 *) (uintptr_t) hop0_pte_addr, hop0_pte_addr); dev_dbg(hdev->dev, "hop1 pte: 0x%llx (0x%llx)\n", - hdev->asic_funcs->read_pte(hdev, hop1_pte_addr), - hop1_pte_addr); + *(u64 *) (uintptr_t) hop1_pte_addr, hop1_pte_addr); dev_dbg(hdev->dev, "hop2 pte: 0x%llx (0x%llx)\n", - hdev->asic_funcs->read_pte(hdev, hop2_pte_addr), - hop2_pte_addr); + *(u64 *) (uintptr_t) hop2_pte_addr, hop2_pte_addr); dev_dbg(hdev->dev, "hop3 pte: 0x%llx (0x%llx)\n", - hdev->asic_funcs->read_pte(hdev, hop3_pte_addr), - hop3_pte_addr); + *(u64 *) (uintptr_t) hop3_pte_addr, hop3_pte_addr); if (!is_huge) dev_dbg(hdev->dev, "hop4 pte: 0x%llx (0x%llx)\n", - hdev->asic_funcs->read_pte(hdev, - hop4_pte_addr), - hop4_pte_addr); + *(u64 *) (uintptr_t) hop4_pte_addr, + hop4_pte_addr); rc = -EINVAL; goto err; @@ -751,28 +824,26 @@ static int _hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, curr_pte = (phys_addr & PTE_PHYS_ADDR_MASK) | LAST_MASK | PAGE_PRESENT_MASK; - hdev->asic_funcs->write_pte(hdev, - is_huge ? hop3_pte_addr : hop4_pte_addr, - curr_pte); + if (is_huge) + write_final_pte(ctx, hop3_pte_addr, curr_pte); + else + write_final_pte(ctx, hop4_pte_addr, curr_pte); if (hop1_new) { - curr_pte = (hop1_addr & PTE_PHYS_ADDR_MASK) | - PAGE_PRESENT_MASK; - ctx->hdev->asic_funcs->write_pte(ctx->hdev, hop0_pte_addr, - curr_pte); + curr_pte = + (hop1_addr & PTE_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK; + write_pte(ctx, hop0_pte_addr, curr_pte); } if (hop2_new) { - curr_pte = (hop2_addr & PTE_PHYS_ADDR_MASK) | - PAGE_PRESENT_MASK; - ctx->hdev->asic_funcs->write_pte(ctx->hdev, hop1_pte_addr, - curr_pte); + curr_pte = + (hop2_addr & PTE_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK; + write_pte(ctx, hop1_pte_addr, curr_pte); get_pte(ctx, hop1_addr); } if (hop3_new) { - curr_pte = (hop3_addr & PTE_PHYS_ADDR_MASK) | - PAGE_PRESENT_MASK; - ctx->hdev->asic_funcs->write_pte(ctx->hdev, hop2_pte_addr, - curr_pte); + curr_pte = + (hop3_addr & PTE_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK; + write_pte(ctx, hop2_pte_addr, curr_pte); get_pte(ctx, hop2_addr); } @@ -780,8 +851,7 @@ static int _hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, if (hop4_new) { curr_pte = (hop4_addr & PTE_PHYS_ADDR_MASK) | PAGE_PRESENT_MASK; - ctx->hdev->asic_funcs->write_pte(ctx->hdev, - hop3_pte_addr, curr_pte); + write_pte(ctx, hop3_pte_addr, curr_pte); get_pte(ctx, hop3_addr); } @@ -790,11 +860,7 @@ static int _hl_mmu_map(struct hl_ctx *ctx, u64 virt_addr, u64 phys_addr, get_pte(ctx, hop3_addr); } - /* flush all writes from all cores to reach PCI */ - mb(); - - hdev->asic_funcs->read_pte(hdev, - is_huge ? hop3_pte_addr : hop4_pte_addr); + flush(ctx); return 0; From d9973871dae1805678ac905318a5d4cecceb6524 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Thu, 7 Mar 2019 18:03:23 +0200 Subject: [PATCH 014/255] habanalabs: keep track of the device's dma mask This patch refactors the code that is responsible to set the DMA mask for the device. Upon each change of the dma mask, the driver will save the new value that was set. This is needed in order to make sure we don't try to increase the mask a second time, in case we failed in the first time. This is especially relevant for Power machines, as that may cause a change in configuration of the TVT which will break the device. Goya will first try to set the device's dma mask to 39 bits, so that the memory that is allocated on the host machine for communication with the device's cpu will be in a bus address which is lower then 39 bits. Later, Goya will try to increase that mask to 48 bits, but only if setting the mask to 39 bits was successful. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 32 ++++-------- drivers/misc/habanalabs/habanalabs.h | 5 +- drivers/misc/habanalabs/habanalabs_drv.c | 3 ++ drivers/misc/habanalabs/pci.c | 64 ++++++++++++++++++------ 4 files changed, 65 insertions(+), 39 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 630979422390..c69f3b928350 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -482,7 +482,7 @@ static int goya_early_init(struct hl_device *hdev) prop->dram_pci_bar_size = pci_resource_len(pdev, DDR_BAR_ID); - rc = hl_pci_init(hdev); + rc = hl_pci_init(hdev, 39); if (rc) return rc; @@ -2445,28 +2445,16 @@ static int goya_hw_init(struct hl_device *hdev) goto disable_msix; } - /* CPU initialization is finished, we can now move to 48 bit DMA mask */ - rc = pci_set_dma_mask(hdev->pdev, DMA_BIT_MASK(48)); - if (rc) { - dev_warn(hdev->dev, "Unable to set pci dma mask to 48 bits\n"); - rc = pci_set_dma_mask(hdev->pdev, DMA_BIT_MASK(32)); - if (rc) { - dev_err(hdev->dev, - "Unable to set pci dma mask to 32 bits\n"); + /* + * Check if we managed to set the DMA mask to more then 32 bits. If so, + * let's try to increase it again because in Goya we set the initial + * dma mask to less then 39 bits so that the allocation of the memory + * area for the device's cpu will be under 39 bits + */ + if (hdev->dma_mask > 32) { + rc = hl_pci_set_dma_mask(hdev, 48); + if (rc) goto disable_pci_access; - } - } - - rc = pci_set_consistent_dma_mask(hdev->pdev, DMA_BIT_MASK(48)); - if (rc) { - dev_warn(hdev->dev, - "Unable to set pci consistent dma mask to 48 bits\n"); - rc = pci_set_consistent_dma_mask(hdev->pdev, DMA_BIT_MASK(32)); - if (rc) { - dev_err(hdev->dev, - "Unable to set pci consistent dma mask to 32 bits\n"); - goto disable_pci_access; - } } /* Perform read from the device to flush all MSI-X configuration */ diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 6991a7f260e8..e9253d937bfc 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -1106,6 +1106,7 @@ struct hl_device_reset_work { * @init_done: is the initialization of the device done. * @mmu_enable: is MMU enabled. * @device_cpu_disabled: is the device CPU disabled (due to timeouts) + * @dma_mask: the dma mask that was set for this device */ struct hl_device { struct pci_dev *pdev; @@ -1176,6 +1177,7 @@ struct hl_device { u8 dram_default_page_mapping; u8 init_done; u8 device_cpu_disabled; + u8 dma_mask; /* Parameters for bring-up */ u8 mmu_enable; @@ -1397,8 +1399,9 @@ int hl_pci_set_dram_bar_base(struct hl_device *hdev, u8 inbound_region, u8 bar, u64 addr); int hl_pci_init_iatu(struct hl_device *hdev, u64 sram_base_address, u64 dram_base_address, u64 host_phys_size); -int hl_pci_init(struct hl_device *hdev); +int hl_pci_init(struct hl_device *hdev, u8 dma_mask); void hl_pci_fini(struct hl_device *hdev); +int hl_pci_set_dma_mask(struct hl_device *hdev, u8 dma_mask); long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr); void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq); diff --git a/drivers/misc/habanalabs/habanalabs_drv.c b/drivers/misc/habanalabs/habanalabs_drv.c index 748601463f11..b697339d3904 100644 --- a/drivers/misc/habanalabs/habanalabs_drv.c +++ b/drivers/misc/habanalabs/habanalabs_drv.c @@ -229,6 +229,9 @@ int create_hdev(struct hl_device **dev, struct pci_dev *pdev, hdev->asic_type = asic_type; } + /* Set default DMA mask to 32 bits */ + hdev->dma_mask = 32; + mutex_lock(&hl_devs_idr_lock); if (minor == -1) { diff --git a/drivers/misc/habanalabs/pci.c b/drivers/misc/habanalabs/pci.c index 822ac110b997..d472d02a8e6e 100644 --- a/drivers/misc/habanalabs/pci.c +++ b/drivers/misc/habanalabs/pci.c @@ -287,42 +287,74 @@ int hl_pci_init_iatu(struct hl_device *hdev, u64 sram_base_address, } /** - * hl_pci_init() - PCI initialization code. + * hl_pci_set_dma_mask() - Set DMA masks for the device. * @hdev: Pointer to hl_device structure. + * @dma_mask: number of bits for the requested dma mask. * - * Set DMA masks, initialize the PCI controller and map the PCI BARs. + * 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. */ -int hl_pci_init(struct hl_device *hdev) +int hl_pci_set_dma_mask(struct hl_device *hdev, u8 dma_mask) { struct pci_dev *pdev = hdev->pdev; int rc; /* set DMA mask */ - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(39)); + rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(dma_mask)); if (rc) { - dev_warn(hdev->dev, "Unable to set pci dma mask to 39 bits\n"); - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + dev_warn(hdev->dev, + "Failed to set pci dma mask to %d bits, error %d\n", + dma_mask, rc); + + dma_mask = hdev->dma_mask; + + rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(dma_mask)); if (rc) { dev_err(hdev->dev, - "Unable to set pci dma mask to 32 bits\n"); + "Failed to set pci dma mask to %d bits, error %d\n", + dma_mask, rc); return rc; } } - rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39)); + /* + * We managed to set the dma mask, so update the dma mask field. If + * the set to the coherent mask will fail with that mask, we will + * fail the entire function + */ + hdev->dma_mask = dma_mask; + + rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(dma_mask)); if (rc) { - dev_warn(hdev->dev, - "Unable to set pci consistent dma mask to 39 bits\n"); - rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); - if (rc) { - dev_err(hdev->dev, - "Unable to set pci consistent dma mask to 32 bits\n"); - return rc; - } + dev_err(hdev->dev, + "Failed to set pci consistent dma mask to %d bits, error %d\n", + dma_mask, rc); + return rc; } + return 0; +} + +/** + * hl_pci_init() - PCI initialization code. + * @hdev: Pointer to hl_device structure. + * @dma_mask: number of bits for the requested dma mask. + * + * Set DMA masks, initialize the PCI controller and map the PCI BARs. + * + * Return: 0 on success, non-zero for failure. + */ +int hl_pci_init(struct hl_device *hdev, u8 dma_mask) +{ + struct pci_dev *pdev = hdev->pdev; + int rc; + + rc = hl_pci_set_dma_mask(hdev, dma_mask); + if (rc) + return rc; + if (hdev->reset_pcilink) hl_pci_reset_link_through_bridge(hdev); From 0878a42086e0a6228f804655bb544147a531bb57 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sun, 17 Mar 2019 09:12:29 +0200 Subject: [PATCH 015/255] habanalabs: never fail hard reset of device Hard-reset of our device should never fail, due to dangers of permanent damage to the H/W. This patch removes the last place in the reset path where the driver might exit before doing the actual reset. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/device.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index 77d51be66c7e..c51d1062d0bc 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -663,17 +663,9 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset, /* Go over all the queues, release all CS and their jobs */ hl_cs_rollback_all(hdev); - if (hard_reset) { - /* Release kernel context */ - if (hl_ctx_put(hdev->kernel_ctx) != 1) { - dev_err(hdev->dev, - "kernel ctx is alive during hard reset\n"); - rc = -EBUSY; - goto out_err; - } - + /* Release kernel context */ + if ((hard_reset) && (hl_ctx_put(hdev->kernel_ctx) == 1)) hdev->kernel_ctx = NULL; - } /* Reset the H/W. It will be in idle state after this returns */ hdev->asic_funcs->hw_fini(hdev, hard_reset); @@ -699,6 +691,13 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset, if (hard_reset) { hdev->device_cpu_disabled = false; + if (hdev->kernel_ctx) { + dev_crit(hdev->dev, + "kernel ctx was alive during hard reset, something is terribly wrong\n"); + rc = -EBUSY; + goto out_err; + } + /* Allocate the kernel context */ hdev->kernel_ctx = kzalloc(sizeof(*hdev->kernel_ctx), GFP_KERNEL); From 106204b56f60abf1bead7dceb88f2be3e34433da Mon Sep 17 00:00:00 2001 From: Kangjie Lu Date: Tue, 12 Mar 2019 03:33:28 -0500 Subject: [PATCH 016/255] thunderbolt: property: Fix a NULL pointer dereference In case kzalloc fails, the fix releases resources and returns -ENOMEM to avoid the NULL pointer dereference. Signed-off-by: Kangjie Lu Signed-off-by: Mika Westerberg --- drivers/thunderbolt/property.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/thunderbolt/property.c b/drivers/thunderbolt/property.c index b2f0d6386cee..ee76449524a3 100644 --- a/drivers/thunderbolt/property.c +++ b/drivers/thunderbolt/property.c @@ -548,6 +548,11 @@ int tb_property_add_data(struct tb_property_dir *parent, const char *key, property->length = size / 4; property->value.data = kzalloc(size, GFP_KERNEL); + if (!property->value.data) { + kfree(property); + return -ENOMEM; + } + memcpy(property->value.data, buf, buflen); list_add_tail(&property->list, &parent->properties); From e4dfdd5804cce1255f99c5dd033526a18135a616 Mon Sep 17 00:00:00 2001 From: Kangjie Lu Date: Thu, 14 Mar 2019 01:55:31 -0500 Subject: [PATCH 017/255] thunderbolt: Fix a missing check of kmemdup kmemdup may fail and return NULL. The fix adds a check and returns NULL in case it fails to avoid NULL pointer dereferecen. Signed-off-by: Kangjie Lu Signed-off-by: Mika Westerberg --- drivers/thunderbolt/property.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/thunderbolt/property.c b/drivers/thunderbolt/property.c index ee76449524a3..841314deb446 100644 --- a/drivers/thunderbolt/property.c +++ b/drivers/thunderbolt/property.c @@ -176,6 +176,10 @@ static struct tb_property_dir *__tb_property_parse_dir(const u32 *block, } else { dir->uuid = kmemdup(&block[dir_offset], sizeof(*dir->uuid), GFP_KERNEL); + if (!dir->uuid) { + tb_property_free_dir(dir); + return NULL; + } content_offset = dir_offset + 4; content_len = dir_len - 4; /* Length includes UUID */ } From a691a1ebb59e7f2a159df8d3c693e2235c5de9dd Mon Sep 17 00:00:00 2001 From: Dalit Ben Zoor Date: Wed, 20 Mar 2019 16:13:23 +0200 Subject: [PATCH 018/255] habanalabs: set new golden value to tpc clock relaxation On init or context switch, set TPC clock relaxation counter register to a golden value. Signed-off-by: Dalit Ben Zoor Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index c69f3b928350..9f775dd81a52 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -1436,6 +1436,7 @@ static void goya_init_golden_registers(struct hl_device *hdev) */ WREG32(mmDMA_CH_0_CFG0, 0x0fff0010); WREG32(mmDMA_CH_1_CFG0, 0x0fff00F0); + WREG32(mmTPC_PLL_CLK_RLX_0, 0x200020); goya->hw_cap_initialized |= HW_CAP_GOLDEN; } @@ -4458,6 +4459,7 @@ static int goya_context_switch(struct hl_device *hdev, u32 asid) return rc; } + WREG32(mmTPC_PLL_CLK_RLX_0, 0x200020); goya_mmu_prepare(hdev, asid); return 0; From 9354c29ed52762e9645d6dc2631045228ed10fbd Mon Sep 17 00:00:00 2001 From: Dalit Ben Zoor Date: Thu, 21 Mar 2019 09:54:49 +0200 Subject: [PATCH 019/255] habanalabs: allow user to modify TPC clock relaxation value This patch allows the user to modify the TPC PLL clock relaxation value on-the-fly in order to reduce power consumption. To enable this, the patch removes the protection from the specific register that controls this behavior. Signed-off-by: Dalit Ben Zoor Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya_security.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya_security.c b/drivers/misc/habanalabs/goya/goya_security.c index 9d2dee67e46f..d95d1b2f860d 100644 --- a/drivers/misc/habanalabs/goya/goya_security.c +++ b/drivers/misc/habanalabs/goya/goya_security.c @@ -2160,6 +2160,8 @@ static void goya_init_protection_bits(struct hl_device *hdev) * Bits 7-11 represents the word offset inside the 128 bytes. * Bits 2-6 represents the bit location inside the word. */ + u32 pb_addr, mask; + u8 word_offset; goya_pb_set_block(hdev, mmPCI_NRTR_BASE); goya_pb_set_block(hdev, mmPCI_RD_REGULATOR_BASE); @@ -2238,6 +2240,14 @@ static void goya_init_protection_bits(struct hl_device *hdev) goya_pb_set_block(hdev, mmPCIE_AUX_BASE); goya_pb_set_block(hdev, mmPCIE_DB_RSV_BASE); goya_pb_set_block(hdev, mmPCIE_PHY_BASE); + goya_pb_set_block(hdev, mmTPC0_NRTR_BASE); + goya_pb_set_block(hdev, mmTPC_PLL_BASE); + + pb_addr = (mmTPC_PLL_CLK_RLX_0 & ~0xFFF) + PROT_BITS_OFFS; + word_offset = ((mmTPC_PLL_CLK_RLX_0 & PROT_BITS_OFFS) >> 7) << 2; + mask = 1 << ((mmTPC_PLL_CLK_RLX_0 & 0x7C) >> 2); + + WREG32(pb_addr + word_offset, mask); goya_init_mme_protection_bits(hdev); @@ -2295,8 +2305,8 @@ void goya_init_security(struct hl_device *hdev) u32 lbw_rng10_base = 0xFCC60000 & DMA_MACRO_LBW_RANGE_BASE_R_MASK; u32 lbw_rng10_mask = 0xFFFE0000 & DMA_MACRO_LBW_RANGE_BASE_R_MASK; - u32 lbw_rng11_base = 0xFCE00000 & DMA_MACRO_LBW_RANGE_BASE_R_MASK; - u32 lbw_rng11_mask = 0xFFFFC000 & DMA_MACRO_LBW_RANGE_BASE_R_MASK; + u32 lbw_rng11_base = 0xFCE02000 & DMA_MACRO_LBW_RANGE_BASE_R_MASK; + u32 lbw_rng11_mask = 0xFFFFE000 & DMA_MACRO_LBW_RANGE_BASE_R_MASK; u32 lbw_rng12_base = 0xFE484000 & DMA_MACRO_LBW_RANGE_BASE_R_MASK; u32 lbw_rng12_mask = 0xFFFFF000 & DMA_MACRO_LBW_RANGE_BASE_R_MASK; From 2cc12751cf464a722ff57b54d17d30c84553f9c0 Mon Sep 17 00:00:00 2001 From: Aditya Pakki Date: Wed, 20 Mar 2019 10:57:54 -0500 Subject: [PATCH 020/255] thunderbolt: Fix to check for kmemdup failure Memory allocated via kmemdup might fail and return a NULL pointer. This patch adds a check on the return value of kmemdup and passes the error upstream. Signed-off-by: Aditya Pakki Reviewed-by: Mukesh Ojha Signed-off-by: Mika Westerberg --- drivers/thunderbolt/switch.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index cd96994dc094..504365d46827 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -1294,13 +1294,14 @@ int tb_switch_configure(struct tb_switch *sw) return tb_plug_events_active(sw, true); } -static void tb_switch_set_uuid(struct tb_switch *sw) +static int tb_switch_set_uuid(struct tb_switch *sw) { u32 uuid[4]; - int cap; + int cap, ret; + ret = 0; if (sw->uuid) - return; + return ret; /* * The newer controllers include fused UUID as part of link @@ -1308,7 +1309,9 @@ static void tb_switch_set_uuid(struct tb_switch *sw) */ cap = tb_switch_find_vse_cap(sw, TB_VSE_CAP_LINK_CONTROLLER); if (cap > 0) { - tb_sw_read(sw, uuid, TB_CFG_SWITCH, cap + 3, 4); + ret = tb_sw_read(sw, uuid, TB_CFG_SWITCH, cap + 3, 4); + if (ret) + return ret; } else { /* * ICM generates UUID based on UID and fills the upper @@ -1323,6 +1326,9 @@ static void tb_switch_set_uuid(struct tb_switch *sw) } sw->uuid = kmemdup(uuid, sizeof(uuid), GFP_KERNEL); + if (!sw->uuid) + ret = -ENOMEM; + return ret; } static int tb_switch_add_dma_port(struct tb_switch *sw) @@ -1372,7 +1378,9 @@ static int tb_switch_add_dma_port(struct tb_switch *sw) if (status) { tb_sw_info(sw, "switch flash authentication failed\n"); - tb_switch_set_uuid(sw); + ret = tb_switch_set_uuid(sw); + if (ret) + return ret; nvm_set_auth_status(sw, status); } @@ -1422,7 +1430,9 @@ int tb_switch_add(struct tb_switch *sw) } tb_sw_dbg(sw, "uid: %#llx\n", sw->uid); - tb_switch_set_uuid(sw); + ret = tb_switch_set_uuid(sw); + if (ret) + return ret; for (i = 0; i <= sw->config.max_port_number; i++) { if (sw->ports[i].disabled) { From 9aabb68568b473bf2f0b179d053b403961e42e4d Mon Sep 17 00:00:00 2001 From: Aditya Pakki Date: Wed, 20 Mar 2019 11:34:09 -0500 Subject: [PATCH 021/255] thunderbolt: Fix to check return value of ida_simple_get In enumerate_services, ida_simple_get on failure can return an error and leaks memory. The patch ensures that the dev_set_name is set on non failure cases, and releases memory during failure. Signed-off-by: Aditya Pakki Signed-off-by: Mika Westerberg --- drivers/thunderbolt/xdomain.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index e27dd8beb94b..e0642dcb8b9b 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -740,6 +740,7 @@ static void enumerate_services(struct tb_xdomain *xd) struct tb_service *svc; struct tb_property *p; struct device *dev; + int id; /* * First remove all services that are not available anymore in @@ -768,7 +769,12 @@ static void enumerate_services(struct tb_xdomain *xd) break; } - svc->id = ida_simple_get(&xd->service_ids, 0, 0, GFP_KERNEL); + id = ida_simple_get(&xd->service_ids, 0, 0, GFP_KERNEL); + if (id < 0) { + kfree(svc); + break; + } + svc->id = id; svc->dev.bus = &tb_bus_type; svc->dev.type = &tb_service_type; svc->dev.parent = &xd->dev; From 48f40b96de2c790eac6114e3e879a48fe9f89349 Mon Sep 17 00:00:00 2001 From: Aditya Pakki Date: Wed, 20 Mar 2019 11:47:20 -0500 Subject: [PATCH 022/255] thunderbolt: xdomain: Fix to check return value of kmemdup kmemdup can fail and return a NULL pointer. The patch modifies the signature of tb_xdp_schedule_request and passes the failure error upstream. Signed-off-by: Aditya Pakki Signed-off-by: Mika Westerberg --- drivers/thunderbolt/xdomain.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index e0642dcb8b9b..e2fc4543142d 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -526,7 +526,7 @@ static void tb_xdp_handle_request(struct work_struct *work) kfree(xw); } -static void +static bool tb_xdp_schedule_request(struct tb *tb, const struct tb_xdp_header *hdr, size_t size) { @@ -534,13 +534,18 @@ tb_xdp_schedule_request(struct tb *tb, const struct tb_xdp_header *hdr, xw = kmalloc(sizeof(*xw), GFP_KERNEL); if (!xw) - return; + return false; INIT_WORK(&xw->work, tb_xdp_handle_request); xw->pkg = kmemdup(hdr, size, GFP_KERNEL); + if (!xw->pkg) { + kfree(xw); + return false; + } xw->tb = tb; queue_work(tb->wq, &xw->work); + return true; } /** @@ -1422,10 +1427,8 @@ bool tb_xdomain_handle_request(struct tb *tb, enum tb_cfg_pkg_type type, * handlers in turn. */ if (uuid_equal(&hdr->uuid, &tb_xdp_uuid)) { - if (type == TB_CFG_PKG_XDOMAIN_REQ) { - tb_xdp_schedule_request(tb, hdr, size); - return true; - } + if (type == TB_CFG_PKG_XDOMAIN_REQ) + return tb_xdp_schedule_request(tb, hdr, size); return false; } From aa957088b4e846146b230e431dd9dad59e907f9a Mon Sep 17 00:00:00 2001 From: Dalit Ben Zoor Date: Sun, 24 Mar 2019 10:15:44 +0200 Subject: [PATCH 023/255] habanalabs: add device status option to INFO IOCTL This patch adds a new opcode to INFO IOCTL that returns the device status. This will allow users to query the device status in order to avoid sending command submissions while device is in reset. Signed-off-by: Dalit Ben Zoor Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/device.c | 15 +++++++++++++++ drivers/misc/habanalabs/habanalabs.h | 1 + drivers/misc/habanalabs/habanalabs_ioctl.c | 19 +++++++++++++++++++ include/uapi/misc/habanalabs.h | 12 ++++++++++++ 4 files changed, 47 insertions(+) diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index c51d1062d0bc..e3797f582436 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -10,6 +10,7 @@ #include #include #include +#include #define HL_PLDM_PENDING_RESET_PER_SEC (HL_PENDING_RESET_PER_SEC * 10) @@ -21,6 +22,20 @@ bool hl_device_disabled_or_in_reset(struct hl_device *hdev) return false; } +enum hl_device_status hl_device_status(struct hl_device *hdev) +{ + enum hl_device_status status; + + if (hdev->disabled) + status = HL_DEVICE_STATUS_MALFUNCTION; + else if (atomic_read(&hdev->in_reset)) + status = HL_DEVICE_STATUS_IN_RESET; + else + status = HL_DEVICE_STATUS_OPERATIONAL; + + return status; +}; + static void hpriv_release(struct kref *ref) { struct hl_fpriv *hpriv; diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index e9253d937bfc..fd7fcdf7050f 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -1272,6 +1272,7 @@ static inline bool hl_mem_area_crosses_range(u64 address, u32 size, int hl_device_open(struct inode *inode, struct file *filp); bool hl_device_disabled_or_in_reset(struct hl_device *hdev); +enum hl_device_status hl_device_status(struct hl_device *hdev); int create_hdev(struct hl_device **dev, struct pci_dev *pdev, enum hl_asic_type asic_type, int minor); void destroy_hdev(struct hl_device *hdev); diff --git a/drivers/misc/habanalabs/habanalabs_ioctl.c b/drivers/misc/habanalabs/habanalabs_ioctl.c index 37f9de8e7404..9000ff615805 100644 --- a/drivers/misc/habanalabs/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/habanalabs_ioctl.c @@ -12,6 +12,21 @@ #include #include +static int device_status_info(struct hl_device *hdev, struct hl_info_args *args) +{ + struct hl_info_device_status dev_stat = {0}; + u32 size = args->return_size; + void __user *out = (void __user *) (uintptr_t) args->return_pointer; + + if ((!size) || (!out)) + return -EINVAL; + + dev_stat.status = hl_device_status(hdev); + + return copy_to_user(out, &dev_stat, + min((size_t)size, sizeof(dev_stat))) ? -EFAULT : 0; +} + static int hw_ip_info(struct hl_device *hdev, struct hl_info_args *args) { struct hl_info_hw_ip_info hw_ip = {0}; @@ -105,6 +120,10 @@ static int hl_info_ioctl(struct hl_fpriv *hpriv, void *data) struct hl_device *hdev = hpriv->hdev; int rc; + /* We want to return device status even if it disabled or in reset */ + if (args->op == HL_INFO_DEVICE_STATUS) + return device_status_info(hdev, args); + if (hl_device_disabled_or_in_reset(hdev)) { dev_warn_ratelimited(hdev->dev, "Device is disabled or in reset. Can't execute INFO IOCTL\n"); diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index ab1957e31077..993a79edad73 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -45,11 +45,18 @@ enum goya_queue_id { GOYA_QUEUE_ID_SIZE }; +enum hl_device_status { + HL_DEVICE_STATUS_OPERATIONAL, + HL_DEVICE_STATUS_IN_RESET, + HL_DEVICE_STATUS_MALFUNCTION +}; + /* Opcode for management ioctl */ #define HL_INFO_HW_IP_INFO 0 #define HL_INFO_HW_EVENTS 1 #define HL_INFO_DRAM_USAGE 2 #define HL_INFO_HW_IDLE 3 +#define HL_INFO_DEVICE_STATUS 4 #define HL_INFO_VERSION_MAX_LEN 128 @@ -82,6 +89,11 @@ struct hl_info_hw_idle { __u32 pad; }; +struct hl_info_device_status { + __u32 status; + __u32 pad; +}; + struct hl_info_args { /* Location of relevant struct in userspace */ __u64 return_pointer; From cab8e3e20d5cb89c876c30d24d38f1caf1d9bdb8 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Wed, 27 Mar 2019 09:44:28 +0200 Subject: [PATCH 024/255] habanalabs: improve error messages This patch improves two error messages to help the user to better understand what error occurred. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/command_submission.c | 3 ++- drivers/misc/habanalabs/memory.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index f908643f871f..02c48da0b645 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -261,7 +261,8 @@ static void cs_timedout(struct work_struct *work) ctx_asid = cs->ctx->asid; /* TODO: add information about last signaled seq and last emitted seq */ - dev_err(hdev->dev, "CS %d.%llu got stuck!\n", ctx_asid, cs->sequence); + dev_err(hdev->dev, "User %d command submission %llu got stuck!\n", + ctx_asid, cs->sequence); cs_put(cs); diff --git a/drivers/misc/habanalabs/memory.c b/drivers/misc/habanalabs/memory.c index ce1fda40a8b8..39788b1cf8d0 100644 --- a/drivers/misc/habanalabs/memory.c +++ b/drivers/misc/habanalabs/memory.c @@ -109,7 +109,7 @@ static int alloc_device_memory(struct hl_ctx *ctx, struct hl_mem_in *args, page_size); if (!phys_pg_pack->pages[i]) { dev_err(hdev->dev, - "ioctl failed to allocate page\n"); + "Failed to allocate device memory (out of memory)\n"); rc = -ENOMEM; goto page_err; } From 21c75ad65f8e5213ec542d99c259ffe3e3671e81 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 21 Mar 2019 16:26:28 +0800 Subject: [PATCH 025/255] parport_cs: Fix memory leak in parport_config parport_probe() alloc parport device 'info', but while parport_config failed it does not free it. Signed-off-by: YueHaibing Reviewed-by: Mukesh Ojha Signed-off-by: Greg Kroah-Hartman --- drivers/parport/parport_cs.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/parport/parport_cs.c b/drivers/parport/parport_cs.c index e9b52e4a4648..e77044c2bf62 100644 --- a/drivers/parport/parport_cs.c +++ b/drivers/parport/parport_cs.c @@ -158,8 +158,9 @@ static int parport_config(struct pcmcia_device *link) return 0; failed: - parport_cs_release(link); - return -ENODEV; + parport_cs_release(link); + kfree(link->priv); + return -ENODEV; } /* parport_config */ static void parport_cs_release(struct pcmcia_device *link) From 3634946f5224c29c88095fc97c5468e0735719d4 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Tue, 12 Mar 2019 00:10:40 +0200 Subject: [PATCH 026/255] mei: add missing SPDX tag to mei Kconfig Add SPDX tag with GPLv2 license to mei Kconfig. Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig index 74e2c667dce0..998fb4ae9791 100644 --- a/drivers/misc/mei/Kconfig +++ b/drivers/misc/mei/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 config INTEL_MEI tristate "Intel Management Engine Interface" depends on X86 && PCI From 9fff0425aab086c10b29ce50d440afde7d31a740 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Tue, 12 Mar 2019 00:10:41 +0200 Subject: [PATCH 027/255] mei: convert to SPDX license tags Replace boiler plate licenses texts with the SPDX license identifiers in the mei files header. Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/bus-fixup.c | 12 +------ drivers/misc/mei/bus.c | 11 +----- drivers/misc/mei/client.c | 12 +------ drivers/misc/mei/client.h | 12 +------ drivers/misc/mei/debugfs.c | 13 ++----- drivers/misc/mei/hbm.c | 13 +------ drivers/misc/mei/hbm.h | 12 +------ drivers/misc/mei/hw-me-regs.h | 66 ++-------------------------------- drivers/misc/mei/hw-me.c | 12 +------ drivers/misc/mei/hw-me.h | 14 +------- drivers/misc/mei/hw-txe-regs.h | 61 ++----------------------------- drivers/misc/mei/hw-txe.c | 12 +------ drivers/misc/mei/hw-txe.h | 12 +------ drivers/misc/mei/hw.h | 12 +------ drivers/misc/mei/init.c | 12 +------ drivers/misc/mei/interrupt.c | 13 +------ drivers/misc/mei/main.c | 13 ++----- drivers/misc/mei/mei-trace.c | 12 +------ drivers/misc/mei/mei-trace.h | 12 +------ drivers/misc/mei/mei_dev.h | 12 +------ drivers/misc/mei/pci-me.c | 13 ++----- drivers/misc/mei/pci-txe.c | 12 +------ include/uapi/linux/mei.h | 65 ++------------------------------- 23 files changed, 31 insertions(+), 407 deletions(-) diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c index 5fcac02233af..c839bdf453d8 100644 --- a/drivers/misc/mei/bus-fixup.c +++ b/drivers/misc/mei/bus-fixup.c @@ -1,17 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2003-2018, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #include diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 65bec998eb6e..e6788fbd611c 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -1,16 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2012-2013, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #include diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index ca4c9cc218a2..306b5fdeaf9c 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -1,17 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2003-2012, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #include diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h index 64e318f589b4..a0e2ec2ed7ab 100644 --- a/drivers/misc/mei/client.h +++ b/drivers/misc/mei/client.h @@ -1,17 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2003-2012, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #ifndef _MEI_CLIENT_H_ diff --git a/drivers/misc/mei/debugfs.c b/drivers/misc/mei/debugfs.c index 7b5df8fd6c5a..3b2dd5a1be06 100644 --- a/drivers/misc/mei/debugfs.c +++ b/drivers/misc/mei/debugfs.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2012-2013, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ + #include #include #include diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c index e6207f614816..dfc21787d978 100644 --- a/drivers/misc/mei/hbm.c +++ b/drivers/misc/mei/hbm.c @@ -1,19 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2003-2012, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ - #include #include #include diff --git a/drivers/misc/mei/hbm.h b/drivers/misc/mei/hbm.h index 0171a7e79bab..1e33359f27f0 100644 --- a/drivers/misc/mei/hbm.h +++ b/drivers/misc/mei/hbm.h @@ -1,17 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2003-2012, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #ifndef _MEI_HBM_H_ diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index bb1ee9834a02..535eb63a9dee 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -1,68 +1,8 @@ -/****************************************************************************** +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* * Intel Management Engine Interface (Intel MEI) Linux driver - * Intel MEI Interface Header - * - * This file is provided under a dual BSD/GPLv2 license. When using or - * redistributing this file, you may do so under either license. - * - * GPL LICENSE SUMMARY - * * Copyright(c) 2003 - 2012 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110, - * USA - * - * The full GNU General Public License is included in this distribution - * in the file called LICENSE.GPL. - * - * Contact Information: - * Intel Corporation. - * linux-mei@linux.intel.com - * http://www.intel.com - * - * BSD LICENSE - * - * Copyright(c) 2003 - 2012 Intel Corporation. All rights reserved. - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name Intel Corporation nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - *****************************************************************************/ + */ #ifndef _MEI_HW_MEI_REGS_H_ #define _MEI_HW_MEI_REGS_H_ diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index 3fbbadfa2ae1..ea1cd7043323 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -1,17 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2003-2012, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #include diff --git a/drivers/misc/mei/hw-me.h b/drivers/misc/mei/hw-me.h index bbcc5fc106cd..e1c1b4e18f3c 100644 --- a/drivers/misc/mei/hw-me.h +++ b/drivers/misc/mei/hw-me.h @@ -1,21 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2003-2012, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ - - #ifndef _MEI_INTERFACE_H_ #define _MEI_INTERFACE_H_ diff --git a/drivers/misc/mei/hw-txe-regs.h b/drivers/misc/mei/hw-txe-regs.h index f19229c4e655..d71798cb6272 100644 --- a/drivers/misc/mei/hw-txe-regs.h +++ b/drivers/misc/mei/hw-txe-regs.h @@ -1,63 +1,8 @@ -/****************************************************************************** +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* * Intel Management Engine Interface (Intel MEI) Linux driver - * Intel MEI Interface Header - * - * This file is provided under a dual BSD/GPLv2 license. When using or - * redistributing this file, you may do so under either license. - * - * GPL LICENSE SUMMARY - * * Copyright(c) 2013 - 2014 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * The full GNU General Public License is included in this distribution - * in the file called COPYING - * - * Contact Information: - * Intel Corporation. - * linux-mei@linux.intel.com - * http://www.intel.com - * - * BSD LICENSE - * - * Copyright(c) 2013 - 2014 Intel Corporation. All rights reserved. - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name Intel Corporation nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - *****************************************************************************/ + */ #ifndef _MEI_HW_TXE_REGS_H_ #define _MEI_HW_TXE_REGS_H_ diff --git a/drivers/misc/mei/hw-txe.c b/drivers/misc/mei/hw-txe.c index 8449fe0367ff..c99a5360df27 100644 --- a/drivers/misc/mei/hw-txe.c +++ b/drivers/misc/mei/hw-txe.c @@ -1,17 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2013-2014, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #include diff --git a/drivers/misc/mei/hw-txe.h b/drivers/misc/mei/hw-txe.h index e1e8b66d7648..b82dd5cb4a78 100644 --- a/drivers/misc/mei/hw-txe.h +++ b/drivers/misc/mei/hw-txe.h @@ -1,17 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2013-2014, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #ifndef _MEI_HW_TXE_H_ diff --git a/drivers/misc/mei/hw.h b/drivers/misc/mei/hw.h index b7d2487b8409..a4c16eaad1fb 100644 --- a/drivers/misc/mei/hw.h +++ b/drivers/misc/mei/hw.h @@ -1,17 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2003-2012, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #ifndef _MEI_HW_TYPES_H_ diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c index eb026e2a0537..0d719f3b941f 100644 --- a/drivers/misc/mei/init.c +++ b/drivers/misc/mei/init.c @@ -1,17 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2003-2012, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #include diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c index 055c2d89b310..5385293b973e 100644 --- a/drivers/misc/mei/interrupt.c +++ b/drivers/misc/mei/interrupt.c @@ -1,20 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2003-2012, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ - #include #include #include diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index 87281b3695e6..e796f149b6a5 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2003-2018, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ + #include #include #include diff --git a/drivers/misc/mei/mei-trace.c b/drivers/misc/mei/mei-trace.c index 374edde72a14..32ee5d3d856c 100644 --- a/drivers/misc/mei/mei-trace.c +++ b/drivers/misc/mei/mei-trace.c @@ -1,17 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2015, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #include diff --git a/drivers/misc/mei/mei-trace.h b/drivers/misc/mei/mei-trace.h index b52e9b97a7c0..9883bd8ece26 100644 --- a/drivers/misc/mei/mei-trace.h +++ b/drivers/misc/mei/mei-trace.h @@ -1,17 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2015, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #if !defined(_MEI_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h index 685b78ce30a5..3b45f12229e0 100644 --- a/drivers/misc/mei/mei_dev.h +++ b/drivers/misc/mei/mei_dev.h @@ -1,17 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2003-2018, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #ifndef _MEI_DEV_H_ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 3ab946ad3257..723f9a8fb53d 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2003-2012, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ + #include #include #include diff --git a/drivers/misc/mei/pci-txe.c b/drivers/misc/mei/pci-txe.c index e1b909123fb0..1e3dd806c483 100644 --- a/drivers/misc/mei/pci-txe.c +++ b/drivers/misc/mei/pci-txe.c @@ -1,17 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * * Intel Management Engine Interface (Intel MEI) Linux driver * Copyright (c) 2013-2014, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * */ #include diff --git a/include/uapi/linux/mei.h b/include/uapi/linux/mei.h index 0f681cbd38d3..1b932cad61b4 100644 --- a/include/uapi/linux/mei.h +++ b/include/uapi/linux/mei.h @@ -1,70 +1,9 @@ /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ -/****************************************************************************** +/* * Intel Management Engine Interface (Intel MEI) Linux driver * Intel MEI Interface Header - * - * This file is provided under a dual BSD/GPLv2 license. When using or - * redistributing this file, you may do so under either license. - * - * GPL LICENSE SUMMARY - * * Copyright(c) 2003 - 2012 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110, - * USA - * - * The full GNU General Public License is included in this distribution - * in the file called LICENSE.GPL. - * - * Contact Information: - * Intel Corporation. - * linux-mei@linux.intel.com - * http://www.intel.com - * - * BSD LICENSE - * - * Copyright(c) 2003 - 2012 Intel Corporation. All rights reserved. - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name Intel Corporation nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - *****************************************************************************/ - + */ #ifndef _LINUX_MEI_H #define _LINUX_MEI_H From 191b0700727ca936d7b34496244cfea27074ddd9 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Tue, 12 Mar 2019 00:10:42 +0200 Subject: [PATCH 028/255] nfc/mei: convert to SPDX license tags Replace boiler plate licenses texts with the SPDX license identifiers in the mei nfc files header. Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- drivers/nfc/mei_phy.c | 18 +++--------------- drivers/nfc/microread/mei.c | 17 +++-------------- drivers/nfc/pn544/mei.c | 15 ++------------- 3 files changed, 8 insertions(+), 42 deletions(-) diff --git a/drivers/nfc/mei_phy.c b/drivers/nfc/mei_phy.c index 8a04c5e02999..0f43bb389566 100644 --- a/drivers/nfc/mei_phy.c +++ b/drivers/nfc/mei_phy.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2013, Intel Corporation. + * * MEI Library for mei bus nfc device access - * - * Copyright (C) 2013 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see . */ - #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include diff --git a/drivers/nfc/microread/mei.c b/drivers/nfc/microread/mei.c index eb5eddf1794e..5dad8847a9b3 100644 --- a/drivers/nfc/microread/mei.c +++ b/drivers/nfc/microread/mei.c @@ -1,19 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* + * Copyright (C) 2013 Intel Corporation. All rights reserved. + * * HCI based Driver for Inside Secure microread NFC Chip - * - * Copyright (C) 2013 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see . */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/nfc/pn544/mei.c b/drivers/nfc/pn544/mei.c index ad57a8ec00d6..579bc599f545 100644 --- a/drivers/nfc/pn544/mei.c +++ b/drivers/nfc/pn544/mei.c @@ -1,19 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* - * HCI based Driver for NXP pn544 NFC Chip - * * Copyright (C) 2013 Intel Corporation. All rights reserved. * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see . + * HCI based Driver for NXP pn544 NFC Chip */ #include From 514c37e320a24507590bd023a554a6671e7fca92 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Tue, 12 Mar 2019 00:10:43 +0200 Subject: [PATCH 029/255] mei/hdcp: Fix SPDX identifiers 1. Remove redundant parentheses around single license 2. Fix the license to GPL-2.0 and not GPL-2.0+ in mei_hdcp.h Cc: Ramalingam C Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/hdcp/mei_hdcp.c | 2 +- drivers/misc/mei/hdcp/mei_hdcp.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/misc/mei/hdcp/mei_hdcp.c b/drivers/misc/mei/hdcp/mei_hdcp.c index 90b6ae8e9dae..b07000202d4a 100644 --- a/drivers/misc/mei/hdcp/mei_hdcp.c +++ b/drivers/misc/mei/hdcp/mei_hdcp.c @@ -1,4 +1,4 @@ -// SPDX-License-Identifier: (GPL-2.0) +// SPDX-License-Identifier: GPL-2.0 /* * Copyright © 2019 Intel Corporation * diff --git a/drivers/misc/mei/hdcp/mei_hdcp.h b/drivers/misc/mei/hdcp/mei_hdcp.h index 5f74b908e486..e4b1cd54c853 100644 --- a/drivers/misc/mei/hdcp/mei_hdcp.h +++ b/drivers/misc/mei/hdcp/mei_hdcp.h @@ -1,4 +1,4 @@ -/* SPDX-License-Identifier: (GPL-2.0+) */ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright © 2019 Intel Corporation * From 1e55b609b983f99290d210bf6578cb1a2eb905d2 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Tue, 12 Mar 2019 00:10:44 +0200 Subject: [PATCH 030/255] mei: adjust the copyright notice in the files. Use unified version of the copyright notice in the files Update copyright years according the year the files were touched, except this patch and SPDX conversions. Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/Kconfig | 1 + drivers/misc/mei/Makefile | 2 +- drivers/misc/mei/bus-fixup.c | 2 +- drivers/misc/mei/bus.c | 2 +- drivers/misc/mei/client.c | 2 +- drivers/misc/mei/client.h | 2 +- drivers/misc/mei/debugfs.c | 2 +- drivers/misc/mei/dma-ring.c | 2 +- drivers/misc/mei/hbm.c | 2 +- drivers/misc/mei/hbm.h | 2 +- drivers/misc/mei/hdcp/Makefile | 2 +- drivers/misc/mei/hw-me-regs.h | 2 +- drivers/misc/mei/hw-me.c | 2 +- drivers/misc/mei/hw-me.h | 2 +- drivers/misc/mei/hw-txe-regs.h | 2 +- drivers/misc/mei/hw-txe.c | 2 +- drivers/misc/mei/hw-txe.h | 2 +- drivers/misc/mei/hw.h | 2 +- drivers/misc/mei/init.c | 2 +- drivers/misc/mei/interrupt.c | 2 +- drivers/misc/mei/main.c | 2 +- drivers/misc/mei/mei-trace.c | 2 +- drivers/misc/mei/mei-trace.h | 2 +- drivers/misc/mei/mei_dev.h | 2 +- drivers/misc/mei/pci-me.c | 2 +- drivers/misc/mei/pci-txe.c | 2 +- include/linux/mei_cl_bus.h | 3 +++ include/uapi/linux/mei.h | 2 +- 28 files changed, 30 insertions(+), 26 deletions(-) diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig index 998fb4ae9791..132b07151f42 100644 --- a/drivers/misc/mei/Kconfig +++ b/drivers/misc/mei/Kconfig @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2003-2019, Intel Corporation. All rights reserved. config INTEL_MEI tristate "Intel Management Engine Interface" depends on X86 && PCI diff --git a/drivers/misc/mei/Makefile b/drivers/misc/mei/Makefile index 8c2d9565a4cb..f1c76f7ee804 100644 --- a/drivers/misc/mei/Makefile +++ b/drivers/misc/mei/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 # +# Copyright (c) 2010-2019, Intel Corporation. All rights reserved. # Makefile - Intel Management Engine Interface (Intel MEI) Linux driver -# Copyright (c) 2010-2014, Intel Corporation. # obj-$(CONFIG_INTEL_MEI) += mei.o mei-objs := init.o diff --git a/drivers/misc/mei/bus-fixup.c b/drivers/misc/mei/bus-fixup.c index c839bdf453d8..32e9b1aed2ca 100644 --- a/drivers/misc/mei/bus-fixup.c +++ b/drivers/misc/mei/bus-fixup.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2013-2019, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2003-2018, Intel Corporation. */ #include diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index e6788fbd611c..985bd4fd3328 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2012-2019, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2012-2013, Intel Corporation. */ #include diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 306b5fdeaf9c..88b83c4bc5b7 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2003-2019, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2003-2012, Intel Corporation. */ #include diff --git a/drivers/misc/mei/client.h b/drivers/misc/mei/client.h index a0e2ec2ed7ab..c1f9e810cf81 100644 --- a/drivers/misc/mei/client.h +++ b/drivers/misc/mei/client.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* + * Copyright (c) 2003-2018, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2003-2012, Intel Corporation. */ #ifndef _MEI_CLIENT_H_ diff --git a/drivers/misc/mei/debugfs.c b/drivers/misc/mei/debugfs.c index 3b2dd5a1be06..0970142bcace 100644 --- a/drivers/misc/mei/debugfs.c +++ b/drivers/misc/mei/debugfs.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2012-2016, Intel Corporation. All rights reserved * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2012-2013, Intel Corporation. */ #include diff --git a/drivers/misc/mei/dma-ring.c b/drivers/misc/mei/dma-ring.c index 795641b82181..ef56f849b251 100644 --- a/drivers/misc/mei/dma-ring.c +++ b/drivers/misc/mei/dma-ring.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright(c) 2016 - 2018 Intel Corporation. All rights reserved. + * Copyright(c) 2016-2018 Intel Corporation. All rights reserved. */ #include #include diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c index dfc21787d978..a44094cdbc36 100644 --- a/drivers/misc/mei/hbm.c +++ b/drivers/misc/mei/hbm.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2003-2019, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2003-2012, Intel Corporation. */ #include #include diff --git a/drivers/misc/mei/hbm.h b/drivers/misc/mei/hbm.h index 1e33359f27f0..5aa58cffdd2e 100644 --- a/drivers/misc/mei/hbm.h +++ b/drivers/misc/mei/hbm.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* + * Copyright (c) 2003-2018, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2003-2012, Intel Corporation. */ #ifndef _MEI_HBM_H_ diff --git a/drivers/misc/mei/hdcp/Makefile b/drivers/misc/mei/hdcp/Makefile index adbe7506282d..3fbb56485ce8 100644 --- a/drivers/misc/mei/hdcp/Makefile +++ b/drivers/misc/mei/hdcp/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # -# Copyright (c) 2019, Intel Corporation. +# Copyright (c) 2019, Intel Corporation. All rights reserved. # # Makefile - HDCP client driver for Intel MEI Bus Driver. diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index 535eb63a9dee..d74b182e19f3 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* + * Copyright (c) 2003-2019, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright(c) 2003 - 2012 Intel Corporation. All rights reserved. */ #ifndef _MEI_HW_MEI_REGS_H_ #define _MEI_HW_MEI_REGS_H_ diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index ea1cd7043323..de21e3083526 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2003-2018, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2003-2012, Intel Corporation. */ #include diff --git a/drivers/misc/mei/hw-me.h b/drivers/misc/mei/hw-me.h index e1c1b4e18f3c..08c84a0de4a8 100644 --- a/drivers/misc/mei/hw-me.h +++ b/drivers/misc/mei/hw-me.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* + * Copyright (c) 2012-2018, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2003-2012, Intel Corporation. */ #ifndef _MEI_INTERFACE_H_ diff --git a/drivers/misc/mei/hw-txe-regs.h b/drivers/misc/mei/hw-txe-regs.h index d71798cb6272..a92b306dac8b 100644 --- a/drivers/misc/mei/hw-txe-regs.h +++ b/drivers/misc/mei/hw-txe-regs.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* + * Copyright (c) 2013-2014, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright(c) 2013 - 2014 Intel Corporation. All rights reserved. */ #ifndef _MEI_HW_TXE_REGS_H_ #define _MEI_HW_TXE_REGS_H_ diff --git a/drivers/misc/mei/hw-txe.c b/drivers/misc/mei/hw-txe.c index c99a5360df27..5e58656b8e19 100644 --- a/drivers/misc/mei/hw-txe.c +++ b/drivers/misc/mei/hw-txe.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2013-2014, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2013-2014, Intel Corporation. */ #include diff --git a/drivers/misc/mei/hw-txe.h b/drivers/misc/mei/hw-txe.h index b82dd5cb4a78..96511b04bf88 100644 --- a/drivers/misc/mei/hw-txe.h +++ b/drivers/misc/mei/hw-txe.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* + * Copyright (c) 2013-2016, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2013-2014, Intel Corporation. */ #ifndef _MEI_HW_TXE_H_ diff --git a/drivers/misc/mei/hw.h b/drivers/misc/mei/hw.h index a4c16eaad1fb..d025a5f8317e 100644 --- a/drivers/misc/mei/hw.h +++ b/drivers/misc/mei/hw.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* + * Copyright (c) 2003-2018, Intel Corporation. All rights reserved * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2003-2012, Intel Corporation. */ #ifndef _MEI_HW_TYPES_H_ diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c index 0d719f3b941f..cc359ae968ce 100644 --- a/drivers/misc/mei/init.c +++ b/drivers/misc/mei/init.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2012-2018, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2003-2012, Intel Corporation. */ #include diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c index 5385293b973e..c70a8c74cc57 100644 --- a/drivers/misc/mei/interrupt.c +++ b/drivers/misc/mei/interrupt.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2003-2018, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2003-2012, Intel Corporation. */ #include diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index e796f149b6a5..b454df214dde 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2003-2018, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2003-2018, Intel Corporation. */ #include diff --git a/drivers/misc/mei/mei-trace.c b/drivers/misc/mei/mei-trace.c index 32ee5d3d856c..48d4c4fcefd2 100644 --- a/drivers/misc/mei/mei-trace.c +++ b/drivers/misc/mei/mei-trace.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2015-2016, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2015, Intel Corporation. */ #include diff --git a/drivers/misc/mei/mei-trace.h b/drivers/misc/mei/mei-trace.h index 9883bd8ece26..df758033dc93 100644 --- a/drivers/misc/mei/mei-trace.h +++ b/drivers/misc/mei/mei-trace.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* + * Copyright (c) 2015-2016, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2015, Intel Corporation. */ #if !defined(_MEI_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h index 3b45f12229e0..3146df37ffb0 100644 --- a/drivers/misc/mei/mei_dev.h +++ b/drivers/misc/mei/mei_dev.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* + * Copyright (c) 2003-2018, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2003-2018, Intel Corporation. */ #ifndef _MEI_DEV_H_ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index 723f9a8fb53d..7a2b3545a7f9 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2003-2019, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2003-2012, Intel Corporation. */ #include diff --git a/drivers/misc/mei/pci-txe.c b/drivers/misc/mei/pci-txe.c index 1e3dd806c483..2e37fc2e0fa8 100644 --- a/drivers/misc/mei/pci-txe.c +++ b/drivers/misc/mei/pci-txe.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* + * Copyright (c) 2013-2017, Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver - * Copyright (c) 2013-2014, Intel Corporation. */ #include diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index 03b6ba2a63f8..52aa4821093a 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -1,4 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2013-2016, Intel Corporation. All rights reserved. + */ #ifndef _LINUX_MEI_CL_BUS_H #define _LINUX_MEI_CL_BUS_H diff --git a/include/uapi/linux/mei.h b/include/uapi/linux/mei.h index 1b932cad61b4..c6aec86cc5de 100644 --- a/include/uapi/linux/mei.h +++ b/include/uapi/linux/mei.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ /* + * Copyright(c) 2003-2015 Intel Corporation. All rights reserved. * Intel Management Engine Interface (Intel MEI) Linux driver * Intel MEI Interface Header - * Copyright(c) 2003 - 2012 Intel Corporation. All rights reserved. */ #ifndef _LINUX_MEI_H #define _LINUX_MEI_H From 34bf9ce91e04ea6a341463f453c3e042e974a29e Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 5 Mar 2019 14:47:46 +0300 Subject: [PATCH 031/255] misc: rtsx: clean up some indenting These lines weren't indented far enough. Signed-off-by: Dan Carpenter Signed-off-by: Greg Kroah-Hartman --- drivers/misc/cardreader/rts5260.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/misc/cardreader/rts5260.c b/drivers/misc/cardreader/rts5260.c index da22bcb62b04..4a2589bdc8ce 100644 --- a/drivers/misc/cardreader/rts5260.c +++ b/drivers/misc/cardreader/rts5260.c @@ -455,13 +455,13 @@ static void rts5260_pwr_saving_setting(struct rtsx_pcr *pcr) pcr_dbg(pcr, "Set parameters for L1.2."); rtsx_pci_write_register(pcr, PWR_GLOBAL_CTRL, 0xFF, PCIE_L1_2_EN); - rtsx_pci_write_register(pcr, RTS5260_DVCC_CTRL, + rtsx_pci_write_register(pcr, RTS5260_DVCC_CTRL, RTS5260_DVCC_OCP_EN | RTS5260_DVCC_OCP_CL_EN, RTS5260_DVCC_OCP_EN | RTS5260_DVCC_OCP_CL_EN); - rtsx_pci_write_register(pcr, PWR_FE_CTL, + rtsx_pci_write_register(pcr, PWR_FE_CTL, 0xFF, PCIE_L1_2_PD_FE_EN); } else if (lss_l1_1) { pcr_dbg(pcr, "Set parameters for L1.1."); From 8e7389c79b40ed44c855193bfb46b496ac25676f Mon Sep 17 00:00:00 2001 From: Thierry Escande Date: Thu, 7 Mar 2019 10:12:22 +0000 Subject: [PATCH 032/255] misc: fastrpc: Avoid free of DMA buffer in interrupt context When the remote DSP invocation is interrupted by the user, the associated DMA buffer can be freed in interrupt context causing a kernel BUG. This patch adds a worker thread associated to the fastrpc context. It is scheduled in the rpmsg callback to decrease its refcount out of the interrupt context. Fixes: c68cfb718c8f ("misc: fastrpc: Add support for context Invoke method") Signed-off-by: Thierry Escande Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 39f832d27288..6483b881f7e4 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -149,6 +149,7 @@ struct fastrpc_invoke_ctx { struct kref refcount; struct list_head node; /* list of ctxs */ struct completion work; + struct work_struct put_work; struct fastrpc_msg msg; struct fastrpc_user *fl; struct fastrpc_remote_arg *rpra; @@ -311,6 +312,14 @@ static void fastrpc_context_put(struct fastrpc_invoke_ctx *ctx) kref_put(&ctx->refcount, fastrpc_context_free); } +static void fastrpc_context_put_wq(struct work_struct *work) +{ + struct fastrpc_invoke_ctx *ctx = + container_of(work, struct fastrpc_invoke_ctx, put_work); + + fastrpc_context_put(ctx); +} + static struct fastrpc_invoke_ctx *fastrpc_context_alloc( struct fastrpc_user *user, u32 kernel, u32 sc, struct fastrpc_invoke_args *args) @@ -345,6 +354,7 @@ static struct fastrpc_invoke_ctx *fastrpc_context_alloc( ctx->tgid = user->tgid; ctx->cctx = cctx; init_completion(&ctx->work); + INIT_WORK(&ctx->put_work, fastrpc_context_put_wq); spin_lock(&user->lock); list_add_tail(&ctx->node, &user->pending); @@ -1349,7 +1359,13 @@ static int fastrpc_rpmsg_callback(struct rpmsg_device *rpdev, void *data, ctx->retval = rsp->retval; complete(&ctx->work); - fastrpc_context_put(ctx); + + /* + * The DMA buffer associated with the context cannot be freed in + * interrupt context so schedule it through a worker thread to + * avoid a kernel BUG. + */ + schedule_work(&ctx->put_work); return 0; } From b49f6d83e290f17e20f4e5cf31288d3bb4955ea6 Mon Sep 17 00:00:00 2001 From: Thierry Escande Date: Thu, 7 Mar 2019 10:12:23 +0000 Subject: [PATCH 033/255] misc: fastrpc: Fix a possible double free This patch fixes the error exit path of fastrpc_init_create_process(). If the DMA allocation or the DSP invoke fails the fastrpc_map was freed but not removed from the mapping list leading to a double free once the mapping list is emptied in fastrpc_device_release(). [srinivas kandagatla]: Cleaned up error path labels and reset init mem to NULL after free Fixes: d73f71c7c6ee("misc: fastrpc: Add support for create remote init process") Signed-off-by: Thierry Escande Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 31 ++++++++++++++++++++----------- 1 file changed, 20 insertions(+), 11 deletions(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 6483b881f7e4..ecb56648b1bb 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -853,12 +853,12 @@ static int fastrpc_init_create_process(struct fastrpc_user *fl, if (copy_from_user(&init, argp, sizeof(init))) { err = -EFAULT; - goto bail; + goto err; } if (init.filelen > INIT_FILELEN_MAX) { err = -EINVAL; - goto bail; + goto err; } inbuf.pgid = fl->tgid; @@ -872,17 +872,15 @@ static int fastrpc_init_create_process(struct fastrpc_user *fl, if (init.filelen && init.filefd) { err = fastrpc_map_create(fl, init.filefd, init.filelen, &map); if (err) - goto bail; + goto err; } memlen = ALIGN(max(INIT_FILELEN_MAX, (int)init.filelen * 4), 1024 * 1024); err = fastrpc_buf_alloc(fl, fl->sctx->dev, memlen, &imem); - if (err) { - fastrpc_map_put(map); - goto bail; - } + if (err) + goto err_alloc; fl->init_mem = imem; args[0].ptr = (u64)(uintptr_t)&inbuf; @@ -918,13 +916,24 @@ static int fastrpc_init_create_process(struct fastrpc_user *fl, err = fastrpc_internal_invoke(fl, true, FASTRPC_INIT_HANDLE, sc, args); + if (err) + goto err_invoke; - if (err) { + kfree(args); + + return 0; + +err_invoke: + fl->init_mem = NULL; + fastrpc_buf_free(imem); +err_alloc: + if (map) { + spin_lock(&fl->lock); + list_del(&map->node); + spin_unlock(&fl->lock); fastrpc_map_put(map); - fastrpc_buf_free(imem); } - -bail: +err: kfree(args); return err; From 415a0729bd1225f0ffbc0ba82888dd65772554f7 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 7 Mar 2019 10:12:24 +0000 Subject: [PATCH 034/255] misc: fastrpc: make sure memory read and writes are visible dma_alloc_coherent buffers could have writes queued in store buffers so commit them before sending buffer to DSP using correct dma barriers. Same with vice-versa. Fixes: c68cfb718c8f ("misc: fastrpc: Add support for context Invoke method") Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index ecb56648b1bb..986c9aee539a 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -792,6 +792,9 @@ static int fastrpc_internal_invoke(struct fastrpc_user *fl, u32 kernel, if (err) goto bail; } + + /* make sure that all CPU memory writes are seen by DSP */ + dma_wmb(); /* Send invoke buffer to remote dsp */ err = fastrpc_invoke_send(fl->sctx, ctx, kernel, handle); if (err) @@ -808,6 +811,8 @@ static int fastrpc_internal_invoke(struct fastrpc_user *fl, u32 kernel, goto bail; if (ctx->nscalars) { + /* make sure that all memory writes by DSP are seen by CPU */ + dma_rmb(); /* populate all the output buffers with results */ err = fastrpc_put_args(ctx, kernel); if (err) From 977e6c8d1d18061e083080c3657631eec17ca3ff Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 7 Mar 2019 10:12:25 +0000 Subject: [PATCH 035/255] misc: fastrpc: use correct spinlock variant context spin lock can be interrupted from callback path so use correct spinlock so that we do not hit spinlock recursion. Fixes: c68cfb718c8f ("misc: fastrpc: Add support for context Invoke method") Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 48 +++++++++++++++++++++++++----------------- 1 file changed, 29 insertions(+), 19 deletions(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 986c9aee539a..8e43f3d85bfd 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -283,6 +283,7 @@ static void fastrpc_context_free(struct kref *ref) { struct fastrpc_invoke_ctx *ctx; struct fastrpc_channel_ctx *cctx; + unsigned long flags; int i; ctx = container_of(ref, struct fastrpc_invoke_ctx, refcount); @@ -294,9 +295,9 @@ static void fastrpc_context_free(struct kref *ref) if (ctx->buf) fastrpc_buf_free(ctx->buf); - spin_lock(&cctx->lock); + spin_lock_irqsave(&cctx->lock, flags); idr_remove(&cctx->ctx_idr, ctx->ctxid >> 4); - spin_unlock(&cctx->lock); + spin_unlock_irqrestore(&cctx->lock, flags); kfree(ctx->maps); kfree(ctx); @@ -326,6 +327,7 @@ static struct fastrpc_invoke_ctx *fastrpc_context_alloc( { struct fastrpc_channel_ctx *cctx = user->cctx; struct fastrpc_invoke_ctx *ctx = NULL; + unsigned long flags; int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); @@ -360,15 +362,15 @@ static struct fastrpc_invoke_ctx *fastrpc_context_alloc( list_add_tail(&ctx->node, &user->pending); spin_unlock(&user->lock); - spin_lock(&cctx->lock); + spin_lock_irqsave(&cctx->lock, flags); ret = idr_alloc_cyclic(&cctx->ctx_idr, ctx, 1, FASTRPC_CTX_MAX, GFP_ATOMIC); if (ret < 0) { - spin_unlock(&cctx->lock); + spin_unlock_irqrestore(&cctx->lock, flags); goto err_idr; } ctx->ctxid = ret << 4; - spin_unlock(&cctx->lock); + spin_unlock_irqrestore(&cctx->lock, flags); kref_init(&ctx->refcount); @@ -948,9 +950,10 @@ static struct fastrpc_session_ctx *fastrpc_session_alloc( struct fastrpc_channel_ctx *cctx) { struct fastrpc_session_ctx *session = NULL; + unsigned long flags; int i; - spin_lock(&cctx->lock); + spin_lock_irqsave(&cctx->lock, flags); for (i = 0; i < cctx->sesscount; i++) { if (!cctx->session[i].used && cctx->session[i].valid) { cctx->session[i].used = true; @@ -958,7 +961,7 @@ static struct fastrpc_session_ctx *fastrpc_session_alloc( break; } } - spin_unlock(&cctx->lock); + spin_unlock_irqrestore(&cctx->lock, flags); return session; } @@ -966,9 +969,11 @@ static struct fastrpc_session_ctx *fastrpc_session_alloc( static void fastrpc_session_free(struct fastrpc_channel_ctx *cctx, struct fastrpc_session_ctx *session) { - spin_lock(&cctx->lock); + unsigned long flags; + + spin_lock_irqsave(&cctx->lock, flags); session->used = false; - spin_unlock(&cctx->lock); + spin_unlock_irqrestore(&cctx->lock, flags); } static int fastrpc_release_current_dsp_process(struct fastrpc_user *fl) @@ -994,12 +999,13 @@ static int fastrpc_device_release(struct inode *inode, struct file *file) struct fastrpc_channel_ctx *cctx = fl->cctx; struct fastrpc_invoke_ctx *ctx, *n; struct fastrpc_map *map, *m; + unsigned long flags; fastrpc_release_current_dsp_process(fl); - spin_lock(&cctx->lock); + spin_lock_irqsave(&cctx->lock, flags); list_del(&fl->user); - spin_unlock(&cctx->lock); + spin_unlock_irqrestore(&cctx->lock, flags); if (fl->init_mem) fastrpc_buf_free(fl->init_mem); @@ -1027,6 +1033,7 @@ static int fastrpc_device_open(struct inode *inode, struct file *filp) { struct fastrpc_channel_ctx *cctx = miscdev_to_cctx(filp->private_data); struct fastrpc_user *fl = NULL; + unsigned long flags; fl = kzalloc(sizeof(*fl), GFP_KERNEL); if (!fl) @@ -1050,9 +1057,9 @@ static int fastrpc_device_open(struct inode *inode, struct file *filp) return -EBUSY; } - spin_lock(&cctx->lock); + spin_lock_irqsave(&cctx->lock, flags); list_add_tail(&fl->user, &cctx->users); - spin_unlock(&cctx->lock); + spin_unlock_irqrestore(&cctx->lock, flags); return 0; } @@ -1208,6 +1215,7 @@ static int fastrpc_cb_probe(struct platform_device *pdev) struct fastrpc_session_ctx *sess; struct device *dev = &pdev->dev; int i, sessions = 0; + unsigned long flags; cctx = dev_get_drvdata(dev->parent); if (!cctx) @@ -1215,7 +1223,7 @@ static int fastrpc_cb_probe(struct platform_device *pdev) of_property_read_u32(dev->of_node, "qcom,nsessions", &sessions); - spin_lock(&cctx->lock); + spin_lock_irqsave(&cctx->lock, flags); sess = &cctx->session[cctx->sesscount]; sess->used = false; sess->valid = true; @@ -1236,7 +1244,7 @@ static int fastrpc_cb_probe(struct platform_device *pdev) } } cctx->sesscount++; - spin_unlock(&cctx->lock); + spin_unlock_irqrestore(&cctx->lock, flags); dma_set_mask(dev, DMA_BIT_MASK(32)); return 0; @@ -1246,16 +1254,17 @@ static int fastrpc_cb_remove(struct platform_device *pdev) { struct fastrpc_channel_ctx *cctx = dev_get_drvdata(pdev->dev.parent); struct fastrpc_session_ctx *sess = dev_get_drvdata(&pdev->dev); + unsigned long flags; int i; - spin_lock(&cctx->lock); + spin_lock_irqsave(&cctx->lock, flags); for (i = 1; i < FASTRPC_MAX_SESSIONS; i++) { if (cctx->session[i].sid == sess->sid) { cctx->session[i].valid = false; cctx->sesscount--; } } - spin_unlock(&cctx->lock); + spin_unlock_irqrestore(&cctx->lock, flags); return 0; } @@ -1337,11 +1346,12 @@ static void fastrpc_rpmsg_remove(struct rpmsg_device *rpdev) { struct fastrpc_channel_ctx *cctx = dev_get_drvdata(&rpdev->dev); struct fastrpc_user *user; + unsigned long flags; - spin_lock(&cctx->lock); + spin_lock_irqsave(&cctx->lock, flags); list_for_each_entry(user, &cctx->users, user) fastrpc_notify_users(user); - spin_unlock(&cctx->lock); + spin_unlock_irqrestore(&cctx->lock, flags); misc_deregister(&cctx->miscdev); of_platform_depopulate(&rpdev->dev); From 80f3afd72bd4149c57daf852905476b43bb47647 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 7 Mar 2019 10:12:26 +0000 Subject: [PATCH 036/255] misc: fastrpc: consider address offset before sending to DSP While passing address phy address to DSP, take care of the offset calculated from virtual address vma. Fixes: c68cfb718c8f ("misc: fastrpc: Add support for context Invoke method") Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 8e43f3d85bfd..5440735c94ba 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -679,8 +679,16 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx) pages[i].size = roundup(len, PAGE_SIZE); if (ctx->maps[i]) { + struct vm_area_struct *vma = NULL; + rpra[i].pv = (u64) ctx->args[i].ptr; pages[i].addr = ctx->maps[i]->phys; + + vma = find_vma(current->mm, ctx->args[i].ptr); + if (vma) + pages[i].addr += ctx->args[i].ptr - + vma->vm_start; + } else { rlen -= ALIGN(args, FASTRPC_ALIGN) - args; args = ALIGN(args, FASTRPC_ALIGN); From 25e8dfb83cda0a123bb1e091d6c3599cde050d76 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 7 Mar 2019 10:12:27 +0000 Subject: [PATCH 037/255] misc: fastrpc: take into account of overlapping buffers Argument buffers that are passed could be derived from a big buffer, and some of the arguments buffers could overlap each other. Take care of such instanaces. This is optimization that DSP expects while sending buffers which overlap. So make the DSP happy doing it. Without which DSP seems to crash. Fixes: c68cfb718c8f ("misc: fastrpc: Add support for context Invoke method") Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 112 +++++++++++++++++++++++++++++++++++------ 1 file changed, 98 insertions(+), 14 deletions(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 5440735c94ba..80fec7b619cc 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include @@ -104,6 +105,15 @@ struct fastrpc_invoke_rsp { int retval; /* invoke return value */ }; +struct fastrpc_buf_overlap { + u64 start; + u64 end; + int raix; + u64 mstart; + u64 mend; + u64 offset; +}; + struct fastrpc_buf { struct fastrpc_user *fl; struct dma_buf *dmabuf; @@ -156,6 +166,7 @@ struct fastrpc_invoke_ctx { struct fastrpc_map **maps; struct fastrpc_buf *buf; struct fastrpc_invoke_args *args; + struct fastrpc_buf_overlap *olaps; struct fastrpc_channel_ctx *cctx; }; @@ -300,6 +311,7 @@ static void fastrpc_context_free(struct kref *ref) spin_unlock_irqrestore(&cctx->lock, flags); kfree(ctx->maps); + kfree(ctx->olaps); kfree(ctx); } @@ -321,6 +333,55 @@ static void fastrpc_context_put_wq(struct work_struct *work) fastrpc_context_put(ctx); } +#define CMP(aa, bb) ((aa) == (bb) ? 0 : (aa) < (bb) ? -1 : 1) +static int olaps_cmp(const void *a, const void *b) +{ + struct fastrpc_buf_overlap *pa = (struct fastrpc_buf_overlap *)a; + struct fastrpc_buf_overlap *pb = (struct fastrpc_buf_overlap *)b; + /* sort with lowest starting buffer first */ + int st = CMP(pa->start, pb->start); + /* sort with highest ending buffer first */ + int ed = CMP(pb->end, pa->end); + + return st == 0 ? ed : st; +} + +static void fastrpc_get_buff_overlaps(struct fastrpc_invoke_ctx *ctx) +{ + u64 max_end = 0; + int i; + + for (i = 0; i < ctx->nbufs; ++i) { + ctx->olaps[i].start = ctx->args[i].ptr; + ctx->olaps[i].end = ctx->olaps[i].start + ctx->args[i].length; + ctx->olaps[i].raix = i; + } + + sort(ctx->olaps, ctx->nbufs, sizeof(*ctx->olaps), olaps_cmp, NULL); + + for (i = 0; i < ctx->nbufs; ++i) { + /* Falling inside previous range */ + if (ctx->olaps[i].start < max_end) { + ctx->olaps[i].mstart = max_end; + ctx->olaps[i].mend = ctx->olaps[i].end; + ctx->olaps[i].offset = max_end - ctx->olaps[i].start; + + if (ctx->olaps[i].end > max_end) { + max_end = ctx->olaps[i].end; + } else { + ctx->olaps[i].mend = 0; + ctx->olaps[i].mstart = 0; + } + + } else { + ctx->olaps[i].mend = ctx->olaps[i].end; + ctx->olaps[i].mstart = ctx->olaps[i].start; + ctx->olaps[i].offset = 0; + max_end = ctx->olaps[i].end; + } + } +} + static struct fastrpc_invoke_ctx *fastrpc_context_alloc( struct fastrpc_user *user, u32 kernel, u32 sc, struct fastrpc_invoke_args *args) @@ -347,7 +408,15 @@ static struct fastrpc_invoke_ctx *fastrpc_context_alloc( kfree(ctx); return ERR_PTR(-ENOMEM); } + ctx->olaps = kcalloc(ctx->nscalars, + sizeof(*ctx->olaps), GFP_KERNEL); + if (!ctx->olaps) { + kfree(ctx->maps); + kfree(ctx); + return ERR_PTR(-ENOMEM); + } ctx->args = args; + fastrpc_get_buff_overlaps(ctx); } ctx->sc = sc; @@ -380,6 +449,7 @@ static struct fastrpc_invoke_ctx *fastrpc_context_alloc( list_del(&ctx->node); spin_unlock(&user->lock); kfree(ctx->maps); + kfree(ctx->olaps); kfree(ctx); return ERR_PTR(ret); @@ -598,8 +668,11 @@ static u64 fastrpc_get_payload_size(struct fastrpc_invoke_ctx *ctx, int metalen) size = ALIGN(metalen, FASTRPC_ALIGN); for (i = 0; i < ctx->nscalars; i++) { if (ctx->args[i].fd == 0 || ctx->args[i].fd == -1) { - size = ALIGN(size, FASTRPC_ALIGN); - size += ctx->args[i].length; + + if (ctx->olaps[i].offset == 0) + size = ALIGN(size, FASTRPC_ALIGN); + + size += (ctx->olaps[i].mend - ctx->olaps[i].mstart); } } @@ -637,12 +710,11 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx) struct fastrpc_remote_arg *rpra; struct fastrpc_invoke_buf *list; struct fastrpc_phy_page *pages; - int inbufs, i, err = 0; - u64 rlen, pkt_size; + int inbufs, i, oix, err = 0; + u64 len, rlen, pkt_size; uintptr_t args; int metalen; - inbufs = REMOTE_SCALARS_INBUFS(ctx->sc); metalen = fastrpc_get_meta_size(ctx); pkt_size = fastrpc_get_payload_size(ctx, metalen); @@ -665,8 +737,11 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx) rlen = pkt_size - metalen; ctx->rpra = rpra; - for (i = 0; i < ctx->nbufs; ++i) { - u64 len = ctx->args[i].length; + for (oix = 0; oix < ctx->nbufs; ++oix) { + int mlen; + + i = ctx->olaps[oix].raix; + len = ctx->args[i].length; rpra[i].pv = 0; rpra[i].len = len; @@ -690,16 +765,25 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx) vma->vm_start; } else { - rlen -= ALIGN(args, FASTRPC_ALIGN) - args; - args = ALIGN(args, FASTRPC_ALIGN); - if (rlen < len) + + if (ctx->olaps[oix].offset == 0) { + rlen -= ALIGN(args, FASTRPC_ALIGN) - args; + args = ALIGN(args, FASTRPC_ALIGN); + } + + mlen = ctx->olaps[oix].mend - ctx->olaps[oix].mstart; + + if (rlen < mlen) goto bail; - rpra[i].pv = args; - pages[i].addr = ctx->buf->phys + (pkt_size - rlen); + rpra[i].pv = args - ctx->olaps[oix].offset; + pages[i].addr = ctx->buf->phys - + ctx->olaps[oix].offset + + (pkt_size - rlen); pages[i].addr = pages[i].addr & PAGE_MASK; - args = args + len; - rlen -= len; + + args = args + mlen; + rlen -= mlen; } if (i < inbufs && !ctx->maps[i]) { From 02b45b47fbe84e23699bb6bdc74d4c2780e282b4 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 7 Mar 2019 10:12:28 +0000 Subject: [PATCH 038/255] misc: fastrpc: fix remote page size calculation Remote page size should be calculated based on address and size, fix this! Without this we will endup with one page less in cases where the buffer is across 3 pages. Fixes: c68cfb718c8f ("misc: fastrpc: Add support for context Invoke method") Reported-by: Krishnaiah Tadakamalla Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index 80fec7b619cc..aa2d55894263 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -712,6 +712,7 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx) struct fastrpc_phy_page *pages; int inbufs, i, oix, err = 0; u64 len, rlen, pkt_size; + u64 pg_start, pg_end; uintptr_t args; int metalen; @@ -751,8 +752,6 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx) if (!len) continue; - pages[i].size = roundup(len, PAGE_SIZE); - if (ctx->maps[i]) { struct vm_area_struct *vma = NULL; @@ -764,6 +763,11 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx) pages[i].addr += ctx->args[i].ptr - vma->vm_start; + pg_start = (ctx->args[i].ptr & PAGE_MASK) >> PAGE_SHIFT; + pg_end = ((ctx->args[i].ptr + len - 1) & PAGE_MASK) >> + PAGE_SHIFT; + pages[i].size = (pg_end - pg_start + 1) * PAGE_SIZE; + } else { if (ctx->olaps[oix].offset == 0) { @@ -782,6 +786,9 @@ static int fastrpc_get_args(u32 kernel, struct fastrpc_invoke_ctx *ctx) (pkt_size - rlen); pages[i].addr = pages[i].addr & PAGE_MASK; + pg_start = (args & PAGE_MASK) >> PAGE_SHIFT; + pg_end = ((args + len - 1) & PAGE_MASK) >> PAGE_SHIFT; + pages[i].size = (pg_end - pg_start + 1) * PAGE_SIZE; args = args + mlen; rlen -= mlen; } From f1cf11c296c599b81549aa2c5221d75138a58aa4 Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Thu, 7 Mar 2019 10:12:29 +0000 Subject: [PATCH 039/255] misc: fastrpc: increase max init file size to 64 MB In some cases where Neural Processing is required the size of init process exceeds default size of 2MB, increase this size to 64MB which is required for QCS404 CDSP Neural Processing. Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/misc/fastrpc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c index aa2d55894263..c4cc8e53243d 100644 --- a/drivers/misc/fastrpc.c +++ b/drivers/misc/fastrpc.c @@ -32,7 +32,7 @@ #define FASTRPC_CTX_MAX (256) #define FASTRPC_INIT_HANDLE 1 #define FASTRPC_CTXID_MASK (0xFF0) -#define INIT_FILELEN_MAX (2 * 1024 * 1024) +#define INIT_FILELEN_MAX (64 * 1024 * 1024) #define INIT_MEMLEN_MAX (8 * 1024 * 1024) #define FASTRPC_DEVICE_NAME "fastrpc" From 19f8d67fc6c261ec55a199afe8863b4a4f04e80b Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 21 Mar 2019 23:20:50 +0800 Subject: [PATCH 040/255] uio: uio_fsl_elbc_gpcm: Make dev_attr_reg_br and dev_attr_reg_or static Fix sparse warnings: drivers/uio/uio_fsl_elbc_gpcm.c:71:1: warning: symbol 'dev_attr_reg_br' was not declared. Should it be static? drivers/uio/uio_fsl_elbc_gpcm.c:72:1: warning: symbol 'dev_attr_reg_or' was not declared. Should it be static? Signed-off-by: YueHaibing Reviewed-by: Mukesh Ojha --- drivers/uio/uio_fsl_elbc_gpcm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/uio/uio_fsl_elbc_gpcm.c b/drivers/uio/uio_fsl_elbc_gpcm.c index 0ee3cd3c25ee..450e2f5c9b43 100644 --- a/drivers/uio/uio_fsl_elbc_gpcm.c +++ b/drivers/uio/uio_fsl_elbc_gpcm.c @@ -68,8 +68,8 @@ static ssize_t reg_show(struct device *dev, struct device_attribute *attr, static ssize_t reg_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); -DEVICE_ATTR(reg_br, S_IRUGO|S_IWUSR|S_IWGRP, reg_show, reg_store); -DEVICE_ATTR(reg_or, S_IRUGO|S_IWUSR|S_IWGRP, reg_show, reg_store); +static DEVICE_ATTR(reg_br, 0664, reg_show, reg_store); +static DEVICE_ATTR(reg_or, 0664, reg_show, reg_store); static ssize_t reg_show(struct device *dev, struct device_attribute *attr, char *buf) From d8fb3fafa220035a8fc6af9822ab6f591ca83a57 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Wed, 20 Mar 2019 11:03:18 -0500 Subject: [PATCH 041/255] sgi-xpc: mark expected switch fall-through MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch fixes the following warning: drivers/misc/sgi-xp/xpc_uv.c: In function ‘xpc_handle_activate_mq_msg_uv’: drivers/misc/sgi-xp/xpc_uv.c:573:3: warning: this statement may fall through [-Wimplicit-fallthrough=] xpc_wakeup_channel_mgr(part); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~ drivers/misc/sgi-xp/xpc_uv.c:575:2: note: here case XPC_ACTIVATE_MQ_MSG_MARK_ENGAGED_UV: ^~~~ Warning level 3 was used: -Wimplicit-fallthrough=3 This patch is part of the ongoing efforts to enable -Wimplicit-fallthrough. Signed-off-by: Gustavo A. R. Silva Acked-by: Robin Holt Signed-off-by: Greg Kroah-Hartman --- drivers/misc/sgi-xp/xpc_uv.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c index 9e443df44b3b..0c6de97dd347 100644 --- a/drivers/misc/sgi-xp/xpc_uv.c +++ b/drivers/misc/sgi-xp/xpc_uv.c @@ -572,6 +572,7 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part, xpc_wakeup_channel_mgr(part); } + /* fall through */ case XPC_ACTIVATE_MQ_MSG_MARK_ENGAGED_UV: spin_lock_irqsave(&part_uv->flags_lock, irq_flags); part_uv->flags |= XPC_P_ENGAGED_UV; From 13bd14a41ce3105d5b1f3cd8b4d1e249d17b6d9b Mon Sep 17 00:00:00 2001 From: Kangjie Lu Date: Fri, 8 Mar 2019 21:50:24 -0600 Subject: [PATCH 042/255] char: hpet: fix a missing check of ioremap Check if ioremap fails, and if so, return AE_ERROR. Signed-off-by: Kangjie Lu Signed-off-by: Greg Kroah-Hartman --- drivers/char/hpet.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index d0ad85900b79..3a1e6b3ccd10 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -973,6 +973,8 @@ static acpi_status hpet_resources(struct acpi_resource *res, void *data) if (ACPI_SUCCESS(status)) { hdp->hd_phys_address = addr.address.minimum; hdp->hd_address = ioremap(addr.address.minimum, addr.address.address_length); + if (!hdp->hd_address) + return AE_ERROR; if (hpet_is_known(hdp)) { iounmap(hdp->hd_address); From 5cb27d30fc3a281e830a2099d520b469e2b82008 Mon Sep 17 00:00:00 2001 From: Mariusz Bialonczyk Date: Mon, 4 Mar 2019 12:23:36 +0100 Subject: [PATCH 043/255] w1: ds2482: cosmetic fixes after 54865314f5a1 We have a helper function ds2482_calculate_config() which is calculating the config value, so just use it instead of passing the same variable in all calls to this function. Also fixes the placement of module parameters to match with: 50fa2951bd74 (w1: Organize driver source to natural/common order) by Andrew F. Davis Signed-off-by: Mariusz Bialonczyk Cc: Andrew Worsley Cc: Andrew F. Davis Signed-off-by: Greg Kroah-Hartman --- drivers/w1/masters/ds2482.c | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/drivers/w1/masters/ds2482.c b/drivers/w1/masters/ds2482.c index 8b5e598ffdb3..8f2b25f1614c 100644 --- a/drivers/w1/masters/ds2482.c +++ b/drivers/w1/masters/ds2482.c @@ -37,6 +37,11 @@ module_param_named(active_pullup, ds2482_active_pullup, int, 0644); MODULE_PARM_DESC(active_pullup, "Active pullup (apply to all buses): " \ "0-disable, 1-enable (default)"); +/* extra configurations - e.g. 1WS */ +static int extra_config; +module_param(extra_config, int, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(extra_config, "Extra Configuration settings 1=APU,2=PPM,3=SPU,8=1WS"); + /** * The DS2482 registers - there are 3 registers that are addressed by a read * pointer. The read pointer is set by the last command executed. @@ -70,8 +75,6 @@ MODULE_PARM_DESC(active_pullup, "Active pullup (apply to all buses): " \ #define DS2482_REG_CFG_PPM 0x02 /* presence pulse masking */ #define DS2482_REG_CFG_APU 0x01 /* active pull-up */ -/* extra configurations - e.g. 1WS */ -static int extra_config; /** * Write and verify codes for the CHANNEL_SELECT command (DS2482-800 only). @@ -130,6 +133,8 @@ struct ds2482_data { */ static inline u8 ds2482_calculate_config(u8 conf) { + conf |= extra_config; + if (ds2482_active_pullup) conf |= DS2482_REG_CFG_APU; @@ -405,7 +410,7 @@ static u8 ds2482_w1_reset_bus(void *data) /* If the chip did reset since detect, re-config it */ if (err & DS2482_REG_STS_RST) ds2482_send_cmd_data(pdev, DS2482_CMD_WRITE_CONFIG, - ds2482_calculate_config(extra_config)); + ds2482_calculate_config(0x00)); } mutex_unlock(&pdev->access_lock); @@ -431,7 +436,8 @@ static u8 ds2482_w1_set_pullup(void *data, int delay) ds2482_wait_1wire_idle(pdev); /* note: it seems like both SPU and APU have to be set! */ retval = ds2482_send_cmd_data(pdev, DS2482_CMD_WRITE_CONFIG, - ds2482_calculate_config(extra_config|DS2482_REG_CFG_SPU|DS2482_REG_CFG_APU)); + ds2482_calculate_config(DS2482_REG_CFG_SPU | + DS2482_REG_CFG_APU)); ds2482_wait_1wire_idle(pdev); } @@ -484,7 +490,7 @@ static int ds2482_probe(struct i2c_client *client, /* Set all config items to 0 (off) */ ds2482_send_cmd_data(data, DS2482_CMD_WRITE_CONFIG, - ds2482_calculate_config(extra_config)); + ds2482_calculate_config(0x00)); mutex_init(&data->access_lock); @@ -559,7 +565,5 @@ module_i2c_driver(ds2482_driver); MODULE_AUTHOR("Ben Gardner "); MODULE_DESCRIPTION("DS2482 driver"); -module_param(extra_config, int, S_IRUGO | S_IWUSR); -MODULE_PARM_DESC(extra_config, "Extra Configuration settings 1=APU,2=PPM,3=SPU,8=1WS"); MODULE_LICENSE("GPL"); From ae21f41e1f569b51e69d8822005d72ed5b8c2e7f Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Mon, 18 Mar 2019 12:41:16 -0700 Subject: [PATCH 044/255] firmware: vpd: Drop __iomem usage for memremap() memory memremap() doesn't return an iomem pointer, so we can just use memcpy() and drop the __iomem annotation here. This silences a sparse warning. Cc: Guenter Roeck Reviewed-by: Guenter Roeck Cc: Dmitry Torokhov Cc: Anton Vasilyev Signed-off-by: Stephen Boyd Signed-off-by: Greg Kroah-Hartman --- drivers/firmware/google/vpd.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/firmware/google/vpd.c b/drivers/firmware/google/vpd.c index c0c0b4e4e281..f240946ed701 100644 --- a/drivers/firmware/google/vpd.c +++ b/drivers/firmware/google/vpd.c @@ -254,7 +254,7 @@ static int vpd_section_destroy(struct vpd_section *sec) static int vpd_sections_init(phys_addr_t physaddr) { - struct vpd_cbmem __iomem *temp; + struct vpd_cbmem *temp; struct vpd_cbmem header; int ret = 0; @@ -262,7 +262,7 @@ static int vpd_sections_init(phys_addr_t physaddr) if (!temp) return -ENOMEM; - memcpy_fromio(&header, temp, sizeof(struct vpd_cbmem)); + memcpy(&header, temp, sizeof(struct vpd_cbmem)); memunmap(temp); if (header.magic != VPD_CBMEM_MAGIC) From 6183d5a51866f3acdeeb66b75e87d44025b01a55 Mon Sep 17 00:00:00 2001 From: Kangjie Lu Date: Mon, 25 Mar 2019 15:23:08 -0500 Subject: [PATCH 045/255] thunderbolt: property: Fix a missing check of kzalloc No check is enforced for the return value of kzalloc, which may lead to NULL-pointer dereference. The patch fixes this issue. Signed-off-by: Kangjie Lu Reviewed-by: Mukesh Ojha Signed-off-by: Mika Westerberg --- drivers/thunderbolt/property.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/thunderbolt/property.c b/drivers/thunderbolt/property.c index 841314deb446..d5b0cdb8f0b1 100644 --- a/drivers/thunderbolt/property.c +++ b/drivers/thunderbolt/property.c @@ -587,7 +587,12 @@ int tb_property_add_text(struct tb_property_dir *parent, const char *key, return -ENOMEM; property->length = size / 4; - property->value.data = kzalloc(size, GFP_KERNEL); + property->value.text = kzalloc(size, GFP_KERNEL); + if (!property->value.text) { + kfree(property); + return -ENOMEM; + } + strcpy(property->value.text, text); list_add_tail(&property->list, &parent->properties); From fd21b79e541e4666c938a344f3ad2df74b4f5120 Mon Sep 17 00:00:00 2001 From: Aditya Pakki Date: Mon, 25 Mar 2019 16:25:22 -0500 Subject: [PATCH 046/255] thunderbolt: Fix to check the return value of kmemdup uuid in add_switch is allocted via kmemdup which can fail. The patch logs the error and cleans up the allocated memory for switch. Signed-off-by: Aditya Pakki Reviewed-by: Mukesh Ojha Signed-off-by: Mika Westerberg --- drivers/thunderbolt/icm.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index e3fc920af682..8b7f9131e9d1 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -473,6 +473,11 @@ static void add_switch(struct tb_switch *parent_sw, u64 route, goto out; sw->uuid = kmemdup(uuid, sizeof(*uuid), GFP_KERNEL); + if (!sw->uuid) { + tb_sw_warn(sw, "cannot allocate memory for switch\n"); + tb_switch_put(sw); + goto out; + } sw->connection_id = connection_id; sw->connection_key = connection_key; sw->link = link; From 9336c0216782d3a4cd108b584efe24b64cad8a63 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sun, 31 Mar 2019 11:29:53 +0300 Subject: [PATCH 047/255] habanalabs: remove trailing blank line from EOF GIT does not like extra blank lines at the end of the file, so this patch removes those lines. Signed-off-by: Oded Gabbay Reviewed-by: Mukesh Ojha --- .../misc/habanalabs/include/goya/asic_reg/cpu_ca53_cfg_masks.h | 1 - .../misc/habanalabs/include/goya/asic_reg/cpu_ca53_cfg_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/cpu_if_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/cpu_pll_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_0_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_1_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_2_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_3_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_4_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_macro_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_macro_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_nrtr_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_nrtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_0_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_0_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_1_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_2_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_3_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_4_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/ic_pll_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mc_pll_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mme1_rtr_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mme1_rtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mme2_rtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mme3_rtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mme4_rtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mme5_rtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mme6_rtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mme_cmdq_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mme_cmdq_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mme_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mme_qm_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mme_qm_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mme_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mmu_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/mmu_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/pci_nrtr_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/pci_nrtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/pcie_aux_regs.h | 1 - .../misc/habanalabs/include/goya/asic_reg/psoc_emmc_pll_regs.h | 1 - .../habanalabs/include/goya/asic_reg/psoc_global_conf_masks.h | 1 - .../habanalabs/include/goya/asic_reg/psoc_global_conf_regs.h | 1 - .../misc/habanalabs/include/goya/asic_reg/psoc_mme_pll_regs.h | 1 - .../misc/habanalabs/include/goya/asic_reg/psoc_pci_pll_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/psoc_spi_regs.h | 1 - .../misc/habanalabs/include/goya/asic_reg/sram_y0_x0_rtr_regs.h | 1 - .../misc/habanalabs/include/goya/asic_reg/sram_y0_x1_rtr_regs.h | 1 - .../misc/habanalabs/include/goya/asic_reg/sram_y0_x2_rtr_regs.h | 1 - .../misc/habanalabs/include/goya/asic_reg/sram_y0_x3_rtr_regs.h | 1 - .../misc/habanalabs/include/goya/asic_reg/sram_y0_x4_rtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/stlb_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/stlb_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cfg_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cfg_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cmdq_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cmdq_regs.h | 1 - .../misc/habanalabs/include/goya/asic_reg/tpc0_eml_cfg_masks.h | 1 - .../misc/habanalabs/include/goya/asic_reg/tpc0_eml_cfg_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc0_nrtr_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc0_nrtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc0_qm_masks.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc0_qm_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc1_cfg_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc1_cmdq_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc1_qm_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc1_rtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc2_cfg_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc2_cmdq_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc2_qm_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc2_rtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc3_cfg_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc3_cmdq_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc3_qm_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc3_rtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc4_cfg_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc4_cmdq_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc4_qm_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc4_rtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc5_cfg_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc5_cmdq_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc5_qm_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc5_rtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc6_cfg_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc6_cmdq_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc6_qm_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc6_rtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc7_cfg_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc7_cmdq_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc7_nrtr_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc7_qm_regs.h | 1 - drivers/misc/habanalabs/include/goya/asic_reg/tpc_pll_regs.h | 1 - 91 files changed, 91 deletions(-) diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/cpu_ca53_cfg_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/cpu_ca53_cfg_masks.h index 2cf5c46b6e8e..4e0dbbbbde20 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/cpu_ca53_cfg_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/cpu_ca53_cfg_masks.h @@ -188,4 +188,3 @@ #define CPU_CA53_CFG_ARM_PMU_EVENT_MASK 0x3FFFFFFF #endif /* ASIC_REG_CPU_CA53_CFG_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/cpu_ca53_cfg_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/cpu_ca53_cfg_regs.h index 840ccffa1081..f3faf1aad91a 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/cpu_ca53_cfg_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/cpu_ca53_cfg_regs.h @@ -58,4 +58,3 @@ #define mmCPU_CA53_CFG_ARM_PMU_1 0x441214 #endif /* ASIC_REG_CPU_CA53_CFG_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/cpu_if_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/cpu_if_regs.h index f23cb3e41c30..cf657918962a 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/cpu_if_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/cpu_if_regs.h @@ -46,4 +46,3 @@ #define mmCPU_IF_AXI_SPLIT_INTR 0x442130 #endif /* ASIC_REG_CPU_IF_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/cpu_pll_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/cpu_pll_regs.h index 8fc97f838ada..8c8f9726d4b9 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/cpu_pll_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/cpu_pll_regs.h @@ -102,4 +102,3 @@ #define mmCPU_PLL_FREQ_CALC_EN 0x4A2440 #endif /* ASIC_REG_CPU_PLL_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_0_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_0_regs.h index 61c8cd9ce58b..0b246fe6ad04 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_0_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_0_regs.h @@ -206,4 +206,3 @@ #define mmDMA_CH_0_MEM_INIT_BUSY 0x4011FC #endif /* ASIC_REG_DMA_CH_0_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_1_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_1_regs.h index 92960ef5e308..5449031722f2 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_1_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_1_regs.h @@ -206,4 +206,3 @@ #define mmDMA_CH_1_MEM_INIT_BUSY 0x4091FC #endif /* ASIC_REG_DMA_CH_1_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_2_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_2_regs.h index 4e37871a51bb..a4768521d18a 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_2_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_2_regs.h @@ -206,4 +206,3 @@ #define mmDMA_CH_2_MEM_INIT_BUSY 0x4111FC #endif /* ASIC_REG_DMA_CH_2_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_3_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_3_regs.h index a2d6aeb32a18..619d01897ff8 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_3_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_3_regs.h @@ -206,4 +206,3 @@ #define mmDMA_CH_3_MEM_INIT_BUSY 0x4191FC #endif /* ASIC_REG_DMA_CH_3_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_4_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_4_regs.h index 400d6fd3acf5..038617e163f1 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_4_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_ch_4_regs.h @@ -206,4 +206,3 @@ #define mmDMA_CH_4_MEM_INIT_BUSY 0x4211FC #endif /* ASIC_REG_DMA_CH_4_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_macro_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_macro_masks.h index 8d965443c51e..f43b564af1be 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_macro_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_macro_masks.h @@ -102,4 +102,3 @@ #define DMA_MACRO_RAZWI_HBW_RD_ID_R_MASK 0x1FFFFFFF #endif /* ASIC_REG_DMA_MACRO_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_macro_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_macro_regs.h index 8bfcb001189d..c3bfc1b8e3fd 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_macro_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_macro_regs.h @@ -178,4 +178,3 @@ #define mmDMA_MACRO_RAZWI_HBW_RD_ID 0x4B0158 #endif /* ASIC_REG_DMA_MACRO_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_nrtr_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_nrtr_masks.h index 9f33f351a3c1..bc977488c072 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_nrtr_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_nrtr_masks.h @@ -206,4 +206,3 @@ #define DMA_NRTR_NON_LIN_SCRAMB_EN_MASK 0x1 #endif /* ASIC_REG_DMA_NRTR_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_nrtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_nrtr_regs.h index d8293745a02b..c4abc7ff1fc6 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_nrtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_nrtr_regs.h @@ -224,4 +224,3 @@ #define mmDMA_NRTR_NON_LIN_SCRAMB 0x1C0604 #endif /* ASIC_REG_DMA_NRTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_0_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_0_masks.h index 10619dbb9b17..b17f72c31ab6 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_0_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_0_masks.h @@ -462,4 +462,3 @@ #define DMA_QM_0_CQ_BUF_RDATA_VAL_MASK 0xFFFFFFFF #endif /* ASIC_REG_DMA_QM_0_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_0_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_0_regs.h index c693bc5dcb22..bf360b301154 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_0_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_0_regs.h @@ -176,4 +176,3 @@ #define mmDMA_QM_0_CQ_BUF_RDATA 0x40030C #endif /* ASIC_REG_DMA_QM_0_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_1_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_1_regs.h index da928390f89c..51d432d05ac4 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_1_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_1_regs.h @@ -176,4 +176,3 @@ #define mmDMA_QM_1_CQ_BUF_RDATA 0x40830C #endif /* ASIC_REG_DMA_QM_1_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_2_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_2_regs.h index b4f06e9b71d6..18fc0c2b6cc2 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_2_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_2_regs.h @@ -176,4 +176,3 @@ #define mmDMA_QM_2_CQ_BUF_RDATA 0x41030C #endif /* ASIC_REG_DMA_QM_2_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_3_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_3_regs.h index 53e3cd78a06b..6cf7204bf5cc 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_3_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_3_regs.h @@ -176,4 +176,3 @@ #define mmDMA_QM_3_CQ_BUF_RDATA 0x41830C #endif /* ASIC_REG_DMA_QM_3_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_4_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_4_regs.h index e0eb5f260201..36fef2682875 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_4_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/dma_qm_4_regs.h @@ -176,4 +176,3 @@ #define mmDMA_QM_4_CQ_BUF_RDATA 0x42030C #endif /* ASIC_REG_DMA_QM_4_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/ic_pll_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/ic_pll_regs.h index 0a743817aad7..4ae7fed8b18c 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/ic_pll_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/ic_pll_regs.h @@ -102,4 +102,3 @@ #define mmIC_PLL_FREQ_CALC_EN 0x4A3440 #endif /* ASIC_REG_IC_PLL_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mc_pll_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/mc_pll_regs.h index 4408188aa067..6d35d852798b 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mc_pll_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mc_pll_regs.h @@ -102,4 +102,3 @@ #define mmMC_PLL_FREQ_CALC_EN 0x4A1440 #endif /* ASIC_REG_MC_PLL_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mme1_rtr_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/mme1_rtr_masks.h index 687bca5c5fe3..6c23f8b96e7e 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mme1_rtr_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mme1_rtr_masks.h @@ -650,4 +650,3 @@ #define MME1_RTR_NON_LIN_SCRAMB_EN_MASK 0x1 #endif /* ASIC_REG_MME1_RTR_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mme1_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/mme1_rtr_regs.h index c248339a1cbe..122e9d529939 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mme1_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mme1_rtr_regs.h @@ -328,4 +328,3 @@ #define mmMME1_RTR_NON_LIN_SCRAMB 0x40604 #endif /* ASIC_REG_MME1_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mme2_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/mme2_rtr_regs.h index 7a2b777bdc4f..00ce2252bbfb 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mme2_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mme2_rtr_regs.h @@ -328,4 +328,3 @@ #define mmMME2_RTR_NON_LIN_SCRAMB 0x80604 #endif /* ASIC_REG_MME2_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mme3_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/mme3_rtr_regs.h index b78f8bc387fc..8e3eb7fd2070 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mme3_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mme3_rtr_regs.h @@ -328,4 +328,3 @@ #define mmMME3_RTR_NON_LIN_SCRAMB 0xC0604 #endif /* ASIC_REG_MME3_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mme4_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/mme4_rtr_regs.h index d9a4a02cefa3..79b67bbc8567 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mme4_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mme4_rtr_regs.h @@ -328,4 +328,3 @@ #define mmMME4_RTR_NON_LIN_SCRAMB 0x100604 #endif /* ASIC_REG_MME4_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mme5_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/mme5_rtr_regs.h index 205adc988407..0ac3c37ce47f 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mme5_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mme5_rtr_regs.h @@ -328,4 +328,3 @@ #define mmMME5_RTR_NON_LIN_SCRAMB 0x140604 #endif /* ASIC_REG_MME5_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mme6_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/mme6_rtr_regs.h index fcec68388278..50c49cce72a6 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mme6_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mme6_rtr_regs.h @@ -328,4 +328,3 @@ #define mmMME6_RTR_NON_LIN_SCRAMB 0x180604 #endif /* ASIC_REG_MME6_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mme_cmdq_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/mme_cmdq_masks.h index a0d4382fbbd0..fe7d95bdcef9 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mme_cmdq_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mme_cmdq_masks.h @@ -370,4 +370,3 @@ #define MME_CMDQ_CQ_BUF_RDATA_VAL_MASK 0xFFFFFFFF #endif /* ASIC_REG_MME_CMDQ_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mme_cmdq_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/mme_cmdq_regs.h index 5c2f6b870a58..5f8b85d2b4b1 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mme_cmdq_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mme_cmdq_regs.h @@ -136,4 +136,3 @@ #define mmMME_CMDQ_CQ_BUF_RDATA 0xD930C #endif /* ASIC_REG_MME_CMDQ_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mme_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/mme_masks.h index c7b1b0bb3384..1882c413cbe0 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mme_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mme_masks.h @@ -1534,4 +1534,3 @@ #define MME_SHADOW_3_E_BUBBLES_PER_SPLIT_ID_MASK 0xFF000000 #endif /* ASIC_REG_MME_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mme_qm_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/mme_qm_masks.h index d4bfa58dce19..e464e381555c 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mme_qm_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mme_qm_masks.h @@ -462,4 +462,3 @@ #define MME_QM_CQ_BUF_RDATA_VAL_MASK 0xFFFFFFFF #endif /* ASIC_REG_MME_QM_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mme_qm_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/mme_qm_regs.h index b5b1c776f6c3..538708beffc9 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mme_qm_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mme_qm_regs.h @@ -176,4 +176,3 @@ #define mmMME_QM_CQ_BUF_RDATA 0xD830C #endif /* ASIC_REG_MME_QM_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mme_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/mme_regs.h index 9436b1e2705a..0396cbfd5c89 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mme_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mme_regs.h @@ -1150,4 +1150,3 @@ #define mmMME_SHADOW_3_E_BUBBLES_PER_SPLIT 0xD0BAC #endif /* ASIC_REG_MME_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mmu_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/mmu_masks.h index 3a78078d3c4c..c3e69062b135 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mmu_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mmu_masks.h @@ -140,4 +140,3 @@ #define MMU_ACCESS_ERROR_CAPTURE_VA_VA_31_0_MASK 0xFFFFFFFF #endif /* ASIC_REG_MMU_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/mmu_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/mmu_regs.h index bec6c014135c..7ec81f12031e 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/mmu_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/mmu_regs.h @@ -50,4 +50,3 @@ #define mmMMU_ACCESS_ERROR_CAPTURE_VA 0x480040 #endif /* ASIC_REG_MMU_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/pci_nrtr_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/pci_nrtr_masks.h index 209e41402a11..ceb59f2e28b3 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/pci_nrtr_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/pci_nrtr_masks.h @@ -206,4 +206,3 @@ #define PCI_NRTR_NON_LIN_SCRAMB_EN_MASK 0x1 #endif /* ASIC_REG_PCI_NRTR_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/pci_nrtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/pci_nrtr_regs.h index 447e5d4e7dc8..dd067f301ac2 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/pci_nrtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/pci_nrtr_regs.h @@ -224,4 +224,3 @@ #define mmPCI_NRTR_NON_LIN_SCRAMB 0x604 #endif /* ASIC_REG_PCI_NRTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/pcie_aux_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/pcie_aux_regs.h index daaf5d9079dc..35b1d8ac6f63 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/pcie_aux_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/pcie_aux_regs.h @@ -240,4 +240,3 @@ #define mmPCIE_AUX_PERST 0xC079B8 #endif /* ASIC_REG_PCIE_AUX_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_emmc_pll_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_emmc_pll_regs.h index 8eda4de58788..9271ea95ebe9 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_emmc_pll_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_emmc_pll_regs.h @@ -102,4 +102,3 @@ #define mmPSOC_EMMC_PLL_FREQ_CALC_EN 0xC70440 #endif /* ASIC_REG_PSOC_EMMC_PLL_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_global_conf_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_global_conf_masks.h index d4bf0e1db4df..324266653c9a 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_global_conf_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_global_conf_masks.h @@ -444,4 +444,3 @@ #define PSOC_GLOBAL_CONF_PAD_SEL_VAL_MASK 0x3 #endif /* ASIC_REG_PSOC_GLOBAL_CONF_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_global_conf_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_global_conf_regs.h index cfbdd2c9c5c7..8141f422e712 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_global_conf_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_global_conf_regs.h @@ -742,4 +742,3 @@ #define mmPSOC_GLOBAL_CONF_PAD_SEL_81 0xC4BA44 #endif /* ASIC_REG_PSOC_GLOBAL_CONF_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_mme_pll_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_mme_pll_regs.h index 6723d8f76f30..4789ebb9c337 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_mme_pll_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_mme_pll_regs.h @@ -102,4 +102,3 @@ #define mmPSOC_MME_PLL_FREQ_CALC_EN 0xC71440 #endif /* ASIC_REG_PSOC_MME_PLL_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_pci_pll_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_pci_pll_regs.h index abcded0531c9..27a296ea6c3d 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_pci_pll_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_pci_pll_regs.h @@ -102,4 +102,3 @@ #define mmPSOC_PCI_PLL_FREQ_CALC_EN 0xC72440 #endif /* ASIC_REG_PSOC_PCI_PLL_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_spi_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_spi_regs.h index 5925c7477c25..66aee7fa6b1e 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/psoc_spi_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/psoc_spi_regs.h @@ -140,4 +140,3 @@ #define mmPSOC_SPI_RSVD_2 0xC430FC #endif /* ASIC_REG_PSOC_SPI_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x0_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x0_rtr_regs.h index d56c9fa0e7ba..2ea1770b078f 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x0_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x0_rtr_regs.h @@ -80,4 +80,3 @@ #define mmSRAM_Y0_X0_RTR_DBG_L_ARB_MAX 0x201330 #endif /* ASIC_REG_SRAM_Y0_X0_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x1_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x1_rtr_regs.h index 5624544303ca..37e0713efa73 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x1_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x1_rtr_regs.h @@ -80,4 +80,3 @@ #define mmSRAM_Y0_X1_RTR_DBG_L_ARB_MAX 0x205330 #endif /* ASIC_REG_SRAM_Y0_X1_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x2_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x2_rtr_regs.h index 3322bc0bd1df..d2572279a2b9 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x2_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x2_rtr_regs.h @@ -80,4 +80,3 @@ #define mmSRAM_Y0_X2_RTR_DBG_L_ARB_MAX 0x209330 #endif /* ASIC_REG_SRAM_Y0_X2_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x3_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x3_rtr_regs.h index 81e393db2027..68c5b402c506 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x3_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x3_rtr_regs.h @@ -80,4 +80,3 @@ #define mmSRAM_Y0_X3_RTR_DBG_L_ARB_MAX 0x20D330 #endif /* ASIC_REG_SRAM_Y0_X3_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x4_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x4_rtr_regs.h index b2e11b1de385..a42f1ba06d28 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x4_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/sram_y0_x4_rtr_regs.h @@ -80,4 +80,3 @@ #define mmSRAM_Y0_X4_RTR_DBG_L_ARB_MAX 0x211330 #endif /* ASIC_REG_SRAM_Y0_X4_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/stlb_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/stlb_masks.h index b4ea8cae2757..94f2ed4a36bd 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/stlb_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/stlb_masks.h @@ -114,4 +114,3 @@ #define STLB_SRAM_INIT_BUSY_DATA_MASK 0x10 #endif /* ASIC_REG_STLB_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/stlb_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/stlb_regs.h index 0f5281d3e65b..35013f65acd2 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/stlb_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/stlb_regs.h @@ -52,4 +52,3 @@ #define mmSTLB_SRAM_INIT 0x49004C #endif /* ASIC_REG_STLB_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cfg_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cfg_masks.h index e5587b49eecd..89c9507a512f 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cfg_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cfg_masks.h @@ -1604,4 +1604,3 @@ #define TPC0_CFG_FUNC_MBIST_MEM_LAST_FAILED_PATTERN_MASK 0x70000000 #endif /* ASIC_REG_TPC0_CFG_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cfg_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cfg_regs.h index 2be28a63c50a..7d71c4b73a5e 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cfg_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cfg_regs.h @@ -884,4 +884,3 @@ #define mmTPC0_CFG_FUNC_MBIST_MEM_9 0xE06E2C #endif /* ASIC_REG_TPC0_CFG_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cmdq_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cmdq_masks.h index 9aa2d8b53207..9395f2458771 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cmdq_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cmdq_masks.h @@ -370,4 +370,3 @@ #define TPC0_CMDQ_CQ_BUF_RDATA_VAL_MASK 0xFFFFFFFF #endif /* ASIC_REG_TPC0_CMDQ_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cmdq_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cmdq_regs.h index 3572752ba66e..bc51df573bf0 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cmdq_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_cmdq_regs.h @@ -136,4 +136,3 @@ #define mmTPC0_CMDQ_CQ_BUF_RDATA 0xE0930C #endif /* ASIC_REG_TPC0_CMDQ_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_eml_cfg_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_eml_cfg_masks.h index ed866d93c440..553c6b6bd5ec 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_eml_cfg_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_eml_cfg_masks.h @@ -344,4 +344,3 @@ #define TPC0_EML_CFG_DBG_INST_INSERT_CTL_INSERT_MASK 0x1 #endif /* ASIC_REG_TPC0_EML_CFG_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_eml_cfg_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_eml_cfg_regs.h index f1a1b4fa4841..8495479c3659 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_eml_cfg_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_eml_cfg_regs.h @@ -310,4 +310,3 @@ #define mmTPC0_EML_CFG_DBG_INST_INSERT_CTL 0x3040334 #endif /* ASIC_REG_TPC0_EML_CFG_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_nrtr_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_nrtr_masks.h index 7f86621179a5..43fafcf01041 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_nrtr_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_nrtr_masks.h @@ -206,4 +206,3 @@ #define TPC0_NRTR_NON_LIN_SCRAMB_EN_MASK 0x1 #endif /* ASIC_REG_TPC0_NRTR_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_nrtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_nrtr_regs.h index dc280f4e6608..ce3346dd2042 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_nrtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_nrtr_regs.h @@ -224,4 +224,3 @@ #define mmTPC0_NRTR_NON_LIN_SCRAMB 0xE00604 #endif /* ASIC_REG_TPC0_NRTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_qm_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_qm_masks.h index 80d97ee3d8d6..2e4b45947944 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_qm_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_qm_masks.h @@ -462,4 +462,3 @@ #define TPC0_QM_CQ_BUF_RDATA_VAL_MASK 0xFFFFFFFF #endif /* ASIC_REG_TPC0_QM_MASKS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_qm_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_qm_regs.h index 7552d4ba61fe..4fa09eb88878 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_qm_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc0_qm_regs.h @@ -176,4 +176,3 @@ #define mmTPC0_QM_CQ_BUF_RDATA 0xE0830C #endif /* ASIC_REG_TPC0_QM_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_cfg_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_cfg_regs.h index 19894413474a..928eef1808ae 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_cfg_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_cfg_regs.h @@ -884,4 +884,3 @@ #define mmTPC1_CFG_FUNC_MBIST_MEM_9 0xE46E2C #endif /* ASIC_REG_TPC1_CFG_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_cmdq_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_cmdq_regs.h index 9099ebd7ab23..30ae0f307328 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_cmdq_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_cmdq_regs.h @@ -136,4 +136,3 @@ #define mmTPC1_CMDQ_CQ_BUF_RDATA 0xE4930C #endif /* ASIC_REG_TPC1_CMDQ_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_qm_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_qm_regs.h index bc8b9a10391f..b95de4f95ba9 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_qm_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_qm_regs.h @@ -176,4 +176,3 @@ #define mmTPC1_QM_CQ_BUF_RDATA 0xE4830C #endif /* ASIC_REG_TPC1_QM_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_rtr_regs.h index ae267f8f457e..0f91e307879e 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc1_rtr_regs.h @@ -320,4 +320,3 @@ #define mmTPC1_RTR_NON_LIN_SCRAMB 0xE40604 #endif /* ASIC_REG_TPC1_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_cfg_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_cfg_regs.h index 9c33fc039036..73421227f35b 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_cfg_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_cfg_regs.h @@ -884,4 +884,3 @@ #define mmTPC2_CFG_FUNC_MBIST_MEM_9 0xE86E2C #endif /* ASIC_REG_TPC2_CFG_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_cmdq_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_cmdq_regs.h index 7a643887d6e1..27b66bf2da9f 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_cmdq_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_cmdq_regs.h @@ -136,4 +136,3 @@ #define mmTPC2_CMDQ_CQ_BUF_RDATA 0xE8930C #endif /* ASIC_REG_TPC2_CMDQ_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_qm_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_qm_regs.h index f3e32c018064..31e5b2f53905 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_qm_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_qm_regs.h @@ -176,4 +176,3 @@ #define mmTPC2_QM_CQ_BUF_RDATA 0xE8830C #endif /* ASIC_REG_TPC2_QM_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_rtr_regs.h index 0eb0cd1fbd19..4eddeaa15d94 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc2_rtr_regs.h @@ -320,4 +320,3 @@ #define mmTPC2_RTR_NON_LIN_SCRAMB 0xE80604 #endif /* ASIC_REG_TPC2_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_cfg_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_cfg_regs.h index 0baf63c69b25..ce573a1a8361 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_cfg_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_cfg_regs.h @@ -884,4 +884,3 @@ #define mmTPC3_CFG_FUNC_MBIST_MEM_9 0xEC6E2C #endif /* ASIC_REG_TPC3_CFG_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_cmdq_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_cmdq_regs.h index 82a5261e852f..11d81fca0a0f 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_cmdq_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_cmdq_regs.h @@ -136,4 +136,3 @@ #define mmTPC3_CMDQ_CQ_BUF_RDATA 0xEC930C #endif /* ASIC_REG_TPC3_CMDQ_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_qm_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_qm_regs.h index b05b1e18e664..e41595a19e69 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_qm_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_qm_regs.h @@ -176,4 +176,3 @@ #define mmTPC3_QM_CQ_BUF_RDATA 0xEC830C #endif /* ASIC_REG_TPC3_QM_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_rtr_regs.h index 5a2fd7652650..34a438b1efe5 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc3_rtr_regs.h @@ -320,4 +320,3 @@ #define mmTPC3_RTR_NON_LIN_SCRAMB 0xEC0604 #endif /* ASIC_REG_TPC3_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_cfg_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_cfg_regs.h index d64a100075f2..d44caf0fc1bb 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_cfg_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_cfg_regs.h @@ -884,4 +884,3 @@ #define mmTPC4_CFG_FUNC_MBIST_MEM_9 0xF06E2C #endif /* ASIC_REG_TPC4_CFG_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_cmdq_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_cmdq_regs.h index 565b42885b0d..f13a6532961f 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_cmdq_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_cmdq_regs.h @@ -136,4 +136,3 @@ #define mmTPC4_CMDQ_CQ_BUF_RDATA 0xF0930C #endif /* ASIC_REG_TPC4_CMDQ_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_qm_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_qm_regs.h index 196da3f12710..db081fc17cfc 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_qm_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_qm_regs.h @@ -176,4 +176,3 @@ #define mmTPC4_QM_CQ_BUF_RDATA 0xF0830C #endif /* ASIC_REG_TPC4_QM_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_rtr_regs.h index 8b54041d144a..8c5372303b28 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc4_rtr_regs.h @@ -320,4 +320,3 @@ #define mmTPC4_RTR_NON_LIN_SCRAMB 0xF00604 #endif /* ASIC_REG_TPC4_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_cfg_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_cfg_regs.h index 3f00954fcdba..5139fde71011 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_cfg_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_cfg_regs.h @@ -884,4 +884,3 @@ #define mmTPC5_CFG_FUNC_MBIST_MEM_9 0xF46E2C #endif /* ASIC_REG_TPC5_CFG_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_cmdq_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_cmdq_regs.h index d8e72a8e18d7..1e7cd6e1e888 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_cmdq_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_cmdq_regs.h @@ -136,4 +136,3 @@ #define mmTPC5_CMDQ_CQ_BUF_RDATA 0xF4930C #endif /* ASIC_REG_TPC5_CMDQ_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_qm_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_qm_regs.h index be2e68624709..ac0d3820cd6b 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_qm_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_qm_regs.h @@ -176,4 +176,3 @@ #define mmTPC5_QM_CQ_BUF_RDATA 0xF4830C #endif /* ASIC_REG_TPC5_QM_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_rtr_regs.h index 6f301c7bbc2f..57f83bc3b17d 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc5_rtr_regs.h @@ -320,4 +320,3 @@ #define mmTPC5_RTR_NON_LIN_SCRAMB 0xF40604 #endif /* ASIC_REG_TPC5_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_cfg_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_cfg_regs.h index 1e1168601c41..94e0191c06c1 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_cfg_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_cfg_regs.h @@ -884,4 +884,3 @@ #define mmTPC6_CFG_FUNC_MBIST_MEM_9 0xF86E2C #endif /* ASIC_REG_TPC6_CFG_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_cmdq_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_cmdq_regs.h index fbca6b47284e..7a1a0e87b225 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_cmdq_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_cmdq_regs.h @@ -136,4 +136,3 @@ #define mmTPC6_CMDQ_CQ_BUF_RDATA 0xF8930C #endif /* ASIC_REG_TPC6_CMDQ_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_qm_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_qm_regs.h index bf32465dabcb..80fa0fe0f60f 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_qm_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_qm_regs.h @@ -176,4 +176,3 @@ #define mmTPC6_QM_CQ_BUF_RDATA 0xF8830C #endif /* ASIC_REG_TPC6_QM_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_rtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_rtr_regs.h index 609bb90e1046..d6cae8b8af66 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_rtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc6_rtr_regs.h @@ -320,4 +320,3 @@ #define mmTPC6_RTR_NON_LIN_SCRAMB 0xF80604 #endif /* ASIC_REG_TPC6_RTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_cfg_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_cfg_regs.h index bf2fd0f73906..234147adb779 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_cfg_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_cfg_regs.h @@ -884,4 +884,3 @@ #define mmTPC7_CFG_FUNC_MBIST_MEM_9 0xFC6E2C #endif /* ASIC_REG_TPC7_CFG_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_cmdq_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_cmdq_regs.h index 65d83043bf63..4c160632fe7d 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_cmdq_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_cmdq_regs.h @@ -136,4 +136,3 @@ #define mmTPC7_CMDQ_CQ_BUF_RDATA 0xFC930C #endif /* ASIC_REG_TPC7_CMDQ_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_nrtr_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_nrtr_regs.h index 3d5848d87304..0c13d4d167aa 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_nrtr_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_nrtr_regs.h @@ -224,4 +224,3 @@ #define mmTPC7_NRTR_NON_LIN_SCRAMB 0xFC0604 #endif /* ASIC_REG_TPC7_NRTR_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_qm_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_qm_regs.h index 25f5095f68fb..cbe11425bfb0 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_qm_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc7_qm_regs.h @@ -176,4 +176,3 @@ #define mmTPC7_QM_CQ_BUF_RDATA 0xFC830C #endif /* ASIC_REG_TPC7_QM_REGS_H_ */ - diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/tpc_pll_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/tpc_pll_regs.h index 920231d0afa5..e25e19660a9d 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/tpc_pll_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/tpc_pll_regs.h @@ -102,4 +102,3 @@ #define mmTPC_PLL_FREQ_CALC_EN 0xE01440 #endif /* ASIC_REG_TPC_PLL_REGS_H_ */ - From e850b89f50d2c1439f58d547b888ee6e43312dea Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sun, 31 Mar 2019 21:37:42 +0300 Subject: [PATCH 048/255] habanalabs: prevent CPU soft lockup on Palladium Unmapping ptes in the device MMU on Palladium can take a long time, which can cause a kernel BUG of CPU soft lockup. This patch minimize the chances for this bug by sleeping a little between unmapping ptes. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/memory.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/misc/habanalabs/memory.c b/drivers/misc/habanalabs/memory.c index 39788b1cf8d0..e9e163545584 100644 --- a/drivers/misc/habanalabs/memory.c +++ b/drivers/misc/habanalabs/memory.c @@ -1046,10 +1046,17 @@ static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr) mutex_lock(&ctx->mmu_lock); - for (i = 0 ; i < phys_pg_pack->npages ; i++, next_vaddr += page_size) + for (i = 0 ; i < phys_pg_pack->npages ; i++, next_vaddr += page_size) { if (hl_mmu_unmap(ctx, next_vaddr, page_size)) dev_warn_ratelimited(hdev->dev, - "unmap failed for vaddr: 0x%llx\n", next_vaddr); + "unmap failed for vaddr: 0x%llx\n", next_vaddr); + + /* unmapping on Palladium can be really long, so avoid a CPU + * soft lockup bug by sleeping a little between unmapping pages + */ + if (hdev->pldm) + usleep_range(500, 1000); + } hdev->asic_funcs->mmu_invalidate_cache(hdev, true); From a1c92d1c2a67d7b61dd5ed2d3bce810269613d37 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Tue, 2 Apr 2019 15:46:02 +0300 Subject: [PATCH 049/255] habanalabs: remove extra semicolon This patch removes an extra ; after the closing brackets of a while loop. Signed-off-by: Oded Gabbay Reviewed-by: Mukesh Ojha --- drivers/misc/habanalabs/device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index e3797f582436..6cbfd560721e 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -1044,7 +1044,7 @@ void hl_device_fini(struct hl_device *hdev) WARN(1, "Failed to remove device because reset function did not finish\n"); return; } - }; + } /* Mark device as disabled */ hdev->disabled = true; From 315bc055ed5667232859b17adb837f87c1629f81 Mon Sep 17 00:00:00 2001 From: Omer Shpigelman Date: Mon, 1 Apr 2019 22:31:22 +0300 Subject: [PATCH 050/255] habanalabs: add new IOCTL for debug, tracing and profiling Habanalabs ASICs use the ARM coresight infrastructure to support debug, tracing and profiling of neural networks topologies. Because the coresight is configured using register writes and reads, and some of the registers hold sensitive information (e.g. the address in the device's DRAM where the trace data is written to), the user must go through the kernel driver to configure this mechanism. This patch implements the common code of the IOCTL and calls the ASIC-specific function for the actual H/W configuration. The IOCTL supports configuration of seven coresight components: ETR, ETF, STM, FUNNEL, BMON, SPMU and TIMESTAMP The user specifies which component he wishes to configure and provides a pointer to a structure (located in its process space) that contains the relevant configuration. The common code copies the relevant data from the user-space to kernel space and then calls the ASIC-specific function to do the H/W configuration. After the configuration is done, which is usually composed of several IOCTL calls depending on what the user wanted to trace, the user can start executing the topology. The trace data will be written to the user's area in the device's DRAM. After the tracing operation is complete, and user will call the IOCTL again to disable the tracing operation. The user also need to read values from registers for some of the components (e.g. the size of the trace data in the device's DRAM). In that case, the user will provide a pointer to an "output" structure in user-space, which the IOCTL code will fill according the to selected component. Signed-off-by: Omer Shpigelman Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/Makefile | 3 +- drivers/misc/habanalabs/goya/goya.c | 1 + drivers/misc/habanalabs/goya/goyaP.h | 1 + drivers/misc/habanalabs/goya/goya_coresight.c | 13 ++ drivers/misc/habanalabs/habanalabs.h | 25 ++++ drivers/misc/habanalabs/habanalabs_ioctl.c | 113 ++++++++++++++++- include/uapi/misc/habanalabs.h | 116 +++++++++++++++++- 7 files changed, 269 insertions(+), 3 deletions(-) create mode 100644 drivers/misc/habanalabs/goya/goya_coresight.c diff --git a/drivers/misc/habanalabs/goya/Makefile b/drivers/misc/habanalabs/goya/Makefile index e458e5ba500b..131432f677e2 100644 --- a/drivers/misc/habanalabs/goya/Makefile +++ b/drivers/misc/habanalabs/goya/Makefile @@ -1,3 +1,4 @@ subdir-ccflags-y += -I$(src) -HL_GOYA_FILES := goya/goya.o goya/goya_security.o goya/goya_hwmgr.o +HL_GOYA_FILES := goya/goya.o goya/goya_security.o goya/goya_hwmgr.o \ + goya/goya_coresight.o diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 9f775dd81a52..3af883ada479 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -4815,6 +4815,7 @@ static const struct hl_asic_funcs goya_funcs = { .send_heartbeat = goya_send_heartbeat, .enable_clock_gating = goya_init_clock_gating, .disable_clock_gating = goya_disable_clock_gating, + .debug_coresight = goya_debug_coresight, .is_device_idle = goya_is_device_idle, .soft_reset_late_init = goya_soft_reset_late_init, .hw_queues_lock = goya_hw_queues_lock, diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h index b99d92f197eb..6f1f7715075d 100644 --- a/drivers/misc/habanalabs/goya/goyaP.h +++ b/drivers/misc/habanalabs/goya/goyaP.h @@ -175,6 +175,7 @@ void goya_add_device_attr(struct hl_device *hdev, struct attribute_group *dev_attr_grp); int goya_armcp_info_get(struct hl_device *hdev); void goya_init_security(struct hl_device *hdev); +int goya_debug_coresight(struct hl_device *hdev, void *data); u64 goya_get_max_power(struct hl_device *hdev); void goya_set_max_power(struct hl_device *hdev, u64 value); diff --git a/drivers/misc/habanalabs/goya/goya_coresight.c b/drivers/misc/habanalabs/goya/goya_coresight.c new file mode 100644 index 000000000000..8957b8b1c0d6 --- /dev/null +++ b/drivers/misc/habanalabs/goya/goya_coresight.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2016-2019 HabanaLabs, Ltd. + * All Rights Reserved. + */ + +#include "goyaP.h" + +int goya_debug_coresight(struct hl_device *hdev, void *data) +{ + return -ENOTTY; +} diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index fd7fcdf7050f..18a03657780a 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -483,6 +483,7 @@ enum hl_pll_frequency { * @send_heartbeat: send is-alive packet to ArmCP and verify response. * @enable_clock_gating: enable clock gating for reducing power consumption. * @disable_clock_gating: disable clock for accessing registers on HBW. + * @debug_coresight: perform certain actions on Coresight for debugging. * @is_device_idle: return true if device is idle, false otherwise. * @soft_reset_late_init: perform certain actions needed after soft reset. * @hw_queues_lock: acquire H/W queues lock. @@ -557,6 +558,7 @@ struct hl_asic_funcs { int (*send_heartbeat)(struct hl_device *hdev); void (*enable_clock_gating)(struct hl_device *hdev); void (*disable_clock_gating)(struct hl_device *hdev); + int (*debug_coresight)(struct hl_device *hdev, void *data); bool (*is_device_idle)(struct hl_device *hdev, char *buf, size_t size); int (*soft_reset_late_init)(struct hl_device *hdev); void (*hw_queues_lock)(struct hl_device *hdev); @@ -867,6 +869,29 @@ struct hl_vm { u8 init_done; }; + +/* + * DEBUG, PROFILING STRUCTURE + */ + +/** + * struct hl_debug_params - Coresight debug parameters. + * @input: pointer to component specific input parameters. + * @output: pointer to component specific output parameters. + * @output_size: size of output buffer. + * @reg_idx: relevant register ID. + * @op: component operation to execute. + * @enable: true if to enable component debugging, false otherwise. + */ +struct hl_debug_params { + void *input; + void *output; + u32 output_size; + u32 reg_idx; + u32 op; + bool enable; +}; + /* * FILE PRIVATE STRUCTURE */ diff --git a/drivers/misc/habanalabs/habanalabs_ioctl.c b/drivers/misc/habanalabs/habanalabs_ioctl.c index 9000ff615805..810e65446075 100644 --- a/drivers/misc/habanalabs/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/habanalabs_ioctl.c @@ -12,6 +12,17 @@ #include #include +static u32 hl_debug_struct_size[HL_DEBUG_OP_TIMESTAMP + 1] = { + [HL_DEBUG_OP_ETR] = sizeof(struct hl_debug_params_etr), + [HL_DEBUG_OP_ETF] = sizeof(struct hl_debug_params_etf), + [HL_DEBUG_OP_STM] = sizeof(struct hl_debug_params_stm), + [HL_DEBUG_OP_FUNNEL] = 0, + [HL_DEBUG_OP_BMON] = sizeof(struct hl_debug_params_bmon), + [HL_DEBUG_OP_SPMU] = sizeof(struct hl_debug_params_spmu), + [HL_DEBUG_OP_TIMESTAMP] = 0 + +}; + static int device_status_info(struct hl_device *hdev, struct hl_info_args *args) { struct hl_info_device_status dev_stat = {0}; @@ -114,6 +125,71 @@ static int hw_idle(struct hl_device *hdev, struct hl_info_args *args) min((size_t) max_size, sizeof(hw_idle))) ? -EFAULT : 0; } +static int debug_coresight(struct hl_device *hdev, struct hl_debug_args *args) +{ + struct hl_debug_params *params; + void *input = NULL, *output = NULL; + int rc; + + params = kzalloc(sizeof(*params), GFP_KERNEL); + if (!params) + return -ENOMEM; + + params->reg_idx = args->reg_idx; + params->enable = args->enable; + params->op = args->op; + + if (args->input_ptr && args->input_size) { + input = memdup_user((const void __user *) args->input_ptr, + args->input_size); + if (IS_ERR(input)) { + rc = PTR_ERR(input); + input = NULL; + dev_err(hdev->dev, + "error %d when copying input debug data\n", rc); + goto out; + } + + params->input = input; + } + + if (args->output_ptr && args->output_size) { + output = kzalloc(args->output_size, GFP_KERNEL); + if (!output) { + rc = -ENOMEM; + goto out; + } + + params->output = output; + params->output_size = args->output_size; + } + + rc = hdev->asic_funcs->debug_coresight(hdev, params); + if (rc) { + dev_err(hdev->dev, + "debug coresight operation failed %d\n", rc); + goto out; + } + + if (output) { + if (copy_to_user((void __user *) (uintptr_t) args->output_ptr, + output, + args->output_size)) { + dev_err(hdev->dev, + "copy to user failed in debug ioctl\n"); + rc = -EFAULT; + goto out; + } + } + +out: + kfree(params); + kfree(output); + kfree(input); + + return rc; +} + static int hl_info_ioctl(struct hl_fpriv *hpriv, void *data) { struct hl_info_args *args = data; @@ -156,6 +232,40 @@ static int hl_info_ioctl(struct hl_fpriv *hpriv, void *data) return rc; } +static int hl_debug_ioctl(struct hl_fpriv *hpriv, void *data) +{ + struct hl_debug_args *args = data; + struct hl_device *hdev = hpriv->hdev; + int rc = 0; + + if (hl_device_disabled_or_in_reset(hdev)) { + dev_warn_ratelimited(hdev->dev, + "Device is %s. Can't execute DEBUG IOCTL\n", + atomic_read(&hdev->in_reset) ? "in_reset" : "disabled"); + return -EBUSY; + } + + switch (args->op) { + case HL_DEBUG_OP_ETR: + case HL_DEBUG_OP_ETF: + case HL_DEBUG_OP_STM: + case HL_DEBUG_OP_FUNNEL: + case HL_DEBUG_OP_BMON: + case HL_DEBUG_OP_SPMU: + case HL_DEBUG_OP_TIMESTAMP: + args->input_size = + min(args->input_size, hl_debug_struct_size[args->op]); + rc = debug_coresight(hdev, args); + break; + default: + dev_err(hdev->dev, "Invalid request %d\n", args->op); + rc = -ENOTTY; + break; + } + + return rc; +} + #define HL_IOCTL_DEF(ioctl, _func) \ [_IOC_NR(ioctl)] = {.cmd = ioctl, .func = _func} @@ -164,7 +274,8 @@ static const struct hl_ioctl_desc hl_ioctls[] = { HL_IOCTL_DEF(HL_IOCTL_CB, hl_cb_ioctl), HL_IOCTL_DEF(HL_IOCTL_CS, hl_cs_ioctl), HL_IOCTL_DEF(HL_IOCTL_WAIT_CS, hl_cs_wait_ioctl), - HL_IOCTL_DEF(HL_IOCTL_MEMORY, hl_mem_ioctl) + HL_IOCTL_DEF(HL_IOCTL_MEMORY, hl_mem_ioctl), + HL_IOCTL_DEF(HL_IOCTL_DEBUG, hl_debug_ioctl) }; #define HL_CORE_IOCTL_COUNT ARRAY_SIZE(hl_ioctls) diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 993a79edad73..7704fe08c3ad 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -335,6 +335,107 @@ union hl_mem_args { struct hl_mem_out out; }; +#define HL_DEBUG_MAX_AUX_VALUES 10 + +struct hl_debug_params_etr { + /* Address in memory to allocate buffer */ + __u64 buffer_address; + + /* Size of buffer to allocate */ + __u64 buffer_size; + + /* Sink operation mode: SW fifo, HW fifo, Circular buffer */ + __u32 sink_mode; + __u32 pad; +}; + +struct hl_debug_params_etf { + /* Address in memory to allocate buffer */ + __u64 buffer_address; + + /* Size of buffer to allocate */ + __u64 buffer_size; + + /* Sink operation mode: SW fifo, HW fifo, Circular buffer */ + __u32 sink_mode; + __u32 pad; +}; + +struct hl_debug_params_stm { + /* Two bit masks for HW event and Stimulus Port */ + __u64 he_mask; + __u64 sp_mask; + + /* Trace source ID */ + __u32 id; + + /* Frequency for the timestamp register */ + __u32 frequency; +}; + +struct hl_debug_params_bmon { + /* Transaction address filter */ + __u64 addr_range0; + __u64 addr_range1; + + /* Capture window configuration */ + __u32 bw_win; + __u32 win_capture; + + /* Trace source ID */ + __u32 id; + __u32 pad; +}; + +struct hl_debug_params_spmu { + /* Event types selection */ + __u64 event_types[HL_DEBUG_MAX_AUX_VALUES]; + + /* Number of event types selection */ + __u32 event_types_num; + __u32 pad; +}; + +/* Opcode for ETR component */ +#define HL_DEBUG_OP_ETR 0 +/* Opcode for ETF component */ +#define HL_DEBUG_OP_ETF 1 +/* Opcode for STM component */ +#define HL_DEBUG_OP_STM 2 +/* Opcode for FUNNEL component */ +#define HL_DEBUG_OP_FUNNEL 3 +/* Opcode for BMON component */ +#define HL_DEBUG_OP_BMON 4 +/* Opcode for SPMU component */ +#define HL_DEBUG_OP_SPMU 5 +/* Opcode for timestamp */ +#define HL_DEBUG_OP_TIMESTAMP 6 + +struct hl_debug_args { + /* + * Pointer to user input structure. + * This field is relevant to specific opcodes. + */ + __u64 input_ptr; + /* Pointer to user output structure */ + __u64 output_ptr; + /* Size of user input structure */ + __u32 input_size; + /* Size of user output structure */ + __u32 output_size; + /* HL_DEBUG_OP_* */ + __u32 op; + /* + * Register index in the component, taken from the debug_regs_index enum + * in the various ASIC header files + */ + __u32 reg_idx; + /* Enable/disable */ + __u32 enable; + /* Context ID - Currently not in use */ + __u32 ctx_id; +}; + /* * Various information operations such as: * - H/W IP information @@ -459,7 +560,20 @@ union hl_mem_args { #define HL_IOCTL_MEMORY \ _IOWR('H', 0x05, union hl_mem_args) +/* + * Debug + * - Enable/disable the ETR/ETF/FUNNEL/STM/BMON/SPMU debug traces + * + * This IOCTL allows the user to get debug traces from the chip. + * + * The user needs to provide the register index and essential data such as + * buffer address and size. + * + */ +#define HL_IOCTL_DEBUG \ + _IOWR('H', 0x06, struct hl_debug_args) + #define HL_COMMAND_START 0x01 -#define HL_COMMAND_END 0x06 +#define HL_COMMAND_END 0x07 #endif /* HABANALABS_H_ */ From 8ba2876ddf935b845340571e2d197347b428879e Mon Sep 17 00:00:00 2001 From: Omer Shpigelman Date: Mon, 1 Apr 2019 22:23:02 +0300 Subject: [PATCH 051/255] habanalabs: add goya implementation for debug configuration This patch adds the ASIC-specific function for GOYA to configure the coresight components. Most of the components have an enabled/disabled flag, depending on whether the user wants to enable the component or disable it. For some of the components, such as ETR and SPMU, the user can also request to read values from them. Those values are needed for the user to parse the trace data. The ETR configuration is also checked for security purposes, to make sure the trace data is written to the device's DRAM. Signed-off-by: Omer Shpigelman Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 9 +- drivers/misc/habanalabs/goya/goyaP.h | 2 + drivers/misc/habanalabs/goya/goya_coresight.c | 609 +++++++++++++++++- .../include/goya/asic_reg/goya_regs.h | 3 +- .../include/goya/asic_reg/pcie_wrap_regs.h | 306 +++++++++ .../habanalabs/include/goya/goya_coresight.h | 199 ++++++ 6 files changed, 1122 insertions(+), 6 deletions(-) create mode 100644 drivers/misc/habanalabs/include/goya/asic_reg/pcie_wrap_regs.h create mode 100644 drivers/misc/habanalabs/include/goya/goya_coresight.h diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 3af883ada479..c6b9d4aabef6 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -69,7 +69,7 @@ * */ -#define GOYA_MMU_REGS_NUM 61 +#define GOYA_MMU_REGS_NUM 63 #define GOYA_DMA_POOL_BLK_SIZE 0x100 /* 256 bytes */ @@ -85,8 +85,6 @@ #define GOYA_QMAN0_FENCE_VAL 0xD169B243 -#define GOYA_MAX_INITIATORS 20 - #define GOYA_MAX_STRING_LEN 20 #define GOYA_CB_POOL_CB_CNT 512 @@ -171,7 +169,9 @@ static u64 goya_mmu_regs[GOYA_MMU_REGS_NUM] = { mmMME_SBA_CONTROL_DATA, mmMME_SBB_CONTROL_DATA, mmMME_SBC_CONTROL_DATA, - mmMME_WBC_CONTROL_DATA + mmMME_WBC_CONTROL_DATA, + mmPCIE_WRAP_PSOC_ARUSER, + mmPCIE_WRAP_PSOC_AWUSER }; static u32 goya_all_events[] = { @@ -1436,6 +1436,7 @@ static void goya_init_golden_registers(struct hl_device *hdev) */ WREG32(mmDMA_CH_0_CFG0, 0x0fff0010); WREG32(mmDMA_CH_1_CFG0, 0x0fff00F0); + WREG32(mmTPC_PLL_CLK_RLX_0, 0x200020); goya->hw_cap_initialized |= HW_CAP_GOLDEN; diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h index 6f1f7715075d..2a6cdca744dd 100644 --- a/drivers/misc/habanalabs/goya/goyaP.h +++ b/drivers/misc/habanalabs/goya/goyaP.h @@ -43,6 +43,8 @@ #define QMAN_STOP_TIMEOUT_USEC 100000 /* 100 ms */ +#define CORESIGHT_TIMEOUT_USEC 100000 /* 100 ms */ + #define TPC_ENABLED_MASK 0xFF #define PLL_HIGH_DEFAULT 1575000000 /* 1.575 GHz */ diff --git a/drivers/misc/habanalabs/goya/goya_coresight.c b/drivers/misc/habanalabs/goya/goya_coresight.c index 8957b8b1c0d6..68726fb4c56a 100644 --- a/drivers/misc/habanalabs/goya/goya_coresight.c +++ b/drivers/misc/habanalabs/goya/goya_coresight.c @@ -6,8 +6,615 @@ */ #include "goyaP.h" +#include "include/goya/goya_coresight.h" +#include "include/goya/asic_reg/goya_regs.h" + +#include + +#include + +#define GOYA_PLDM_CORESIGHT_TIMEOUT_USEC (CORESIGHT_TIMEOUT_USEC * 100) + +static u64 debug_stm_regs[GOYA_STM_LAST + 1] = { + [GOYA_STM_CPU] = mmCPU_STM_BASE, + [GOYA_STM_DMA_CH_0_CS] = mmDMA_CH_0_CS_STM_BASE, + [GOYA_STM_DMA_CH_1_CS] = mmDMA_CH_1_CS_STM_BASE, + [GOYA_STM_DMA_CH_2_CS] = mmDMA_CH_2_CS_STM_BASE, + [GOYA_STM_DMA_CH_3_CS] = mmDMA_CH_3_CS_STM_BASE, + [GOYA_STM_DMA_CH_4_CS] = mmDMA_CH_4_CS_STM_BASE, + [GOYA_STM_DMA_MACRO_CS] = mmDMA_MACRO_CS_STM_BASE, + [GOYA_STM_MME1_SBA] = mmMME1_SBA_STM_BASE, + [GOYA_STM_MME3_SBB] = mmMME3_SBB_STM_BASE, + [GOYA_STM_MME4_WACS2] = mmMME4_WACS2_STM_BASE, + [GOYA_STM_MME4_WACS] = mmMME4_WACS_STM_BASE, + [GOYA_STM_MMU_CS] = mmMMU_CS_STM_BASE, + [GOYA_STM_PCIE] = mmPCIE_STM_BASE, + [GOYA_STM_PSOC] = mmPSOC_STM_BASE, + [GOYA_STM_TPC0_EML] = mmTPC0_EML_STM_BASE, + [GOYA_STM_TPC1_EML] = mmTPC1_EML_STM_BASE, + [GOYA_STM_TPC2_EML] = mmTPC2_EML_STM_BASE, + [GOYA_STM_TPC3_EML] = mmTPC3_EML_STM_BASE, + [GOYA_STM_TPC4_EML] = mmTPC4_EML_STM_BASE, + [GOYA_STM_TPC5_EML] = mmTPC5_EML_STM_BASE, + [GOYA_STM_TPC6_EML] = mmTPC6_EML_STM_BASE, + [GOYA_STM_TPC7_EML] = mmTPC7_EML_STM_BASE +}; + +static u64 debug_etf_regs[GOYA_ETF_LAST + 1] = { + [GOYA_ETF_CPU_0] = mmCPU_ETF_0_BASE, + [GOYA_ETF_CPU_1] = mmCPU_ETF_1_BASE, + [GOYA_ETF_CPU_TRACE] = mmCPU_ETF_TRACE_BASE, + [GOYA_ETF_DMA_CH_0_CS] = mmDMA_CH_0_CS_ETF_BASE, + [GOYA_ETF_DMA_CH_1_CS] = mmDMA_CH_1_CS_ETF_BASE, + [GOYA_ETF_DMA_CH_2_CS] = mmDMA_CH_2_CS_ETF_BASE, + [GOYA_ETF_DMA_CH_3_CS] = mmDMA_CH_3_CS_ETF_BASE, + [GOYA_ETF_DMA_CH_4_CS] = mmDMA_CH_4_CS_ETF_BASE, + [GOYA_ETF_DMA_MACRO_CS] = mmDMA_MACRO_CS_ETF_BASE, + [GOYA_ETF_MME1_SBA] = mmMME1_SBA_ETF_BASE, + [GOYA_ETF_MME3_SBB] = mmMME3_SBB_ETF_BASE, + [GOYA_ETF_MME4_WACS2] = mmMME4_WACS2_ETF_BASE, + [GOYA_ETF_MME4_WACS] = mmMME4_WACS_ETF_BASE, + [GOYA_ETF_MMU_CS] = mmMMU_CS_ETF_BASE, + [GOYA_ETF_PCIE] = mmPCIE_ETF_BASE, + [GOYA_ETF_PSOC] = mmPSOC_ETF_BASE, + [GOYA_ETF_TPC0_EML] = mmTPC0_EML_ETF_BASE, + [GOYA_ETF_TPC1_EML] = mmTPC1_EML_ETF_BASE, + [GOYA_ETF_TPC2_EML] = mmTPC2_EML_ETF_BASE, + [GOYA_ETF_TPC3_EML] = mmTPC3_EML_ETF_BASE, + [GOYA_ETF_TPC4_EML] = mmTPC4_EML_ETF_BASE, + [GOYA_ETF_TPC5_EML] = mmTPC5_EML_ETF_BASE, + [GOYA_ETF_TPC6_EML] = mmTPC6_EML_ETF_BASE, + [GOYA_ETF_TPC7_EML] = mmTPC7_EML_ETF_BASE +}; + +static u64 debug_funnel_regs[GOYA_FUNNEL_LAST + 1] = { + [GOYA_FUNNEL_CPU] = mmCPU_FUNNEL_BASE, + [GOYA_FUNNEL_DMA_CH_6_1] = mmDMA_CH_FUNNEL_6_1_BASE, + [GOYA_FUNNEL_DMA_MACRO_3_1] = mmDMA_MACRO_FUNNEL_3_1_BASE, + [GOYA_FUNNEL_MME0_RTR] = mmMME0_RTR_FUNNEL_BASE, + [GOYA_FUNNEL_MME1_RTR] = mmMME1_RTR_FUNNEL_BASE, + [GOYA_FUNNEL_MME2_RTR] = mmMME2_RTR_FUNNEL_BASE, + [GOYA_FUNNEL_MME3_RTR] = mmMME3_RTR_FUNNEL_BASE, + [GOYA_FUNNEL_MME4_RTR] = mmMME4_RTR_FUNNEL_BASE, + [GOYA_FUNNEL_MME5_RTR] = mmMME5_RTR_FUNNEL_BASE, + [GOYA_FUNNEL_PCIE] = mmPCIE_FUNNEL_BASE, + [GOYA_FUNNEL_PSOC] = mmPSOC_FUNNEL_BASE, + [GOYA_FUNNEL_TPC0_EML] = mmTPC0_EML_FUNNEL_BASE, + [GOYA_FUNNEL_TPC1_EML] = mmTPC1_EML_FUNNEL_BASE, + [GOYA_FUNNEL_TPC1_RTR] = mmTPC1_RTR_FUNNEL_BASE, + [GOYA_FUNNEL_TPC2_EML] = mmTPC2_EML_FUNNEL_BASE, + [GOYA_FUNNEL_TPC2_RTR] = mmTPC2_RTR_FUNNEL_BASE, + [GOYA_FUNNEL_TPC3_EML] = mmTPC3_EML_FUNNEL_BASE, + [GOYA_FUNNEL_TPC3_RTR] = mmTPC3_RTR_FUNNEL_BASE, + [GOYA_FUNNEL_TPC4_EML] = mmTPC4_EML_FUNNEL_BASE, + [GOYA_FUNNEL_TPC4_RTR] = mmTPC4_RTR_FUNNEL_BASE, + [GOYA_FUNNEL_TPC5_EML] = mmTPC5_EML_FUNNEL_BASE, + [GOYA_FUNNEL_TPC5_RTR] = mmTPC5_RTR_FUNNEL_BASE, + [GOYA_FUNNEL_TPC6_EML] = mmTPC6_EML_FUNNEL_BASE, + [GOYA_FUNNEL_TPC6_RTR] = mmTPC6_RTR_FUNNEL_BASE, + [GOYA_FUNNEL_TPC7_EML] = mmTPC7_EML_FUNNEL_BASE +}; + +static u64 debug_bmon_regs[GOYA_BMON_LAST + 1] = { + [GOYA_BMON_CPU_RD] = mmCPU_RD_BMON_BASE, + [GOYA_BMON_CPU_WR] = mmCPU_WR_BMON_BASE, + [GOYA_BMON_DMA_CH_0_0] = mmDMA_CH_0_BMON_0_BASE, + [GOYA_BMON_DMA_CH_0_1] = mmDMA_CH_0_BMON_1_BASE, + [GOYA_BMON_DMA_CH_1_0] = mmDMA_CH_1_BMON_0_BASE, + [GOYA_BMON_DMA_CH_1_1] = mmDMA_CH_1_BMON_1_BASE, + [GOYA_BMON_DMA_CH_2_0] = mmDMA_CH_2_BMON_0_BASE, + [GOYA_BMON_DMA_CH_2_1] = mmDMA_CH_2_BMON_1_BASE, + [GOYA_BMON_DMA_CH_3_0] = mmDMA_CH_3_BMON_0_BASE, + [GOYA_BMON_DMA_CH_3_1] = mmDMA_CH_3_BMON_1_BASE, + [GOYA_BMON_DMA_CH_4_0] = mmDMA_CH_4_BMON_0_BASE, + [GOYA_BMON_DMA_CH_4_1] = mmDMA_CH_4_BMON_1_BASE, + [GOYA_BMON_DMA_MACRO_0] = mmDMA_MACRO_BMON_0_BASE, + [GOYA_BMON_DMA_MACRO_1] = mmDMA_MACRO_BMON_1_BASE, + [GOYA_BMON_DMA_MACRO_2] = mmDMA_MACRO_BMON_2_BASE, + [GOYA_BMON_DMA_MACRO_3] = mmDMA_MACRO_BMON_3_BASE, + [GOYA_BMON_DMA_MACRO_4] = mmDMA_MACRO_BMON_4_BASE, + [GOYA_BMON_DMA_MACRO_5] = mmDMA_MACRO_BMON_5_BASE, + [GOYA_BMON_DMA_MACRO_6] = mmDMA_MACRO_BMON_6_BASE, + [GOYA_BMON_DMA_MACRO_7] = mmDMA_MACRO_BMON_7_BASE, + [GOYA_BMON_MME1_SBA_0] = mmMME1_SBA_BMON0_BASE, + [GOYA_BMON_MME1_SBA_1] = mmMME1_SBA_BMON1_BASE, + [GOYA_BMON_MME3_SBB_0] = mmMME3_SBB_BMON0_BASE, + [GOYA_BMON_MME3_SBB_1] = mmMME3_SBB_BMON1_BASE, + [GOYA_BMON_MME4_WACS2_0] = mmMME4_WACS2_BMON0_BASE, + [GOYA_BMON_MME4_WACS2_1] = mmMME4_WACS2_BMON1_BASE, + [GOYA_BMON_MME4_WACS2_2] = mmMME4_WACS2_BMON2_BASE, + [GOYA_BMON_MME4_WACS_0] = mmMME4_WACS_BMON0_BASE, + [GOYA_BMON_MME4_WACS_1] = mmMME4_WACS_BMON1_BASE, + [GOYA_BMON_MME4_WACS_2] = mmMME4_WACS_BMON2_BASE, + [GOYA_BMON_MME4_WACS_3] = mmMME4_WACS_BMON3_BASE, + [GOYA_BMON_MME4_WACS_4] = mmMME4_WACS_BMON4_BASE, + [GOYA_BMON_MME4_WACS_5] = mmMME4_WACS_BMON5_BASE, + [GOYA_BMON_MME4_WACS_6] = mmMME4_WACS_BMON6_BASE, + [GOYA_BMON_MMU_0] = mmMMU_BMON_0_BASE, + [GOYA_BMON_MMU_1] = mmMMU_BMON_1_BASE, + [GOYA_BMON_PCIE_MSTR_RD] = mmPCIE_BMON_MSTR_RD_BASE, + [GOYA_BMON_PCIE_MSTR_WR] = mmPCIE_BMON_MSTR_WR_BASE, + [GOYA_BMON_PCIE_SLV_RD] = mmPCIE_BMON_SLV_RD_BASE, + [GOYA_BMON_PCIE_SLV_WR] = mmPCIE_BMON_SLV_WR_BASE, + [GOYA_BMON_TPC0_EML_0] = mmTPC0_EML_BUSMON_0_BASE, + [GOYA_BMON_TPC0_EML_1] = mmTPC0_EML_BUSMON_1_BASE, + [GOYA_BMON_TPC0_EML_2] = mmTPC0_EML_BUSMON_2_BASE, + [GOYA_BMON_TPC0_EML_3] = mmTPC0_EML_BUSMON_3_BASE, + [GOYA_BMON_TPC1_EML_0] = mmTPC1_EML_BUSMON_0_BASE, + [GOYA_BMON_TPC1_EML_1] = mmTPC1_EML_BUSMON_1_BASE, + [GOYA_BMON_TPC1_EML_2] = mmTPC1_EML_BUSMON_2_BASE, + [GOYA_BMON_TPC1_EML_3] = mmTPC1_EML_BUSMON_3_BASE, + [GOYA_BMON_TPC2_EML_0] = mmTPC2_EML_BUSMON_0_BASE, + [GOYA_BMON_TPC2_EML_1] = mmTPC2_EML_BUSMON_1_BASE, + [GOYA_BMON_TPC2_EML_2] = mmTPC2_EML_BUSMON_2_BASE, + [GOYA_BMON_TPC2_EML_3] = mmTPC2_EML_BUSMON_3_BASE, + [GOYA_BMON_TPC3_EML_0] = mmTPC3_EML_BUSMON_0_BASE, + [GOYA_BMON_TPC3_EML_1] = mmTPC3_EML_BUSMON_1_BASE, + [GOYA_BMON_TPC3_EML_2] = mmTPC3_EML_BUSMON_2_BASE, + [GOYA_BMON_TPC3_EML_3] = mmTPC3_EML_BUSMON_3_BASE, + [GOYA_BMON_TPC4_EML_0] = mmTPC4_EML_BUSMON_0_BASE, + [GOYA_BMON_TPC4_EML_1] = mmTPC4_EML_BUSMON_1_BASE, + [GOYA_BMON_TPC4_EML_2] = mmTPC4_EML_BUSMON_2_BASE, + [GOYA_BMON_TPC4_EML_3] = mmTPC4_EML_BUSMON_3_BASE, + [GOYA_BMON_TPC5_EML_0] = mmTPC5_EML_BUSMON_0_BASE, + [GOYA_BMON_TPC5_EML_1] = mmTPC5_EML_BUSMON_1_BASE, + [GOYA_BMON_TPC5_EML_2] = mmTPC5_EML_BUSMON_2_BASE, + [GOYA_BMON_TPC5_EML_3] = mmTPC5_EML_BUSMON_3_BASE, + [GOYA_BMON_TPC6_EML_0] = mmTPC6_EML_BUSMON_0_BASE, + [GOYA_BMON_TPC6_EML_1] = mmTPC6_EML_BUSMON_1_BASE, + [GOYA_BMON_TPC6_EML_2] = mmTPC6_EML_BUSMON_2_BASE, + [GOYA_BMON_TPC6_EML_3] = mmTPC6_EML_BUSMON_3_BASE, + [GOYA_BMON_TPC7_EML_0] = mmTPC7_EML_BUSMON_0_BASE, + [GOYA_BMON_TPC7_EML_1] = mmTPC7_EML_BUSMON_1_BASE, + [GOYA_BMON_TPC7_EML_2] = mmTPC7_EML_BUSMON_2_BASE, + [GOYA_BMON_TPC7_EML_3] = mmTPC7_EML_BUSMON_3_BASE +}; + +static u64 debug_spmu_regs[GOYA_SPMU_LAST + 1] = { + [GOYA_SPMU_DMA_CH_0_CS] = mmDMA_CH_0_CS_SPMU_BASE, + [GOYA_SPMU_DMA_CH_1_CS] = mmDMA_CH_1_CS_SPMU_BASE, + [GOYA_SPMU_DMA_CH_2_CS] = mmDMA_CH_2_CS_SPMU_BASE, + [GOYA_SPMU_DMA_CH_3_CS] = mmDMA_CH_3_CS_SPMU_BASE, + [GOYA_SPMU_DMA_CH_4_CS] = mmDMA_CH_4_CS_SPMU_BASE, + [GOYA_SPMU_DMA_MACRO_CS] = mmDMA_MACRO_CS_SPMU_BASE, + [GOYA_SPMU_MME1_SBA] = mmMME1_SBA_SPMU_BASE, + [GOYA_SPMU_MME3_SBB] = mmMME3_SBB_SPMU_BASE, + [GOYA_SPMU_MME4_WACS2] = mmMME4_WACS2_SPMU_BASE, + [GOYA_SPMU_MME4_WACS] = mmMME4_WACS_SPMU_BASE, + [GOYA_SPMU_MMU_CS] = mmMMU_CS_SPMU_BASE, + [GOYA_SPMU_PCIE] = mmPCIE_SPMU_BASE, + [GOYA_SPMU_TPC0_EML] = mmTPC0_EML_SPMU_BASE, + [GOYA_SPMU_TPC1_EML] = mmTPC1_EML_SPMU_BASE, + [GOYA_SPMU_TPC2_EML] = mmTPC2_EML_SPMU_BASE, + [GOYA_SPMU_TPC3_EML] = mmTPC3_EML_SPMU_BASE, + [GOYA_SPMU_TPC4_EML] = mmTPC4_EML_SPMU_BASE, + [GOYA_SPMU_TPC5_EML] = mmTPC5_EML_SPMU_BASE, + [GOYA_SPMU_TPC6_EML] = mmTPC6_EML_SPMU_BASE, + [GOYA_SPMU_TPC7_EML] = mmTPC7_EML_SPMU_BASE +}; + +static int goya_coresight_timeout(struct hl_device *hdev, u64 addr, + int position, bool up) +{ + int rc; + u32 val, timeout_usec; + + if (hdev->pldm) + timeout_usec = GOYA_PLDM_CORESIGHT_TIMEOUT_USEC; + else + timeout_usec = CORESIGHT_TIMEOUT_USEC; + + rc = hl_poll_timeout( + hdev, + addr, + val, + up ? val & BIT(position) : !(val & BIT(position)), + 1000, + timeout_usec); + + if (rc) { + dev_err(hdev->dev, + "Timeout while waiting for coresight, addr: 0x%llx, position: %d, up: %d\n", + addr, position, up); + return -EFAULT; + } + + return 0; +} + +static int goya_config_stm(struct hl_device *hdev, + struct hl_debug_params *params) +{ + struct hl_debug_params_stm *input; + u64 base_reg = debug_stm_regs[params->reg_idx] - CFG_BASE; + int rc; + + WREG32(base_reg + 0xFB0, CORESIGHT_UNLOCK); + + if (params->enable) { + input = params->input; + + if (!input) + return -EINVAL; + + WREG32(base_reg + 0xE80, 0x80004); + WREG32(base_reg + 0xD64, 7); + WREG32(base_reg + 0xD60, 0); + WREG32(base_reg + 0xD00, lower_32_bits(input->he_mask)); + WREG32(base_reg + 0xD20, lower_32_bits(input->sp_mask)); + WREG32(base_reg + 0xD60, 1); + WREG32(base_reg + 0xD00, upper_32_bits(input->he_mask)); + WREG32(base_reg + 0xD20, upper_32_bits(input->sp_mask)); + WREG32(base_reg + 0xE70, 0x10); + WREG32(base_reg + 0xE60, 0); + WREG32(base_reg + 0xE64, 0x420000); + WREG32(base_reg + 0xE00, 0xFFFFFFFF); + WREG32(base_reg + 0xE20, 0xFFFFFFFF); + WREG32(base_reg + 0xEF4, input->id); + WREG32(base_reg + 0xDF4, 0x80); + WREG32(base_reg + 0xE8C, input->frequency); + WREG32(base_reg + 0xE90, 0x7FF); + WREG32(base_reg + 0xE80, 0x7 | (input->id << 16)); + } else { + WREG32(base_reg + 0xE80, 4); + WREG32(base_reg + 0xD64, 0); + WREG32(base_reg + 0xD60, 1); + WREG32(base_reg + 0xD00, 0); + WREG32(base_reg + 0xD20, 0); + WREG32(base_reg + 0xD60, 0); + WREG32(base_reg + 0xE20, 0); + WREG32(base_reg + 0xE00, 0); + WREG32(base_reg + 0xDF4, 0x80); + WREG32(base_reg + 0xE70, 0); + WREG32(base_reg + 0xE60, 0); + WREG32(base_reg + 0xE64, 0); + WREG32(base_reg + 0xE8C, 0); + + rc = goya_coresight_timeout(hdev, base_reg + 0xE80, 23, false); + if (rc) { + dev_err(hdev->dev, + "Failed to disable STM on timeout, error %d\n", + rc); + return rc; + } + + WREG32(base_reg + 0xE80, 4); + } + + return 0; +} + +static int goya_config_etf(struct hl_device *hdev, + struct hl_debug_params *params) +{ + struct hl_debug_params_etf *input; + u64 base_reg = debug_etf_regs[params->reg_idx] - CFG_BASE; + u32 val; + int rc; + + WREG32(base_reg + 0xFB0, CORESIGHT_UNLOCK); + + val = RREG32(base_reg + 0x304); + val |= 0x1000; + WREG32(base_reg + 0x304, val); + val |= 0x40; + WREG32(base_reg + 0x304, val); + + rc = goya_coresight_timeout(hdev, base_reg + 0x304, 6, false); + if (rc) { + dev_err(hdev->dev, + "Failed to %s ETF on timeout, error %d\n", + params->enable ? "enable" : "disable", rc); + return rc; + } + + rc = goya_coresight_timeout(hdev, base_reg + 0xC, 2, true); + if (rc) { + dev_err(hdev->dev, + "Failed to %s ETF on timeout, error %d\n", + params->enable ? "enable" : "disable", rc); + return rc; + } + + WREG32(base_reg + 0x20, 0); + + if (params->enable) { + input = params->input; + + if (!input) + return -EINVAL; + + WREG32(base_reg + 0x34, 0x3FFC); + WREG32(base_reg + 0x28, input->sink_mode); + WREG32(base_reg + 0x304, 0x4001); + WREG32(base_reg + 0x308, 0xA); + WREG32(base_reg + 0x20, 1); + } else { + WREG32(base_reg + 0x34, 0); + WREG32(base_reg + 0x28, 0); + WREG32(base_reg + 0x304, 0); + } + + return 0; +} + +static int goya_etr_validate_address(struct hl_device *hdev, u64 addr, + u32 size) +{ + struct asic_fixed_properties *prop = &hdev->asic_prop; + u64 range_start, range_end; + + if (hdev->mmu_enable) { + range_start = prop->va_space_dram_start_address; + range_end = prop->va_space_dram_end_address; + } else { + range_start = prop->dram_user_base_address; + range_end = prop->dram_end_address; + } + + return hl_mem_area_inside_range(addr, size, range_start, range_end); +} + +static int goya_config_etr(struct hl_device *hdev, + struct hl_debug_params *params) +{ + struct hl_debug_params_etr *input; + u64 base_reg = mmPSOC_ETR_BASE - CFG_BASE; + u32 val; + int rc; + + WREG32(base_reg + 0xFB0, CORESIGHT_UNLOCK); + + val = RREG32(base_reg + 0x304); + val |= 0x1000; + WREG32(base_reg + 0x304, val); + val |= 0x40; + WREG32(base_reg + 0x304, val); + + rc = goya_coresight_timeout(hdev, base_reg + 0x304, 6, false); + if (rc) { + dev_err(hdev->dev, "Failed to %s ETR on timeout, error %d\n", + params->enable ? "enable" : "disable", rc); + return rc; + } + + rc = goya_coresight_timeout(hdev, base_reg + 0xC, 2, true); + if (rc) { + dev_err(hdev->dev, "Failed to %s ETR on timeout, error %d\n", + params->enable ? "enable" : "disable", rc); + return rc; + } + + WREG32(base_reg + 0x20, 0); + + if (params->enable) { + input = params->input; + + if (!input) + return -EINVAL; + + if (input->buffer_size == 0) { + dev_err(hdev->dev, + "ETR buffer size should be bigger than 0\n"); + return -EINVAL; + } + + if (!goya_etr_validate_address(hdev, + input->buffer_address, input->buffer_size)) { + dev_err(hdev->dev, "buffer address is not valid\n"); + return -EINVAL; + } + + WREG32(base_reg + 0x34, 0x3FFC); + WREG32(base_reg + 0x4, input->buffer_size); + WREG32(base_reg + 0x28, input->sink_mode); + WREG32(base_reg + 0x110, 0x700); + WREG32(base_reg + 0x118, + lower_32_bits(input->buffer_address)); + WREG32(base_reg + 0x11C, + upper_32_bits(input->buffer_address)); + WREG32(base_reg + 0x304, 3); + WREG32(base_reg + 0x308, 0xA); + WREG32(base_reg + 0x20, 1); + } else { + WREG32(base_reg + 0x34, 0); + WREG32(base_reg + 0x4, 0x400); + WREG32(base_reg + 0x118, 0); + WREG32(base_reg + 0x11C, 0); + WREG32(base_reg + 0x308, 0); + WREG32(base_reg + 0x28, 0); + WREG32(base_reg + 0x304, 0); + + if (params->output_size >= sizeof(u32)) + *(u32 *) params->output = RREG32(base_reg + 0x18); + } + + return 0; +} + +static int goya_config_funnel(struct hl_device *hdev, + struct hl_debug_params *params) +{ + WREG32(debug_funnel_regs[params->reg_idx] - CFG_BASE + 0xFB0, + CORESIGHT_UNLOCK); + + WREG32(debug_funnel_regs[params->reg_idx] - CFG_BASE, + params->enable ? 0x33F : 0); + + return 0; +} + +static int goya_config_bmon(struct hl_device *hdev, + struct hl_debug_params *params) +{ + struct hl_debug_params_bmon *input; + u64 base_reg = debug_bmon_regs[params->reg_idx] - CFG_BASE; + u32 pcie_base = 0; + + WREG32(base_reg + 0x104, 1); + + if (params->enable) { + input = params->input; + + if (!input) + return -EINVAL; + + WREG32(base_reg + 0x208, lower_32_bits(input->addr_range0)); + WREG32(base_reg + 0x20C, upper_32_bits(input->addr_range0)); + WREG32(base_reg + 0x248, lower_32_bits(input->addr_range1)); + WREG32(base_reg + 0x24C, upper_32_bits(input->addr_range1)); + WREG32(base_reg + 0x224, 0); + WREG32(base_reg + 0x234, 0); + WREG32(base_reg + 0x30C, input->bw_win); + WREG32(base_reg + 0x308, input->win_capture); + + /* PCIE IF BMON bug WA */ + if (params->reg_idx != GOYA_BMON_PCIE_MSTR_RD && + params->reg_idx != GOYA_BMON_PCIE_MSTR_WR && + params->reg_idx != GOYA_BMON_PCIE_SLV_RD && + params->reg_idx != GOYA_BMON_PCIE_SLV_WR) + pcie_base = 0xA000000; + + WREG32(base_reg + 0x700, pcie_base | 0xB00 | (input->id << 12)); + WREG32(base_reg + 0x708, pcie_base | 0xA00 | (input->id << 12)); + WREG32(base_reg + 0x70C, pcie_base | 0xC00 | (input->id << 12)); + + WREG32(base_reg + 0x100, 0x11); + WREG32(base_reg + 0x304, 0x1); + } else { + WREG32(base_reg + 0x208, 0xFFFFFFFF); + WREG32(base_reg + 0x20C, 0xFFFFFFFF); + WREG32(base_reg + 0x248, 0xFFFFFFFF); + WREG32(base_reg + 0x24C, 0xFFFFFFFF); + WREG32(base_reg + 0x224, 0xFFFFFFFF); + WREG32(base_reg + 0x234, 0x1070F); + WREG32(base_reg + 0x30C, 0); + WREG32(base_reg + 0x308, 0xFFFF); + WREG32(base_reg + 0x700, 0xA000B00); + WREG32(base_reg + 0x708, 0xA000A00); + WREG32(base_reg + 0x70C, 0xA000C00); + WREG32(base_reg + 0x100, 1); + WREG32(base_reg + 0x304, 0); + WREG32(base_reg + 0x104, 0); + } + + return 0; +} + +static int goya_config_spmu(struct hl_device *hdev, + struct hl_debug_params *params) +{ + u64 base_reg = debug_spmu_regs[params->reg_idx] - CFG_BASE; + struct hl_debug_params_spmu *input = params->input; + u64 *output; + u32 output_arr_len; + u32 events_num; + u32 overflow_idx; + u32 cycle_cnt_idx; + int i; + + if (params->enable) { + input = params->input; + + if (!input) + return -EINVAL; + + if (input->event_types_num < 3) { + dev_err(hdev->dev, + "not enough values for SPMU enable\n"); + return -EINVAL; + } + + WREG32(base_reg + 0xE04, 0x41013046); + WREG32(base_reg + 0xE04, 0x41013040); + + for (i = 0 ; i < input->event_types_num ; i++) + WREG32(base_reg + 0x400 + i * 4, input->event_types[i]); + + WREG32(base_reg + 0xE04, 0x41013041); + WREG32(base_reg + 0xC00, 0x8000003F); + } else { + output = params->output; + output_arr_len = params->output_size / 8; + events_num = output_arr_len - 2; + overflow_idx = output_arr_len - 2; + cycle_cnt_idx = output_arr_len - 1; + + if (!output) + return -EINVAL; + + if (output_arr_len < 3) { + dev_err(hdev->dev, + "not enough values for SPMU disable\n"); + return -EINVAL; + } + + WREG32(base_reg + 0xE04, 0x41013040); + + for (i = 0 ; i < events_num ; i++) + output[i] = RREG32(base_reg + i * 8); + + output[overflow_idx] = RREG32(base_reg + 0xCC0); + + output[cycle_cnt_idx] = RREG32(base_reg + 0xFC); + output[cycle_cnt_idx] <<= 32; + output[cycle_cnt_idx] |= RREG32(base_reg + 0xF8); + + WREG32(base_reg + 0xCC0, 0); + } + + return 0; +} + +static int goya_config_timestamp(struct hl_device *hdev, + struct hl_debug_params *params) +{ + WREG32(mmPSOC_TIMESTAMP_BASE - CFG_BASE, 0); + if (params->enable) { + WREG32(mmPSOC_TIMESTAMP_BASE - CFG_BASE + 0xC, 0); + WREG32(mmPSOC_TIMESTAMP_BASE - CFG_BASE + 0x8, 0); + WREG32(mmPSOC_TIMESTAMP_BASE - CFG_BASE, 1); + } + + return 0; +} int goya_debug_coresight(struct hl_device *hdev, void *data) { - return -ENOTTY; + struct hl_debug_params *params = data; + u32 val; + int rc; + + switch (params->op) { + case HL_DEBUG_OP_STM: + rc = goya_config_stm(hdev, params); + break; + case HL_DEBUG_OP_ETF: + rc = goya_config_etf(hdev, params); + break; + case HL_DEBUG_OP_ETR: + rc = goya_config_etr(hdev, params); + break; + case HL_DEBUG_OP_FUNNEL: + rc = goya_config_funnel(hdev, params); + break; + case HL_DEBUG_OP_BMON: + rc = goya_config_bmon(hdev, params); + break; + case HL_DEBUG_OP_SPMU: + rc = goya_config_spmu(hdev, params); + break; + case HL_DEBUG_OP_TIMESTAMP: + rc = goya_config_timestamp(hdev, params); + break; + + default: + dev_err(hdev->dev, "Unknown coresight id %d\n", params->op); + return -EINVAL; + } + + /* Perform read from the device to flush all configuration */ + val = RREG32(mmPCIE_DBI_DEVICE_ID_VENDOR_ID_REG); + + return rc; } diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h index 6cb0b6e54d41..506e71e201e1 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/goya_regs.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 * - * Copyright 2016-2018 HabanaLabs, Ltd. + * Copyright 2016-2019 HabanaLabs, Ltd. * All Rights Reserved. * */ @@ -12,6 +12,7 @@ #include "stlb_regs.h" #include "mmu_regs.h" #include "pcie_aux_regs.h" +#include "pcie_wrap_regs.h" #include "psoc_global_conf_regs.h" #include "psoc_spi_regs.h" #include "psoc_mme_pll_regs.h" diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/pcie_wrap_regs.h b/drivers/misc/habanalabs/include/goya/asic_reg/pcie_wrap_regs.h new file mode 100644 index 000000000000..d1e55aace4a0 --- /dev/null +++ b/drivers/misc/habanalabs/include/goya/asic_reg/pcie_wrap_regs.h @@ -0,0 +1,306 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright 2016-2018 HabanaLabs, Ltd. + * All Rights Reserved. + * + */ + +/************************************ + ** This is an auto-generated file ** + ** DO NOT EDIT BELOW ** + ************************************/ + +#ifndef ASIC_REG_PCIE_WRAP_REGS_H_ +#define ASIC_REG_PCIE_WRAP_REGS_H_ + +/* + ***************************************** + * PCIE_WRAP (Prototype: PCIE_WRAP) + ***************************************** + */ + +#define mmPCIE_WRAP_PHY_RST_N 0xC01300 + +#define mmPCIE_WRAP_OUTSTAND_TRANS 0xC01400 + +#define mmPCIE_WRAP_MASK_REQ 0xC01404 + +#define mmPCIE_WRAP_IND_AWADDR_L 0xC01500 + +#define mmPCIE_WRAP_IND_AWADDR_H 0xC01504 + +#define mmPCIE_WRAP_IND_AWLEN 0xC01508 + +#define mmPCIE_WRAP_IND_AWSIZE 0xC0150C + +#define mmPCIE_WRAP_IND_AWBURST 0xC01510 + +#define mmPCIE_WRAP_IND_AWLOCK 0xC01514 + +#define mmPCIE_WRAP_IND_AWCACHE 0xC01518 + +#define mmPCIE_WRAP_IND_AWPROT 0xC0151C + +#define mmPCIE_WRAP_IND_AWVALID 0xC01520 + +#define mmPCIE_WRAP_IND_WDATA_0 0xC01524 + +#define mmPCIE_WRAP_IND_WDATA_1 0xC01528 + +#define mmPCIE_WRAP_IND_WDATA_2 0xC0152C + +#define mmPCIE_WRAP_IND_WDATA_3 0xC01530 + +#define mmPCIE_WRAP_IND_WSTRB 0xC01544 + +#define mmPCIE_WRAP_IND_WLAST 0xC01548 + +#define mmPCIE_WRAP_IND_WVALID 0xC0154C + +#define mmPCIE_WRAP_IND_BRESP 0xC01550 + +#define mmPCIE_WRAP_IND_BVALID 0xC01554 + +#define mmPCIE_WRAP_IND_ARADDR_0 0xC01558 + +#define mmPCIE_WRAP_IND_ARADDR_1 0xC0155C + +#define mmPCIE_WRAP_IND_ARLEN 0xC01560 + +#define mmPCIE_WRAP_IND_ARSIZE 0xC01564 + +#define mmPCIE_WRAP_IND_ARBURST 0xC01568 + +#define mmPCIE_WRAP_IND_ARLOCK 0xC0156C + +#define mmPCIE_WRAP_IND_ARCACHE 0xC01570 + +#define mmPCIE_WRAP_IND_ARPROT 0xC01574 + +#define mmPCIE_WRAP_IND_ARVALID 0xC01578 + +#define mmPCIE_WRAP_IND_RDATA_0 0xC0157C + +#define mmPCIE_WRAP_IND_RDATA_1 0xC01580 + +#define mmPCIE_WRAP_IND_RDATA_2 0xC01584 + +#define mmPCIE_WRAP_IND_RDATA_3 0xC01588 + +#define mmPCIE_WRAP_IND_RLAST 0xC0159C + +#define mmPCIE_WRAP_IND_RRESP 0xC015A0 + +#define mmPCIE_WRAP_IND_RVALID 0xC015A4 + +#define mmPCIE_WRAP_IND_AWMISC_INFO 0xC015A8 + +#define mmPCIE_WRAP_IND_AWMISC_INFO_HDR_34DW_0 0xC015AC + +#define mmPCIE_WRAP_IND_AWMISC_INFO_HDR_34DW_1 0xC015B0 + +#define mmPCIE_WRAP_IND_AWMISC_INFO_P_TAG 0xC015B4 + +#define mmPCIE_WRAP_IND_AWMISC_INFO_ATU_BYPAS 0xC015B8 + +#define mmPCIE_WRAP_IND_AWMISC_INFO_FUNC_NUM 0xC015BC + +#define mmPCIE_WRAP_IND_AWMISC_INFO_VFUNC_ACT 0xC015C0 + +#define mmPCIE_WRAP_IND_AWMISC_INFO_VFUNC_NUM 0xC015C4 + +#define mmPCIE_WRAP_IND_AWMISC_INFO_TLPPRFX 0xC015C8 + +#define mmPCIE_WRAP_IND_ARMISC_INFO 0xC015CC + +#define mmPCIE_WRAP_IND_ARMISC_INFO_TLPPRFX 0xC015D0 + +#define mmPCIE_WRAP_IND_ARMISC_INFO_ATU_BYP 0xC015D4 + +#define mmPCIE_WRAP_IND_ARMISC_INFO_FUNC_NUM 0xC015D8 + +#define mmPCIE_WRAP_IND_ARMISC_INFO_VFUNC_ACT 0xC015DC + +#define mmPCIE_WRAP_IND_ARMISC_INFO_VFUNC_NUM 0xC015E0 + +#define mmPCIE_WRAP_SLV_AWMISC_INFO 0xC01800 + +#define mmPCIE_WRAP_SLV_AWMISC_INFO_HDR_34DW_0 0xC01804 + +#define mmPCIE_WRAP_SLV_AWMISC_INFO_HDR_34DW_1 0xC01808 + +#define mmPCIE_WRAP_SLV_AWMISC_INFO_P_TAG 0xC0180C + +#define mmPCIE_WRAP_SLV_AWMISC_INFO_ATU_BYPAS 0xC01810 + +#define mmPCIE_WRAP_SLV_AWMISC_INFO_FUNC_NUM 0xC01814 + +#define mmPCIE_WRAP_SLV_AWMISC_INFO_VFUNC_ACT 0xC01818 + +#define mmPCIE_WRAP_SLV_AWMISC_INFO_VFUNC_NUM 0xC0181C + +#define mmPCIE_WRAP_SLV_AWMISC_INFO_TLPPRFX 0xC01820 + +#define mmPCIE_WRAP_SLV_ARMISC_INFO 0xC01824 + +#define mmPCIE_WRAP_SLV_ARMISC_INFO_TLPPRFX 0xC01828 + +#define mmPCIE_WRAP_SLV_ARMISC_INFO_ATU_BYP 0xC0182C + +#define mmPCIE_WRAP_SLV_ARMISC_INFO_FUNC_NUM 0xC01830 + +#define mmPCIE_WRAP_SLV_ARMISC_INFO_VFUNC_ACT 0xC01834 + +#define mmPCIE_WRAP_SLV_ARMISC_INFO_VFUNC_NUM 0xC01838 + +#define mmPCIE_WRAP_MAX_QID 0xC01900 + +#define mmPCIE_WRAP_DB_BASE_ADDR_L_0 0xC01910 + +#define mmPCIE_WRAP_DB_BASE_ADDR_L_1 0xC01914 + +#define mmPCIE_WRAP_DB_BASE_ADDR_L_2 0xC01918 + +#define mmPCIE_WRAP_DB_BASE_ADDR_L_3 0xC0191C + +#define mmPCIE_WRAP_DB_BASE_ADDR_H_0 0xC01920 + +#define mmPCIE_WRAP_DB_BASE_ADDR_H_1 0xC01924 + +#define mmPCIE_WRAP_DB_BASE_ADDR_H_2 0xC01928 + +#define mmPCIE_WRAP_DB_BASE_ADDR_H_3 0xC0192C + +#define mmPCIE_WRAP_DB_MASK 0xC01940 + +#define mmPCIE_WRAP_SQ_BASE_ADDR_H 0xC01A00 + +#define mmPCIE_WRAP_SQ_BASE_ADDR_L 0xC01A04 + +#define mmPCIE_WRAP_SQ_STRIDE_ACCRESS 0xC01A08 + +#define mmPCIE_WRAP_SQ_POP_CMD 0xC01A10 + +#define mmPCIE_WRAP_SQ_POP_DATA 0xC01A14 + +#define mmPCIE_WRAP_DB_INTR_0 0xC01A20 + +#define mmPCIE_WRAP_DB_INTR_1 0xC01A24 + +#define mmPCIE_WRAP_DB_INTR_2 0xC01A28 + +#define mmPCIE_WRAP_DB_INTR_3 0xC01A2C + +#define mmPCIE_WRAP_DB_INTR_4 0xC01A30 + +#define mmPCIE_WRAP_DB_INTR_5 0xC01A34 + +#define mmPCIE_WRAP_DB_INTR_6 0xC01A38 + +#define mmPCIE_WRAP_DB_INTR_7 0xC01A3C + +#define mmPCIE_WRAP_MMU_BYPASS_DMA 0xC01A80 + +#define mmPCIE_WRAP_MMU_BYPASS_NON_DMA 0xC01A84 + +#define mmPCIE_WRAP_ASID_NON_DMA 0xC01A90 + +#define mmPCIE_WRAP_ASID_DMA_0 0xC01AA0 + +#define mmPCIE_WRAP_ASID_DMA_1 0xC01AA4 + +#define mmPCIE_WRAP_ASID_DMA_2 0xC01AA8 + +#define mmPCIE_WRAP_ASID_DMA_3 0xC01AAC + +#define mmPCIE_WRAP_ASID_DMA_4 0xC01AB0 + +#define mmPCIE_WRAP_ASID_DMA_5 0xC01AB4 + +#define mmPCIE_WRAP_ASID_DMA_6 0xC01AB8 + +#define mmPCIE_WRAP_ASID_DMA_7 0xC01ABC + +#define mmPCIE_WRAP_CPU_HOT_RST 0xC01AE0 + +#define mmPCIE_WRAP_AXI_PROT_OVR 0xC01AE4 + +#define mmPCIE_WRAP_CACHE_OVR 0xC01B00 + +#define mmPCIE_WRAP_LOCK_OVR 0xC01B04 + +#define mmPCIE_WRAP_PROT_OVR 0xC01B08 + +#define mmPCIE_WRAP_ARUSER_OVR 0xC01B0C + +#define mmPCIE_WRAP_AWUSER_OVR 0xC01B10 + +#define mmPCIE_WRAP_ARUSER_OVR_EN 0xC01B14 + +#define mmPCIE_WRAP_AWUSER_OVR_EN 0xC01B18 + +#define mmPCIE_WRAP_MAX_OUTSTAND 0xC01B20 + +#define mmPCIE_WRAP_MST_IN 0xC01B24 + +#define mmPCIE_WRAP_RSP_OK 0xC01B28 + +#define mmPCIE_WRAP_LBW_CACHE_OVR 0xC01B40 + +#define mmPCIE_WRAP_LBW_LOCK_OVR 0xC01B44 + +#define mmPCIE_WRAP_LBW_PROT_OVR 0xC01B48 + +#define mmPCIE_WRAP_LBW_ARUSER_OVR 0xC01B4C + +#define mmPCIE_WRAP_LBW_AWUSER_OVR 0xC01B50 + +#define mmPCIE_WRAP_LBW_ARUSER_OVR_EN 0xC01B58 + +#define mmPCIE_WRAP_LBW_AWUSER_OVR_EN 0xC01B5C + +#define mmPCIE_WRAP_LBW_MAX_OUTSTAND 0xC01B60 + +#define mmPCIE_WRAP_LBW_MST_IN 0xC01B64 + +#define mmPCIE_WRAP_LBW_RSP_OK 0xC01B68 + +#define mmPCIE_WRAP_QUEUE_INIT 0xC01C00 + +#define mmPCIE_WRAP_AXI_SPLIT_INTR_0 0xC01C10 + +#define mmPCIE_WRAP_AXI_SPLIT_INTR_1 0xC01C14 + +#define mmPCIE_WRAP_DB_AWUSER 0xC01D00 + +#define mmPCIE_WRAP_DB_ARUSER 0xC01D04 + +#define mmPCIE_WRAP_PCIE_AWUSER 0xC01D08 + +#define mmPCIE_WRAP_PCIE_ARUSER 0xC01D0C + +#define mmPCIE_WRAP_PSOC_AWUSER 0xC01D10 + +#define mmPCIE_WRAP_PSOC_ARUSER 0xC01D14 + +#define mmPCIE_WRAP_SCH_Q_AWUSER 0xC01D18 + +#define mmPCIE_WRAP_SCH_Q_ARUSER 0xC01D1C + +#define mmPCIE_WRAP_PSOC2PCI_AWUSER 0xC01D40 + +#define mmPCIE_WRAP_PSOC2PCI_ARUSER 0xC01D44 + +#define mmPCIE_WRAP_DRAIN_TIMEOUT 0xC01D50 + +#define mmPCIE_WRAP_DRAIN_CFG 0xC01D54 + +#define mmPCIE_WRAP_DB_AXI_ERR 0xC01DE0 + +#define mmPCIE_WRAP_SPMU_INTR 0xC01DE4 + +#define mmPCIE_WRAP_AXI_INTR 0xC01DE8 + +#define mmPCIE_WRAP_E2E_CTRL 0xC01DF0 + +#endif /* ASIC_REG_PCIE_WRAP_REGS_H_ */ diff --git a/drivers/misc/habanalabs/include/goya/goya_coresight.h b/drivers/misc/habanalabs/include/goya/goya_coresight.h new file mode 100644 index 000000000000..6e933c0ca5cd --- /dev/null +++ b/drivers/misc/habanalabs/include/goya/goya_coresight.h @@ -0,0 +1,199 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright 2016-2018 HabanaLabs, Ltd. + * All Rights Reserved. + * + */ + +#ifndef GOYA_CORESIGHT_H +#define GOYA_CORESIGHT_H + +enum goya_debug_stm_regs_index { + GOYA_STM_FIRST = 0, + GOYA_STM_CPU = GOYA_STM_FIRST, + GOYA_STM_DMA_CH_0_CS, + GOYA_STM_DMA_CH_1_CS, + GOYA_STM_DMA_CH_2_CS, + GOYA_STM_DMA_CH_3_CS, + GOYA_STM_DMA_CH_4_CS, + GOYA_STM_DMA_MACRO_CS, + GOYA_STM_MME1_SBA, + GOYA_STM_MME3_SBB, + GOYA_STM_MME4_WACS2, + GOYA_STM_MME4_WACS, + GOYA_STM_MMU_CS, + GOYA_STM_PCIE, + GOYA_STM_PSOC, + GOYA_STM_TPC0_EML, + GOYA_STM_TPC1_EML, + GOYA_STM_TPC2_EML, + GOYA_STM_TPC3_EML, + GOYA_STM_TPC4_EML, + GOYA_STM_TPC5_EML, + GOYA_STM_TPC6_EML, + GOYA_STM_TPC7_EML, + GOYA_STM_LAST = GOYA_STM_TPC7_EML +}; + +enum goya_debug_etf_regs_index { + GOYA_ETF_FIRST = 0, + GOYA_ETF_CPU_0 = GOYA_ETF_FIRST, + GOYA_ETF_CPU_1, + GOYA_ETF_CPU_TRACE, + GOYA_ETF_DMA_CH_0_CS, + GOYA_ETF_DMA_CH_1_CS, + GOYA_ETF_DMA_CH_2_CS, + GOYA_ETF_DMA_CH_3_CS, + GOYA_ETF_DMA_CH_4_CS, + GOYA_ETF_DMA_MACRO_CS, + GOYA_ETF_MME1_SBA, + GOYA_ETF_MME3_SBB, + GOYA_ETF_MME4_WACS2, + GOYA_ETF_MME4_WACS, + GOYA_ETF_MMU_CS, + GOYA_ETF_PCIE, + GOYA_ETF_PSOC, + GOYA_ETF_TPC0_EML, + GOYA_ETF_TPC1_EML, + GOYA_ETF_TPC2_EML, + GOYA_ETF_TPC3_EML, + GOYA_ETF_TPC4_EML, + GOYA_ETF_TPC5_EML, + GOYA_ETF_TPC6_EML, + GOYA_ETF_TPC7_EML, + GOYA_ETF_LAST = GOYA_ETF_TPC7_EML +}; + +enum goya_debug_funnel_regs_index { + GOYA_FUNNEL_FIRST = 0, + GOYA_FUNNEL_CPU = GOYA_FUNNEL_FIRST, + GOYA_FUNNEL_DMA_CH_6_1, + GOYA_FUNNEL_DMA_MACRO_3_1, + GOYA_FUNNEL_MME0_RTR, + GOYA_FUNNEL_MME1_RTR, + GOYA_FUNNEL_MME2_RTR, + GOYA_FUNNEL_MME3_RTR, + GOYA_FUNNEL_MME4_RTR, + GOYA_FUNNEL_MME5_RTR, + GOYA_FUNNEL_PCIE, + GOYA_FUNNEL_PSOC, + GOYA_FUNNEL_TPC0_EML, + GOYA_FUNNEL_TPC1_EML, + GOYA_FUNNEL_TPC1_RTR, + GOYA_FUNNEL_TPC2_EML, + GOYA_FUNNEL_TPC2_RTR, + GOYA_FUNNEL_TPC3_EML, + GOYA_FUNNEL_TPC3_RTR, + GOYA_FUNNEL_TPC4_EML, + GOYA_FUNNEL_TPC4_RTR, + GOYA_FUNNEL_TPC5_EML, + GOYA_FUNNEL_TPC5_RTR, + GOYA_FUNNEL_TPC6_EML, + GOYA_FUNNEL_TPC6_RTR, + GOYA_FUNNEL_TPC7_EML, + GOYA_FUNNEL_LAST = GOYA_FUNNEL_TPC7_EML +}; + +enum goya_debug_bmon_regs_index { + GOYA_BMON_FIRST = 0, + GOYA_BMON_CPU_RD = GOYA_BMON_FIRST, + GOYA_BMON_CPU_WR, + GOYA_BMON_DMA_CH_0_0, + GOYA_BMON_DMA_CH_0_1, + GOYA_BMON_DMA_CH_1_0, + GOYA_BMON_DMA_CH_1_1, + GOYA_BMON_DMA_CH_2_0, + GOYA_BMON_DMA_CH_2_1, + GOYA_BMON_DMA_CH_3_0, + GOYA_BMON_DMA_CH_3_1, + GOYA_BMON_DMA_CH_4_0, + GOYA_BMON_DMA_CH_4_1, + GOYA_BMON_DMA_MACRO_0, + GOYA_BMON_DMA_MACRO_1, + GOYA_BMON_DMA_MACRO_2, + GOYA_BMON_DMA_MACRO_3, + GOYA_BMON_DMA_MACRO_4, + GOYA_BMON_DMA_MACRO_5, + GOYA_BMON_DMA_MACRO_6, + GOYA_BMON_DMA_MACRO_7, + GOYA_BMON_MME1_SBA_0, + GOYA_BMON_MME1_SBA_1, + GOYA_BMON_MME3_SBB_0, + GOYA_BMON_MME3_SBB_1, + GOYA_BMON_MME4_WACS2_0, + GOYA_BMON_MME4_WACS2_1, + GOYA_BMON_MME4_WACS2_2, + GOYA_BMON_MME4_WACS_0, + GOYA_BMON_MME4_WACS_1, + GOYA_BMON_MME4_WACS_2, + GOYA_BMON_MME4_WACS_3, + GOYA_BMON_MME4_WACS_4, + GOYA_BMON_MME4_WACS_5, + GOYA_BMON_MME4_WACS_6, + GOYA_BMON_MMU_0, + GOYA_BMON_MMU_1, + GOYA_BMON_PCIE_MSTR_RD, + GOYA_BMON_PCIE_MSTR_WR, + GOYA_BMON_PCIE_SLV_RD, + GOYA_BMON_PCIE_SLV_WR, + GOYA_BMON_TPC0_EML_0, + GOYA_BMON_TPC0_EML_1, + GOYA_BMON_TPC0_EML_2, + GOYA_BMON_TPC0_EML_3, + GOYA_BMON_TPC1_EML_0, + GOYA_BMON_TPC1_EML_1, + GOYA_BMON_TPC1_EML_2, + GOYA_BMON_TPC1_EML_3, + GOYA_BMON_TPC2_EML_0, + GOYA_BMON_TPC2_EML_1, + GOYA_BMON_TPC2_EML_2, + GOYA_BMON_TPC2_EML_3, + GOYA_BMON_TPC3_EML_0, + GOYA_BMON_TPC3_EML_1, + GOYA_BMON_TPC3_EML_2, + GOYA_BMON_TPC3_EML_3, + GOYA_BMON_TPC4_EML_0, + GOYA_BMON_TPC4_EML_1, + GOYA_BMON_TPC4_EML_2, + GOYA_BMON_TPC4_EML_3, + GOYA_BMON_TPC5_EML_0, + GOYA_BMON_TPC5_EML_1, + GOYA_BMON_TPC5_EML_2, + GOYA_BMON_TPC5_EML_3, + GOYA_BMON_TPC6_EML_0, + GOYA_BMON_TPC6_EML_1, + GOYA_BMON_TPC6_EML_2, + GOYA_BMON_TPC6_EML_3, + GOYA_BMON_TPC7_EML_0, + GOYA_BMON_TPC7_EML_1, + GOYA_BMON_TPC7_EML_2, + GOYA_BMON_TPC7_EML_3, + GOYA_BMON_LAST = GOYA_BMON_TPC7_EML_3 +}; + +enum goya_debug_spmu_regs_index { + GOYA_SPMU_FIRST = 0, + GOYA_SPMU_DMA_CH_0_CS = GOYA_SPMU_FIRST, + GOYA_SPMU_DMA_CH_1_CS, + GOYA_SPMU_DMA_CH_2_CS, + GOYA_SPMU_DMA_CH_3_CS, + GOYA_SPMU_DMA_CH_4_CS, + GOYA_SPMU_DMA_MACRO_CS, + GOYA_SPMU_MME1_SBA, + GOYA_SPMU_MME3_SBB, + GOYA_SPMU_MME4_WACS2, + GOYA_SPMU_MME4_WACS, + GOYA_SPMU_MMU_CS, + GOYA_SPMU_PCIE, + GOYA_SPMU_TPC0_EML, + GOYA_SPMU_TPC1_EML, + GOYA_SPMU_TPC2_EML, + GOYA_SPMU_TPC3_EML, + GOYA_SPMU_TPC4_EML, + GOYA_SPMU_TPC5_EML, + GOYA_SPMU_TPC6_EML, + GOYA_SPMU_TPC7_EML, + GOYA_SPMU_LAST = GOYA_SPMU_TPC7_EML +}; + +#endif /* GOYA_CORESIGHT_H */ From 90027296adad1e9935a893f1e5973959274fa0d1 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Wed, 3 Apr 2019 09:51:04 +0300 Subject: [PATCH 052/255] uapi/habanalabs: fix some comments in uapi file This patch adds a better explanation about the sequence number that is returned per CS. It also fixes the comment about queue numbering rules. Signed-off-by: Oded Gabbay --- include/uapi/misc/habanalabs.h | 23 ++++++++++++++--------- 1 file changed, 14 insertions(+), 9 deletions(-) diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 7704fe08c3ad..613d431da783 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -20,8 +20,8 @@ /* * Queue Numbering * - * The external queues (DMA channels + CPU) MUST be before the internal queues - * and each group (DMA channels + CPU and internal) must be contiguous inside + * The external queues (PCI DMA channels) MUST be before the internal queues + * and each group (PCI DMA channels and internal) must be contiguous inside * itself but there can be a gap between the two groups (although not * recommended) */ @@ -477,6 +477,12 @@ struct hl_debug_args { * Each JOB will be enqueued on a specific queue, according to the user's input. * There can be more then one JOB per queue. * + * The CS IOCTL will receive three sets of JOBS. One set is for "restore" phase, + * a second set is for "execution" phase and a third set is for "store" phase. + * The JOBS on the "restore" phase are enqueued only after context-switch + * (or if its the first CS for this context). The user can also order the + * driver to run the "restore" phase explicitly + * * There are two types of queues - external and internal. External queues * are DMA queues which transfer data from/to the Host. All other queues are * internal. The driver will get completion notifications from the device only @@ -493,19 +499,18 @@ struct hl_debug_args { * relevant queues. Therefore, the user mustn't assume the CS has been completed * or has even started to execute. * - * Upon successful enqueue, the IOCTL returns an opaque handle which the user + * Upon successful enqueue, the IOCTL returns a sequence number which the user * can use with the "Wait for CS" IOCTL to check whether the handle's CS * external JOBS have been completed. Note that if the CS has internal JOBS * which can execute AFTER the external JOBS have finished, the driver might * report that the CS has finished executing BEFORE the internal JOBS have * actually finish executing. * - * The CS IOCTL will receive three sets of JOBS. One set is for "restore" phase, - * a second set is for "execution" phase and a third set is for "store" phase. - * The JOBS on the "restore" phase are enqueued only after context-switch - * (or if its the first CS for this context). The user can also order the - * driver to run the "restore" phase explicitly - * + * Even though the sequence number increments per CS, the user can NOT + * automatically assume that if CS with sequence number N finished, then CS + * with sequence number N-1 also finished. The user can make this assumption if + * and only if CS N and CS N-1 are exactly the same (same CBs for the same + * queues). */ #define HL_IOCTL_CS \ _IOWR('H', 0x03, union hl_cs_args) From bedd14425d86a8fac6972055dcd7591de21c10be Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Tue, 2 Apr 2019 15:56:16 +0300 Subject: [PATCH 053/255] habanalabs: refactoring in goya.c This patch does some refactoring in goya.c to make code more reusable between goya code and the goya simulator code (which is not upstreamed). In addition, the patch removes some dead functions from goya.c which are not used by the current upstream code Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 146 +++++++++++++-------------- drivers/misc/habanalabs/goya/goyaP.h | 19 +++- drivers/misc/habanalabs/habanalabs.h | 4 - 3 files changed, 88 insertions(+), 81 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index c6b9d4aabef6..aaa05662ca9f 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -78,7 +78,6 @@ #define GOYA_RESET_WAIT_MSEC 1 /* 1ms */ #define GOYA_CPU_RESET_WAIT_MSEC 100 /* 100ms */ #define GOYA_PLDM_RESET_WAIT_MSEC 1000 /* 1s */ -#define GOYA_CPU_TIMEOUT_USEC 10000000 /* 10s */ #define GOYA_TEST_QUEUE_WAIT_USEC 100000 /* 100ms */ #define GOYA_PLDM_MMU_TIMEOUT_USEC (MMU_CONFIG_TIMEOUT_USEC * 100) #define GOYA_PLDM_QMAN0_TIMEOUT_USEC (HL_DEVICE_TIMEOUT_USEC * 30) @@ -298,12 +297,6 @@ static u32 goya_all_events[] = { GOYA_ASYNC_EVENT_ID_DMA_BM_CH4 }; -static void goya_mmu_prepare(struct hl_device *hdev, u32 asid); -static int goya_mmu_clear_pgt_range(struct hl_device *hdev); -static int goya_mmu_set_dram_default_page(struct hl_device *hdev); -static int goya_mmu_update_asid_hop0_addr(struct hl_device *hdev, u32 asid, - u64 phys_addr); - static void goya_get_fixed_properties(struct hl_device *hdev) { struct asic_fixed_properties *prop = &hdev->asic_prop; @@ -511,6 +504,28 @@ static int goya_early_fini(struct hl_device *hdev) return 0; } +static void goya_mmu_prepare_reg(struct hl_device *hdev, u64 reg, u32 asid) +{ + /* mask to zero the MMBP and ASID bits */ + WREG32_AND(reg, ~0x7FF); + WREG32_OR(reg, asid); +} + +static void goya_qman0_set_security(struct hl_device *hdev, bool secure) +{ + struct goya_device *goya = hdev->asic_specific; + + if (!(goya->hw_cap_initialized & HW_CAP_MMU)) + return; + + if (secure) + WREG32(mmDMA_QM_0_GLBL_PROT, QMAN_DMA_FULLY_TRUSTED); + else + WREG32(mmDMA_QM_0_GLBL_PROT, QMAN_DMA_PARTLY_TRUSTED); + + RREG32(mmDMA_QM_0_GLBL_PROT); +} + /* * goya_fetch_psoc_frequency - Fetch PSOC frequency values * @@ -633,6 +648,9 @@ static int goya_sw_init(struct hl_device *hdev) goya->tpc_clk = GOYA_PLL_FREQ_LOW; goya->ic_clk = GOYA_PLL_FREQ_LOW; + goya->mmu_prepare_reg = goya_mmu_prepare_reg; + goya->qman0_set_security = goya_qman0_set_security; + hdev->asic_specific = goya; /* Create DMA pool for small allocations */ @@ -2324,6 +2342,38 @@ static int goya_init_cpu(struct hl_device *hdev, u32 cpu_timeout) return 0; } +static int goya_mmu_update_asid_hop0_addr(struct hl_device *hdev, u32 asid, + u64 phys_addr) +{ + u32 status, timeout_usec; + int rc; + + if (hdev->pldm) + timeout_usec = GOYA_PLDM_MMU_TIMEOUT_USEC; + else + timeout_usec = MMU_CONFIG_TIMEOUT_USEC; + + WREG32(MMU_HOP0_PA43_12, phys_addr >> MMU_HOP0_PA43_12_SHIFT); + WREG32(MMU_HOP0_PA49_44, phys_addr >> MMU_HOP0_PA49_44_SHIFT); + WREG32(MMU_ASID_BUSY, 0x80000000 | asid); + + rc = hl_poll_timeout( + hdev, + MMU_ASID_BUSY, + status, + !(status & 0x80000000), + 1000, + timeout_usec); + + if (rc) { + dev_err(hdev->dev, + "Timeout during MMU hop0 config of asid %d\n", asid); + return rc; + } + + return 0; +} + static int goya_mmu_init(struct hl_device *hdev) { struct asic_fixed_properties *prop = &hdev->asic_prop; @@ -2798,10 +2848,7 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) *fence_ptr = 0; - if (goya->hw_cap_initialized & HW_CAP_MMU) { - WREG32(mmDMA_QM_0_GLBL_PROT, QMAN_DMA_FULLY_TRUSTED); - RREG32(mmDMA_QM_0_GLBL_PROT); - } + goya->qman0_set_security(hdev, true); /* * goya cs parser saves space for 2xpacket_msg_prot at end of CB. For @@ -2843,10 +2890,7 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) hdev->asic_funcs->dma_pool_free(hdev, (void *) fence_ptr, fence_dma_addr); - if (goya->hw_cap_initialized & HW_CAP_MMU) { - WREG32(mmDMA_QM_0_GLBL_PROT, QMAN_DMA_PARTLY_TRUSTED); - RREG32(mmDMA_QM_0_GLBL_PROT); - } + goya->qman0_set_security(hdev, false); return rc; } @@ -2953,7 +2997,7 @@ int goya_test_cpu_queue(struct hl_device *hdev) return hl_fw_test_cpu_queue(hdev); } -static int goya_test_queues(struct hl_device *hdev) +int goya_test_queues(struct hl_device *hdev) { int i, rc, ret_val = 0; @@ -2987,14 +3031,14 @@ static void goya_dma_pool_free(struct hl_device *hdev, void *vaddr, dma_pool_free(hdev->dma_pool, vaddr, dma_addr); } -static void *goya_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, - size_t size, dma_addr_t *dma_handle) +void *goya_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size, + dma_addr_t *dma_handle) { return hl_fw_cpu_accessible_dma_pool_alloc(hdev, size, dma_handle); } -static void goya_cpu_accessible_dma_pool_free(struct hl_device *hdev, - size_t size, void *vaddr) +void goya_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size, + void *vaddr) { hl_fw_cpu_accessible_dma_pool_free(hdev, size, vaddr); } @@ -4211,8 +4255,8 @@ static int goya_unmask_irq_arr(struct hl_device *hdev, u32 *irq_arr, pkt->armcp_pkt.ctl = cpu_to_le32(ARMCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY << ARMCP_PKT_CTL_OPCODE_SHIFT); - rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) pkt, - total_pkt_size, HL_DEVICE_TIMEOUT_USEC, &result); + rc = goya_send_cpu_message(hdev, (u32 *) pkt, total_pkt_size, + HL_DEVICE_TIMEOUT_USEC, &result); if (rc) dev_err(hdev->dev, "failed to unmask IRQ array\n"); @@ -4244,7 +4288,7 @@ static int goya_unmask_irq(struct hl_device *hdev, u16 event_type) ARMCP_PKT_CTL_OPCODE_SHIFT); pkt.value = cpu_to_le64(event_type); - rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), + rc = goya_send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), HL_DEVICE_TIMEOUT_USEC, &result); if (rc) @@ -4466,7 +4510,7 @@ static int goya_context_switch(struct hl_device *hdev, u32 asid) return 0; } -static int goya_mmu_clear_pgt_range(struct hl_device *hdev) +int goya_mmu_clear_pgt_range(struct hl_device *hdev) { struct asic_fixed_properties *prop = &hdev->asic_prop; struct goya_device *goya = hdev->asic_specific; @@ -4480,7 +4524,7 @@ static int goya_mmu_clear_pgt_range(struct hl_device *hdev) return goya_memset_device_memory(hdev, addr, size, 0, true); } -static int goya_mmu_set_dram_default_page(struct hl_device *hdev) +int goya_mmu_set_dram_default_page(struct hl_device *hdev) { struct goya_device *goya = hdev->asic_specific; u64 addr = hdev->asic_prop.mmu_dram_default_page_addr; @@ -4493,7 +4537,7 @@ static int goya_mmu_set_dram_default_page(struct hl_device *hdev) return goya_memset_device_memory(hdev, addr, size, val, true); } -static void goya_mmu_prepare(struct hl_device *hdev, u32 asid) +void goya_mmu_prepare(struct hl_device *hdev, u32 asid) { struct goya_device *goya = hdev->asic_specific; int i; @@ -4507,10 +4551,8 @@ static void goya_mmu_prepare(struct hl_device *hdev, u32 asid) } /* zero the MMBP and ASID bits and then set the ASID */ - for (i = 0 ; i < GOYA_MMU_REGS_NUM ; i++) { - WREG32_AND(goya_mmu_regs[i], ~0x7FF); - WREG32_OR(goya_mmu_regs[i], asid); - } + for (i = 0 ; i < GOYA_MMU_REGS_NUM ; i++) + goya->mmu_prepare_reg(hdev, goya_mmu_regs[i], asid); } static void goya_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard) @@ -4601,38 +4643,6 @@ static void goya_mmu_invalidate_cache_range(struct hl_device *hdev, "Timeout when waiting for MMU cache invalidation\n"); } -static int goya_mmu_update_asid_hop0_addr(struct hl_device *hdev, u32 asid, - u64 phys_addr) -{ - u32 status, timeout_usec; - int rc; - - if (hdev->pldm) - timeout_usec = GOYA_PLDM_MMU_TIMEOUT_USEC; - else - timeout_usec = MMU_CONFIG_TIMEOUT_USEC; - - WREG32(MMU_HOP0_PA43_12, phys_addr >> MMU_HOP0_PA43_12_SHIFT); - WREG32(MMU_HOP0_PA49_44, phys_addr >> MMU_HOP0_PA49_44_SHIFT); - WREG32(MMU_ASID_BUSY, 0x80000000 | asid); - - rc = hl_poll_timeout( - hdev, - MMU_ASID_BUSY, - status, - !(status & 0x80000000), - 1000, - timeout_usec); - - if (rc) { - dev_err(hdev->dev, - "Timeout during MMU hop0 config of asid %d\n", asid); - return rc; - } - - return 0; -} - int goya_send_heartbeat(struct hl_device *hdev) { struct goya_device *goya = hdev->asic_specific; @@ -4674,16 +4684,6 @@ int goya_armcp_info_get(struct hl_device *hdev) return 0; } -static void goya_init_clock_gating(struct hl_device *hdev) -{ - -} - -static void goya_disable_clock_gating(struct hl_device *hdev) -{ - -} - static bool goya_is_device_idle(struct hl_device *hdev, char *buf, size_t size) { u64 offset, dma_qm_reg, tpc_qm_reg, tpc_cmdq_reg, tpc_cfg_reg; @@ -4814,8 +4814,6 @@ static const struct hl_asic_funcs goya_funcs = { .mmu_invalidate_cache = goya_mmu_invalidate_cache, .mmu_invalidate_cache_range = goya_mmu_invalidate_cache_range, .send_heartbeat = goya_send_heartbeat, - .enable_clock_gating = goya_init_clock_gating, - .disable_clock_gating = goya_disable_clock_gating, .debug_coresight = goya_debug_coresight, .is_device_idle = goya_is_device_idle, .soft_reset_late_init = goya_soft_reset_late_init, diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h index 2a6cdca744dd..b572e0263ac5 100644 --- a/drivers/misc/habanalabs/goya/goyaP.h +++ b/drivers/misc/habanalabs/goya/goyaP.h @@ -39,11 +39,13 @@ #error "Number of MSIX interrupts must be smaller or equal to GOYA_MSIX_ENTRIES" #endif -#define QMAN_FENCE_TIMEOUT_USEC 10000 /* 10 ms */ +#define QMAN_FENCE_TIMEOUT_USEC 10000 /* 10 ms */ -#define QMAN_STOP_TIMEOUT_USEC 100000 /* 100 ms */ +#define QMAN_STOP_TIMEOUT_USEC 100000 /* 100 ms */ -#define CORESIGHT_TIMEOUT_USEC 100000 /* 100 ms */ +#define CORESIGHT_TIMEOUT_USEC 100000 /* 100 ms */ + +#define GOYA_CPU_TIMEOUT_USEC 10000000 /* 10s */ #define TPC_ENABLED_MASK 0xFF @@ -145,6 +147,9 @@ enum goya_fw_component { }; struct goya_device { + void (*mmu_prepare_reg)(struct hl_device *hdev, u64 reg, u32 asid); + void (*qman0_set_security)(struct hl_device *hdev, bool secure); + /* TODO: remove hw_queues_lock after moving to scheduler code */ spinlock_t hw_queues_lock; @@ -180,6 +185,10 @@ void goya_init_security(struct hl_device *hdev); int goya_debug_coresight(struct hl_device *hdev, void *data); u64 goya_get_max_power(struct hl_device *hdev); void goya_set_max_power(struct hl_device *hdev, u64 value); +int goya_test_queues(struct hl_device *hdev); +void goya_mmu_prepare(struct hl_device *hdev, u32 asid); +int goya_mmu_clear_pgt_range(struct hl_device *hdev); +int goya_mmu_set_dram_default_page(struct hl_device *hdev); void goya_late_fini(struct hl_device *hdev); int goya_suspend(struct hl_device *hdev); @@ -195,5 +204,9 @@ void *goya_get_int_queue_base(struct hl_device *hdev, u32 queue_id, u32 goya_get_dma_desc_list_size(struct hl_device *hdev, struct sg_table *sgt); int goya_test_queue(struct hl_device *hdev, u32 hw_queue_id); int goya_send_heartbeat(struct hl_device *hdev); +void *goya_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size, + dma_addr_t *dma_handle); +void goya_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size, + void *vaddr); #endif /* GOYAP_H_ */ diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 18a03657780a..535d4f9531f6 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -481,8 +481,6 @@ enum hl_pll_frequency { * @mmu_invalidate_cache_range: flush specific MMU STLB cache lines with * ASID-VA-size mask. * @send_heartbeat: send is-alive packet to ArmCP and verify response. - * @enable_clock_gating: enable clock gating for reducing power consumption. - * @disable_clock_gating: disable clock for accessing registers on HBW. * @debug_coresight: perform certain actions on Coresight for debugging. * @is_device_idle: return true if device is idle, false otherwise. * @soft_reset_late_init: perform certain actions needed after soft reset. @@ -556,8 +554,6 @@ struct hl_asic_funcs { void (*mmu_invalidate_cache_range)(struct hl_device *hdev, bool is_hard, u32 asid, u64 va, u64 size); int (*send_heartbeat)(struct hl_device *hdev); - void (*enable_clock_gating)(struct hl_device *hdev); - void (*disable_clock_gating)(struct hl_device *hdev); int (*debug_coresight)(struct hl_device *hdev, void *data); bool (*is_device_idle)(struct hl_device *hdev, char *buf, size_t size); int (*soft_reset_late_init)(struct hl_device *hdev); From 9a41691e5e01ba38865afa7a1eaa352974bf4a6e Mon Sep 17 00:00:00 2001 From: Vishnu DASA Date: Mon, 11 Mar 2019 23:19:42 +0000 Subject: [PATCH 054/255] VMCI: Use BIT() macro for bit definitions No functional changes, cleanup only. Reviewed-by: Adit Ranadive Reviewed-by: Jorgen Hansen Signed-off-by: Vishnu Dasa Signed-off-by: Greg Kroah-Hartman --- include/linux/vmw_vmci_defs.h | 35 ++++++++++++++++++----------------- 1 file changed, 18 insertions(+), 17 deletions(-) diff --git a/include/linux/vmw_vmci_defs.h b/include/linux/vmw_vmci_defs.h index eaa1e762bf06..0c06178e4985 100644 --- a/include/linux/vmw_vmci_defs.h +++ b/include/linux/vmw_vmci_defs.h @@ -17,6 +17,7 @@ #define _VMW_VMCI_DEF_H_ #include +#include /* Register offsets. */ #define VMCI_STATUS_ADDR 0x00 @@ -33,27 +34,27 @@ #define VMCI_MAX_DEVICES 1 /* Status register bits. */ -#define VMCI_STATUS_INT_ON 0x1 +#define VMCI_STATUS_INT_ON BIT(0) /* Control register bits. */ -#define VMCI_CONTROL_RESET 0x1 -#define VMCI_CONTROL_INT_ENABLE 0x2 -#define VMCI_CONTROL_INT_DISABLE 0x4 +#define VMCI_CONTROL_RESET BIT(0) +#define VMCI_CONTROL_INT_ENABLE BIT(1) +#define VMCI_CONTROL_INT_DISABLE BIT(2) /* Capabilities register bits. */ -#define VMCI_CAPS_HYPERCALL 0x1 -#define VMCI_CAPS_GUESTCALL 0x2 -#define VMCI_CAPS_DATAGRAM 0x4 -#define VMCI_CAPS_NOTIFICATIONS 0x8 -#define VMCI_CAPS_PPN64 0x10 +#define VMCI_CAPS_HYPERCALL BIT(0) +#define VMCI_CAPS_GUESTCALL BIT(1) +#define VMCI_CAPS_DATAGRAM BIT(2) +#define VMCI_CAPS_NOTIFICATIONS BIT(3) +#define VMCI_CAPS_PPN64 BIT(4) /* Interrupt Cause register bits. */ -#define VMCI_ICR_DATAGRAM 0x1 -#define VMCI_ICR_NOTIFICATION 0x2 +#define VMCI_ICR_DATAGRAM BIT(0) +#define VMCI_ICR_NOTIFICATION BIT(1) /* Interrupt Mask register bits. */ -#define VMCI_IMR_DATAGRAM 0x1 -#define VMCI_IMR_NOTIFICATION 0x2 +#define VMCI_IMR_DATAGRAM BIT(0) +#define VMCI_IMR_NOTIFICATION BIT(1) /* Maximum MSI/MSI-X interrupt vectors in the device. */ #define VMCI_MAX_INTRS 2 @@ -463,9 +464,9 @@ struct vmci_datagram { * datagram callback is invoked in a delayed context (not interrupt context). */ #define VMCI_FLAG_DG_NONE 0 -#define VMCI_FLAG_WELLKNOWN_DG_HND 0x1 -#define VMCI_FLAG_ANYCID_DG_HND 0x2 -#define VMCI_FLAG_DG_DELAYED_CB 0x4 +#define VMCI_FLAG_WELLKNOWN_DG_HND BIT(0) +#define VMCI_FLAG_ANYCID_DG_HND BIT(1) +#define VMCI_FLAG_DG_DELAYED_CB BIT(2) /* * Maximum supported size of a VMCI datagram for routable datagrams. @@ -694,7 +695,7 @@ struct vmci_qp_detach_msg { }; /* VMCI Doorbell API. */ -#define VMCI_FLAG_DELAYED_CB 0x01 +#define VMCI_FLAG_DELAYED_CB BIT(0) typedef void (*vmci_callback) (void *client_data); From de36e16d1557a0b6eb328bc3516359a12ba5c25c Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Fri, 15 Feb 2019 20:27:11 +0800 Subject: [PATCH 055/255] chardev: add additional check for minor range overlap Current overlap checking cannot correctly handle a case which is baseminor < existing baseminor && baseminor + minorct > existing baseminor + minorct. Signed-off-by: Chengguang Xu Signed-off-by: Greg Kroah-Hartman --- fs/char_dev.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/char_dev.c b/fs/char_dev.c index a279c58fe360..8a63cfa29005 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -159,6 +159,12 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, ret = -EBUSY; goto out; } + + if (new_min < old_min && new_max > old_max) { + ret = -EBUSY; + goto out; + } + } cd->next = *cp; From 4712d3796f19b32241b41e538107fb7ae7a3fcff Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Fri, 15 Feb 2019 20:27:12 +0800 Subject: [PATCH 056/255] chardev: add a check for given minor range register_chrdev_region() carefully checks minor range before calling __register_chrdev_region() but there is another path from alloc_chrdev_region() which does not check the range properly. So add a check for given minor range in __register_chrdev_region(). Signed-off-by: Chengguang Xu Signed-off-by: Greg Kroah-Hartman --- fs/char_dev.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/char_dev.c b/fs/char_dev.c index 8a63cfa29005..6803e98414f1 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -104,6 +104,12 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, int ret = 0; int i; + if (minorct > MINORMASK + 1 - baseminor) { + pr_err("CHRDEV \"%s\" minor range requested (%u-%u) is out of range of maximum range (%u-%u) for a single major\n", + name, baseminor, baseminor + minorct - 1, 0, MINORMASK); + return ERR_PTR(-EINVAL); + } + cd = kzalloc(sizeof(struct char_device_struct), GFP_KERNEL); if (cd == NULL) return ERR_PTR(-ENOMEM); From 4b0be572603233b4240f6072f0bd35542d311ed8 Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Fri, 15 Feb 2019 20:27:13 +0800 Subject: [PATCH 057/255] chardev: code cleanup for __register_chrdev_region() It's just code cleanup, not functional change. Signed-off-by: Chengguang Xu Signed-off-by: Greg Kroah-Hartman --- fs/char_dev.c | 69 +++++++++++++++++++++------------------------------ 1 file changed, 28 insertions(+), 41 deletions(-) diff --git a/fs/char_dev.c b/fs/char_dev.c index 6803e98414f1..bd2bf1fd847e 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -100,10 +100,16 @@ static struct char_device_struct * __register_chrdev_region(unsigned int major, unsigned int baseminor, int minorct, const char *name) { - struct char_device_struct *cd, **cp; - int ret = 0; + struct char_device_struct *cd, *curr, *prev = NULL; + int ret = -EBUSY; int i; + if (major >= CHRDEV_MAJOR_MAX) { + pr_err("CHRDEV \"%s\" major requested (%u) is greater than the maximum (%u)\n", + name, major, CHRDEV_MAJOR_MAX-1); + return ERR_PTR(-EINVAL); + } + if (minorct > MINORMASK + 1 - baseminor) { pr_err("CHRDEV \"%s\" minor range requested (%u-%u) is out of range of maximum range (%u-%u) for a single major\n", name, baseminor, baseminor + minorct - 1, 0, MINORMASK); @@ -126,10 +132,20 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, major = ret; } - if (major >= CHRDEV_MAJOR_MAX) { - pr_err("CHRDEV \"%s\" major requested (%u) is greater than the maximum (%u)\n", - name, major, CHRDEV_MAJOR_MAX-1); - ret = -EINVAL; + i = major_to_index(major); + for (curr = chrdevs[i]; curr; prev = curr, curr = curr->next) { + if (curr->major < major) + continue; + + if (curr->major > major) + break; + + if (curr->baseminor + curr->minorct <= baseminor) + continue; + + if (curr->baseminor >= baseminor + minorct) + break; + goto out; } @@ -138,43 +154,14 @@ __register_chrdev_region(unsigned int major, unsigned int baseminor, cd->minorct = minorct; strlcpy(cd->name, name, sizeof(cd->name)); - i = major_to_index(major); - - for (cp = &chrdevs[i]; *cp; cp = &(*cp)->next) - if ((*cp)->major > major || - ((*cp)->major == major && - (((*cp)->baseminor >= baseminor) || - ((*cp)->baseminor + (*cp)->minorct > baseminor)))) - break; - - /* Check for overlapping minor ranges. */ - if (*cp && (*cp)->major == major) { - int old_min = (*cp)->baseminor; - int old_max = (*cp)->baseminor + (*cp)->minorct - 1; - int new_min = baseminor; - int new_max = baseminor + minorct - 1; - - /* New driver overlaps from the left. */ - if (new_max >= old_min && new_max <= old_max) { - ret = -EBUSY; - goto out; - } - - /* New driver overlaps from the right. */ - if (new_min <= old_max && new_min >= old_min) { - ret = -EBUSY; - goto out; - } - - if (new_min < old_min && new_max > old_max) { - ret = -EBUSY; - goto out; - } - + if (!prev) { + cd->next = curr; + chrdevs[i] = cd; + } else { + cd->next = prev->next; + prev->next = cd; } - cd->next = *cp; - *cp = cd; mutex_unlock(&chrdevs_lock); return cd; out: From d358b1733fc33d9f0261ce07c3d328787652245d Mon Sep 17 00:00:00 2001 From: Chengguang Xu Date: Fri, 15 Feb 2019 20:27:14 +0800 Subject: [PATCH 058/255] chardev: update comment based on the code The function comment of __register_chrdev_region() is out of date, so update it based on the code. Signed-off-by: Chengguang Xu Signed-off-by: Greg Kroah-Hartman --- fs/char_dev.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/fs/char_dev.c b/fs/char_dev.c index bd2bf1fd847e..d18cad28c1c3 100644 --- a/fs/char_dev.c +++ b/fs/char_dev.c @@ -88,13 +88,10 @@ static int find_dynamic_major(void) /* * Register a single major with a specified minor range. * - * If major == 0 this functions will dynamically allocate a major and return - * its number. + * If major == 0 this function will dynamically allocate an unused major. + * If major > 0 this function will attempt to reserve the range of minors + * with given major. * - * If major > 0 this function will attempt to reserve the passed range of - * minors and will return zero on success. - * - * Returns a -ve errno on failure. */ static struct char_device_struct * __register_chrdev_region(unsigned int major, unsigned int baseminor, From ae40e94fca6d5747f85188d01686df350e524019 Mon Sep 17 00:00:00 2001 From: Ondrej Jirman Date: Mon, 1 Apr 2019 13:56:15 +0200 Subject: [PATCH 059/255] dt-bindings: gnss: add u-blox,neo-6m compatible Add compatible for u-blox NEO-6M GPS module. Signed-off-by: Ondrej Jirman Reviewed-by: Rob Herring Signed-off-by: Johan Hovold --- Documentation/devicetree/bindings/gnss/u-blox.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/gnss/u-blox.txt b/Documentation/devicetree/bindings/gnss/u-blox.txt index e475659cb85f..7cdefd058fe0 100644 --- a/Documentation/devicetree/bindings/gnss/u-blox.txt +++ b/Documentation/devicetree/bindings/gnss/u-blox.txt @@ -9,6 +9,7 @@ Required properties: - compatible : Must be one of + "u-blox,neo-6m" "u-blox,neo-8" "u-blox,neo-m8" From 7cc10c5cb14397d61d203d0a319ef796d4f6d943 Mon Sep 17 00:00:00 2001 From: Ondrej Jirman Date: Mon, 1 Apr 2019 13:56:14 +0200 Subject: [PATCH 060/255] gnss: ubx: add u-blox,neo-6m compatible Add compatible for u-blox NEO-6M GPS module. Signed-off-by: Ondrej Jirman Signed-off-by: Johan Hovold --- drivers/gnss/ubx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gnss/ubx.c b/drivers/gnss/ubx.c index 12568aebb7f6..7b05bc40532e 100644 --- a/drivers/gnss/ubx.c +++ b/drivers/gnss/ubx.c @@ -130,6 +130,7 @@ static void ubx_remove(struct serdev_device *serdev) #ifdef CONFIG_OF static const struct of_device_id ubx_of_match[] = { + { .compatible = "u-blox,neo-6m" }, { .compatible = "u-blox,neo-8" }, { .compatible = "u-blox,neo-m8" }, {}, From 295938406cbcb541de8893d0280a2265c41e506d Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Thu, 4 Apr 2019 14:33:34 +0300 Subject: [PATCH 061/255] habanalabs: ASIC_AUTO_DETECT enum value is redundant This patch removes the enum value of ASIC_AUTO_DETECT because we can use the validity of the pdev variable to know whether we have a real device or a simulator. For a real device, we detect the asic type from the device ID while for a simulator, the simulator code calls create_hdev() with the specified ASIC type. Set ASIC_INVALID as the first option in the enum to make sure that no other enum value will receive the value 0 (which indicates a non-existing entry in the simulator array). Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/habanalabs.h | 8 +++----- drivers/misc/habanalabs/habanalabs_drv.c | 4 ++-- 2 files changed, 5 insertions(+), 7 deletions(-) diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 535d4f9531f6..2f02bb55f66a 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -390,14 +390,12 @@ struct hl_eq { /** * enum hl_asic_type - supported ASIC types. - * @ASIC_AUTO_DETECT: ASIC type will be automatically set. - * @ASIC_GOYA: Goya device. * @ASIC_INVALID: Invalid ASIC type. + * @ASIC_GOYA: Goya device. */ enum hl_asic_type { - ASIC_AUTO_DETECT, - ASIC_GOYA, - ASIC_INVALID + ASIC_INVALID, + ASIC_GOYA }; struct hl_cs_parser; diff --git a/drivers/misc/habanalabs/habanalabs_drv.c b/drivers/misc/habanalabs/habanalabs_drv.c index b697339d3904..1667df7ca64c 100644 --- a/drivers/misc/habanalabs/habanalabs_drv.c +++ b/drivers/misc/habanalabs/habanalabs_drv.c @@ -218,7 +218,7 @@ int create_hdev(struct hl_device **dev, struct pci_dev *pdev, hdev->disabled = true; hdev->pdev = pdev; /* can be NULL in case of simulator device */ - if (asic_type == ASIC_AUTO_DETECT) { + if (pdev) { hdev->asic_type = get_asic_type(pdev->device); if (hdev->asic_type == ASIC_INVALID) { dev_err(&pdev->dev, "Unsupported ASIC\n"); @@ -337,7 +337,7 @@ static int hl_pci_probe(struct pci_dev *pdev, " device found [%04x:%04x] (rev %x)\n", (int)pdev->vendor, (int)pdev->device, (int)pdev->revision); - rc = create_hdev(&hdev, pdev, ASIC_AUTO_DETECT, -1); + rc = create_hdev(&hdev, pdev, ASIC_INVALID, -1); if (rc) return rc; From 54303a1aef95b0cbd6a04c3b729c93da7a58e0f7 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Thu, 4 Apr 2019 14:42:26 +0300 Subject: [PATCH 062/255] habanalabs: split mmu/no-mmu code paths in memory ioctl To make the memory ioctl code more readable, this patch moves the legacy/debug code path of mmu-disabled to a separate function, which is called (if necessary) from the main memory ioctl function. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/memory.c | 187 ++++++++++++++++--------------- 1 file changed, 97 insertions(+), 90 deletions(-) diff --git a/drivers/misc/habanalabs/memory.c b/drivers/misc/habanalabs/memory.c index e9e163545584..05919f913300 100644 --- a/drivers/misc/habanalabs/memory.c +++ b/drivers/misc/habanalabs/memory.c @@ -1090,6 +1090,64 @@ static int unmap_device_va(struct hl_ctx *ctx, u64 vaddr) return rc; } +static int mem_ioctl_no_mmu(struct hl_fpriv *hpriv, union hl_mem_args *args) +{ + struct hl_device *hdev = hpriv->hdev; + struct hl_ctx *ctx = hpriv->ctx; + u64 device_addr = 0; + u32 handle = 0; + int rc; + + switch (args->in.op) { + case HL_MEM_OP_ALLOC: + if (args->in.alloc.mem_size == 0) { + dev_err(hdev->dev, + "alloc size must be larger than 0\n"); + rc = -EINVAL; + goto out; + } + + /* Force contiguous as there are no real MMU + * translations to overcome physical memory gaps + */ + args->in.flags |= HL_MEM_CONTIGUOUS; + rc = alloc_device_memory(ctx, &args->in, &handle); + + memset(args, 0, sizeof(*args)); + args->out.handle = (__u64) handle; + break; + + case HL_MEM_OP_FREE: + rc = free_device_memory(ctx, args->in.free.handle); + break; + + case HL_MEM_OP_MAP: + if (args->in.flags & HL_MEM_USERPTR) { + device_addr = args->in.map_host.host_virt_addr; + rc = 0; + } else { + rc = get_paddr_from_handle(ctx, &args->in, + &device_addr); + } + + memset(args, 0, sizeof(*args)); + args->out.device_virt_addr = device_addr; + break; + + case HL_MEM_OP_UNMAP: + rc = 0; + break; + + default: + dev_err(hdev->dev, "Unknown opcode for memory IOCTL\n"); + rc = -ENOTTY; + break; + } + +out: + return rc; +} + int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data) { union hl_mem_args *args = data; @@ -1105,100 +1163,49 @@ int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data) return -EBUSY; } - if (hdev->mmu_enable) { - switch (args->in.op) { - case HL_MEM_OP_ALLOC: - if (!hdev->dram_supports_virtual_memory) { - dev_err(hdev->dev, - "DRAM alloc is not supported\n"); - rc = -EINVAL; - goto out; - } - if (args->in.alloc.mem_size == 0) { - dev_err(hdev->dev, - "alloc size must be larger than 0\n"); - rc = -EINVAL; - goto out; - } - rc = alloc_device_memory(ctx, &args->in, &handle); + if (!hdev->mmu_enable) + return mem_ioctl_no_mmu(hpriv, args); - memset(args, 0, sizeof(*args)); - args->out.handle = (__u64) handle; - break; - - case HL_MEM_OP_FREE: - if (!hdev->dram_supports_virtual_memory) { - dev_err(hdev->dev, - "DRAM free is not supported\n"); - rc = -EINVAL; - goto out; - } - rc = free_device_memory(ctx, args->in.free.handle); - break; - - case HL_MEM_OP_MAP: - rc = map_device_va(ctx, &args->in, &device_addr); - - memset(args, 0, sizeof(*args)); - args->out.device_virt_addr = device_addr; - break; - - case HL_MEM_OP_UNMAP: - rc = unmap_device_va(ctx, - args->in.unmap.device_virt_addr); - break; - - default: - dev_err(hdev->dev, "Unknown opcode for memory IOCTL\n"); - rc = -ENOTTY; - break; + switch (args->in.op) { + case HL_MEM_OP_ALLOC: + if (!hdev->dram_supports_virtual_memory) { + dev_err(hdev->dev, "DRAM alloc is not supported\n"); + rc = -EINVAL; + goto out; } - } else { - switch (args->in.op) { - case HL_MEM_OP_ALLOC: - if (args->in.alloc.mem_size == 0) { - dev_err(hdev->dev, - "alloc size must be larger than 0\n"); - rc = -EINVAL; - goto out; - } - /* Force contiguous as there are no real MMU - * translations to overcome physical memory gaps - */ - args->in.flags |= HL_MEM_CONTIGUOUS; - rc = alloc_device_memory(ctx, &args->in, &handle); - - memset(args, 0, sizeof(*args)); - args->out.handle = (__u64) handle; - break; - - case HL_MEM_OP_FREE: - rc = free_device_memory(ctx, args->in.free.handle); - break; - - case HL_MEM_OP_MAP: - if (args->in.flags & HL_MEM_USERPTR) { - device_addr = args->in.map_host.host_virt_addr; - rc = 0; - } else { - rc = get_paddr_from_handle(ctx, &args->in, - &device_addr); - } - - memset(args, 0, sizeof(*args)); - args->out.device_virt_addr = device_addr; - break; - - case HL_MEM_OP_UNMAP: - rc = 0; - break; - - default: - dev_err(hdev->dev, "Unknown opcode for memory IOCTL\n"); - rc = -ENOTTY; - break; + if (args->in.alloc.mem_size == 0) { + dev_err(hdev->dev, + "alloc size must be larger than 0\n"); + rc = -EINVAL; + goto out; } + rc = alloc_device_memory(ctx, &args->in, &handle); + + memset(args, 0, sizeof(*args)); + args->out.handle = (__u64) handle; + break; + + case HL_MEM_OP_FREE: + rc = free_device_memory(ctx, args->in.free.handle); + break; + + case HL_MEM_OP_MAP: + rc = map_device_va(ctx, &args->in, &device_addr); + + memset(args, 0, sizeof(*args)); + args->out.device_virt_addr = device_addr; + break; + + case HL_MEM_OP_UNMAP: + rc = unmap_device_va(ctx, + args->in.unmap.device_virt_addr); + break; + + default: + dev_err(hdev->dev, "Unknown opcode for memory IOCTL\n"); + rc = -ENOTTY; + break; } out: From 3137301b6d970219706d887eb6bdcabbf54f1f3b Mon Sep 17 00:00:00 2001 From: Yauhen Kharuzhy Date: Sun, 3 Mar 2019 23:16:12 +0300 Subject: [PATCH 063/255] extcon: intel-cht-wc: Make charger detection co-existed with OTG host mode Whiskey Cove Cherry Trail PMIC requires disabling OTG host mode before of charger detection procedure. Do this by manipulationg of CHGRCTRL1 register. Source: APCI DSDT code of Lenovo Yoga Book YB1-X91L and open-sourced Intel's drivers. Signed-off-by: Yauhen Kharuzhy Reviewed-by: Andy Shevchenko Reviewed-by: Hans de Goede Tested-by: Hans de Goede Signed-off-by: Chanwoo Choi --- drivers/extcon/extcon-intel-cht-wc.c | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/drivers/extcon/extcon-intel-cht-wc.c b/drivers/extcon/extcon-intel-cht-wc.c index 5ef215297101..8d20e913536f 100644 --- a/drivers/extcon/extcon-intel-cht-wc.c +++ b/drivers/extcon/extcon-intel-cht-wc.c @@ -29,7 +29,15 @@ #define CHT_WC_CHGRCTRL0_DBPOFF BIT(6) #define CHT_WC_CHGRCTRL0_CHR_WDT_NOKICK BIT(7) -#define CHT_WC_CHGRCTRL1 0x5e17 +#define CHT_WC_CHGRCTRL1 0x5e17 +#define CHT_WC_CHGRCTRL1_FUSB_INLMT_100 BIT(0) +#define CHT_WC_CHGRCTRL1_FUSB_INLMT_150 BIT(1) +#define CHT_WC_CHGRCTRL1_FUSB_INLMT_500 BIT(2) +#define CHT_WC_CHGRCTRL1_FUSB_INLMT_900 BIT(3) +#define CHT_WC_CHGRCTRL1_FUSB_INLMT_1500 BIT(4) +#define CHT_WC_CHGRCTRL1_FTEMP_EVENT BIT(5) +#define CHT_WC_CHGRCTRL1_OTGMODE BIT(6) +#define CHT_WC_CHGRCTRL1_DBPEN BIT(7) #define CHT_WC_USBSRC 0x5e29 #define CHT_WC_USBSRC_STS_MASK GENMASK(1, 0) @@ -198,6 +206,18 @@ static void cht_wc_extcon_set_5v_boost(struct cht_wc_extcon_data *ext, dev_err(ext->dev, "Error writing Vbus GPIO CTLO: %d\n", ret); } +static void cht_wc_extcon_set_otgmode(struct cht_wc_extcon_data *ext, + bool enable) +{ + unsigned int val = enable ? CHT_WC_CHGRCTRL1_OTGMODE : 0; + int ret; + + ret = regmap_update_bits(ext->regmap, CHT_WC_CHGRCTRL1, + CHT_WC_CHGRCTRL1_OTGMODE, val); + if (ret) + dev_err(ext->dev, "Error updating CHGRCTRL1 reg: %d\n", ret); +} + /* Small helper to sync EXTCON_CHG_USB_SDP and EXTCON_USB state */ static void cht_wc_extcon_set_state(struct cht_wc_extcon_data *ext, unsigned int cable, bool state) @@ -222,10 +242,14 @@ static void cht_wc_extcon_pwrsrc_event(struct cht_wc_extcon_data *ext) id = cht_wc_extcon_get_id(ext, pwrsrc_sts); if (id == USB_ID_GND) { + cht_wc_extcon_set_otgmode(ext, true); + /* The 5v boost causes a false VBUS / SDP detect, skip */ goto charger_det_done; } + cht_wc_extcon_set_otgmode(ext, false); + /* Plugged into a host/charger or not connected? */ if (!(pwrsrc_sts & CHT_WC_PWRSRC_VBUS)) { /* Route D+ and D- to PMIC for future charger detection */ From a72a1be0de71b3bdab3d8b2e708267f32ea33ee2 Mon Sep 17 00:00:00 2001 From: Yauhen Kharuzhy Date: Sun, 3 Mar 2019 23:16:13 +0300 Subject: [PATCH 064/255] extcon: intel-cht-wc: Enable external charger In some configuration external charger "#charge enable" signal is connected to PMIC. Enable it at device probing to allow charging. Save CHGRCTRL0 and CHGDISCTR registers at driver probing and restore them at driver unbind to re-enable hardware charging control if it was enabled before. Tested at Lenovo Yoga Book (YB1-X91L). Signed-off-by: Yauhen Kharuzhy Reviewed-by: Andy Shevchenko Reviewed-by: Hans de Goede Tested-by: Hans de Goede Signed-off-by: Chanwoo Choi --- drivers/extcon/extcon-intel-cht-wc.c | 34 +++++++++++++++++++++++++++- 1 file changed, 33 insertions(+), 1 deletion(-) diff --git a/drivers/extcon/extcon-intel-cht-wc.c b/drivers/extcon/extcon-intel-cht-wc.c index 8d20e913536f..53b28ecc4ad1 100644 --- a/drivers/extcon/extcon-intel-cht-wc.c +++ b/drivers/extcon/extcon-intel-cht-wc.c @@ -56,6 +56,13 @@ #define CHT_WC_USBSRC_TYPE_OTHER 8 #define CHT_WC_USBSRC_TYPE_DCP_EXTPHY 9 +#define CHT_WC_CHGDISCTRL 0x5e2f +#define CHT_WC_CHGDISCTRL_OUT BIT(0) +/* 0 - open drain, 1 - regular push-pull output */ +#define CHT_WC_CHGDISCTRL_DRV BIT(4) +/* 0 - pin is controlled by SW, 1 - by HW */ +#define CHT_WC_CHGDISCTRL_FN BIT(6) + #define CHT_WC_PWRSRC_IRQ 0x6e03 #define CHT_WC_PWRSRC_IRQ_MASK 0x6e0f #define CHT_WC_PWRSRC_STS 0x6e1e @@ -218,6 +225,18 @@ static void cht_wc_extcon_set_otgmode(struct cht_wc_extcon_data *ext, dev_err(ext->dev, "Error updating CHGRCTRL1 reg: %d\n", ret); } +static void cht_wc_extcon_enable_charging(struct cht_wc_extcon_data *ext, + bool enable) +{ + unsigned int val = enable ? 0 : CHT_WC_CHGDISCTRL_OUT; + int ret; + + ret = regmap_update_bits(ext->regmap, CHT_WC_CHGDISCTRL, + CHT_WC_CHGDISCTRL_OUT, val); + if (ret) + dev_err(ext->dev, "Error updating CHGDISCTRL reg: %d\n", ret); +} + /* Small helper to sync EXTCON_CHG_USB_SDP and EXTCON_USB state */ static void cht_wc_extcon_set_state(struct cht_wc_extcon_data *ext, unsigned int cable, bool state) @@ -242,6 +261,7 @@ static void cht_wc_extcon_pwrsrc_event(struct cht_wc_extcon_data *ext) id = cht_wc_extcon_get_id(ext, pwrsrc_sts); if (id == USB_ID_GND) { + cht_wc_extcon_enable_charging(ext, false); cht_wc_extcon_set_otgmode(ext, true); /* The 5v boost causes a false VBUS / SDP detect, skip */ @@ -249,6 +269,7 @@ static void cht_wc_extcon_pwrsrc_event(struct cht_wc_extcon_data *ext) } cht_wc_extcon_set_otgmode(ext, false); + cht_wc_extcon_enable_charging(ext, true); /* Plugged into a host/charger or not connected? */ if (!(pwrsrc_sts & CHT_WC_PWRSRC_VBUS)) { @@ -302,6 +323,14 @@ static int cht_wc_extcon_sw_control(struct cht_wc_extcon_data *ext, bool enable) { int ret, mask, val; + val = enable ? 0 : CHT_WC_CHGDISCTRL_FN; + ret = regmap_update_bits(ext->regmap, CHT_WC_CHGDISCTRL, + CHT_WC_CHGDISCTRL_FN, val); + if (ret) + dev_err(ext->dev, + "Error setting sw control for CHGDIS pin: %d\n", + ret); + mask = CHT_WC_CHGRCTRL0_SWCONTROL | CHT_WC_CHGRCTRL0_CCSM_OFF; val = enable ? mask : 0; ret = regmap_update_bits(ext->regmap, CHT_WC_CHGRCTRL0, mask, val); @@ -353,7 +382,10 @@ static int cht_wc_extcon_probe(struct platform_device *pdev) /* Enable sw control */ ret = cht_wc_extcon_sw_control(ext, true); if (ret) - return ret; + goto disable_sw_control; + + /* Disable charging by external battery charger */ + cht_wc_extcon_enable_charging(ext, false); /* Register extcon device */ ret = devm_extcon_dev_register(ext->dev, ext->edev); From db8b4aefd17b1ccf108d81a4fbb181c8e50abf0e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Valdis=20Kl=C4=93tnieks?= Date: Tue, 12 Mar 2019 06:42:31 -0400 Subject: [PATCH 065/255] extcon: Fix build warning for extcon_unregister_notifier comment Give the line the asterisk it wanted to fix the build warning. [Build warning message] Building with W=1 reports: CC drivers/extcon/devres.o drivers/extcon/devres.c:208: warning: bad line: - Resource-managed extcon_unregister_notifier() Signed-off-by: Valdis Kletnieks [cw00.choi: Edit the patch subject and description] Signed-off-by: Chanwoo Choi --- drivers/extcon/devres.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/extcon/devres.c b/drivers/extcon/devres.c index f599aeddf8e5..f487d877ab5d 100644 --- a/drivers/extcon/devres.c +++ b/drivers/extcon/devres.c @@ -205,7 +205,7 @@ EXPORT_SYMBOL(devm_extcon_register_notifier); /** * devm_extcon_unregister_notifier() - - Resource-managed extcon_unregister_notifier() + * - Resource-managed extcon_unregister_notifier() * @dev: the device owning the extcon device being created * @edev: the extcon device * @id: the unique id among the extcon enumeration From 098b7ae8ec431465b319e2157f848df50dc6b7e0 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 19 Mar 2019 16:30:41 +0200 Subject: [PATCH 066/255] extcon: intel: Split out some definitions to a common header We are going to use some definitions in the other Intel extcon drivers, thus, split out them to a common header file. Signed-off-by: Andy Shevchenko Signed-off-by: Chanwoo Choi --- drivers/extcon/extcon-intel-cht-wc.c | 21 +++++++-------------- drivers/extcon/extcon-intel.h | 20 ++++++++++++++++++++ 2 files changed, 27 insertions(+), 14 deletions(-) create mode 100644 drivers/extcon/extcon-intel.h diff --git a/drivers/extcon/extcon-intel-cht-wc.c b/drivers/extcon/extcon-intel-cht-wc.c index 53b28ecc4ad1..9d32150e68db 100644 --- a/drivers/extcon/extcon-intel-cht-wc.c +++ b/drivers/extcon/extcon-intel-cht-wc.c @@ -17,6 +17,8 @@ #include #include +#include "extcon-intel.h" + #define CHT_WC_PHYCTRL 0x5e07 #define CHT_WC_CHGRCTRL0 0x5e16 @@ -80,15 +82,6 @@ #define CHT_WC_VBUS_GPIO_CTLO_DRV_OD BIT(4) #define CHT_WC_VBUS_GPIO_CTLO_DIR_OUT BIT(5) -enum cht_wc_usb_id { - USB_ID_OTG, - USB_ID_GND, - USB_ID_FLOAT, - USB_RID_A, - USB_RID_B, - USB_RID_C, -}; - enum cht_wc_mux_select { MUX_SEL_PMIC = 0, MUX_SEL_SOC, @@ -116,9 +109,9 @@ static int cht_wc_extcon_get_id(struct cht_wc_extcon_data *ext, int pwrsrc_sts) { switch ((pwrsrc_sts & CHT_WC_PWRSRC_USBID_MASK) >> CHT_WC_PWRSRC_USBID_SHIFT) { case CHT_WC_PWRSRC_RID_GND: - return USB_ID_GND; + return INTEL_USB_ID_GND; case CHT_WC_PWRSRC_RID_FLOAT: - return USB_ID_FLOAT; + return INTEL_USB_ID_FLOAT; case CHT_WC_PWRSRC_RID_ACA: default: /* @@ -126,7 +119,7 @@ static int cht_wc_extcon_get_id(struct cht_wc_extcon_data *ext, int pwrsrc_sts) * the USBID GPADC channel here and determine ACA role * based on that. */ - return USB_ID_FLOAT; + return INTEL_USB_ID_FLOAT; } } @@ -260,7 +253,7 @@ static void cht_wc_extcon_pwrsrc_event(struct cht_wc_extcon_data *ext) } id = cht_wc_extcon_get_id(ext, pwrsrc_sts); - if (id == USB_ID_GND) { + if (id == INTEL_USB_ID_GND) { cht_wc_extcon_enable_charging(ext, false); cht_wc_extcon_set_otgmode(ext, true); @@ -293,7 +286,7 @@ static void cht_wc_extcon_pwrsrc_event(struct cht_wc_extcon_data *ext) ext->previous_cable = cable; } - ext->usb_host = ((id == USB_ID_GND) || (id == USB_RID_A)); + ext->usb_host = ((id == INTEL_USB_ID_GND) || (id == INTEL_USB_RID_A)); extcon_set_state_sync(ext->edev, EXTCON_USB_HOST, ext->usb_host); } diff --git a/drivers/extcon/extcon-intel.h b/drivers/extcon/extcon-intel.h new file mode 100644 index 000000000000..0ad645ec7b33 --- /dev/null +++ b/drivers/extcon/extcon-intel.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Header file for Intel extcon hardware + * + * Copyright (C) 2019 Intel Corporation. All rights reserved. + */ + +#ifndef __EXTCON_INTEL_H__ +#define __EXTCON_INTEL_H__ + +enum extcon_intel_usb_id { + INTEL_USB_ID_OTG, + INTEL_USB_ID_GND, + INTEL_USB_ID_FLOAT, + INTEL_USB_RID_A, + INTEL_USB_RID_B, + INTEL_USB_RID_C, +}; + +#endif /* __EXTCON_INTEL_H__ */ From 492929c547913f77460c20be994482d57bc74840 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 19 Mar 2019 16:30:42 +0200 Subject: [PATCH 067/255] extcon: mrfld: Introduce extcon driver for Basin Cove PMIC On Intel Merrifield the Basin Cove PMIC provides a feature to detect the USB connection type. This driver utilizes the feature in order to support the USB dual role detection. Signed-off-by: Andy Shevchenko Signed-off-by: Chanwoo Choi --- drivers/extcon/Kconfig | 7 + drivers/extcon/Makefile | 1 + drivers/extcon/extcon-intel-mrfld.c | 284 ++++++++++++++++++++++++++++ 3 files changed, 292 insertions(+) create mode 100644 drivers/extcon/extcon-intel-mrfld.c diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig index 540e8cd16ee6..1ed4b45536c7 100644 --- a/drivers/extcon/Kconfig +++ b/drivers/extcon/Kconfig @@ -60,6 +60,13 @@ config EXTCON_INTEL_CHT_WC Say Y here to enable extcon support for charger detection / control on the Intel Cherrytrail Whiskey Cove PMIC. +config EXTCON_INTEL_MRFLD + tristate "Intel Merrifield Basin Cove PMIC extcon driver" + depends on INTEL_SOC_PMIC_MRFLD + help + Say Y here to enable extcon support for charger detection / control + on the Intel Merrifield Basin Cove PMIC. + config EXTCON_MAX14577 tristate "Maxim MAX14577/77836 EXTCON Support" depends on MFD_MAX14577 diff --git a/drivers/extcon/Makefile b/drivers/extcon/Makefile index 261ce4cfe209..d3941a735df3 100644 --- a/drivers/extcon/Makefile +++ b/drivers/extcon/Makefile @@ -11,6 +11,7 @@ obj-$(CONFIG_EXTCON_AXP288) += extcon-axp288.o obj-$(CONFIG_EXTCON_GPIO) += extcon-gpio.o obj-$(CONFIG_EXTCON_INTEL_INT3496) += extcon-intel-int3496.o obj-$(CONFIG_EXTCON_INTEL_CHT_WC) += extcon-intel-cht-wc.o +obj-$(CONFIG_EXTCON_INTEL_MRFLD) += extcon-intel-mrfld.o obj-$(CONFIG_EXTCON_MAX14577) += extcon-max14577.o obj-$(CONFIG_EXTCON_MAX3355) += extcon-max3355.o obj-$(CONFIG_EXTCON_MAX77693) += extcon-max77693.o diff --git a/drivers/extcon/extcon-intel-mrfld.c b/drivers/extcon/extcon-intel-mrfld.c new file mode 100644 index 000000000000..f47016fb28a8 --- /dev/null +++ b/drivers/extcon/extcon-intel-mrfld.c @@ -0,0 +1,284 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * extcon driver for Basin Cove PMIC + * + * Copyright (c) 2019, Intel Corporation. + * Author: Andy Shevchenko + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "extcon-intel.h" + +#define BCOVE_USBIDCTRL 0x19 +#define BCOVE_USBIDCTRL_ID BIT(0) +#define BCOVE_USBIDCTRL_ACA BIT(1) +#define BCOVE_USBIDCTRL_ALL (BCOVE_USBIDCTRL_ID | BCOVE_USBIDCTRL_ACA) + +#define BCOVE_USBIDSTS 0x1a +#define BCOVE_USBIDSTS_GND BIT(0) +#define BCOVE_USBIDSTS_RARBRC_MASK GENMASK(2, 1) +#define BCOVE_USBIDSTS_RARBRC_SHIFT 1 +#define BCOVE_USBIDSTS_NO_ACA 0 +#define BCOVE_USBIDSTS_R_ID_A 1 +#define BCOVE_USBIDSTS_R_ID_B 2 +#define BCOVE_USBIDSTS_R_ID_C 3 +#define BCOVE_USBIDSTS_FLOAT BIT(3) +#define BCOVE_USBIDSTS_SHORT BIT(4) + +#define BCOVE_CHGRIRQ_ALL (BCOVE_CHGRIRQ_VBUSDET | BCOVE_CHGRIRQ_DCDET | \ + BCOVE_CHGRIRQ_BATTDET | BCOVE_CHGRIRQ_USBIDDET) + +#define BCOVE_CHGRCTRL0 0x4b +#define BCOVE_CHGRCTRL0_CHGRRESET BIT(0) +#define BCOVE_CHGRCTRL0_EMRGCHREN BIT(1) +#define BCOVE_CHGRCTRL0_EXTCHRDIS BIT(2) +#define BCOVE_CHGRCTRL0_SWCONTROL BIT(3) +#define BCOVE_CHGRCTRL0_TTLCK BIT(4) +#define BCOVE_CHGRCTRL0_BIT_5 BIT(5) +#define BCOVE_CHGRCTRL0_BIT_6 BIT(6) +#define BCOVE_CHGRCTRL0_CHR_WDT_NOKICK BIT(7) + +struct mrfld_extcon_data { + struct device *dev; + struct regmap *regmap; + struct extcon_dev *edev; + unsigned int status; + unsigned int id; +}; + +static const unsigned int mrfld_extcon_cable[] = { + EXTCON_USB, + EXTCON_USB_HOST, + EXTCON_CHG_USB_SDP, + EXTCON_CHG_USB_CDP, + EXTCON_CHG_USB_DCP, + EXTCON_CHG_USB_ACA, + EXTCON_NONE, +}; + +static int mrfld_extcon_clear(struct mrfld_extcon_data *data, unsigned int reg, + unsigned int mask) +{ + return regmap_update_bits(data->regmap, reg, mask, 0x00); +} + +static int mrfld_extcon_set(struct mrfld_extcon_data *data, unsigned int reg, + unsigned int mask) +{ + return regmap_update_bits(data->regmap, reg, mask, 0xff); +} + +static int mrfld_extcon_sw_control(struct mrfld_extcon_data *data, bool enable) +{ + unsigned int mask = BCOVE_CHGRCTRL0_SWCONTROL; + struct device *dev = data->dev; + int ret; + + if (enable) + ret = mrfld_extcon_set(data, BCOVE_CHGRCTRL0, mask); + else + ret = mrfld_extcon_clear(data, BCOVE_CHGRCTRL0, mask); + if (ret) + dev_err(dev, "can't set SW control: %d\n", ret); + return ret; +} + +static int mrfld_extcon_get_id(struct mrfld_extcon_data *data) +{ + struct regmap *regmap = data->regmap; + unsigned int id; + bool ground; + int ret; + + ret = regmap_read(regmap, BCOVE_USBIDSTS, &id); + if (ret) + return ret; + + if (id & BCOVE_USBIDSTS_FLOAT) + return INTEL_USB_ID_FLOAT; + + switch ((id & BCOVE_USBIDSTS_RARBRC_MASK) >> BCOVE_USBIDSTS_RARBRC_SHIFT) { + case BCOVE_USBIDSTS_R_ID_A: + return INTEL_USB_RID_A; + case BCOVE_USBIDSTS_R_ID_B: + return INTEL_USB_RID_B; + case BCOVE_USBIDSTS_R_ID_C: + return INTEL_USB_RID_C; + } + + /* + * PMIC A0 reports USBIDSTS_GND = 1 for ID_GND, + * but PMIC B0 reports USBIDSTS_GND = 0 for ID_GND. + * Thus we must check this bit at last. + */ + ground = id & BCOVE_USBIDSTS_GND; + switch ('A' + BCOVE_MAJOR(data->id)) { + case 'A': + return ground ? INTEL_USB_ID_GND : INTEL_USB_ID_FLOAT; + case 'B': + return ground ? INTEL_USB_ID_FLOAT : INTEL_USB_ID_GND; + } + + /* Unknown or unsupported type */ + return INTEL_USB_ID_FLOAT; +} + +static int mrfld_extcon_role_detect(struct mrfld_extcon_data *data) +{ + unsigned int id; + bool usb_host; + int ret; + + ret = mrfld_extcon_get_id(data); + if (ret < 0) + return ret; + + id = ret; + + usb_host = (id == INTEL_USB_ID_GND) || (id == INTEL_USB_RID_A); + extcon_set_state_sync(data->edev, EXTCON_USB_HOST, usb_host); + + return 0; +} + +static int mrfld_extcon_cable_detect(struct mrfld_extcon_data *data) +{ + struct regmap *regmap = data->regmap; + unsigned int status, change; + int ret; + + /* + * It seems SCU firmware clears the content of BCOVE_CHGRIRQ1 + * and makes it useless for OS. Instead we compare a previously + * stored status to the current one, provided by BCOVE_SCHGRIRQ1. + */ + ret = regmap_read(regmap, BCOVE_SCHGRIRQ1, &status); + if (ret) + return ret; + + change = status ^ data->status; + if (!change) + return -ENODATA; + + if (change & BCOVE_CHGRIRQ_USBIDDET) { + ret = mrfld_extcon_role_detect(data); + if (ret) + return ret; + } + + data->status = status; + + return 0; +} + +static irqreturn_t mrfld_extcon_interrupt(int irq, void *dev_id) +{ + struct mrfld_extcon_data *data = dev_id; + int ret; + + ret = mrfld_extcon_cable_detect(data); + + mrfld_extcon_clear(data, BCOVE_MIRQLVL1, BCOVE_LVL1_CHGR); + + return ret ? IRQ_NONE: IRQ_HANDLED; +} + +static int mrfld_extcon_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct intel_soc_pmic *pmic = dev_get_drvdata(dev->parent); + struct regmap *regmap = pmic->regmap; + struct mrfld_extcon_data *data; + unsigned int id; + int irq, ret; + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->dev = dev; + data->regmap = regmap; + + data->edev = devm_extcon_dev_allocate(dev, mrfld_extcon_cable); + if (IS_ERR(data->edev)) + return -ENOMEM; + + ret = devm_extcon_dev_register(dev, data->edev); + if (ret < 0) { + dev_err(dev, "can't register extcon device: %d\n", ret); + return ret; + } + + ret = devm_request_threaded_irq(dev, irq, NULL, mrfld_extcon_interrupt, + IRQF_ONESHOT | IRQF_SHARED, pdev->name, + data); + if (ret) { + dev_err(dev, "can't register IRQ handler: %d\n", ret); + return ret; + } + + ret = regmap_read(regmap, BCOVE_ID, &id); + if (ret) { + dev_err(dev, "can't read PMIC ID: %d\n", ret); + return ret; + } + + data->id = id; + + ret = mrfld_extcon_sw_control(data, true); + if (ret) + return ret; + + /* Get initial state */ + mrfld_extcon_role_detect(data); + + mrfld_extcon_clear(data, BCOVE_MIRQLVL1, BCOVE_LVL1_CHGR); + mrfld_extcon_clear(data, BCOVE_MCHGRIRQ1, BCOVE_CHGRIRQ_ALL); + + mrfld_extcon_set(data, BCOVE_USBIDCTRL, BCOVE_USBIDCTRL_ALL); + + platform_set_drvdata(pdev, data); + + return 0; +} + +static int mrfld_extcon_remove(struct platform_device *pdev) +{ + struct mrfld_extcon_data *data = platform_get_drvdata(pdev); + + mrfld_extcon_sw_control(data, false); + + return 0; +} + +static const struct platform_device_id mrfld_extcon_id_table[] = { + { .name = "mrfld_bcove_pwrsrc" }, + {} +}; +MODULE_DEVICE_TABLE(platform, mrfld_extcon_id_table); + +static struct platform_driver mrfld_extcon_driver = { + .driver = { + .name = "mrfld_bcove_pwrsrc", + }, + .probe = mrfld_extcon_probe, + .remove = mrfld_extcon_remove, + .id_table = mrfld_extcon_id_table, +}; +module_platform_driver(mrfld_extcon_driver); + +MODULE_AUTHOR("Andy Shevchenko "); +MODULE_DESCRIPTION("extcon driver for Intel Merrifield Basin Cove PMIC"); +MODULE_LICENSE("GPL v2"); From caa3c8e52582fc4d2ed82afd5e7ea164c18ef4fe Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sat, 6 Apr 2019 13:23:54 +0300 Subject: [PATCH 068/255] habanalabs: all FD must be closed before removing device This patch fixes a bug in the implementation of the function that removes the device. The bug can happen when the device is removed but not the driver itself (e.g. remove by the OS due to PCI freeze in Power architecture). In that case, there maybe open users that are calling IOCTLs while the device is removed. This is a possible race condition that the driver must handle. Otherwise, a kernel panic may occur. This race is prevented in the hard-reset flow, because the driver makes sure the users are closed before continuing with the hard-reset. This race can not occur when the driver itself is removed because the OS makes sure all the file descriptors are closed. The fix is to make sure the open users close their file descriptors and if they don't (after a certain amount of time), the driver sends them a SIGKILL, because the remove of the device can't be stopped. The patch re-uses the same code that is called from the hard-reset flow. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/device.c | 32 +++++++++++++++++++++++++++----- 1 file changed, 27 insertions(+), 5 deletions(-) diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index 6cbfd560721e..56d3ba53c661 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -513,11 +513,8 @@ int hl_device_resume(struct hl_device *hdev) return rc; } -static void hl_device_hard_reset_pending(struct work_struct *work) +static void device_kill_open_processes(struct hl_device *hdev) { - struct hl_device_reset_work *device_reset_work = - container_of(work, struct hl_device_reset_work, reset_work); - struct hl_device *hdev = device_reset_work->hdev; u16 pending_total, pending_cnt; struct task_struct *task = NULL; @@ -552,6 +549,12 @@ static void hl_device_hard_reset_pending(struct work_struct *work) } } + /* We killed the open users, but because the driver cleans up after the + * user contexts are closed (e.g. mmu mappings), we need to wait again + * to make sure the cleaning phase is finished before continuing with + * the reset + */ + pending_cnt = pending_total; while ((atomic_read(&hdev->fd_open_cnt)) && (pending_cnt)) { @@ -567,6 +570,16 @@ static void hl_device_hard_reset_pending(struct work_struct *work) mutex_unlock(&hdev->fd_open_cnt_lock); +} + +static void device_hard_reset_pending(struct work_struct *work) +{ + struct hl_device_reset_work *device_reset_work = + container_of(work, struct hl_device_reset_work, reset_work); + struct hl_device *hdev = device_reset_work->hdev; + + device_kill_open_processes(hdev); + hl_device_reset(hdev, true, true); kfree(device_reset_work); @@ -650,7 +663,7 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset, * from a dedicated work */ INIT_WORK(&device_reset_work->reset_work, - hl_device_hard_reset_pending); + device_hard_reset_pending); device_reset_work->hdev = hdev; schedule_work(&device_reset_work->reset_work); @@ -1049,6 +1062,15 @@ void hl_device_fini(struct hl_device *hdev) /* Mark device as disabled */ hdev->disabled = true; + /* + * Flush anyone that is inside the critical section of enqueue + * jobs to the H/W + */ + hdev->asic_funcs->hw_queues_lock(hdev); + hdev->asic_funcs->hw_queues_unlock(hdev); + + device_kill_open_processes(hdev); + hl_hwmon_fini(hdev); device_late_fini(hdev); From 3f5398cfbf051dc1850b4f64fbe5267cbd699ce0 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sat, 6 Apr 2019 15:41:35 +0300 Subject: [PATCH 069/255] habanalabs: improve IOCTLs behavior when disabled or reset This patch makes some improvement in how IOCTLs behave when the device is disabled or under reset. The new code checks, at the start of every IOCTL, if the device is disabled or in reset. If so, it prints an appropriate kernel message and returns -EBUSY to user-space. In addition, the code modifies the location of where the hard_reset_pending flag is being set or cleared: 1. It is now cleared immediately after the reset *tear-down* flow is finished but before the re-initialization flow begins. 2. It is being set in the remove function of the device, to make the behavior the same with the hard-reset flow There are two exceptions to the disable or in reset check: 1. The HL_INFO_DEVICE_STATUS opcode in the INFO IOCTL. This opcode allows the user to inquire about the status of the device, whether it is operational, in reset or malfunction (disabled). If the driver will block this IOCTL, the user won't be able to retrieve the status in case of malfunction or in reset. 2. The WAIT_FOR_CS IOCTL. This IOCTL allows the user to inquire about the status of a CS. We want to allow the user to continue to do so, even if we started a soft-reset process because it will allow the user to get the correct error code for each CS he submitted. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/command_buffer.c | 7 +++++++ drivers/misc/habanalabs/device.c | 9 +++++---- drivers/misc/habanalabs/habanalabs_ioctl.c | 3 ++- drivers/misc/habanalabs/memory.c | 3 ++- 4 files changed, 16 insertions(+), 6 deletions(-) diff --git a/drivers/misc/habanalabs/command_buffer.c b/drivers/misc/habanalabs/command_buffer.c index 85f75806a9a7..b1ffca47d748 100644 --- a/drivers/misc/habanalabs/command_buffer.c +++ b/drivers/misc/habanalabs/command_buffer.c @@ -214,6 +214,13 @@ int hl_cb_ioctl(struct hl_fpriv *hpriv, void *data) u64 handle; int rc; + if (hl_device_disabled_or_in_reset(hdev)) { + dev_warn_ratelimited(hdev->dev, + "Device is %s. Can't execute CB IOCTL\n", + atomic_read(&hdev->in_reset) ? "in_reset" : "disabled"); + return -EBUSY; + } + switch (args->in.op) { case HL_CB_OP_CREATE: rc = hl_cb_create(hdev, &hpriv->cb_mgr, args->in.cb_size, diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index 56d3ba53c661..25bfb093ff26 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -641,6 +641,8 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset, if ((hard_reset) && (!from_hard_reset_thread)) { struct hl_device_reset_work *device_reset_work; + hdev->hard_reset_pending = true; + if (!hdev->pdev) { dev_err(hdev->dev, "Reset action is NOT supported in simulator\n"); @@ -648,8 +650,6 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset, goto out_err; } - hdev->hard_reset_pending = true; - device_reset_work = kzalloc(sizeof(*device_reset_work), GFP_ATOMIC); if (!device_reset_work) { @@ -718,6 +718,7 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset, if (hard_reset) { hdev->device_cpu_disabled = false; + hdev->hard_reset_pending = false; if (hdev->kernel_ctx) { dev_crit(hdev->dev, @@ -779,8 +780,6 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset, } hl_set_max_power(hdev, hdev->max_power); - - hdev->hard_reset_pending = false; } else { rc = hdev->asic_funcs->soft_reset_late_init(hdev); if (rc) { @@ -1069,6 +1068,8 @@ void hl_device_fini(struct hl_device *hdev) hdev->asic_funcs->hw_queues_lock(hdev); hdev->asic_funcs->hw_queues_unlock(hdev); + hdev->hard_reset_pending = true; + device_kill_open_processes(hdev); hl_hwmon_fini(hdev); diff --git a/drivers/misc/habanalabs/habanalabs_ioctl.c b/drivers/misc/habanalabs/habanalabs_ioctl.c index 810e65446075..eeefb22023e9 100644 --- a/drivers/misc/habanalabs/habanalabs_ioctl.c +++ b/drivers/misc/habanalabs/habanalabs_ioctl.c @@ -202,7 +202,8 @@ static int hl_info_ioctl(struct hl_fpriv *hpriv, void *data) if (hl_device_disabled_or_in_reset(hdev)) { dev_warn_ratelimited(hdev->dev, - "Device is disabled or in reset. Can't execute INFO IOCTL\n"); + "Device is %s. Can't execute INFO IOCTL\n", + atomic_read(&hdev->in_reset) ? "in_reset" : "disabled"); return -EBUSY; } diff --git a/drivers/misc/habanalabs/memory.c b/drivers/misc/habanalabs/memory.c index 05919f913300..43ef3ad8438a 100644 --- a/drivers/misc/habanalabs/memory.c +++ b/drivers/misc/habanalabs/memory.c @@ -1159,7 +1159,8 @@ int hl_mem_ioctl(struct hl_fpriv *hpriv, void *data) if (hl_device_disabled_or_in_reset(hdev)) { dev_warn_ratelimited(hdev->dev, - "Device is disabled or in reset. Can't execute memory IOCTL\n"); + "Device is %s. Can't execute MEMORY IOCTL\n", + atomic_read(&hdev->in_reset) ? "in_reset" : "disabled"); return -EBUSY; } From 9f201aba56b92c3daa4b76efae056ddbb80d91e6 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sat, 6 Apr 2019 15:33:38 +0300 Subject: [PATCH 070/255] habanalabs: prevent device PTE read/write during hard-reset During hard-reset, contexts are closed as part of the tear-down process. After a context is closed, the driver cleans up the page tables of that context in the device's DRAM. This action is both dangerous and unnecessary. It is unnecessary, because the device is going through a hard-reset, which means the device's DRAM contents are no longer valid and the device's MMU is being reset. It is dangerous, because if the hard-reset came as a result of a PCI freeze, this action may cause the entire host machine to hang. Therefore, prevent all device PTE updates when a hard-reset operation is pending. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index aaa05662ca9f..5100dfbf3acc 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -4058,6 +4058,9 @@ static u64 goya_read_pte(struct hl_device *hdev, u64 addr) { struct goya_device *goya = hdev->asic_specific; + if (hdev->hard_reset_pending) + return U64_MAX; + return readq(hdev->pcie_bar[DDR_BAR_ID] + (addr - goya->ddr_bar_cur_addr)); } @@ -4066,6 +4069,9 @@ static void goya_write_pte(struct hl_device *hdev, u64 addr, u64 val) { struct goya_device *goya = hdev->asic_specific; + if (hdev->hard_reset_pending) + return; + writeq(val, hdev->pcie_bar[DDR_BAR_ID] + (addr - goya->ddr_bar_cur_addr)); } From f03f73c2a974f784251e9b1a829178cab7a2000a Mon Sep 17 00:00:00 2001 From: Georgi Djakov Date: Fri, 22 Mar 2019 12:04:41 +0200 Subject: [PATCH 071/255] MAINTAINERS: Add mailing list for the interconnect API Add a mailing list for patch reviews and discussions related to tuning the on-chip interconnects. For now i am not expecting a lot of traffic, so let's use the linux-pm@ list. Acked-by: Rafael J. Wysocki Signed-off-by: Georgi Djakov --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 43b36dbed48e..c6b36645a77b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8045,6 +8045,7 @@ F: drivers/gpio/gpio-intel-mid.c INTERCONNECT API M: Georgi Djakov +L: linux-pm@vger.kernel.org S: Maintained F: Documentation/interconnect/ F: Documentation/devicetree/bindings/interconnect/ From 83fdb2dfb0c2925f253449677830ed11461ac5c8 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Wed, 27 Mar 2019 09:31:37 -0400 Subject: [PATCH 072/255] interconnect: convert to DEFINE_SHOW_ATTRIBUTE Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code. Signed-off-by: Yangtao Li Signed-off-by: Georgi Djakov --- drivers/interconnect/core.c | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index 6005a1c189f6..871eb4bc4efc 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -90,18 +90,7 @@ static int icc_summary_show(struct seq_file *s, void *data) return 0; } - -static int icc_summary_open(struct inode *inode, struct file *file) -{ - return single_open(file, icc_summary_show, inode->i_private); -} - -static const struct file_operations icc_summary_fops = { - .open = icc_summary_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; +DEFINE_SHOW_ATTRIBUTE(icc_summary); static struct icc_node *node_find(const int id) { From e00dac3daaa75fc91ec67f656ca56859075059c8 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Wed, 10 Apr 2019 15:18:46 +0300 Subject: [PATCH 073/255] habanalabs: Cancel pr_fmt() definition dependency on includes order pr_fmt() should be defined before including linux/printk.h, either directly or indirectly, in order to avoid redefinition of the macro. Currently the macro definition is in habanalabs.h, which is included in many files, and that makes the addition/reorder of includes to be prone to compilation errors. This patch cancels this dependency by defining the macro only in the few source files that use it. Signed-off-by: Tomer Tayar Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/device.c | 2 ++ drivers/misc/habanalabs/habanalabs.h | 2 -- drivers/misc/habanalabs/habanalabs_drv.c | 2 ++ 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index 25bfb093ff26..a88f7be23c7f 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -5,6 +5,8 @@ * All Rights Reserved. */ +#define pr_fmt(fmt) "habanalabs: " fmt + #include "habanalabs.h" #include diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 2f02bb55f66a..86bd5298efd6 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -11,8 +11,6 @@ #include "include/armcp_if.h" #include "include/qman_if.h" -#define pr_fmt(fmt) "habanalabs: " fmt - #include #include #include diff --git a/drivers/misc/habanalabs/habanalabs_drv.c b/drivers/misc/habanalabs/habanalabs_drv.c index 1667df7ca64c..5f4d155be767 100644 --- a/drivers/misc/habanalabs/habanalabs_drv.c +++ b/drivers/misc/habanalabs/habanalabs_drv.c @@ -6,6 +6,8 @@ * */ +#define pr_fmt(fmt) "habanalabs: " fmt + #include "habanalabs.h" #include From fa3c098c2d52a268f6372fa053932e11f50cecb1 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 4 Apr 2019 22:17:48 +0800 Subject: [PATCH 074/255] extcon: axp288: Add a depends on ACPI to the Kconfig entry As Hans de Goede pointed, using this driver without ACPI makes little sense, so add ACPI dependency to Kconfig entry to fix a build error while CONFIG_ACPI is not set. drivers/extcon/extcon-axp288.c: In function 'axp288_extcon_probe': drivers/extcon/extcon-axp288.c:363:20: error: dereferencing pointer to incomplete type put_device(&adev->dev); Fixes: 0cf064db948a ("extcon: axp288: Convert to use acpi_dev_get_first_match_dev()") Reported-by: Hulk Robot Suggested-by: Hans de Goede Signed-off-by: YueHaibing Reviewed-by: Hans de Goede Reviewed-by: Mukesh Ojha Signed-off-by: Chanwoo Choi --- drivers/extcon/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/extcon/Kconfig b/drivers/extcon/Kconfig index 1ed4b45536c7..de06fafb52ff 100644 --- a/drivers/extcon/Kconfig +++ b/drivers/extcon/Kconfig @@ -30,7 +30,7 @@ config EXTCON_ARIZONA config EXTCON_AXP288 tristate "X-Power AXP288 EXTCON support" - depends on MFD_AXP20X && USB_SUPPORT && X86 + depends on MFD_AXP20X && USB_SUPPORT && X86 && ACPI select USB_ROLE_SWITCH help Say Y here to enable support for USB peripheral detection From 00053de52231117ddc154042549f2256183ffb86 Mon Sep 17 00:00:00 2001 From: Charles Keepax Date: Thu, 4 Apr 2019 17:33:56 +0100 Subject: [PATCH 075/255] extcon: arizona: Disable mic detect if running when driver is removed Microphone detection provides the button detection features on the Arizona CODECs as such it will be running if the jack is currently inserted. If the driver is unbound whilst the jack is still inserted this will cause warnings from the regulator framework as the MICVDD regulator is put but was never disabled. Correct this by disabling microphone detection on driver removal and if the microphone detection was running disable the regulator and put the runtime reference that was currently held. Signed-off-by: Charles Keepax Signed-off-by: Chanwoo Choi --- drivers/extcon/extcon-arizona.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/drivers/extcon/extcon-arizona.c b/drivers/extcon/extcon-arizona.c index da0e9bc4262f..9327479c719c 100644 --- a/drivers/extcon/extcon-arizona.c +++ b/drivers/extcon/extcon-arizona.c @@ -1726,6 +1726,16 @@ static int arizona_extcon_remove(struct platform_device *pdev) struct arizona_extcon_info *info = platform_get_drvdata(pdev); struct arizona *arizona = info->arizona; int jack_irq_rise, jack_irq_fall; + bool change; + + regmap_update_bits_check(arizona->regmap, ARIZONA_MIC_DETECT_1, + ARIZONA_MICD_ENA, 0, + &change); + + if (change) { + regulator_disable(info->micvdd); + pm_runtime_put(info->dev); + } gpiod_put(info->micd_pol_gpio); From 4ac5627acc3e32c6a2acf5d570efc998792f2a65 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 10 Apr 2019 22:16:57 -0500 Subject: [PATCH 076/255] soundwire: intel: fix inversion in devm_kcalloc parameters the number of elements and size are inverted, fix. This probably only worked because the number of properties is hard-coded to 1. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Takashi Iwai Signed-off-by: Vinod Koul --- drivers/soundwire/intel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index fd8d034cfec1..8669b314c476 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -796,8 +796,8 @@ static int intel_prop_read(struct sdw_bus *bus) /* BIOS is not giving some values correctly. So, lets override them */ bus->prop.num_freq = 1; - bus->prop.freq = devm_kcalloc(bus->dev, sizeof(*bus->prop.freq), - bus->prop.num_freq, GFP_KERNEL); + bus->prop.freq = devm_kcalloc(bus->dev, bus->prop.num_freq, + sizeof(*bus->prop.freq), GFP_KERNEL); if (!bus->prop.freq) return -ENOMEM; From 7de8d238dd91dcb4c1200facdf7d510896927883 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 10 Apr 2019 22:16:59 -0500 Subject: [PATCH 077/255] soundwire: remove useless initializations No need for explicit initialization of page and ssp fields, they are already zeroed with a memset. Detected with cppcheck: [drivers/soundwire/bus.c:309]: (style) Variable 'msg->page' is reassigned a value before the old one has been used. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Takashi Iwai Signed-off-by: Vinod Koul --- drivers/soundwire/bus.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 1cbfedfc20ef..688848637099 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -271,8 +271,6 @@ int sdw_fill_msg(struct sdw_msg *msg, struct sdw_slave *slave, msg->dev_num = dev_num; msg->flags = flags; msg->buf = buf; - msg->ssp_sync = false; - msg->page = false; if (addr < SDW_REG_NO_PAGE) { /* no paging area */ return 0; From a25eab299165927a4e187bc40f20b549152779d9 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 10 Apr 2019 22:17:00 -0500 Subject: [PATCH 078/255] soundwire: stream: remove useless initialization of local variable no need to reset return value. Detected with cppcheck: [drivers/soundwire/stream.c:332]: (style) Variable 'ret' is assigned a value that is never used. Signed-off-by: Pierre-Louis Bossart Reviewed-by: Takashi Iwai Signed-off-by: Vinod Koul --- drivers/soundwire/stream.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index bd879b1a76c8..63b162feecfc 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -327,7 +327,7 @@ static int sdw_enable_disable_master_ports(struct sdw_master_runtime *m_rt, struct sdw_transport_params *t_params = &p_rt->transport_params; struct sdw_bus *bus = m_rt->bus; struct sdw_enable_ch enable_ch; - int ret = 0; + int ret; enable_ch.port_num = p_rt->num; enable_ch.ch_mask = p_rt->ch_mask; From 4abbd783d126cabfc20d1b8d50b1d5026b5cba09 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Sat, 13 Apr 2019 11:12:52 -0400 Subject: [PATCH 079/255] soundwire: intel: fix implicit header use of module.h/export.h These two files are implicitly relying on an instance of including module.h from . Ideally, header files under include/linux shouldn't be adding includes of other headers, in anticipation of their consumers, but just the headers needed for the header itself to pass parsing with CPP. The module.h is particularly bad in this sense, as it itself does include a whole bunch of other headers, due to the complexity of module support. Here, we make those includes explicit, in order to allow a future removal of module.h from linux/acpi.h without causing build breakage. Cc: Vinod Koul Cc: Sanyog Kale Cc: Pierre-Louis Bossart Signed-off-by: Paul Gortmaker Signed-off-by: Vinod Koul --- drivers/soundwire/intel.c | 1 + drivers/soundwire/intel_init.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 8669b314c476..70ca27ccad85 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -7,6 +7,7 @@ #include #include +#include #include #include #include diff --git a/drivers/soundwire/intel_init.c b/drivers/soundwire/intel_init.c index 5c8a20d99878..e0f2903101c7 100644 --- a/drivers/soundwire/intel_init.c +++ b/drivers/soundwire/intel_init.c @@ -8,6 +8,8 @@ */ #include +#include +#include #include #include #include "intel.h" From 9872760eb7b1d4f6066ad8b560714a5d0a728fdb Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 28 Sep 2018 12:21:17 +0300 Subject: [PATCH 080/255] net: thunderbolt: Unregister ThunderboltIP protocol handler when suspending The XDomain protocol messages may start as soon as Thunderbolt control channel is started. This means that if the other host starts sending ThunderboltIP packets early enough they will be passed to the network driver which then gets confused because its resume hook is not called yet. Fix this by unregistering the ThunderboltIP protocol handler when suspending and registering it back on resume. Signed-off-by: Mika Westerberg Acked-by: David S. Miller --- drivers/net/thunderbolt.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c index c48c3a1eb1f8..fcf31335a8b6 100644 --- a/drivers/net/thunderbolt.c +++ b/drivers/net/thunderbolt.c @@ -1282,6 +1282,7 @@ static int __maybe_unused tbnet_suspend(struct device *dev) tbnet_tear_down(net, true); } + tb_unregister_protocol_handler(&net->handler); return 0; } @@ -1290,6 +1291,8 @@ static int __maybe_unused tbnet_resume(struct device *dev) struct tb_service *svc = tb_to_service(dev); struct tbnet *net = tb_service_get_drvdata(svc); + tb_register_protocol_handler(&net->handler); + netif_carrier_off(net->dev); if (netif_running(net->dev)) { netif_device_attach(net->dev); From a336b62769499202f27ed2c3b6b28bb44ba9bab8 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 28 Mar 2019 11:59:26 +0300 Subject: [PATCH 081/255] thunderbolt: Remove unused work field in struct tb_switch This field is not used anywhere so remove it. Reported-by: Lukas Wunner Signed-off-by: Mika Westerberg --- drivers/thunderbolt/tb.h | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 52584c4003e3..8058ea02d572 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -70,7 +70,6 @@ struct tb_switch_nvm { * @boot: Whether the switch was already authorized on boot or not * @rpm: The switch supports runtime PM * @authorized: Whether the switch is authorized by user or policy - * @work: Work used to automatically authorize a switch * @security_level: Switch supported security level * @key: Contains the key used to challenge the device or %NULL if not * supported. Size of the key is %TB_SWITCH_KEY_SIZE. @@ -105,7 +104,6 @@ struct tb_switch { bool boot; bool rpm; unsigned int authorized; - struct work_struct work; enum tb_security_level security_level; u8 *key; u8 connection_id; From 8f965efd215a09c20b0b5e5bb4e20009a954472e Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 15 Mar 2019 14:56:21 +0200 Subject: [PATCH 082/255] thunderbolt: Drop duplicated get_switch_at_route() tb_switch_find_by_route() does the same already so use it instead and remove duplicated get_switch_at_route(). Signed-off-by: Mika Westerberg Reviewed-by: Lukas Wunner --- drivers/thunderbolt/icm.c | 12 ++++++++---- drivers/thunderbolt/switch.c | 18 ------------------ drivers/thunderbolt/tb.c | 9 ++++++--- drivers/thunderbolt/tb.h | 1 - 4 files changed, 14 insertions(+), 26 deletions(-) diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index 8b7f9131e9d1..7c923e16a7d8 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -798,9 +798,11 @@ icm_fr_xdomain_connected(struct tb *tb, const struct icm_pkg_header *hdr) * connected another host to the same port, remove the switch * first. */ - sw = get_switch_at_route(tb->root_switch, route); - if (sw) + sw = tb_switch_find_by_route(tb, route); + if (sw) { remove_switch(sw); + tb_switch_put(sw); + } sw = tb_switch_find_by_link_depth(tb, link, depth); if (!sw) { @@ -1143,9 +1145,11 @@ icm_tr_xdomain_connected(struct tb *tb, const struct icm_pkg_header *hdr) * connected another host to the same port, remove the switch * first. */ - sw = get_switch_at_route(tb->root_switch, route); - if (sw) + sw = tb_switch_find_by_route(tb, route); + if (sw) { remove_switch(sw); + tb_switch_put(sw); + } sw = tb_switch_find_by_route(tb, get_parent_route(route)); if (!sw) { diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 504365d46827..5c2c0201ae7f 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -644,24 +644,6 @@ int tb_switch_reset(struct tb *tb, u64 route) return res.err; } -struct tb_switch *get_switch_at_route(struct tb_switch *sw, u64 route) -{ - u8 next_port = route; /* - * Routes use a stride of 8 bits, - * eventhough a port index has 6 bits at most. - * */ - if (route == 0) - return sw; - if (next_port > sw->config.max_port_number) - return NULL; - if (tb_is_upstream_port(&sw->ports[next_port])) - return NULL; - if (!sw->ports[next_port].remote) - return NULL; - return get_switch_at_route(sw->ports[next_port].remote->sw, - route >> TB_ROUTE_SHIFT); -} - /** * tb_plug_events_active() - enable/disable plug events on a switch * diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 30e02c716f6c..d8f4ed0f2ef8 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -258,7 +258,7 @@ static void tb_handle_hotplug(struct work_struct *work) if (!tcm->hotplug_active) goto out; /* during init, suspend or shutdown */ - sw = get_switch_at_route(tb->root_switch, ev->route); + sw = tb_switch_find_by_route(tb, ev->route); if (!sw) { tb_warn(tb, "hotplug event from non existent switch %llx:%x (unplug: %d)\n", @@ -269,14 +269,14 @@ static void tb_handle_hotplug(struct work_struct *work) tb_warn(tb, "hotplug event from non existent port %llx:%x (unplug: %d)\n", ev->route, ev->port, ev->unplug); - goto out; + goto put_sw; } port = &sw->ports[ev->port]; if (tb_is_upstream_port(port)) { tb_warn(tb, "hotplug event for upstream port %llx:%x (unplug: %d)\n", ev->route, ev->port, ev->unplug); - goto out; + goto put_sw; } if (ev->unplug) { if (port->remote) { @@ -306,6 +306,9 @@ static void tb_handle_hotplug(struct work_struct *work) tb_activate_pcie_devices(tb); } } + +put_sw: + tb_switch_put(sw); out: mutex_unlock(&tb->lock); kfree(ev); diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 8058ea02d572..aea668c40d27 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -399,7 +399,6 @@ void tb_switch_suspend(struct tb_switch *sw); int tb_switch_resume(struct tb_switch *sw); int tb_switch_reset(struct tb *tb, u64 route); void tb_sw_set_unplugged(struct tb_switch *sw); -struct tb_switch *get_switch_at_route(struct tb_switch *sw, u64 route); struct tb_switch *tb_switch_find_by_link_depth(struct tb *tb, u8 link, u8 depth); struct tb_switch *tb_switch_find_by_uuid(struct tb *tb, const uuid_t *uuid); From 4708384f35ff6e5aac3dd70555f8765ecf9b6d56 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Tue, 19 Mar 2019 17:07:37 +0200 Subject: [PATCH 083/255] thunderbolt: Block reads and writes if switch is unplugged If switch is already disconnected there is no point sending it commands and waiting for timeout. Instead in that case return error immediately. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/tb.h | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index aea668c40d27..496dcd03ede1 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -277,6 +277,8 @@ static inline struct tb_port *tb_port_at(u64 route, struct tb_switch *sw) static inline int tb_sw_read(struct tb_switch *sw, void *buffer, enum tb_cfg_space space, u32 offset, u32 length) { + if (sw->is_unplugged) + return -ENODEV; return tb_cfg_read(sw->tb->ctl, buffer, tb_route(sw), @@ -289,6 +291,8 @@ static inline int tb_sw_read(struct tb_switch *sw, void *buffer, static inline int tb_sw_write(struct tb_switch *sw, void *buffer, enum tb_cfg_space space, u32 offset, u32 length) { + if (sw->is_unplugged) + return -ENODEV; return tb_cfg_write(sw->tb->ctl, buffer, tb_route(sw), @@ -301,6 +305,8 @@ static inline int tb_sw_write(struct tb_switch *sw, void *buffer, static inline int tb_port_read(struct tb_port *port, void *buffer, enum tb_cfg_space space, u32 offset, u32 length) { + if (port->sw->is_unplugged) + return -ENODEV; return tb_cfg_read(port->sw->tb->ctl, buffer, tb_route(port->sw), @@ -313,6 +319,8 @@ static inline int tb_port_read(struct tb_port *port, void *buffer, static inline int tb_port_write(struct tb_port *port, const void *buffer, enum tb_cfg_space space, u32 offset, u32 length) { + if (port->sw->is_unplugged) + return -ENODEV; return tb_cfg_write(port->sw->tb->ctl, buffer, tb_route(port->sw), From 09f11b6c99feaf86a26444bca85dc693b3f58f8b Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Tue, 19 Mar 2019 16:48:41 +0200 Subject: [PATCH 084/255] thunderbolt: Take domain lock in switch sysfs attribute callbacks switch_lock was introduced because it allowed serialization of device authorization requests from userspace without need to take the big domain lock (tb->lock). This was fine because device authorization with ICM is just one command that is sent to the firmware. Now that we start to handle all tunneling in the driver switch_lock is not enough because we need to walk over the topology to establish paths. For this reason drop switch_lock from the driver completely in favour of big domain lock. There is one complication, though. If userspace is waiting for the lock in tb_switch_set_authorized(), it keeps the device_del() from removing the sysfs attribute because it waits for active users to release the attribute first which leads into following splat: INFO: task kworker/u8:3:73 blocked for more than 61 seconds. Tainted: G W 5.1.0-rc1+ #244 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/u8:3 D12976 73 2 0x80000000 Workqueue: thunderbolt0 tb_handle_hotplug [thunderbolt] Call Trace: ? __schedule+0x2e5/0x740 ? _raw_spin_lock_irqsave+0x12/0x40 ? prepare_to_wait_event+0xc5/0x160 schedule+0x2d/0x80 __kernfs_remove.part.17+0x183/0x1f0 ? finish_wait+0x80/0x80 kernfs_remove_by_name_ns+0x4a/0x90 remove_files.isra.1+0x2b/0x60 sysfs_remove_group+0x38/0x80 sysfs_remove_groups+0x24/0x40 device_remove_attrs+0x3d/0x70 device_del+0x14c/0x360 device_unregister+0x15/0x50 tb_switch_remove+0x9e/0x1d0 [thunderbolt] tb_handle_hotplug+0x119/0x5a0 [thunderbolt] ? process_one_work+0x1b7/0x420 process_one_work+0x1b7/0x420 worker_thread+0x37/0x380 ? _raw_spin_unlock_irqrestore+0xf/0x30 ? process_one_work+0x420/0x420 kthread+0x118/0x130 ? kthread_create_on_node+0x60/0x60 ret_from_fork+0x35/0x40 We deal this by following what network stack did for some of their attributes and use mutex_trylock() with restart_syscall(). This makes userspace release the attribute allowing sysfs attribute removal to progress before the write is restarted and eventually fail when the attribute is removed. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/switch.c | 45 +++++++++++++++--------------------- drivers/thunderbolt/tb.h | 3 +-- 2 files changed, 20 insertions(+), 28 deletions(-) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 5c2c0201ae7f..7fa4ab076404 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -10,15 +10,13 @@ #include #include #include +#include #include #include #include #include "tb.h" -/* Switch authorization from userspace is serialized by this lock */ -static DEFINE_MUTEX(switch_lock); - /* Switch NVM support */ #define NVM_DEVID 0x05 @@ -254,8 +252,8 @@ static int tb_switch_nvm_write(void *priv, unsigned int offset, void *val, struct tb_switch *sw = priv; int ret = 0; - if (mutex_lock_interruptible(&switch_lock)) - return -ERESTARTSYS; + if (!mutex_trylock(&sw->tb->lock)) + return restart_syscall(); /* * Since writing the NVM image might require some special steps, @@ -275,7 +273,7 @@ static int tb_switch_nvm_write(void *priv, unsigned int offset, void *val, memcpy(sw->nvm->buf + offset, val, bytes); unlock: - mutex_unlock(&switch_lock); + mutex_unlock(&sw->tb->lock); return ret; } @@ -364,10 +362,7 @@ static int tb_switch_nvm_add(struct tb_switch *sw) } nvm->non_active = nvm_dev; - mutex_lock(&switch_lock); sw->nvm = nvm; - mutex_unlock(&switch_lock); - return 0; err_nvm_active: @@ -384,10 +379,8 @@ static void tb_switch_nvm_remove(struct tb_switch *sw) { struct tb_switch_nvm *nvm; - mutex_lock(&switch_lock); nvm = sw->nvm; sw->nvm = NULL; - mutex_unlock(&switch_lock); if (!nvm) return; @@ -698,8 +691,8 @@ static int tb_switch_set_authorized(struct tb_switch *sw, unsigned int val) { int ret = -EINVAL; - if (mutex_lock_interruptible(&switch_lock)) - return -ERESTARTSYS; + if (!mutex_trylock(&sw->tb->lock)) + return restart_syscall(); if (sw->authorized) goto unlock; @@ -742,7 +735,7 @@ static int tb_switch_set_authorized(struct tb_switch *sw, unsigned int val) } unlock: - mutex_unlock(&switch_lock); + mutex_unlock(&sw->tb->lock); return ret; } @@ -799,15 +792,15 @@ static ssize_t key_show(struct device *dev, struct device_attribute *attr, struct tb_switch *sw = tb_to_switch(dev); ssize_t ret; - if (mutex_lock_interruptible(&switch_lock)) - return -ERESTARTSYS; + if (!mutex_trylock(&sw->tb->lock)) + return restart_syscall(); if (sw->key) ret = sprintf(buf, "%*phN\n", TB_SWITCH_KEY_SIZE, sw->key); else ret = sprintf(buf, "\n"); - mutex_unlock(&switch_lock); + mutex_unlock(&sw->tb->lock); return ret; } @@ -824,8 +817,8 @@ static ssize_t key_store(struct device *dev, struct device_attribute *attr, else if (hex2bin(key, buf, sizeof(key))) return -EINVAL; - if (mutex_lock_interruptible(&switch_lock)) - return -ERESTARTSYS; + if (!mutex_trylock(&sw->tb->lock)) + return restart_syscall(); if (sw->authorized) { ret = -EBUSY; @@ -840,7 +833,7 @@ static ssize_t key_store(struct device *dev, struct device_attribute *attr, } } - mutex_unlock(&switch_lock); + mutex_unlock(&sw->tb->lock); return ret; } static DEVICE_ATTR(key, 0600, key_show, key_store); @@ -886,8 +879,8 @@ static ssize_t nvm_authenticate_store(struct device *dev, bool val; int ret; - if (mutex_lock_interruptible(&switch_lock)) - return -ERESTARTSYS; + if (!mutex_trylock(&sw->tb->lock)) + return restart_syscall(); /* If NVMem devices are not yet added */ if (!sw->nvm) { @@ -935,7 +928,7 @@ static ssize_t nvm_authenticate_store(struct device *dev, } exit_unlock: - mutex_unlock(&switch_lock); + mutex_unlock(&sw->tb->lock); if (ret) return ret; @@ -949,8 +942,8 @@ static ssize_t nvm_version_show(struct device *dev, struct tb_switch *sw = tb_to_switch(dev); int ret; - if (mutex_lock_interruptible(&switch_lock)) - return -ERESTARTSYS; + if (!mutex_trylock(&sw->tb->lock)) + return restart_syscall(); if (sw->safe_mode) ret = -ENODATA; @@ -959,7 +952,7 @@ static ssize_t nvm_version_show(struct device *dev, else ret = sprintf(buf, "%x.%x\n", sw->nvm->major, sw->nvm->minor); - mutex_unlock(&switch_lock); + mutex_unlock(&sw->tb->lock); return ret; } diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 496dcd03ede1..f7b0c43c29a7 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -79,8 +79,7 @@ struct tb_switch_nvm { * @depth: Depth in the chain this switch is connected (ICM only) * * When the switch is being added or removed to the domain (other - * switches) you need to have domain lock held. For switch authorization - * internal switch_lock is enough. + * switches) you need to have domain lock held. */ struct tb_switch { struct device dev; From f0342e757c271e7c6dd5adedfb6e6695c5af52bf Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sun, 30 Dec 2018 12:14:46 +0200 Subject: [PATCH 085/255] thunderbolt: Do not allocate switch if depth is greater than 6 Maximum depth in Thunderbolt topology is 6 so make sure it is not possible to allocate switches that exceed the depth limit. While at it update tb_switch_alloc() to use upper/lower_32_bits() following tb_switch_alloc_safe_mode(). Signed-off-by: Mika Westerberg --- drivers/thunderbolt/icm.c | 5 ++--- drivers/thunderbolt/switch.c | 18 ++++++++++++------ drivers/thunderbolt/tb.h | 1 + 3 files changed, 15 insertions(+), 9 deletions(-) diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index 7c923e16a7d8..bec360eef6cf 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -42,7 +42,6 @@ #define ICM_TIMEOUT 5000 /* ms */ #define ICM_APPROVE_TIMEOUT 10000 /* ms */ #define ICM_MAX_LINK 4 -#define ICM_MAX_DEPTH 6 /** * struct icm - Internal connection manager private data @@ -714,7 +713,7 @@ icm_fr_device_disconnected(struct tb *tb, const struct icm_pkg_header *hdr) depth = (pkg->link_info & ICM_LINK_INFO_DEPTH_MASK) >> ICM_LINK_INFO_DEPTH_SHIFT; - if (link > ICM_MAX_LINK || depth > ICM_MAX_DEPTH) { + if (link > ICM_MAX_LINK || depth > TB_SWITCH_MAX_DEPTH) { tb_warn(tb, "invalid topology %u.%u, ignoring\n", link, depth); return; } @@ -744,7 +743,7 @@ icm_fr_xdomain_connected(struct tb *tb, const struct icm_pkg_header *hdr) depth = (pkg->link_info & ICM_LINK_INFO_DEPTH_MASK) >> ICM_LINK_INFO_DEPTH_SHIFT; - if (link > ICM_MAX_LINK || depth > ICM_MAX_DEPTH) { + if (link > ICM_MAX_LINK || depth > TB_SWITCH_MAX_DEPTH) { tb_warn(tb, "invalid topology %u.%u, ignoring\n", link, depth); return; } diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 7fa4ab076404..1e29c06947af 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -1130,10 +1130,16 @@ static int tb_switch_get_generation(struct tb_switch *sw) struct tb_switch *tb_switch_alloc(struct tb *tb, struct device *parent, u64 route) { - int i; - int cap; struct tb_switch *sw; - int upstream_port = tb_cfg_get_upstream_port(tb->ctl, route); + int upstream_port; + int i, cap, depth; + + /* Make sure we do not exceed maximum topology limit */ + depth = tb_route_length(route); + if (depth > TB_SWITCH_MAX_DEPTH) + return NULL; + + upstream_port = tb_cfg_get_upstream_port(tb->ctl, route); if (upstream_port < 0) return NULL; @@ -1150,9 +1156,9 @@ struct tb_switch *tb_switch_alloc(struct tb *tb, struct device *parent, /* configure switch */ sw->config.upstream_port_number = upstream_port; - sw->config.depth = tb_route_length(route); - sw->config.route_lo = route; - sw->config.route_hi = route >> 32; + sw->config.depth = depth; + sw->config.route_hi = upper_32_bits(route); + sw->config.route_lo = lower_32_bits(route); sw->config.enabled = 0; /* initialize ports */ diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index f7b0c43c29a7..93c1ea21feeb 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -43,6 +43,7 @@ struct tb_switch_nvm { }; #define TB_SWITCH_KEY_SIZE 32 +#define TB_SWITCH_MAX_DEPTH 6 /** * struct tb_switch - a thunderbolt switch From 8b0110d9d10d211fc8a0e2cbb2db4533af30d36e Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Tue, 8 Jan 2019 18:55:09 +0200 Subject: [PATCH 086/255] thunderbolt: Enable TMU access when accessing port space on legacy devices Light Ridge and Eagle Ridge both need to have TMU access enabled before port space can be fully accessed so make sure it happens on those. This allows us to get rid of the offset quirk in tb_port_find_cap(). Signed-off-by: Mika Westerberg --- drivers/thunderbolt/cap.c | 69 +++++++++++++++++++++++++++++---------- drivers/thunderbolt/tb.h | 10 ++++++ 2 files changed, 62 insertions(+), 17 deletions(-) diff --git a/drivers/thunderbolt/cap.c b/drivers/thunderbolt/cap.c index 9553305c63ea..a58585b4e6d9 100644 --- a/drivers/thunderbolt/cap.c +++ b/drivers/thunderbolt/cap.c @@ -13,6 +13,7 @@ #define CAP_OFFSET_MAX 0xff #define VSE_CAP_OFFSET_MAX 0xffff +#define TMU_ACCESS_EN BIT(20) struct tb_cap_any { union { @@ -22,28 +23,38 @@ struct tb_cap_any { }; } __packed; -/** - * tb_port_find_cap() - Find port capability - * @port: Port to find the capability for - * @cap: Capability to look - * - * Returns offset to start of capability or %-ENOENT if no such - * capability was found. Negative errno is returned if there was an - * error. - */ -int tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap) +static int tb_port_enable_tmu(struct tb_port *port, bool enable) { - u32 offset; + struct tb_switch *sw = port->sw; + u32 value, offset; + int ret; /* - * DP out adapters claim to implement TMU capability but in - * reality they do not so we hard code the adapter specific - * capability offset here. + * Legacy devices need to have TMU access enabled before port + * space can be fully accessed. */ - if (port->config.type == TB_TYPE_DP_HDMI_OUT) - offset = 0x39; + if (tb_switch_is_lr(sw)) + offset = 0x26; + else if (tb_switch_is_er(sw)) + offset = 0x2a; else - offset = 0x1; + return 0; + + ret = tb_sw_read(sw, &value, TB_CFG_SWITCH, offset, 1); + if (ret) + return ret; + + if (enable) + value |= TMU_ACCESS_EN; + else + value &= ~TMU_ACCESS_EN; + + return tb_sw_write(sw, &value, TB_CFG_SWITCH, offset, 1); +} + +static int __tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap) +{ + u32 offset = 1; do { struct tb_cap_any header; @@ -62,6 +73,30 @@ int tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap) return -ENOENT; } +/** + * tb_port_find_cap() - Find port capability + * @port: Port to find the capability for + * @cap: Capability to look + * + * Returns offset to start of capability or %-ENOENT if no such + * capability was found. Negative errno is returned if there was an + * error. + */ +int tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap) +{ + int ret; + + ret = tb_port_enable_tmu(port, true); + if (ret) + return ret; + + ret = __tb_port_find_cap(port, cap); + + tb_port_enable_tmu(port, false); + + return ret; +} + static int tb_switch_find_cap(struct tb_switch *sw, enum tb_switch_cap cap) { int offset = sw->config.first_cap_offset; diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 93c1ea21feeb..a166265dfcf9 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -436,6 +436,16 @@ static inline struct tb_switch *tb_to_switch(struct device *dev) return NULL; } +static inline bool tb_switch_is_lr(const struct tb_switch *sw) +{ + return sw->config.device_id == PCI_DEVICE_ID_INTEL_LIGHT_RIDGE; +} + +static inline bool tb_switch_is_er(const struct tb_switch *sw) +{ + return sw->config.device_id == PCI_DEVICE_ID_INTEL_EAGLE_RIDGE; +} + int tb_wait_for_port(struct tb_port *port, bool wait_if_unplugged); int tb_port_add_nfc_credits(struct tb_port *port, int credits); int tb_port_clear_counter(struct tb_port *port, int counter); From ffd003b2f8cba8dde0f7259e2207d63f75691096 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Tue, 8 Jan 2019 19:08:06 +0200 Subject: [PATCH 087/255] thunderbolt: Add dummy read after port capability list walk on Light Ridge Light Ridge has an issue where reading the next capability pointer location in port config space the read data is not cleared. It is fine to read capabilities each after another so only thing we need to do is to make sure we issue dummy read after tb_port_find_cap() is finished to avoid the issue in next read. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/cap.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/thunderbolt/cap.c b/drivers/thunderbolt/cap.c index a58585b4e6d9..8bf8e031f0bc 100644 --- a/drivers/thunderbolt/cap.c +++ b/drivers/thunderbolt/cap.c @@ -52,6 +52,21 @@ static int tb_port_enable_tmu(struct tb_port *port, bool enable) return tb_sw_write(sw, &value, TB_CFG_SWITCH, offset, 1); } +static void tb_port_dummy_read(struct tb_port *port) +{ + /* + * When reading from next capability pointer location in port + * config space the read data is not cleared on LR. To avoid + * reading stale data on next read perform one dummy read after + * port capabilities are walked. + */ + if (tb_switch_is_lr(port->sw)) { + u32 dummy; + + tb_port_read(port, &dummy, TB_CFG_PORT, 0, 1); + } +} + static int __tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap) { u32 offset = 1; @@ -92,6 +107,7 @@ int tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap) ret = __tb_port_find_cap(port, cap); + tb_port_dummy_read(port); tb_port_enable_tmu(port, false); return ret; From a9be55824a10653d0247de12dc6b9a741ce3fc98 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 9 Jan 2019 16:42:12 +0200 Subject: [PATCH 088/255] thunderbolt: Move LC specific functionality into a separate file We will be adding more link controller functionality in subsequent patches and it does not make sense to keep all that in switch.c, so separate LC functionality into its own file. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/Makefile | 2 +- drivers/thunderbolt/lc.c | 21 +++++++++++++++++++++ drivers/thunderbolt/switch.c | 21 ++++++++++----------- drivers/thunderbolt/tb.h | 3 +++ drivers/thunderbolt/tb_regs.h | 2 ++ 5 files changed, 37 insertions(+), 12 deletions(-) create mode 100644 drivers/thunderbolt/lc.c diff --git a/drivers/thunderbolt/Makefile b/drivers/thunderbolt/Makefile index f2f0de27252b..8531f15d3b3c 100644 --- a/drivers/thunderbolt/Makefile +++ b/drivers/thunderbolt/Makefile @@ -1,3 +1,3 @@ obj-${CONFIG_THUNDERBOLT} := thunderbolt.o thunderbolt-objs := nhi.o ctl.o tb.o switch.o cap.o path.o tunnel_pci.o eeprom.o -thunderbolt-objs += domain.o dma_port.o icm.o property.o xdomain.o +thunderbolt-objs += domain.o dma_port.o icm.o property.o xdomain.o lc.o diff --git a/drivers/thunderbolt/lc.c b/drivers/thunderbolt/lc.c new file mode 100644 index 000000000000..2134a55ed837 --- /dev/null +++ b/drivers/thunderbolt/lc.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Thunderbolt link controller support + * + * Copyright (C) 2019, Intel Corporation + * Author: Mika Westerberg + */ + +#include "tb.h" + +/** + * tb_lc_read_uuid() - Read switch UUID from link controller common register + * @sw: Switch whose UUID is read + * @uuid: UUID is placed here + */ +int tb_lc_read_uuid(struct tb_switch *sw, u32 *uuid) +{ + if (!sw->cap_lc) + return -EINVAL; + return tb_sw_read(sw, uuid, TB_CFG_SWITCH, sw->cap_lc + TB_LC_FUSE, 4); +} diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 1e29c06947af..63ff4c753d89 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -1182,6 +1182,10 @@ struct tb_switch *tb_switch_alloc(struct tb *tb, struct device *parent, } sw->cap_plug_events = cap; + cap = tb_switch_find_vse_cap(sw, TB_VSE_CAP_LINK_CONTROLLER); + if (cap > 0) + sw->cap_lc = cap; + /* Root switch is always authorized */ if (!route) sw->authorized = true; @@ -1278,22 +1282,17 @@ int tb_switch_configure(struct tb_switch *sw) static int tb_switch_set_uuid(struct tb_switch *sw) { u32 uuid[4]; - int cap, ret; + int ret; - ret = 0; if (sw->uuid) - return ret; + return 0; /* * The newer controllers include fused UUID as part of link * controller specific registers */ - cap = tb_switch_find_vse_cap(sw, TB_VSE_CAP_LINK_CONTROLLER); - if (cap > 0) { - ret = tb_sw_read(sw, uuid, TB_CFG_SWITCH, cap + 3, 4); - if (ret) - return ret; - } else { + ret = tb_lc_read_uuid(sw, uuid); + if (ret) { /* * ICM generates UUID based on UID and fills the upper * two words with ones. This is not strictly following @@ -1308,8 +1307,8 @@ static int tb_switch_set_uuid(struct tb_switch *sw) sw->uuid = kmemdup(uuid, sizeof(uuid), GFP_KERNEL); if (!sw->uuid) - ret = -ENOMEM; - return ret; + return -ENOMEM; + return 0; } static int tb_switch_add_dma_port(struct tb_switch *sw) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index a166265dfcf9..e52d39b25266 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -63,6 +63,7 @@ struct tb_switch_nvm { * @device_name: Name of the device (or %NULL if not known) * @generation: Switch Thunderbolt generation * @cap_plug_events: Offset to the plug events capability (%0 if not found) + * @cap_lc: Offset to the link controller capability (%0 if not found) * @is_unplugged: The switch is going away * @drom: DROM of the switch (%NULL if not found) * @nvm: Pointer to the NVM if the switch has one (%NULL otherwise) @@ -96,6 +97,7 @@ struct tb_switch { const char *device_name; unsigned int generation; int cap_plug_events; + int cap_lc; bool is_unplugged; u8 *drom; struct tb_switch_nvm *nvm; @@ -462,6 +464,7 @@ bool tb_path_is_invalid(struct tb_path *path); int tb_drom_read(struct tb_switch *sw); int tb_drom_read_uid_only(struct tb_switch *sw, u64 *uid); +int tb_lc_read_uuid(struct tb_switch *sw, u32 *uuid); static inline int tb_route_length(u64 route) { diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h index 6f1ff04ee195..4895ae9f0b40 100644 --- a/drivers/thunderbolt/tb_regs.h +++ b/drivers/thunderbolt/tb_regs.h @@ -237,5 +237,7 @@ struct tb_regs_hop { u32 unknown3:4; /* set to zero */ } __packed; +/* Common link controller registers */ +#define TB_LC_FUSE 0x03 #endif From e879a709de0210802ba14243a168d632cb7ab527 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 11 Oct 2018 12:33:08 +0300 Subject: [PATCH 089/255] thunderbolt: Configure lanes when switch is initialized Thunderbolt 2 devices and beyond need to have additional bits set in link controller specific registers. This includes two bits in LC_SX_CTRL that tell the link controller which lane is connected and whether it is upstream facing or not. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/lc.c | 114 ++++++++++++++++++++++++++++++++++ drivers/thunderbolt/switch.c | 9 +++ drivers/thunderbolt/tb.h | 2 + drivers/thunderbolt/tb_regs.h | 11 ++++ 4 files changed, 136 insertions(+) diff --git a/drivers/thunderbolt/lc.c b/drivers/thunderbolt/lc.c index 2134a55ed837..a5dddf176546 100644 --- a/drivers/thunderbolt/lc.c +++ b/drivers/thunderbolt/lc.c @@ -19,3 +19,117 @@ int tb_lc_read_uuid(struct tb_switch *sw, u32 *uuid) return -EINVAL; return tb_sw_read(sw, uuid, TB_CFG_SWITCH, sw->cap_lc + TB_LC_FUSE, 4); } + +static int read_lc_desc(struct tb_switch *sw, u32 *desc) +{ + if (!sw->cap_lc) + return -EINVAL; + return tb_sw_read(sw, desc, TB_CFG_SWITCH, sw->cap_lc + TB_LC_DESC, 1); +} + +static int find_port_lc_cap(struct tb_port *port) +{ + struct tb_switch *sw = port->sw; + int start, phys, ret, size; + u32 desc; + + ret = read_lc_desc(sw, &desc); + if (ret) + return ret; + + /* Start of port LC registers */ + start = (desc & TB_LC_DESC_SIZE_MASK) >> TB_LC_DESC_SIZE_SHIFT; + size = (desc & TB_LC_DESC_PORT_SIZE_MASK) >> TB_LC_DESC_PORT_SIZE_SHIFT; + phys = tb_phy_port_from_link(port->port); + + return sw->cap_lc + start + phys * size; +} + +static int tb_lc_configure_lane(struct tb_port *port, bool configure) +{ + bool upstream = tb_is_upstream_port(port); + struct tb_switch *sw = port->sw; + u32 ctrl, lane; + int cap, ret; + + if (sw->generation < 2) + return 0; + + cap = find_port_lc_cap(port); + if (cap < 0) + return cap; + + ret = tb_sw_read(sw, &ctrl, TB_CFG_SWITCH, cap + TB_LC_SX_CTRL, 1); + if (ret) + return ret; + + /* Resolve correct lane */ + if (port->port % 2) + lane = TB_LC_SX_CTRL_L1C; + else + lane = TB_LC_SX_CTRL_L2C; + + if (configure) { + ctrl |= lane; + if (upstream) + ctrl |= TB_LC_SX_CTRL_UPSTREAM; + } else { + ctrl &= ~lane; + if (upstream) + ctrl &= ~TB_LC_SX_CTRL_UPSTREAM; + } + + return tb_sw_write(sw, &ctrl, TB_CFG_SWITCH, cap + TB_LC_SX_CTRL, 1); +} + +/** + * tb_lc_configure_link() - Let LC know about configured link + * @sw: Switch that is being added + * + * Informs LC of both parent switch and @sw that there is established + * link between the two. + */ +int tb_lc_configure_link(struct tb_switch *sw) +{ + struct tb_port *up, *down; + int ret; + + if (!sw->config.enabled || !tb_route(sw)) + return 0; + + up = tb_upstream_port(sw); + down = tb_port_at(tb_route(sw), tb_to_switch(sw->dev.parent)); + + /* Configure parent link toward this switch */ + ret = tb_lc_configure_lane(down, true); + if (ret) + return ret; + + /* Configure upstream link from this switch to the parent */ + ret = tb_lc_configure_lane(up, true); + if (ret) + tb_lc_configure_lane(down, false); + + return ret; +} + +/** + * tb_lc_unconfigure_link() - Let LC know about unconfigured link + * @sw: Switch to unconfigure + * + * Informs LC of both parent switch and @sw that the link between the + * two does not exist anymore. + */ +void tb_lc_unconfigure_link(struct tb_switch *sw) +{ + struct tb_port *up, *down; + + if (sw->is_unplugged || !sw->config.enabled || !tb_route(sw)) + return; + + up = tb_upstream_port(sw); + down = tb_port_at(tb_route(sw), tb_to_switch(sw->dev.parent)); + + tb_lc_configure_lane(up, false); + tb_lc_configure_lane(down, false); +} diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 63ff4c753d89..dd218dc4781b 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -1276,6 +1276,10 @@ int tb_switch_configure(struct tb_switch *sw) if (ret) return ret; + ret = tb_lc_configure_link(sw); + if (ret) + return ret; + return tb_plug_events_active(sw, true); } @@ -1486,6 +1490,7 @@ void tb_switch_remove(struct tb_switch *sw) if (!sw->is_unplugged) tb_plug_events_active(sw, false); + tb_lc_unconfigure_link(sw); tb_switch_nvm_remove(sw); @@ -1545,6 +1550,10 @@ int tb_switch_resume(struct tb_switch *sw) if (err) return err; + err = tb_lc_configure_link(sw); + if (err) + return err; + err = tb_plug_events_active(sw, true); if (err) return err; diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index e52d39b25266..69e0534224d8 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -465,6 +465,8 @@ int tb_drom_read(struct tb_switch *sw); int tb_drom_read_uid_only(struct tb_switch *sw, u64 *uid); int tb_lc_read_uuid(struct tb_switch *sw, u32 *uuid); +int tb_lc_configure_link(struct tb_switch *sw); +void tb_lc_unconfigure_link(struct tb_switch *sw); static inline int tb_route_length(u64 route) { diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h index 4895ae9f0b40..e0f867dad5cf 100644 --- a/drivers/thunderbolt/tb_regs.h +++ b/drivers/thunderbolt/tb_regs.h @@ -238,6 +238,17 @@ struct tb_regs_hop { } __packed; /* Common link controller registers */ +#define TB_LC_DESC 0x02 +#define TB_LC_DESC_SIZE_SHIFT 8 +#define TB_LC_DESC_SIZE_MASK GENMASK(15, 8) +#define TB_LC_DESC_PORT_SIZE_SHIFT 16 +#define TB_LC_DESC_PORT_SIZE_MASK GENMASK(27, 16) #define TB_LC_FUSE 0x03 +/* Link controller registers */ +#define TB_LC_SX_CTRL 0x96 +#define TB_LC_SX_CTRL_L1C BIT(16) +#define TB_LC_SX_CTRL_L2C BIT(20) +#define TB_LC_SX_CTRL_UPSTREAM BIT(30) + #endif From 5480dfc275aa7e5f892505ce082d71635d6a22f8 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 9 Jan 2019 17:25:43 +0200 Subject: [PATCH 090/255] thunderbolt: Set sleep bit when suspending switch Thunderbolt 2 devices and beyond link controller needs to be notified when a switch is going to be suspended by setting bit 31 in LC_SX_CTRL register. Add this functionality to the software connection manager. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/lc.c | 44 +++++++++++++++++++++++++++++++++++ drivers/thunderbolt/switch.c | 6 ++--- drivers/thunderbolt/tb.h | 1 + drivers/thunderbolt/tb_regs.h | 2 ++ 4 files changed, 49 insertions(+), 4 deletions(-) diff --git a/drivers/thunderbolt/lc.c b/drivers/thunderbolt/lc.c index a5dddf176546..ae1e92611c3e 100644 --- a/drivers/thunderbolt/lc.c +++ b/drivers/thunderbolt/lc.c @@ -133,3 +133,47 @@ void tb_lc_unconfigure_link(struct tb_switch *sw) tb_lc_configure_lane(up, false); tb_lc_configure_lane(down, false); } + +/** + * tb_lc_set_sleep() - Inform LC that the switch is going to sleep + * @sw: Switch to set sleep + * + * Let the switch link controllers know that the switch is going to + * sleep. + */ +int tb_lc_set_sleep(struct tb_switch *sw) +{ + int start, size, nlc, ret, i; + u32 desc; + + if (sw->generation < 2) + return 0; + + ret = read_lc_desc(sw, &desc); + if (ret) + return ret; + + /* Figure out number of link controllers */ + nlc = desc & TB_LC_DESC_NLC_MASK; + start = (desc & TB_LC_DESC_SIZE_MASK) >> TB_LC_DESC_SIZE_SHIFT; + size = (desc & TB_LC_DESC_PORT_SIZE_MASK) >> TB_LC_DESC_PORT_SIZE_SHIFT; + + /* For each link controller set sleep bit */ + for (i = 0; i < nlc; i++) { + unsigned int offset = sw->cap_lc + start + i * size; + u32 ctrl; + + ret = tb_sw_read(sw, &ctrl, TB_CFG_SWITCH, + offset + TB_LC_SX_CTRL, 1); + if (ret) + return ret; + + ctrl |= TB_LC_SX_CTRL_SLP; + ret = tb_sw_write(sw, &ctrl, TB_CFG_SWITCH, + offset + TB_LC_SX_CTRL, 1); + if (ret) + return ret; + } + + return 0; +} diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index dd218dc4781b..b3f93ebe6e39 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -1586,10 +1586,8 @@ void tb_switch_suspend(struct tb_switch *sw) if (!tb_is_upstream_port(&sw->ports[i]) && sw->ports[i].remote) tb_switch_suspend(sw->ports[i].remote->sw); } - /* - * TODO: invoke tb_cfg_prepare_to_sleep here? does not seem to have any - * effect? - */ + + tb_lc_set_sleep(sw); } struct tb_sw_lookup { diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 69e0534224d8..985a48a67a43 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -467,6 +467,7 @@ int tb_drom_read_uid_only(struct tb_switch *sw, u64 *uid); int tb_lc_read_uuid(struct tb_switch *sw, u32 *uuid); int tb_lc_configure_link(struct tb_switch *sw); void tb_lc_unconfigure_link(struct tb_switch *sw); +int tb_lc_set_sleep(struct tb_switch *sw); static inline int tb_route_length(u64 route) { diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h index e0f867dad5cf..1ab6e0fb31c0 100644 --- a/drivers/thunderbolt/tb_regs.h +++ b/drivers/thunderbolt/tb_regs.h @@ -239,6 +239,7 @@ struct tb_regs_hop { /* Common link controller registers */ #define TB_LC_DESC 0x02 +#define TB_LC_DESC_NLC_MASK GENMASK(3, 0) #define TB_LC_DESC_SIZE_SHIFT 8 #define TB_LC_DESC_SIZE_MASK GENMASK(15, 8) #define TB_LC_DESC_PORT_SIZE_SHIFT 16 @@ -250,5 +251,6 @@ struct tb_regs_hop { #define TB_LC_SX_CTRL_L1C BIT(16) #define TB_LC_SX_CTRL_L2C BIT(20) #define TB_LC_SX_CTRL_UPSTREAM BIT(30) +#define TB_LC_SX_CTRL_SLP BIT(31) #endif From 4944269305df09c719f9c406c20c255f1724542a Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 17 Feb 2017 17:05:37 +0200 Subject: [PATCH 091/255] thunderbolt: Properly disable path We need to wait until all buffers have been drained before the path can be considered disabled. Do this for every hop in a path. This adds another bit field to struct tb_regs_hop even if we are trying to get rid of them but we can clean them up another day. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/path.c | 47 ++++++++++++++++++++++++++++++++--- drivers/thunderbolt/tb_regs.h | 3 ++- 2 files changed, 45 insertions(+), 5 deletions(-) diff --git a/drivers/thunderbolt/path.c b/drivers/thunderbolt/path.c index a11956522bac..8c2e19a6117a 100644 --- a/drivers/thunderbolt/path.c +++ b/drivers/thunderbolt/path.c @@ -7,6 +7,8 @@ #include #include +#include +#include #include "tb.h" @@ -74,14 +76,51 @@ static void __tb_path_deallocate_nfc(struct tb_path *path, int first_hop) } } +static int __tb_path_deactivate_hop(struct tb_port *port, int hop_index) +{ + struct tb_regs_hop hop; + ktime_t timeout; + int ret; + + /* Disable the path */ + ret = tb_port_read(port, &hop, TB_CFG_HOPS, 2 * hop_index, 2); + if (ret) + return ret; + + /* Already disabled */ + if (!hop.enable) + return 0; + + hop.enable = 0; + + ret = tb_port_write(port, &hop, TB_CFG_HOPS, 2 * hop_index, 2); + if (ret) + return ret; + + /* Wait until it is drained */ + timeout = ktime_add_ms(ktime_get(), 500); + do { + ret = tb_port_read(port, &hop, TB_CFG_HOPS, 2 * hop_index, 2); + if (ret) + return ret; + + if (!hop.pending) + return 0; + + usleep_range(10, 20); + } while (ktime_before(ktime_get(), timeout)); + + return -ETIMEDOUT; +} + static void __tb_path_deactivate_hops(struct tb_path *path, int first_hop) { int i, res; - struct tb_regs_hop hop = { }; + for (i = first_hop; i < path->path_length; i++) { - res = tb_port_write(path->hops[i].in_port, &hop, TB_CFG_HOPS, - 2 * path->hops[i].in_hop_index, 2); - if (res) + res = __tb_path_deactivate_hop(path->hops[i].in_port, + path->hops[i].in_hop_index); + if (res && res != -ENODEV) tb_port_warn(path->hops[i].in_port, "hop deactivation failed for hop %d, index %d\n", i, path->hops[i].in_hop_index); diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h index 1ab6e0fb31c0..82ac4ec8757f 100644 --- a/drivers/thunderbolt/tb_regs.h +++ b/drivers/thunderbolt/tb_regs.h @@ -234,7 +234,8 @@ struct tb_regs_hop { bool egress_fc:1; bool ingress_shared_buffer:1; bool egress_shared_buffer:1; - u32 unknown3:4; /* set to zero */ + bool pending:1; + u32 unknown3:3; /* set to zero */ } __packed; /* Common link controller registers */ From 56183c88f368eef7134c32df826792ee140f2864 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sun, 19 Feb 2017 10:39:34 +0200 Subject: [PATCH 092/255] thunderbolt: Cache adapter specific capability offset into struct port The adapter specific capability either is there or not if the port does not hold an adapter. Instead of always finding it on-demand we read the offset just once when the port is initialized. While there we update the struct port documentation to follow kernel-doc format. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/switch.c | 4 ++++ drivers/thunderbolt/tb.c | 8 ++++---- drivers/thunderbolt/tb.h | 2 ++ drivers/thunderbolt/tunnel_pci.c | 9 +++------ 4 files changed, 13 insertions(+), 10 deletions(-) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index b3f93ebe6e39..9756e6279dc9 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -586,6 +586,10 @@ static int tb_init_port(struct tb_port *port) port->cap_phy = cap; else tb_port_WARN(port, "non switch port without a PHY\n"); + } else if (port->port != 0) { + cap = tb_port_find_cap(port, TB_PORT_CAP_ADAP); + if (cap > 0) + port->cap_adap = cap; } tb_dump_port(port->sw->tb, &port->config); diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index d8f4ed0f2ef8..e71530d0af65 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -151,8 +151,8 @@ static struct tb_port *tb_find_unused_down_port(struct tb_switch *sw) continue; if (sw->ports[i].config.type != TB_TYPE_PCIE_DOWN) continue; - cap = tb_port_find_cap(&sw->ports[i], TB_PORT_CAP_ADAP); - if (cap < 0) + cap = sw->ports[i].cap_adap; + if (!cap) continue; res = tb_port_read(&sw->ports[i], &data, TB_CFG_PORT, cap, 1); if (res < 0) @@ -197,8 +197,8 @@ static void tb_activate_pcie_devices(struct tb *tb) } /* check whether port is already activated */ - cap = tb_port_find_cap(up_port, TB_PORT_CAP_ADAP); - if (cap < 0) + cap = up_port->cap_adap; + if (!cap) continue; if (tb_port_read(up_port, &data, TB_CFG_PORT, cap, 1)) continue; diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 985a48a67a43..b4d7c4d408bd 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -121,6 +121,7 @@ struct tb_switch { * @remote: Remote port (%NULL if not connected) * @xdomain: Remote host (%NULL if not connected) * @cap_phy: Offset, zero if not found + * @cap_adap: Offset of the adapter specific capability (%0 if not present) * @port: Port number on switch * @disabled: Disabled by eeprom * @dual_link_port: If the switch is connected using two ports, points @@ -133,6 +134,7 @@ struct tb_port { struct tb_port *remote; struct tb_xdomain *xdomain; int cap_phy; + int cap_adap; u8 port; bool disabled; struct tb_port *dual_link_port; diff --git a/drivers/thunderbolt/tunnel_pci.c b/drivers/thunderbolt/tunnel_pci.c index 0637537ea53f..2de4edccbd6d 100644 --- a/drivers/thunderbolt/tunnel_pci.c +++ b/drivers/thunderbolt/tunnel_pci.c @@ -148,12 +148,9 @@ bool tb_pci_is_invalid(struct tb_pci_tunnel *tunnel) static int tb_pci_port_active(struct tb_port *port, bool active) { u32 word = active ? 0x80000000 : 0x0; - int cap = tb_port_find_cap(port, TB_PORT_CAP_ADAP); - if (cap < 0) { - tb_port_warn(port, "TB_PORT_CAP_ADAP not found: %d\n", cap); - return cap; - } - return tb_port_write(port, &word, TB_CFG_PORT, cap, 1); + if (!port->cap_adap) + return -ENXIO; + return tb_port_write(port, &word, TB_CFG_PORT, port->cap_adap, 1); } /** From 1752b9f78713c7a188495319ebafbe7868718962 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sun, 19 Feb 2017 10:58:35 +0200 Subject: [PATCH 093/255] thunderbolt: Rename tunnel_pci to tunnel In order to tunnel non-PCIe traffic as well rename tunnel_pci.[ch] to tunnel.[ch] to reflect this fact. No functional changes. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/Makefile | 2 +- drivers/thunderbolt/tb.c | 2 +- drivers/thunderbolt/{tunnel_pci.c => tunnel.c} | 4 ++-- drivers/thunderbolt/{tunnel_pci.h => tunnel.h} | 6 +++--- 4 files changed, 7 insertions(+), 7 deletions(-) rename drivers/thunderbolt/{tunnel_pci.c => tunnel.c} (98%) rename drivers/thunderbolt/{tunnel_pci.h => tunnel.h} (87%) diff --git a/drivers/thunderbolt/Makefile b/drivers/thunderbolt/Makefile index 8531f15d3b3c..833bdee3cec7 100644 --- a/drivers/thunderbolt/Makefile +++ b/drivers/thunderbolt/Makefile @@ -1,3 +1,3 @@ obj-${CONFIG_THUNDERBOLT} := thunderbolt.o -thunderbolt-objs := nhi.o ctl.o tb.o switch.o cap.o path.o tunnel_pci.o eeprom.o +thunderbolt-objs := nhi.o ctl.o tb.o switch.o cap.o path.o tunnel.o eeprom.o thunderbolt-objs += domain.o dma_port.o icm.o property.o xdomain.o lc.o diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index e71530d0af65..8de43a2ab205 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -12,7 +12,7 @@ #include "tb.h" #include "tb_regs.h" -#include "tunnel_pci.h" +#include "tunnel.h" /** * struct tb_cm - Simple Thunderbolt connection manager diff --git a/drivers/thunderbolt/tunnel_pci.c b/drivers/thunderbolt/tunnel.c similarity index 98% rename from drivers/thunderbolt/tunnel_pci.c rename to drivers/thunderbolt/tunnel.c index 2de4edccbd6d..1e470564e99d 100644 --- a/drivers/thunderbolt/tunnel_pci.c +++ b/drivers/thunderbolt/tunnel.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Thunderbolt Cactus Ridge driver - PCIe tunnel + * Thunderbolt Cactus Ridge driver - Tunneling support * * Copyright (c) 2014 Andreas Noever */ @@ -8,7 +8,7 @@ #include #include -#include "tunnel_pci.h" +#include "tunnel.h" #include "tb.h" #define __TB_TUNNEL_PRINT(level, tunnel, fmt, arg...) \ diff --git a/drivers/thunderbolt/tunnel_pci.h b/drivers/thunderbolt/tunnel.h similarity index 87% rename from drivers/thunderbolt/tunnel_pci.h rename to drivers/thunderbolt/tunnel.h index f9b65fa1fd4d..dff0f27d6ab5 100644 --- a/drivers/thunderbolt/tunnel_pci.h +++ b/drivers/thunderbolt/tunnel.h @@ -1,12 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Thunderbolt Cactus Ridge driver - PCIe tunnel + * Thunderbolt Cactus Ridge driver - Tunneling support * * Copyright (c) 2014 Andreas Noever */ -#ifndef TB_PCI_H_ -#define TB_PCI_H_ +#ifndef TB_TUNNEL_H_ +#define TB_TUNNEL_H_ #include "tb.h" From 93f36ade5b7b82a842a3d6284b8cdb68adb93e85 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sun, 19 Feb 2017 13:48:29 +0200 Subject: [PATCH 094/255] thunderbolt: Generalize tunnel creation functionality To be able to tunnel non-PCIe traffic, separate tunnel functionality into generic and PCIe specific parts. Rename struct tb_pci_tunnel to tb_tunnel, and make it hold an array of paths instead of just two. Update all the tunneling functions to take this structure as parameter. We also move tb_pci_port_active() to switch.c (and rename it) where we will be keeping all port and switch related functions. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/switch.c | 13 ++ drivers/thunderbolt/tb.c | 30 ++-- drivers/thunderbolt/tb.h | 2 + drivers/thunderbolt/tb_regs.h | 4 + drivers/thunderbolt/tunnel.c | 298 ++++++++++++++++++++-------------- drivers/thunderbolt/tunnel.h | 38 +++-- 6 files changed, 235 insertions(+), 150 deletions(-) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 9756e6279dc9..b132439618da 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -599,6 +599,19 @@ static int tb_init_port(struct tb_port *port) } +/** + * tb_pci_port_enable() - Enable PCIe adapter port + * @port: PCIe port to enable + * @enable: Enable/disable the PCIe adapter + */ +int tb_pci_port_enable(struct tb_port *port, bool enable) +{ + u32 word = enable ? TB_PCI_EN : 0x0; + if (!port->cap_adap) + return -ENXIO; + return tb_port_write(port, &word, TB_CFG_PORT, port->cap_adap, 1); +} + /* switch utility functions */ static void tb_dump_switch(struct tb *tb, struct tb_regs_switch_header *sw) diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 8de43a2ab205..36dad0a00ac2 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -91,14 +91,14 @@ static void tb_scan_port(struct tb_port *port) static void tb_free_invalid_tunnels(struct tb *tb) { struct tb_cm *tcm = tb_priv(tb); - struct tb_pci_tunnel *tunnel; - struct tb_pci_tunnel *n; + struct tb_tunnel *tunnel; + struct tb_tunnel *n; list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) { - if (tb_pci_is_invalid(tunnel)) { - tb_pci_deactivate(tunnel); + if (tb_tunnel_is_invalid(tunnel)) { + tb_tunnel_deactivate(tunnel); list_del(&tunnel->list); - tb_pci_free(tunnel); + tb_tunnel_free(tunnel); } } } @@ -178,7 +178,7 @@ static void tb_activate_pcie_devices(struct tb *tb) struct tb_switch *sw; struct tb_port *up_port; struct tb_port *down_port; - struct tb_pci_tunnel *tunnel; + struct tb_tunnel *tunnel; struct tb_cm *tcm = tb_priv(tb); /* scan for pcie devices at depth 1*/ @@ -214,17 +214,17 @@ static void tb_activate_pcie_devices(struct tb *tb) "All PCIe down ports are occupied, aborting\n"); continue; } - tunnel = tb_pci_alloc(tb, up_port, down_port); + tunnel = tb_tunnel_alloc_pci(tb, up_port, down_port); if (!tunnel) { tb_port_info(up_port, "PCIe tunnel allocation failed, aborting\n"); continue; } - if (tb_pci_activate(tunnel)) { + if (tb_tunnel_activate(tunnel)) { tb_port_info(up_port, "PCIe tunnel activation failed, aborting\n"); - tb_pci_free(tunnel); + tb_tunnel_free(tunnel); continue; } @@ -353,13 +353,13 @@ static void tb_handle_event(struct tb *tb, enum tb_cfg_pkg_type type, static void tb_stop(struct tb *tb) { struct tb_cm *tcm = tb_priv(tb); - struct tb_pci_tunnel *tunnel; - struct tb_pci_tunnel *n; + struct tb_tunnel *tunnel; + struct tb_tunnel *n; /* tunnels are only present after everything has been initialized */ list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) { - tb_pci_deactivate(tunnel); - tb_pci_free(tunnel); + tb_tunnel_deactivate(tunnel); + tb_tunnel_free(tunnel); } tb_switch_remove(tb->root_switch); tcm->hotplug_active = false; /* signal tb_handle_hotplug to quit */ @@ -418,7 +418,7 @@ static int tb_suspend_noirq(struct tb *tb) static int tb_resume_noirq(struct tb *tb) { struct tb_cm *tcm = tb_priv(tb); - struct tb_pci_tunnel *tunnel, *n; + struct tb_tunnel *tunnel, *n; tb_dbg(tb, "resuming...\n"); @@ -429,7 +429,7 @@ static int tb_resume_noirq(struct tb *tb) tb_free_invalid_tunnels(tb); tb_free_unplugged_children(tb->root_switch); list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) - tb_pci_restart(tunnel); + tb_tunnel_restart(tunnel); if (!list_empty(&tcm->tunnel_list)) { /* * the pcie links need some time to get going. diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index b4d7c4d408bd..d1f8e9722f33 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -457,6 +457,8 @@ int tb_port_clear_counter(struct tb_port *port, int counter); int tb_switch_find_vse_cap(struct tb_switch *sw, enum tb_switch_vse_cap vsec); int tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap); +int tb_pci_port_enable(struct tb_port *port, bool enable); + struct tb_path *tb_path_alloc(struct tb *tb, int num_hops); void tb_path_free(struct tb_path *path); int tb_path_activate(struct tb_path *path); diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h index 82ac4ec8757f..75e935acade5 100644 --- a/drivers/thunderbolt/tb_regs.h +++ b/drivers/thunderbolt/tb_regs.h @@ -211,6 +211,10 @@ struct tb_regs_port_header { } __packed; +/* PCIe adapter registers */ + +#define TB_PCI_EN BIT(31) + /* Hop register from TB_CFG_HOPS. 8 byte per entry. */ struct tb_regs_hop { /* DWORD 0 */ diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index 1e470564e99d..20ce28276f7a 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -1,8 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Thunderbolt Cactus Ridge driver - Tunneling support + * Thunderbolt driver - Tunneling support * * Copyright (c) 2014 Andreas Noever + * Copyright (C) 2019, Intel Corporation */ #include @@ -11,14 +12,17 @@ #include "tunnel.h" #include "tb.h" +#define TB_PCI_PATH_DOWN 0 +#define TB_PCI_PATH_UP 1 + #define __TB_TUNNEL_PRINT(level, tunnel, fmt, arg...) \ do { \ - struct tb_pci_tunnel *__tunnel = (tunnel); \ + struct tb_tunnel *__tunnel = (tunnel); \ level(__tunnel->tb, "%llx:%x <-> %llx:%x (PCI): " fmt, \ - tb_route(__tunnel->down_port->sw), \ - __tunnel->down_port->port, \ - tb_route(__tunnel->up_port->sw), \ - __tunnel->up_port->port, \ + tb_route(__tunnel->src_port->sw), \ + __tunnel->src_port->port, \ + tb_route(__tunnel->dst_port->sw), \ + __tunnel->dst_port->port, \ ## arg); \ } while (0) @@ -29,6 +33,38 @@ #define tb_tunnel_info(tunnel, fmt, arg...) \ __TB_TUNNEL_PRINT(tb_info, tunnel, fmt, ##arg) +static struct tb_tunnel *tb_tunnel_alloc(struct tb *tb, size_t npaths) +{ + struct tb_tunnel *tunnel; + + tunnel = kzalloc(sizeof(*tunnel), GFP_KERNEL); + if (!tunnel) + return NULL; + + tunnel->paths = kcalloc(npaths, sizeof(tunnel->paths[0]), GFP_KERNEL); + if (!tunnel->paths) { + tb_tunnel_free(tunnel); + return NULL; + } + + INIT_LIST_HEAD(&tunnel->list); + tunnel->tb = tb; + tunnel->npaths = npaths; + + return tunnel; +} + +static int tb_pci_activate(struct tb_tunnel *tunnel, bool activate) +{ + int res; + + res = tb_pci_port_enable(tunnel->src_port, activate); + if (res) + return res; + + return tb_pci_port_enable(tunnel->dst_port, activate); +} + static void tb_pci_init_path(struct tb_path *path) { path->egress_fc_enable = TB_PATH_SOURCE | TB_PATH_INTERNAL; @@ -42,7 +78,10 @@ static void tb_pci_init_path(struct tb_path *path) } /** - * tb_pci_alloc() - allocate a pci tunnel + * tb_tunnel_alloc_pci() - allocate a pci tunnel + * @tb: Pointer to the domain structure + * @up: PCIe upstream adapter port + * @down: PCIe downstream adapter port * * Allocate a PCI tunnel. The ports must be of type TB_TYPE_PCIE_UP and * TB_TYPE_PCIE_DOWN. @@ -54,170 +93,185 @@ static void tb_pci_init_path(struct tb_path *path) * my thunderbolt devices). Therefore at most ONE path per device may be * activated. * - * Return: Returns a tb_pci_tunnel on success or NULL on failure. + * Return: Returns a tb_tunnel on success or NULL on failure. */ -struct tb_pci_tunnel *tb_pci_alloc(struct tb *tb, struct tb_port *up, - struct tb_port *down) +struct tb_tunnel *tb_tunnel_alloc_pci(struct tb *tb, struct tb_port *up, + struct tb_port *down) { - struct tb_pci_tunnel *tunnel = kzalloc(sizeof(*tunnel), GFP_KERNEL); + struct tb_path *path_to_up; + struct tb_path *path_to_down; + struct tb_tunnel *tunnel; + + tunnel = tb_tunnel_alloc(tb, 2); if (!tunnel) - goto err; - tunnel->tb = tb; - tunnel->down_port = down; - tunnel->up_port = up; - INIT_LIST_HEAD(&tunnel->list); - tunnel->path_to_up = tb_path_alloc(up->sw->tb, 2); - if (!tunnel->path_to_up) - goto err; - tunnel->path_to_down = tb_path_alloc(up->sw->tb, 2); - if (!tunnel->path_to_down) - goto err; - tb_pci_init_path(tunnel->path_to_up); - tb_pci_init_path(tunnel->path_to_down); + return NULL; - tunnel->path_to_up->hops[0].in_port = down; - tunnel->path_to_up->hops[0].in_hop_index = 8; - tunnel->path_to_up->hops[0].in_counter_index = -1; - tunnel->path_to_up->hops[0].out_port = tb_upstream_port(up->sw)->remote; - tunnel->path_to_up->hops[0].next_hop_index = 8; + tunnel->activate = tb_pci_activate; + tunnel->src_port = down; + tunnel->dst_port = up; - tunnel->path_to_up->hops[1].in_port = tb_upstream_port(up->sw); - tunnel->path_to_up->hops[1].in_hop_index = 8; - tunnel->path_to_up->hops[1].in_counter_index = -1; - tunnel->path_to_up->hops[1].out_port = up; - tunnel->path_to_up->hops[1].next_hop_index = 8; - - tunnel->path_to_down->hops[0].in_port = up; - tunnel->path_to_down->hops[0].in_hop_index = 8; - tunnel->path_to_down->hops[0].in_counter_index = -1; - tunnel->path_to_down->hops[0].out_port = tb_upstream_port(up->sw); - tunnel->path_to_down->hops[0].next_hop_index = 8; - - tunnel->path_to_down->hops[1].in_port = - tb_upstream_port(up->sw)->remote; - tunnel->path_to_down->hops[1].in_hop_index = 8; - tunnel->path_to_down->hops[1].in_counter_index = -1; - tunnel->path_to_down->hops[1].out_port = down; - tunnel->path_to_down->hops[1].next_hop_index = 8; - return tunnel; - -err: - if (tunnel) { - if (tunnel->path_to_down) - tb_path_free(tunnel->path_to_down); - if (tunnel->path_to_up) - tb_path_free(tunnel->path_to_up); - kfree(tunnel); + path_to_up = tb_path_alloc(tb, 2); + if (!path_to_up) { + tb_tunnel_free(tunnel); + return NULL; } - return NULL; + tunnel->paths[TB_PCI_PATH_UP] = path_to_up; + + path_to_down = tb_path_alloc(tb, 2); + if (!path_to_down) { + tb_tunnel_free(tunnel); + return NULL; + } + tunnel->paths[TB_PCI_PATH_DOWN] = path_to_down; + + tb_pci_init_path(path_to_up); + tb_pci_init_path(path_to_down); + + path_to_up->hops[0].in_port = down; + path_to_up->hops[0].in_hop_index = 8; + path_to_up->hops[0].in_counter_index = -1; + path_to_up->hops[0].out_port = tb_upstream_port(up->sw)->remote; + path_to_up->hops[0].next_hop_index = 8; + + path_to_up->hops[1].in_port = tb_upstream_port(up->sw); + path_to_up->hops[1].in_hop_index = 8; + path_to_up->hops[1].in_counter_index = -1; + path_to_up->hops[1].out_port = up; + path_to_up->hops[1].next_hop_index = 8; + + path_to_down->hops[0].in_port = up; + path_to_down->hops[0].in_hop_index = 8; + path_to_down->hops[0].in_counter_index = -1; + path_to_down->hops[0].out_port = tb_upstream_port(up->sw); + path_to_down->hops[0].next_hop_index = 8; + + path_to_down->hops[1].in_port = tb_upstream_port(up->sw)->remote; + path_to_down->hops[1].in_hop_index = 8; + path_to_down->hops[1].in_counter_index = -1; + path_to_down->hops[1].out_port = down; + path_to_down->hops[1].next_hop_index = 8; + + return tunnel; } /** - * tb_pci_free() - free a tunnel + * tb_tunnel_free() - free a tunnel + * @tunnel: Tunnel to be freed * * The tunnel must have been deactivated. */ -void tb_pci_free(struct tb_pci_tunnel *tunnel) +void tb_tunnel_free(struct tb_tunnel *tunnel) { - if (tunnel->path_to_up->activated || tunnel->path_to_down->activated) { - tb_tunnel_WARN(tunnel, "trying to free an activated tunnel\n"); + int i; + + if (!tunnel) return; + + for (i = 0; i < tunnel->npaths; i++) { + if (tunnel->paths[i] && tunnel->paths[i]->activated) { + tb_tunnel_WARN(tunnel, + "trying to free an activated tunnel\n"); + return; + } } - tb_path_free(tunnel->path_to_up); - tb_path_free(tunnel->path_to_down); + + for (i = 0; i < tunnel->npaths; i++) { + if (tunnel->paths[i]) + tb_path_free(tunnel->paths[i]); + } + + kfree(tunnel->paths); kfree(tunnel); } /** - * tb_pci_is_invalid - check whether an activated path is still valid + * tb_tunnel_is_invalid - check whether an activated path is still valid + * @tunnel: Tunnel to check */ -bool tb_pci_is_invalid(struct tb_pci_tunnel *tunnel) +bool tb_tunnel_is_invalid(struct tb_tunnel *tunnel) { - WARN_ON(!tunnel->path_to_up->activated); - WARN_ON(!tunnel->path_to_down->activated); + int i; - return tb_path_is_invalid(tunnel->path_to_up) - || tb_path_is_invalid(tunnel->path_to_down); + for (i = 0; i < tunnel->npaths; i++) { + WARN_ON(!tunnel->paths[i]->activated); + if (tb_path_is_invalid(tunnel->paths[i])) + return true; + } + + return false; } /** - * tb_pci_port_active() - activate/deactivate PCI capability + * tb_tunnel_restart() - activate a tunnel after a hardware reset + * @tunnel: Tunnel to restart * - * Return: Returns 0 on success or an error code on failure. + * Return: 0 on success and negative errno in case if failure */ -static int tb_pci_port_active(struct tb_port *port, bool active) +int tb_tunnel_restart(struct tb_tunnel *tunnel) { - u32 word = active ? 0x80000000 : 0x0; - if (!port->cap_adap) - return -ENXIO; - return tb_port_write(port, &word, TB_CFG_PORT, port->cap_adap, 1); -} - -/** - * tb_pci_restart() - activate a tunnel after a hardware reset - */ -int tb_pci_restart(struct tb_pci_tunnel *tunnel) -{ - int res; - tunnel->path_to_up->activated = false; - tunnel->path_to_down->activated = false; + int res, i; tb_tunnel_info(tunnel, "activating\n"); - res = tb_path_activate(tunnel->path_to_up); - if (res) - goto err; - res = tb_path_activate(tunnel->path_to_down); - if (res) - goto err; + for (i = 0; i < tunnel->npaths; i++) { + tunnel->paths[i]->activated = false; + res = tb_path_activate(tunnel->paths[i]); + if (res) + goto err; + } - res = tb_pci_port_active(tunnel->down_port, true); - if (res) - goto err; + if (tunnel->activate) { + res = tunnel->activate(tunnel, true); + if (res) + goto err; + } - res = tb_pci_port_active(tunnel->up_port, true); - if (res) - goto err; return 0; + err: tb_tunnel_warn(tunnel, "activation failed\n"); - tb_pci_deactivate(tunnel); + tb_tunnel_deactivate(tunnel); return res; } /** - * tb_pci_activate() - activate a tunnel + * tb_tunnel_activate() - activate a tunnel + * @tunnel: Tunnel to activate * * Return: Returns 0 on success or an error code on failure. */ -int tb_pci_activate(struct tb_pci_tunnel *tunnel) +int tb_tunnel_activate(struct tb_tunnel *tunnel) { - if (tunnel->path_to_up->activated || tunnel->path_to_down->activated) { - tb_tunnel_WARN(tunnel, - "trying to activate an already activated tunnel\n"); - return -EINVAL; + int i; + + tb_tunnel_info(tunnel, "activating\n"); + + for (i = 0; i < tunnel->npaths; i++) { + if (tunnel->paths[i]->activated) { + tb_tunnel_WARN(tunnel, + "trying to activate an already activated tunnel\n"); + return -EINVAL; + } } - return tb_pci_restart(tunnel); + return tb_tunnel_restart(tunnel); } - - /** - * tb_pci_deactivate() - deactivate a tunnel + * tb_tunnel_deactivate() - deactivate a tunnel + * @tunnel: Tunnel to deactivate */ -void tb_pci_deactivate(struct tb_pci_tunnel *tunnel) +void tb_tunnel_deactivate(struct tb_tunnel *tunnel) { - tb_tunnel_info(tunnel, "deactivating\n"); - /* - * TODO: enable reset by writing 0x04000000 to TB_CAP_PCIE + 1 on up - * port. Seems to have no effect? - */ - tb_pci_port_active(tunnel->up_port, false); - tb_pci_port_active(tunnel->down_port, false); - if (tunnel->path_to_down->activated) - tb_path_deactivate(tunnel->path_to_down); - if (tunnel->path_to_up->activated) - tb_path_deactivate(tunnel->path_to_up); -} + int i; + tb_tunnel_info(tunnel, "deactivating\n"); + + if (tunnel->activate) + tunnel->activate(tunnel, false); + + for (i = 0; i < tunnel->npaths; i++) { + if (tunnel->paths[i]->activated) + tb_path_deactivate(tunnel->paths[i]); + } +} diff --git a/drivers/thunderbolt/tunnel.h b/drivers/thunderbolt/tunnel.h index dff0f27d6ab5..b4e992165e56 100644 --- a/drivers/thunderbolt/tunnel.h +++ b/drivers/thunderbolt/tunnel.h @@ -1,8 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * Thunderbolt Cactus Ridge driver - Tunneling support + * Thunderbolt driver - Tunneling support * * Copyright (c) 2014 Andreas Noever + * Copyright (C) 2019, Intel Corporation */ #ifndef TB_TUNNEL_H_ @@ -10,22 +11,33 @@ #include "tb.h" -struct tb_pci_tunnel { +/** + * struct tb_tunnel - Tunnel between two ports + * @tb: Pointer to the domain + * @src_port: Source port of the tunnel + * @dst_port: Destination port of the tunnel + * @paths: All paths required by the tunnel + * @npaths: Number of paths in @paths + * @activate: Optional tunnel specific activation/deactivation + * @list: Tunnels are linked using this field + */ +struct tb_tunnel { struct tb *tb; - struct tb_port *up_port; - struct tb_port *down_port; - struct tb_path *path_to_up; - struct tb_path *path_to_down; + struct tb_port *src_port; + struct tb_port *dst_port; + struct tb_path **paths; + size_t npaths; + int (*activate)(struct tb_tunnel *tunnel, bool activate); struct list_head list; }; -struct tb_pci_tunnel *tb_pci_alloc(struct tb *tb, struct tb_port *up, - struct tb_port *down); -void tb_pci_free(struct tb_pci_tunnel *tunnel); -int tb_pci_activate(struct tb_pci_tunnel *tunnel); -int tb_pci_restart(struct tb_pci_tunnel *tunnel); -void tb_pci_deactivate(struct tb_pci_tunnel *tunnel); -bool tb_pci_is_invalid(struct tb_pci_tunnel *tunnel); +struct tb_tunnel *tb_tunnel_alloc_pci(struct tb *tb, struct tb_port *up, + struct tb_port *down); +void tb_tunnel_free(struct tb_tunnel *tunnel); +int tb_tunnel_activate(struct tb_tunnel *tunnel); +int tb_tunnel_restart(struct tb_tunnel *tunnel); +void tb_tunnel_deactivate(struct tb_tunnel *tunnel); +bool tb_tunnel_is_invalid(struct tb_tunnel *tunnel); #endif From 0b2863ac3cfdea2e0e27f9e722d178efb367e4db Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sun, 19 Feb 2017 16:57:27 +0200 Subject: [PATCH 095/255] thunderbolt: Add functions for allocating and releasing HopIDs Each port has a separate path configuration space that is used for finding the next hop (switch) in the path. HopID is an index to this configuration space. HopIDs 0 - 7 are reserved by the protocol. In order to get next available HopID for each direction we provide two pairs of helper functions that can be used to allocate and release HopIDs for a given port. While there remove obsolete TODO comment. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/nhi.c | 3 +- drivers/thunderbolt/switch.c | 87 +++++++++++++++++++++++++++++++++++- drivers/thunderbolt/tb.h | 11 +++++ 3 files changed, 98 insertions(+), 3 deletions(-) diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c index 9aa44f9762a3..cac1ead5e302 100644 --- a/drivers/thunderbolt/nhi.c +++ b/drivers/thunderbolt/nhi.c @@ -27,8 +27,7 @@ * use this ring for anything else. */ #define RING_E2E_UNUSED_HOPID 2 -/* HopIDs 0-7 are reserved by the Thunderbolt protocol */ -#define RING_FIRST_USABLE_HOPID 8 +#define RING_FIRST_USABLE_HOPID TB_PATH_MIN_HOPID /* * Minimal number of vectors when we use MSI-X. Two for control channel diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index b132439618da..30f3d6a9fe90 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -594,11 +594,88 @@ static int tb_init_port(struct tb_port *port) tb_dump_port(port->sw->tb, &port->config); - /* TODO: Read dual link port, DP port and more from EEPROM. */ + /* Control port does not need HopID allocation */ + if (port->port) { + ida_init(&port->in_hopids); + ida_init(&port->out_hopids); + } + return 0; } +static int tb_port_alloc_hopid(struct tb_port *port, bool in, int min_hopid, + int max_hopid) +{ + int port_max_hopid; + struct ida *ida; + + if (in) { + port_max_hopid = port->config.max_in_hop_id; + ida = &port->in_hopids; + } else { + port_max_hopid = port->config.max_out_hop_id; + ida = &port->out_hopids; + } + + /* HopIDs 0-7 are reserved */ + if (min_hopid < TB_PATH_MIN_HOPID) + min_hopid = TB_PATH_MIN_HOPID; + + if (max_hopid < 0 || max_hopid > port_max_hopid) + max_hopid = port_max_hopid; + + return ida_simple_get(ida, min_hopid, max_hopid + 1, GFP_KERNEL); +} + +/** + * tb_port_alloc_in_hopid() - Allocate input HopID from port + * @port: Port to allocate HopID for + * @min_hopid: Minimum acceptable input HopID + * @max_hopid: Maximum acceptable input HopID + * + * Return: HopID between @min_hopid and @max_hopid or negative errno in + * case of error. + */ +int tb_port_alloc_in_hopid(struct tb_port *port, int min_hopid, int max_hopid) +{ + return tb_port_alloc_hopid(port, true, min_hopid, max_hopid); +} + +/** + * tb_port_alloc_out_hopid() - Allocate output HopID from port + * @port: Port to allocate HopID for + * @min_hopid: Minimum acceptable output HopID + * @max_hopid: Maximum acceptable output HopID + * + * Return: HopID between @min_hopid and @max_hopid or negative errno in + * case of error. + */ +int tb_port_alloc_out_hopid(struct tb_port *port, int min_hopid, int max_hopid) +{ + return tb_port_alloc_hopid(port, false, min_hopid, max_hopid); +} + +/** + * tb_port_release_in_hopid() - Release allocated input HopID from port + * @port: Port whose HopID to release + * @hopid: HopID to release + */ +void tb_port_release_in_hopid(struct tb_port *port, int hopid) +{ + ida_simple_remove(&port->in_hopids, hopid); +} + +/** + * tb_port_release_out_hopid() - Release allocated output HopID from port + * @port: Port whose HopID to release + * @hopid: HopID to release + */ +void tb_port_release_out_hopid(struct tb_port *port, int hopid) +{ + ida_simple_remove(&port->out_hopids, hopid); +} + /** * tb_pci_port_enable() - Enable PCIe adapter port * @port: PCIe port to enable @@ -1055,9 +1132,17 @@ static const struct attribute_group *switch_groups[] = { static void tb_switch_release(struct device *dev) { struct tb_switch *sw = tb_to_switch(dev); + int i; dma_port_free(sw->dma_port); + for (i = 1; i <= sw->config.max_port_number; i++) { + if (!sw->ports[i].disabled) { + ida_destroy(&sw->ports[i].in_hopids); + ida_destroy(&sw->ports[i].out_hopids); + } + } + kfree(sw->uuid); kfree(sw->device_name); kfree(sw->vendor_name); diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index d1f8e9722f33..1cb5009195f9 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -127,6 +127,8 @@ struct tb_switch { * @dual_link_port: If the switch is connected using two ports, points * to the other port. * @link_nr: Is this primary or secondary port on the dual_link. + * @in_hopids: Currently allocated input HopIDs + * @out_hopids: Currently allocated output HopIDs */ struct tb_port { struct tb_regs_port_header config; @@ -139,6 +141,8 @@ struct tb_port { bool disabled; struct tb_port *dual_link_port; u8 link_nr:1; + struct ida in_hopids; + struct ida out_hopids; }; /** @@ -194,6 +198,9 @@ struct tb_path { int path_length; /* number of hops */ }; +/* HopIDs 0-7 are reserved by the Thunderbolt protocol */ +#define TB_PATH_MIN_HOPID 8 + /** * struct tb_cm_ops - Connection manager specific operations vector * @driver_ready: Called right after control channel is started. Used by @@ -453,6 +460,10 @@ static inline bool tb_switch_is_er(const struct tb_switch *sw) int tb_wait_for_port(struct tb_port *port, bool wait_if_unplugged); int tb_port_add_nfc_credits(struct tb_port *port, int credits); int tb_port_clear_counter(struct tb_port *port, int counter); +int tb_port_alloc_in_hopid(struct tb_port *port, int hopid, int max_hopid); +void tb_port_release_in_hopid(struct tb_port *port, int hopid); +int tb_port_alloc_out_hopid(struct tb_port *port, int hopid, int max_hopid); +void tb_port_release_out_hopid(struct tb_port *port, int hopid); int tb_switch_find_vse_cap(struct tb_switch *sw, enum tb_switch_vse_cap vsec); int tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap); From dfe40ca486f60dca1e3223d82acf78cfb39925b8 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 7 Mar 2019 15:26:45 +0200 Subject: [PATCH 096/255] thunderbolt: Assign remote for both ports in case of dual link Currently the driver only assigns remote port for the primary port if in case of dual link. This makes things such as walking from one port to another more complex than necessary because the code needs to change from secondary to primary port if the path that is established is created using secondary links. In order to always assign both remote pointers we need to prevent the scanning code from following the secondary link. Failing to do that might cause problems as the same switch may be enumerated twice (or removed in case of unplug). Handle that properly by introducing a new function tb_port_has_remote() that returns true only for the primary port. We also update tb_is_upstream_port() to support both dual link ports, make it take const port pointer and move it below tb_upstream_port() to keep similar functions close. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/icm.c | 33 ++++++++++---------------------- drivers/thunderbolt/switch.c | 21 ++++++++++---------- drivers/thunderbolt/tb.c | 30 ++++++++++++++++++++--------- drivers/thunderbolt/tb.h | 36 ++++++++++++++++++++++++++++++----- drivers/thunderbolt/xdomain.c | 5 +---- 5 files changed, 73 insertions(+), 52 deletions(-) diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index bec360eef6cf..805958e53c58 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -1761,16 +1761,10 @@ static void icm_unplug_children(struct tb_switch *sw) for (i = 1; i <= sw->config.max_port_number; i++) { struct tb_port *port = &sw->ports[i]; - if (tb_is_upstream_port(port)) - continue; - if (port->xdomain) { + if (port->xdomain) port->xdomain->is_unplugged = true; - continue; - } - if (!port->remote) - continue; - - icm_unplug_children(port->remote->sw); + else if (tb_port_has_remote(port)) + icm_unplug_children(port->remote->sw); } } @@ -1781,23 +1775,16 @@ static void icm_free_unplugged_children(struct tb_switch *sw) for (i = 1; i <= sw->config.max_port_number; i++) { struct tb_port *port = &sw->ports[i]; - if (tb_is_upstream_port(port)) - continue; - if (port->xdomain && port->xdomain->is_unplugged) { tb_xdomain_remove(port->xdomain); port->xdomain = NULL; - continue; - } - - if (!port->remote) - continue; - - if (port->remote->sw->is_unplugged) { - tb_switch_remove(port->remote->sw); - port->remote = NULL; - } else { - icm_free_unplugged_children(port->remote->sw); + } else if (tb_port_has_remote(port)) { + if (port->remote->sw->is_unplugged) { + tb_switch_remove(port->remote->sw); + port->remote = NULL; + } else { + icm_free_unplugged_children(port->remote->sw); + } } } } diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 30f3d6a9fe90..6f98b3d6eb2a 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -1580,14 +1580,13 @@ void tb_switch_remove(struct tb_switch *sw) /* port 0 is the switch itself and never has a remote */ for (i = 1; i <= sw->config.max_port_number; i++) { - if (tb_is_upstream_port(&sw->ports[i])) - continue; - if (sw->ports[i].remote) + if (tb_port_has_remote(&sw->ports[i])) { tb_switch_remove(sw->ports[i].remote->sw); - sw->ports[i].remote = NULL; - if (sw->ports[i].xdomain) + sw->ports[i].remote = NULL; + } else if (sw->ports[i].xdomain) { tb_xdomain_remove(sw->ports[i].xdomain); - sw->ports[i].xdomain = NULL; + sw->ports[i].xdomain = NULL; + } } if (!sw->is_unplugged) @@ -1617,7 +1616,7 @@ void tb_sw_set_unplugged(struct tb_switch *sw) } sw->is_unplugged = true; for (i = 0; i <= sw->config.max_port_number; i++) { - if (!tb_is_upstream_port(&sw->ports[i]) && sw->ports[i].remote) + if (tb_port_has_remote(&sw->ports[i])) tb_sw_set_unplugged(sw->ports[i].remote->sw); } } @@ -1663,10 +1662,10 @@ int tb_switch_resume(struct tb_switch *sw) /* check for surviving downstream switches */ for (i = 1; i <= sw->config.max_port_number; i++) { struct tb_port *port = &sw->ports[i]; - if (tb_is_upstream_port(port)) - continue; - if (!port->remote) + + if (!tb_port_has_remote(port)) continue; + if (tb_wait_for_port(port, true) <= 0 || tb_switch_resume(port->remote->sw)) { tb_port_warn(port, @@ -1685,7 +1684,7 @@ void tb_switch_suspend(struct tb_switch *sw) return; for (i = 1; i <= sw->config.max_port_number; i++) { - if (!tb_is_upstream_port(&sw->ports[i]) && sw->ports[i].remote) + if (tb_port_has_remote(&sw->ports[i])) tb_switch_suspend(sw->ports[i].remote->sw); } diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 36dad0a00ac2..0485f4ef9a62 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -47,7 +47,9 @@ static void tb_scan_switch(struct tb_switch *sw) */ static void tb_scan_port(struct tb_port *port) { + struct tb_port *upstream_port; struct tb_switch *sw; + if (tb_is_upstream_port(port)) return; if (port->config.type != TB_TYPE_PORT) @@ -80,8 +82,15 @@ static void tb_scan_port(struct tb_port *port) return; } - port->remote = tb_upstream_port(sw); - tb_upstream_port(sw)->remote = port; + /* Link the switches using both links if available */ + upstream_port = tb_upstream_port(sw); + port->remote = upstream_port; + upstream_port->remote = port; + if (port->dual_link_port && upstream_port->dual_link_port) { + port->dual_link_port->remote = upstream_port->dual_link_port; + upstream_port->dual_link_port->remote = port->dual_link_port; + } + tb_scan_switch(sw); } @@ -111,13 +120,15 @@ static void tb_free_unplugged_children(struct tb_switch *sw) int i; for (i = 1; i <= sw->config.max_port_number; i++) { struct tb_port *port = &sw->ports[i]; - if (tb_is_upstream_port(port)) - continue; - if (!port->remote) + + if (!tb_port_has_remote(port)) continue; + if (port->remote->sw->is_unplugged) { tb_switch_remove(port->remote->sw); port->remote = NULL; + if (port->dual_link_port) + port->dual_link_port->remote = NULL; } else { tb_free_unplugged_children(port->remote->sw); } @@ -273,18 +284,19 @@ static void tb_handle_hotplug(struct work_struct *work) } port = &sw->ports[ev->port]; if (tb_is_upstream_port(port)) { - tb_warn(tb, - "hotplug event for upstream port %llx:%x (unplug: %d)\n", - ev->route, ev->port, ev->unplug); + tb_dbg(tb, "hotplug event for upstream port %llx:%x (unplug: %d)\n", + ev->route, ev->port, ev->unplug); goto put_sw; } if (ev->unplug) { - if (port->remote) { + if (tb_port_has_remote(port)) { tb_port_info(port, "unplugged\n"); tb_sw_set_unplugged(port->remote->sw); tb_free_invalid_tunnels(tb); tb_switch_remove(port->remote->sw); port->remote = NULL; + if (port->dual_link_port) + port->dual_link_port->remote = NULL; } else { tb_port_info(port, "got unplug event for disconnected port, ignoring\n"); diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 1cb5009195f9..43bc4f490021 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -270,6 +270,19 @@ static inline struct tb_port *tb_upstream_port(struct tb_switch *sw) return &sw->ports[sw->config.upstream_port_number]; } +/** + * tb_is_upstream_port() - Is the port upstream facing + * @port: Port to check + * + * Returns true if @port is upstream facing port. In case of dual link + * ports both return true. + */ +static inline bool tb_is_upstream_port(const struct tb_port *port) +{ + const struct tb_port *upstream_port = tb_upstream_port(port->sw); + return port == upstream_port || port->dual_link_port == upstream_port; +} + static inline u64 tb_route(struct tb_switch *sw) { return ((u64) sw->config.route_hi) << 32 | sw->config.route_lo; @@ -285,6 +298,24 @@ static inline struct tb_port *tb_port_at(u64 route, struct tb_switch *sw) return &sw->ports[port]; } +/** + * tb_port_has_remote() - Does the port have switch connected downstream + * @port: Port to check + * + * Returns true only when the port is primary port and has remote set. + */ +static inline bool tb_port_has_remote(const struct tb_port *port) +{ + if (tb_is_upstream_port(port)) + return false; + if (!port->remote) + return false; + if (port->dual_link_port && port->link_nr) + return false; + + return true; +} + static inline int tb_sw_read(struct tb_switch *sw, void *buffer, enum tb_cfg_space space, u32 offset, u32 length) { @@ -489,11 +520,6 @@ static inline int tb_route_length(u64 route) return (fls64(route) + TB_ROUTE_SHIFT - 1) / TB_ROUTE_SHIFT; } -static inline bool tb_is_upstream_port(struct tb_port *port) -{ - return port == tb_upstream_port(port->sw); -} - /** * tb_downstream_route() - get route to downstream switch * diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index e2fc4543142d..7bae92bc486f 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -1293,9 +1293,6 @@ static struct tb_xdomain *switch_find_xdomain(struct tb_switch *sw, struct tb_port *port = &sw->ports[i]; struct tb_xdomain *xd; - if (tb_is_upstream_port(port)) - continue; - if (port->xdomain) { xd = port->xdomain; @@ -1310,7 +1307,7 @@ static struct tb_xdomain *switch_find_xdomain(struct tb_switch *sw, lookup->route == xd->route) { return xd; } - } else if (port->remote) { + } else if (tb_port_has_remote(port)) { xd = switch_find_xdomain(port->remote->sw, lookup); if (xd) return xd; From fb19fac1d734504073fee64e9f9b28ccd41ab350 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sun, 19 Feb 2017 21:51:30 +0200 Subject: [PATCH 097/255] thunderbolt: Add helper function to iterate from one port to another We need to be able to walk from one port to another when we are creating paths where there are multiple switches between two ports. For this reason introduce a new function tb_next_port_on_path(). Signed-off-by: Mika Westerberg Reviewed-by: Lukas Wunner --- drivers/thunderbolt/switch.c | 54 ++++++++++++++++++++++++++++++++++++ drivers/thunderbolt/tb.h | 2 ++ 2 files changed, 56 insertions(+) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 6f98b3d6eb2a..ecd41f7b7649 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -676,6 +676,60 @@ void tb_port_release_out_hopid(struct tb_port *port, int hopid) ida_simple_remove(&port->out_hopids, hopid); } +/** + * tb_next_port_on_path() - Return next port for given port on a path + * @start: Start port of the walk + * @end: End port of the walk + * @prev: Previous port (%NULL if this is the first) + * + * This function can be used to walk from one port to another if they + * are connected through zero or more switches. If the @prev is dual + * link port, the function follows that link and returns another end on + * that same link. + * + * If the @end port has been reached, return %NULL. + * + * Domain tb->lock must be held when this function is called. + */ +struct tb_port *tb_next_port_on_path(struct tb_port *start, struct tb_port *end, + struct tb_port *prev) +{ + struct tb_port *next; + + if (!prev) + return start; + + if (prev->sw == end->sw) { + if (prev == end) + return NULL; + return end; + } + + if (start->sw->config.depth < end->sw->config.depth) { + if (prev->remote && + prev->remote->sw->config.depth > prev->sw->config.depth) + next = prev->remote; + else + next = tb_port_at(tb_route(end->sw), prev->sw); + } else { + if (tb_is_upstream_port(prev)) { + next = prev->remote; + } else { + next = tb_upstream_port(prev->sw); + /* + * Keep the same link if prev and next are both + * dual link ports. + */ + if (next->dual_link_port && + next->link_nr != prev->link_nr) { + next = next->dual_link_port; + } + } + } + + return next; +} + /** * tb_pci_port_enable() - Enable PCIe adapter port * @port: PCIe port to enable diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 43bc4f490021..11d5ab53ad36 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -495,6 +495,8 @@ int tb_port_alloc_in_hopid(struct tb_port *port, int hopid, int max_hopid); void tb_port_release_in_hopid(struct tb_port *port, int hopid); int tb_port_alloc_out_hopid(struct tb_port *port, int hopid, int max_hopid); void tb_port_release_out_hopid(struct tb_port *port, int hopid); +struct tb_port *tb_next_port_on_path(struct tb_port *start, struct tb_port *end, + struct tb_port *prev); int tb_switch_find_vse_cap(struct tb_switch *sw, enum tb_switch_vse_cap vsec); int tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap); From 8c7acaaf020fe54baf2eccc5e1071341754d22be Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sun, 19 Feb 2017 22:11:41 +0200 Subject: [PATCH 098/255] thunderbolt: Extend tunnel creation to more than 2 adjacent switches Now that we can allocate hop IDs per port on a path, we can take advantage of this and create tunnels covering longer paths than just between two adjacent switches. PCIe actually does not need this as it is typically a daisy chain between two adjacent switches but this way we do not need to hard-code creation of the tunnel. While there add name to struct tb_path to make debugging easier, and update kernel-doc comments. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/path.c | 121 ++++++++++++++++++++++++++++++----- drivers/thunderbolt/tb.h | 54 ++++++++++++---- drivers/thunderbolt/tunnel.c | 56 ++++------------ 3 files changed, 163 insertions(+), 68 deletions(-) diff --git a/drivers/thunderbolt/path.c b/drivers/thunderbolt/path.c index 8c2e19a6117a..a7cdac7f6808 100644 --- a/drivers/thunderbolt/path.c +++ b/drivers/thunderbolt/path.c @@ -31,23 +31,100 @@ static void tb_dump_hop(struct tb_port *port, struct tb_regs_hop *hop) } /** - * tb_path_alloc() - allocate a thunderbolt path + * tb_path_alloc() - allocate a thunderbolt path between two ports + * @tb: Domain pointer + * @src: Source port of the path + * @src_hopid: HopID used for the first ingress port in the path + * @dst: Destination port of the path + * @dst_hopid: HopID used for the last egress port in the path + * @link_nr: Preferred link if there are dual links on the path + * @name: Name of the path + * + * Creates path between two ports starting with given @src_hopid. Reserves + * HopIDs for each port (they can be different from @src_hopid depending on + * how many HopIDs each port already have reserved). If there are dual + * links on the path, prioritizes using @link_nr. * * Return: Returns a tb_path on success or NULL on failure. */ -struct tb_path *tb_path_alloc(struct tb *tb, int num_hops) +struct tb_path *tb_path_alloc(struct tb *tb, struct tb_port *src, int src_hopid, + struct tb_port *dst, int dst_hopid, int link_nr, + const char *name) { - struct tb_path *path = kzalloc(sizeof(*path), GFP_KERNEL); + struct tb_port *in_port, *out_port; + int in_hopid, out_hopid; + struct tb_path *path; + size_t num_hops; + int i, ret; + + path = kzalloc(sizeof(*path), GFP_KERNEL); if (!path) return NULL; + + /* + * Number of hops on a path is the distance between the two + * switches plus the source adapter port. + */ + num_hops = abs(tb_route_length(tb_route(src->sw)) - + tb_route_length(tb_route(dst->sw))) + 1; + path->hops = kcalloc(num_hops, sizeof(*path->hops), GFP_KERNEL); if (!path->hops) { kfree(path); return NULL; } + + in_hopid = src_hopid; + out_port = NULL; + + for (i = 0; i < num_hops; i++) { + in_port = tb_next_port_on_path(src, dst, out_port); + if (!in_port) + goto err; + + if (in_port->dual_link_port && in_port->link_nr != link_nr) + in_port = in_port->dual_link_port; + + ret = tb_port_alloc_in_hopid(in_port, in_hopid, in_hopid); + if (ret < 0) + goto err; + in_hopid = ret; + + out_port = tb_next_port_on_path(src, dst, in_port); + if (!out_port) + goto err; + + if (out_port->dual_link_port && out_port->link_nr != link_nr) + out_port = out_port->dual_link_port; + + if (i == num_hops - 1) + ret = tb_port_alloc_out_hopid(out_port, dst_hopid, + dst_hopid); + else + ret = tb_port_alloc_out_hopid(out_port, -1, -1); + + if (ret < 0) + goto err; + out_hopid = ret; + + path->hops[i].in_hop_index = in_hopid; + path->hops[i].in_port = in_port; + path->hops[i].in_counter_index = -1; + path->hops[i].out_port = out_port; + path->hops[i].next_hop_index = out_hopid; + + in_hopid = out_hopid; + } + path->tb = tb; path->path_length = num_hops; + path->name = name; + return path; + +err: + tb_path_free(path); + return NULL; } /** @@ -55,10 +132,24 @@ struct tb_path *tb_path_alloc(struct tb *tb, int num_hops) */ void tb_path_free(struct tb_path *path) { + int i; + if (path->activated) { tb_WARN(path->tb, "trying to free an activated path\n") return; } + + for (i = 0; i < path->path_length; i++) { + const struct tb_path_hop *hop = &path->hops[i]; + + if (hop->in_port) + tb_port_release_in_hopid(hop->in_port, + hop->in_hop_index); + if (hop->out_port) + tb_port_release_out_hopid(hop->out_port, + hop->next_hop_index); + } + kfree(path->hops); kfree(path); } @@ -133,12 +224,12 @@ void tb_path_deactivate(struct tb_path *path) tb_WARN(path->tb, "trying to deactivate an inactive path\n"); return; } - tb_info(path->tb, - "deactivating path from %llx:%x to %llx:%x\n", - tb_route(path->hops[0].in_port->sw), - path->hops[0].in_port->port, - tb_route(path->hops[path->path_length - 1].out_port->sw), - path->hops[path->path_length - 1].out_port->port); + tb_dbg(path->tb, + "deactivating %s path from %llx:%x to %llx:%x\n", + path->name, tb_route(path->hops[0].in_port->sw), + path->hops[0].in_port->port, + tb_route(path->hops[path->path_length - 1].out_port->sw), + path->hops[path->path_length - 1].out_port->port); __tb_path_deactivate_hops(path, 0); __tb_path_deallocate_nfc(path, 0); path->activated = false; @@ -161,12 +252,12 @@ int tb_path_activate(struct tb_path *path) return -EINVAL; } - tb_info(path->tb, - "activating path from %llx:%x to %llx:%x\n", - tb_route(path->hops[0].in_port->sw), - path->hops[0].in_port->port, - tb_route(path->hops[path->path_length - 1].out_port->sw), - path->hops[path->path_length - 1].out_port->port); + tb_dbg(path->tb, + "activating %s path from %llx:%x to %llx:%x\n", + path->name, tb_route(path->hops[0].in_port->sw), + path->hops[0].in_port->port, + tb_route(path->hops[path->path_length - 1].out_port->sw), + path->hops[path->path_length - 1].out_port->port); /* Clear counters. */ for (i = path->path_length - 1; i >= 0; i--) { diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 11d5ab53ad36..322bbdc00d95 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -147,11 +147,22 @@ struct tb_port { /** * struct tb_path_hop - routing information for a tb_path + * @in_port: Ingress port of a switch + * @out_port: Egress port of a switch where the packet is routed out + * (must be on the same switch than @in_port) + * @in_hop_index: HopID where the path configuration entry is placed in + * the path config space of @in_port. + * @in_counter_index: Used counter index (not used in the driver + * currently, %-1 to disable) + * @next_hop_index: HopID of the packet when it is routed out from @out_port * * Hop configuration is always done on the IN port of a switch. * in_port and out_port have to be on the same switch. Packets arriving on * in_port with "hop" = in_hop_index will get routed to through out_port. The - * next hop to take (on out_port->remote) is determined by next_hop_index. + * next hop to take (on out_port->remote) is determined by + * next_hop_index. When routing packet to another switch (out->remote is + * set) the @next_hop_index must match the @in_hop_index of that next + * hop to make routing possible. * * in_counter_index is the index of a counter (in TB_CFG_COUNTERS) on the in * port. @@ -160,31 +171,50 @@ struct tb_path_hop { struct tb_port *in_port; struct tb_port *out_port; int in_hop_index; - int in_counter_index; /* write -1 to disable counters for this hop. */ + int in_counter_index; int next_hop_index; }; /** * enum tb_path_port - path options mask + * @TB_PATH_NONE: Do not activate on any hop on path + * @TB_PATH_SOURCE: Activate on the first hop (out of src) + * @TB_PATH_INTERNAL: Activate on the intermediate hops (not the first/last) + * @TB_PATH_DESTINATION: Activate on the last hop (into dst) + * @TB_PATH_ALL: Activate on all hops on the path */ enum tb_path_port { TB_PATH_NONE = 0, - TB_PATH_SOURCE = 1, /* activate on the first hop (out of src) */ - TB_PATH_INTERNAL = 2, /* activate on other hops (not the first/last) */ - TB_PATH_DESTINATION = 4, /* activate on the last hop (into dst) */ + TB_PATH_SOURCE = 1, + TB_PATH_INTERNAL = 2, + TB_PATH_DESTINATION = 4, TB_PATH_ALL = 7, }; /** * struct tb_path - a unidirectional path between two ports + * @tb: Pointer to the domain structure + * @name: Name of the path (used for debugging) + * @nfc_credits: Number of non flow controlled credits allocated for the path + * @ingress_shared_buffer: Shared buffering used for ingress ports on the path + * @egress_shared_buffer: Shared buffering used for egress ports on the path + * @ingress_fc_enable: Flow control for ingress ports on the path + * @egress_fc_enable: Flow control for egress ports on the path + * @priority: Priority group if the path + * @weight: Weight of the path inside the priority group + * @drop_packages: Drop packages from queue tail or head + * @activated: Is the path active + * @hops: Path hops + * @path_length: How many hops the path uses * - * A path consists of a number of hops (see tb_path_hop). To establish a PCIe - * tunnel two paths have to be created between the two PCIe ports. - * + * A path consists of a number of hops (see &struct tb_path_hop). To + * establish a PCIe tunnel two paths have to be created between the two + * PCIe ports. */ struct tb_path { struct tb *tb; - int nfc_credits; /* non flow controlled credits */ + const char *name; + int nfc_credits; enum tb_path_port ingress_shared_buffer; enum tb_path_port egress_shared_buffer; enum tb_path_port ingress_fc_enable; @@ -195,7 +225,7 @@ struct tb_path { bool drop_packages; bool activated; struct tb_path_hop *hops; - int path_length; /* number of hops */ + int path_length; }; /* HopIDs 0-7 are reserved by the Thunderbolt protocol */ @@ -503,7 +533,9 @@ int tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap); int tb_pci_port_enable(struct tb_port *port, bool enable); -struct tb_path *tb_path_alloc(struct tb *tb, int num_hops); +struct tb_path *tb_path_alloc(struct tb *tb, struct tb_port *src, int src_hopid, + struct tb_port *dst, int dst_hopid, int link_nr, + const char *name); void tb_path_free(struct tb_path *path); int tb_path_activate(struct tb_path *path); void tb_path_deactivate(struct tb_path *path); diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index 20ce28276f7a..91d7e00516b4 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -12,6 +12,9 @@ #include "tunnel.h" #include "tb.h" +/* PCIe adapters use always HopID of 8 for both directions */ +#define TB_PCI_HOPID 8 + #define TB_PCI_PATH_DOWN 0 #define TB_PCI_PATH_UP 1 @@ -86,21 +89,13 @@ static void tb_pci_init_path(struct tb_path *path) * Allocate a PCI tunnel. The ports must be of type TB_TYPE_PCIE_UP and * TB_TYPE_PCIE_DOWN. * - * Currently only paths consisting of two hops are supported (that is the - * ports must be on "adjacent" switches). - * - * The paths are hard-coded to use hop 8 (the only working hop id available on - * my thunderbolt devices). Therefore at most ONE path per device may be - * activated. - * * Return: Returns a tb_tunnel on success or NULL on failure. */ struct tb_tunnel *tb_tunnel_alloc_pci(struct tb *tb, struct tb_port *up, struct tb_port *down) { - struct tb_path *path_to_up; - struct tb_path *path_to_down; struct tb_tunnel *tunnel; + struct tb_path *path; tunnel = tb_tunnel_alloc(tb, 2); if (!tunnel) @@ -110,46 +105,23 @@ struct tb_tunnel *tb_tunnel_alloc_pci(struct tb *tb, struct tb_port *up, tunnel->src_port = down; tunnel->dst_port = up; - path_to_up = tb_path_alloc(tb, 2); - if (!path_to_up) { + path = tb_path_alloc(tb, down, TB_PCI_HOPID, up, TB_PCI_HOPID, 0, + "PCIe Down"); + if (!path) { tb_tunnel_free(tunnel); return NULL; } - tunnel->paths[TB_PCI_PATH_UP] = path_to_up; + tb_pci_init_path(path); + tunnel->paths[TB_PCI_PATH_UP] = path; - path_to_down = tb_path_alloc(tb, 2); - if (!path_to_down) { + path = tb_path_alloc(tb, up, TB_PCI_HOPID, down, TB_PCI_HOPID, 0, + "PCIe Up"); + if (!path) { tb_tunnel_free(tunnel); return NULL; } - tunnel->paths[TB_PCI_PATH_DOWN] = path_to_down; - - tb_pci_init_path(path_to_up); - tb_pci_init_path(path_to_down); - - path_to_up->hops[0].in_port = down; - path_to_up->hops[0].in_hop_index = 8; - path_to_up->hops[0].in_counter_index = -1; - path_to_up->hops[0].out_port = tb_upstream_port(up->sw)->remote; - path_to_up->hops[0].next_hop_index = 8; - - path_to_up->hops[1].in_port = tb_upstream_port(up->sw); - path_to_up->hops[1].in_hop_index = 8; - path_to_up->hops[1].in_counter_index = -1; - path_to_up->hops[1].out_port = up; - path_to_up->hops[1].next_hop_index = 8; - - path_to_down->hops[0].in_port = up; - path_to_down->hops[0].in_hop_index = 8; - path_to_down->hops[0].in_counter_index = -1; - path_to_down->hops[0].out_port = tb_upstream_port(up->sw); - path_to_down->hops[0].next_hop_index = 8; - - path_to_down->hops[1].in_port = tb_upstream_port(up->sw)->remote; - path_to_down->hops[1].in_hop_index = 8; - path_to_down->hops[1].in_counter_index = -1; - path_to_down->hops[1].out_port = down; - path_to_down->hops[1].next_hop_index = 8; + tb_pci_init_path(path); + tunnel->paths[TB_PCI_PATH_DOWN] = path; return tunnel; } From aae9e27f3b72ed58d6b87c8f511e7812601a93c5 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sun, 19 Feb 2017 23:37:35 +0200 Subject: [PATCH 099/255] thunderbolt: Deactivate all paths before restarting them State of the connected devices and tunnel configuration is not known during resume. For example some paths may not be complete anymore if the user has unplugged the related devices. So instead of marking all paths as inactive we go ahead and deactivate them explicitly before we restart them. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/tunnel.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index 91d7e00516b4..e109578da175 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -185,8 +185,18 @@ int tb_tunnel_restart(struct tb_tunnel *tunnel) tb_tunnel_info(tunnel, "activating\n"); + /* + * Make sure all paths are properly disabled before enabling + * them again. + */ + for (i = 0; i < tunnel->npaths; i++) { + if (tunnel->paths[i]->activated) { + tb_path_deactivate(tunnel->paths[i]); + tunnel->paths[i]->activated = false; + } + } + for (i = 0; i < tunnel->npaths; i++) { - tunnel->paths[i]->activated = false; res = tb_path_activate(tunnel->paths[i]); if (res) goto err; From 0414bec5f39a3c73fa56474b1bcd899101c2727d Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sun, 19 Feb 2017 23:43:26 +0200 Subject: [PATCH 100/255] thunderbolt: Discover preboot PCIe paths the boot firmware established In Apple Macs the boot firmware (EFI) connects all devices automatically when the system is started, before it hands over to the OS. Instead of ignoring we discover all those PCIe tunnels and record them using our internal structures, just like we do when a device is connected after the OS is already up. By doing this we can properly tear down tunnels when devices are disconnected. Also this allows us to resume the existing tunnels after system suspend/resume cycle. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/path.c | 204 +++++++++++++++++++++++++++++++---- drivers/thunderbolt/switch.c | 14 +++ drivers/thunderbolt/tb.c | 39 +++++++ drivers/thunderbolt/tb.h | 18 ++++ drivers/thunderbolt/tunnel.c | 86 ++++++++++++++- drivers/thunderbolt/tunnel.h | 4 +- 6 files changed, 340 insertions(+), 25 deletions(-) diff --git a/drivers/thunderbolt/path.c b/drivers/thunderbolt/path.c index a7cdac7f6808..670a12e60d66 100644 --- a/drivers/thunderbolt/path.c +++ b/drivers/thunderbolt/path.c @@ -1,8 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Thunderbolt Cactus Ridge driver - path/tunnel functionality + * Thunderbolt driver - path/tunnel functionality * * Copyright (c) 2014 Andreas Noever + * Copyright (C) 2019, Intel Corporation */ #include @@ -12,7 +13,6 @@ #include "tb.h" - static void tb_dump_hop(struct tb_port *port, struct tb_regs_hop *hop) { tb_port_dbg(port, " Hop through port %d to hop %d (%s)\n", @@ -30,6 +30,182 @@ static void tb_dump_hop(struct tb_port *port, struct tb_regs_hop *hop) hop->unknown1, hop->unknown2, hop->unknown3); } +static struct tb_port *tb_path_find_dst_port(struct tb_port *src, int src_hopid, + int dst_hopid) +{ + struct tb_port *port, *out_port = NULL; + struct tb_regs_hop hop; + struct tb_switch *sw; + int i, ret, hopid; + + hopid = src_hopid; + port = src; + + for (i = 0; port && i < TB_PATH_MAX_HOPS; i++) { + sw = port->sw; + + ret = tb_port_read(port, &hop, TB_CFG_HOPS, 2 * hopid, 2); + if (ret) { + tb_port_warn(port, "failed to read path at %d\n", hopid); + return NULL; + } + + if (!hop.enable) + return NULL; + + out_port = &sw->ports[hop.out_port]; + hopid = hop.next_hop; + port = out_port->remote; + } + + return out_port && hopid == dst_hopid ? out_port : NULL; +} + +static int tb_path_find_src_hopid(struct tb_port *src, + const struct tb_port *dst, int dst_hopid) +{ + struct tb_port *out; + int i; + + for (i = TB_PATH_MIN_HOPID; i <= src->config.max_in_hop_id; i++) { + out = tb_path_find_dst_port(src, i, dst_hopid); + if (out == dst) + return i; + } + + return 0; +} + +/** + * tb_path_discover() - Discover a path + * @src: First input port of a path + * @src_hopid: Starting HopID of a path (%-1 if don't care) + * @dst: Expected destination port of the path (%NULL if don't care) + * @dst_hopid: HopID to the @dst (%-1 if don't care) + * @last: Last port is filled here if not %NULL + * @name: Name of the path + * + * Follows a path starting from @src and @src_hopid to the last output + * port of the path. Allocates HopIDs for the visited ports. Call + * tb_path_free() to release the path and allocated HopIDs when the path + * is not needed anymore. + * + * Note function discovers also incomplete paths so caller should check + * that the @dst port is the expected one. If it is not, the path can be + * cleaned up by calling tb_path_deactivate() before tb_path_free(). + * + * Return: Discovered path on success, %NULL in case of failure + */ +struct tb_path *tb_path_discover(struct tb_port *src, int src_hopid, + struct tb_port *dst, int dst_hopid, + struct tb_port **last, const char *name) +{ + struct tb_port *out_port; + struct tb_regs_hop hop; + struct tb_path *path; + struct tb_switch *sw; + struct tb_port *p; + size_t num_hops; + int ret, i, h; + + if (src_hopid < 0 && dst) { + /* + * For incomplete paths the intermediate HopID can be + * different from the one used by the protocol adapter + * so in that case find a path that ends on @dst with + * matching @dst_hopid. That should give us the correct + * HopID for the @src. + */ + src_hopid = tb_path_find_src_hopid(src, dst, dst_hopid); + if (!src_hopid) + return NULL; + } + + p = src; + h = src_hopid; + num_hops = 0; + + for (i = 0; p && i < TB_PATH_MAX_HOPS; i++) { + sw = p->sw; + + ret = tb_port_read(p, &hop, TB_CFG_HOPS, 2 * h, 2); + if (ret) { + tb_port_warn(p, "failed to read path at %d\n", h); + return NULL; + } + + /* If the hop is not enabled we got an incomplete path */ + if (!hop.enable) + break; + + out_port = &sw->ports[hop.out_port]; + if (last) + *last = out_port; + + h = hop.next_hop; + p = out_port->remote; + num_hops++; + } + + path = kzalloc(sizeof(*path), GFP_KERNEL); + if (!path) + return NULL; + + path->name = name; + path->tb = src->sw->tb; + path->path_length = num_hops; + path->activated = true; + + path->hops = kcalloc(num_hops, sizeof(*path->hops), GFP_KERNEL); + if (!path->hops) { + kfree(path); + return NULL; + } + + p = src; + h = src_hopid; + + for (i = 0; i < num_hops; i++) { + int next_hop; + + sw = p->sw; + + ret = tb_port_read(p, &hop, TB_CFG_HOPS, 2 * h, 2); + if (ret) { + tb_port_warn(p, "failed to read path at %d\n", h); + goto err; + } + + if (tb_port_alloc_in_hopid(p, h, h) < 0) + goto err; + + out_port = &sw->ports[hop.out_port]; + next_hop = hop.next_hop; + + if (tb_port_alloc_out_hopid(out_port, next_hop, next_hop) < 0) { + tb_port_release_in_hopid(p, h); + goto err; + } + + path->hops[i].in_port = p; + path->hops[i].in_hop_index = h; + path->hops[i].in_counter_index = -1; + path->hops[i].out_port = out_port; + path->hops[i].next_hop_index = next_hop; + + h = next_hop; + p = out_port->remote; + } + + return path; + +err: + tb_port_warn(src, "failed to discover path starting at HopID %d\n", + src_hopid); + tb_path_free(path); + return NULL; +} + /** * tb_path_alloc() - allocate a thunderbolt path between two ports * @tb: Domain pointer @@ -283,30 +459,14 @@ int tb_path_activate(struct tb_path *path) for (i = path->path_length - 1; i >= 0; i--) { struct tb_regs_hop hop = { 0 }; - /* - * We do (currently) not tear down paths setup by the firmeware. - * If a firmware device is unplugged and plugged in again then - * it can happen that we reuse some of the hops from the (now - * defunct) firmeware path. This causes the hotplug operation to - * fail (the pci device does not show up). Clearing the hop - * before overwriting it fixes the problem. - * - * Should be removed once we discover and tear down firmeware - * paths. - */ - res = tb_port_write(path->hops[i].in_port, &hop, TB_CFG_HOPS, - 2 * path->hops[i].in_hop_index, 2); - if (res) { - __tb_path_deactivate_hops(path, i); - __tb_path_deallocate_nfc(path, 0); - goto err; - } + /* If it is left active deactivate it first */ + __tb_path_deactivate_hop(path->hops[i].in_port, + path->hops[i].in_hop_index); /* dword 0 */ hop.next_hop = path->hops[i].next_hop_index; hop.out_port = path->hops[i].out_port->port; - /* TODO: figure out why these are good values */ - hop.initial_credits = (i == path->path_length - 1) ? 16 : 7; + hop.initial_credits = path->hops[i].initial_credits; hop.unknown1 = 0; hop.enable = 1; diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index ecd41f7b7649..00aec2124f79 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -730,6 +730,20 @@ struct tb_port *tb_next_port_on_path(struct tb_port *start, struct tb_port *end, return next; } +/** + * tb_pci_port_is_enabled() - Is the PCIe adapter port enabled + * @port: PCIe port to check + */ +bool tb_pci_port_is_enabled(struct tb_port *port) +{ + u32 data; + + if (tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap, 1)) + return false; + + return !!(data & TB_PCI_EN); +} + /** * tb_pci_port_enable() - Enable PCIe adapter port * @port: PCIe port to enable diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 0485f4ef9a62..a62695a99835 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -29,6 +29,43 @@ struct tb_cm { /* enumeration & hot plug handling */ +static void tb_discover_tunnels(struct tb_switch *sw) +{ + struct tb *tb = sw->tb; + struct tb_cm *tcm = tb_priv(tb); + struct tb_port *port; + int i; + + for (i = 1; i <= sw->config.max_port_number; i++) { + struct tb_tunnel *tunnel = NULL; + + port = &sw->ports[i]; + switch (port->config.type) { + case TB_TYPE_PCIE_DOWN: + tunnel = tb_tunnel_discover_pci(tb, port); + break; + + default: + break; + } + + if (tunnel) { + struct tb_switch *parent = tunnel->dst_port->sw; + + while (parent != tunnel->src_port->sw) { + parent->boot = true; + parent = tb_switch_parent(parent); + } + + list_add_tail(&tunnel->list, &tcm->tunnel_list); + } + } + + for (i = 1; i <= sw->config.max_port_number; i++) { + if (tb_port_has_remote(&sw->ports[i])) + tb_discover_tunnels(sw->ports[i].remote->sw); + } +} static void tb_scan_port(struct tb_port *port); @@ -408,6 +445,8 @@ static int tb_start(struct tb *tb) /* Full scan to discover devices added before the driver was loaded. */ tb_scan_switch(tb->root_switch); + /* Find out tunnels created by the boot firmware */ + tb_discover_tunnels(tb->root_switch); tb_activate_pcie_devices(tb); /* Allow tb_handle_hotplug to progress events */ diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 322bbdc00d95..a558adf6ff10 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -155,6 +155,8 @@ struct tb_port { * @in_counter_index: Used counter index (not used in the driver * currently, %-1 to disable) * @next_hop_index: HopID of the packet when it is routed out from @out_port + * @initial_credits: Number of initial flow control credits allocated for + * the path * * Hop configuration is always done on the IN port of a switch. * in_port and out_port have to be on the same switch. Packets arriving on @@ -173,6 +175,7 @@ struct tb_path_hop { int in_hop_index; int in_counter_index; int next_hop_index; + unsigned int initial_credits; }; /** @@ -230,6 +233,7 @@ struct tb_path { /* HopIDs 0-7 are reserved by the Thunderbolt protocol */ #define TB_PATH_MIN_HOPID 8 +#define TB_PATH_MAX_HOPS 7 /** * struct tb_cm_ops - Connection manager specific operations vector @@ -346,6 +350,11 @@ static inline bool tb_port_has_remote(const struct tb_port *port) return true; } +static inline bool tb_port_is_pcie_up(const struct tb_port *port) +{ + return port && port->config.type == TB_TYPE_PCIE_UP; +} + static inline int tb_sw_read(struct tb_switch *sw, void *buffer, enum tb_cfg_space space, u32 offset, u32 length) { @@ -508,6 +517,11 @@ static inline struct tb_switch *tb_to_switch(struct device *dev) return NULL; } +static inline struct tb_switch *tb_switch_parent(struct tb_switch *sw) +{ + return tb_to_switch(sw->dev.parent); +} + static inline bool tb_switch_is_lr(const struct tb_switch *sw) { return sw->config.device_id == PCI_DEVICE_ID_INTEL_LIGHT_RIDGE; @@ -531,8 +545,12 @@ struct tb_port *tb_next_port_on_path(struct tb_port *start, struct tb_port *end, int tb_switch_find_vse_cap(struct tb_switch *sw, enum tb_switch_vse_cap vsec); int tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap); +bool tb_pci_port_is_enabled(struct tb_port *port); int tb_pci_port_enable(struct tb_port *port, bool enable); +struct tb_path *tb_path_discover(struct tb_port *src, int src_hopid, + struct tb_port *dst, int dst_hopid, + struct tb_port **last, const char *name); struct tb_path *tb_path_alloc(struct tb *tb, struct tb_port *src, int src_hopid, struct tb_port *dst, int dst_hopid, int link_nr, const char *name); diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index e109578da175..71c712300326 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -35,6 +35,8 @@ __TB_TUNNEL_PRINT(tb_warn, tunnel, fmt, ##arg) #define tb_tunnel_info(tunnel, fmt, arg...) \ __TB_TUNNEL_PRINT(tb_info, tunnel, fmt, ##arg) +#define tb_tunnel_dbg(tunnel, fmt, arg...) \ + __TB_TUNNEL_PRINT(tb_dbg, tunnel, fmt, ##arg) static struct tb_tunnel *tb_tunnel_alloc(struct tb *tb, size_t npaths) { @@ -65,7 +67,10 @@ static int tb_pci_activate(struct tb_tunnel *tunnel, bool activate) if (res) return res; - return tb_pci_port_enable(tunnel->dst_port, activate); + if (tb_port_is_pcie_up(tunnel->dst_port)) + return tb_pci_port_enable(tunnel->dst_port, activate); + + return 0; } static void tb_pci_init_path(struct tb_path *path) @@ -78,6 +83,83 @@ static void tb_pci_init_path(struct tb_path *path) path->weight = 1; path->drop_packages = 0; path->nfc_credits = 0; + path->hops[0].initial_credits = 7; + path->hops[1].initial_credits = 16; +} + +/** + * tb_tunnel_discover_pci() - Discover existing PCIe tunnels + * @tb: Pointer to the domain structure + * @down: PCIe downstream adapter + * + * If @down adapter is active, follows the tunnel to the PCIe upstream + * adapter and back. Returns the discovered tunnel or %NULL if there was + * no tunnel. + */ +struct tb_tunnel *tb_tunnel_discover_pci(struct tb *tb, struct tb_port *down) +{ + struct tb_tunnel *tunnel; + struct tb_path *path; + + if (!tb_pci_port_is_enabled(down)) + return NULL; + + tunnel = tb_tunnel_alloc(tb, 2); + if (!tunnel) + return NULL; + + tunnel->activate = tb_pci_activate; + tunnel->src_port = down; + + /* + * Discover both paths even if they are not complete. We will + * clean them up by calling tb_tunnel_deactivate() below in that + * case. + */ + path = tb_path_discover(down, TB_PCI_HOPID, NULL, -1, + &tunnel->dst_port, "PCIe Up"); + if (!path) { + /* Just disable the downstream port */ + tb_pci_port_enable(down, false); + goto err_free; + } + tunnel->paths[TB_PCI_PATH_UP] = path; + tb_pci_init_path(tunnel->paths[TB_PCI_PATH_UP]); + + path = tb_path_discover(tunnel->dst_port, -1, down, TB_PCI_HOPID, NULL, + "PCIe Down"); + if (!path) + goto err_deactivate; + tunnel->paths[TB_PCI_PATH_DOWN] = path; + tb_pci_init_path(tunnel->paths[TB_PCI_PATH_DOWN]); + + /* Validate that the tunnel is complete */ + if (!tb_port_is_pcie_up(tunnel->dst_port)) { + tb_port_warn(tunnel->dst_port, + "path does not end on a PCIe adapter, cleaning up\n"); + goto err_deactivate; + } + + if (down != tunnel->src_port) { + tb_tunnel_warn(tunnel, "path is not complete, cleaning up\n"); + goto err_deactivate; + } + + if (!tb_pci_port_is_enabled(tunnel->dst_port)) { + tb_tunnel_warn(tunnel, + "tunnel is not fully activated, cleaning up\n"); + goto err_deactivate; + } + + tb_tunnel_dbg(tunnel, "discovered\n"); + return tunnel; + +err_deactivate: + tb_tunnel_deactivate(tunnel); +err_free: + tb_tunnel_free(tunnel); + + return NULL; } /** @@ -253,7 +335,7 @@ void tb_tunnel_deactivate(struct tb_tunnel *tunnel) tunnel->activate(tunnel, false); for (i = 0; i < tunnel->npaths; i++) { - if (tunnel->paths[i]->activated) + if (tunnel->paths[i] && tunnel->paths[i]->activated) tb_path_deactivate(tunnel->paths[i]); } } diff --git a/drivers/thunderbolt/tunnel.h b/drivers/thunderbolt/tunnel.h index b4e992165e56..07bf587bed80 100644 --- a/drivers/thunderbolt/tunnel.h +++ b/drivers/thunderbolt/tunnel.h @@ -15,7 +15,8 @@ * struct tb_tunnel - Tunnel between two ports * @tb: Pointer to the domain * @src_port: Source port of the tunnel - * @dst_port: Destination port of the tunnel + * @dst_port: Destination port of the tunnel. For discovered incomplete + * tunnels may be %NULL or null adapter port instead. * @paths: All paths required by the tunnel * @npaths: Number of paths in @paths * @activate: Optional tunnel specific activation/deactivation @@ -31,6 +32,7 @@ struct tb_tunnel { struct list_head list; }; +struct tb_tunnel *tb_tunnel_discover_pci(struct tb *tb, struct tb_port *down); struct tb_tunnel *tb_tunnel_alloc_pci(struct tb *tb, struct tb_port *up, struct tb_port *down); void tb_tunnel_free(struct tb_tunnel *tunnel); From 99cabbb006f1eb509e8bbc88c020c806017ed582 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sun, 30 Dec 2018 21:34:08 +0200 Subject: [PATCH 101/255] thunderbolt: Add support for full PCIe daisy chains Currently the software connection manager (tb.c) has only supported creating a single PCIe tunnel, no PCIe device daisy chaining has been supported so far. This updates the software connection manager so that it now can create PCIe tunnels for full chain of six devices. Because PCIe allows DMA and opens possibility for DMA attacks we change security level to "user" meaning that PCIe tunneling requires that the userspace authorizes the devices first. This makes it possible to block PCIe tunneling completely while still allowing other types of tunnels to be automatically created. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/tb.c | 178 +++++++++++++++++++++++---------------- drivers/thunderbolt/tb.h | 27 ++++++ 2 files changed, 131 insertions(+), 74 deletions(-) diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index a62695a99835..cfc451c938fd 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -1,8 +1,9 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Thunderbolt Cactus Ridge driver - bus logic (NHI independent) + * Thunderbolt driver - bus logic (NHI independent) * * Copyright (c) 2014 Andreas Noever + * Copyright (C) 2019, Intel Corporation */ #include @@ -84,6 +85,7 @@ static void tb_scan_switch(struct tb_switch *sw) */ static void tb_scan_port(struct tb_port *port) { + struct tb_cm *tcm = tb_priv(port->sw->tb); struct tb_port *upstream_port; struct tb_switch *sw; @@ -112,7 +114,13 @@ static void tb_scan_port(struct tb_port *port) return; } - sw->authorized = true; + /* + * Do not send uevents until we have discovered all existing + * tunnels and know which switches were authorized already by + * the boot firmware. + */ + if (!tcm->hotplug_active) + dev_set_uevent_suppress(&sw->dev, true); if (tb_switch_add(sw)) { tb_switch_put(sw); @@ -212,72 +220,78 @@ static struct tb_port *tb_find_unused_down_port(struct tb_switch *sw) return NULL; } -/** - * tb_activate_pcie_devices() - scan for and activate PCIe devices - * - * This method is somewhat ad hoc. For now it only supports one device - * per port and only devices at depth 1. - */ -static void tb_activate_pcie_devices(struct tb *tb) +static struct tb_port *tb_find_pcie_down(struct tb_switch *sw, + const struct tb_port *port) { - int i; - int cap; - u32 data; - struct tb_switch *sw; - struct tb_port *up_port; - struct tb_port *down_port; - struct tb_tunnel *tunnel; - struct tb_cm *tcm = tb_priv(tb); + /* + * To keep plugging devices consistently in the same PCIe + * hierarchy, do mapping here for root switch downstream PCIe + * ports. + */ + if (!tb_route(sw)) { + int phy_port = tb_phy_port_from_link(port->port); + int index; - /* scan for pcie devices at depth 1*/ - for (i = 1; i <= tb->root_switch->config.max_port_number; i++) { - if (tb_is_upstream_port(&tb->root_switch->ports[i])) - continue; - if (tb->root_switch->ports[i].config.type != TB_TYPE_PORT) - continue; - if (!tb->root_switch->ports[i].remote) - continue; - sw = tb->root_switch->ports[i].remote->sw; - up_port = tb_find_pci_up_port(sw); - if (!up_port) { - tb_sw_info(sw, "no PCIe devices found, aborting\n"); - continue; - } + /* + * Hard-coded Thunderbolt port to PCIe down port mapping + * per controller. + */ + if (tb_switch_is_cr(sw)) + index = !phy_port ? 6 : 7; + else if (tb_switch_is_fr(sw)) + index = !phy_port ? 6 : 8; + else + goto out; - /* check whether port is already activated */ - cap = up_port->cap_adap; - if (!cap) - continue; - if (tb_port_read(up_port, &data, TB_CFG_PORT, cap, 1)) - continue; - if (data & 0x80000000) { - tb_port_info(up_port, - "PCIe port already activated, aborting\n"); - continue; - } + /* Validate the hard-coding */ + if (WARN_ON(index > sw->config.max_port_number)) + goto out; + if (WARN_ON(!tb_port_is_pcie_down(&sw->ports[index]))) + goto out; + if (WARN_ON(tb_pci_port_is_enabled(&sw->ports[index]))) + goto out; - down_port = tb_find_unused_down_port(tb->root_switch); - if (!down_port) { - tb_port_info(up_port, - "All PCIe down ports are occupied, aborting\n"); - continue; - } - tunnel = tb_tunnel_alloc_pci(tb, up_port, down_port); - if (!tunnel) { - tb_port_info(up_port, - "PCIe tunnel allocation failed, aborting\n"); - continue; - } - - if (tb_tunnel_activate(tunnel)) { - tb_port_info(up_port, - "PCIe tunnel activation failed, aborting\n"); - tb_tunnel_free(tunnel); - continue; - } - - list_add(&tunnel->list, &tcm->tunnel_list); + return &sw->ports[index]; } + +out: + return tb_find_unused_down_port(sw); +} + +static int tb_tunnel_pci(struct tb *tb, struct tb_switch *sw) +{ + struct tb_port *up, *down, *port; + struct tb_cm *tcm = tb_priv(tb); + struct tb_switch *parent_sw; + struct tb_tunnel *tunnel; + + up = tb_find_pci_up_port(sw); + if (!up) + return 0; + + /* + * Look up available down port. Since we are chaining it should + * be found right above this switch. + */ + parent_sw = tb_to_switch(sw->dev.parent); + port = tb_port_at(tb_route(sw), parent_sw); + down = tb_find_pcie_down(parent_sw, port); + if (!down) + return 0; + + tunnel = tb_tunnel_alloc_pci(tb, up, down); + if (!tunnel) + return -ENOMEM; + + if (tb_tunnel_activate(tunnel)) { + tb_port_info(up, + "PCIe tunnel activation failed, aborting\n"); + tb_tunnel_free(tunnel); + return -EIO; + } + + list_add_tail(&tunnel->list, &tcm->tunnel_list); + return 0; } /* hotplug handling */ @@ -344,16 +358,8 @@ static void tb_handle_hotplug(struct work_struct *work) } else { tb_port_info(port, "hotplug: scanning\n"); tb_scan_port(port); - if (!port->remote) { + if (!port->remote) tb_port_info(port, "hotplug: no switch found\n"); - } else if (port->remote->sw->config.depth > 1) { - tb_sw_warn(port->remote->sw, - "hotplug: chaining not supported\n"); - } else { - tb_sw_info(port->remote->sw, - "hotplug: activating pcie devices\n"); - tb_activate_pcie_devices(tb); - } } put_sw: @@ -414,6 +420,27 @@ static void tb_stop(struct tb *tb) tcm->hotplug_active = false; /* signal tb_handle_hotplug to quit */ } +static int tb_scan_finalize_switch(struct device *dev, void *data) +{ + if (tb_is_switch(dev)) { + struct tb_switch *sw = tb_to_switch(dev); + + /* + * If we found that the switch was already setup by the + * boot firmware, mark it as authorized now before we + * send uevent to userspace. + */ + if (sw->boot) + sw->authorized = 1; + + dev_set_uevent_suppress(dev, false); + kobject_uevent(&dev->kobj, KOBJ_ADD); + device_for_each_child(dev, NULL, tb_scan_finalize_switch); + } + + return 0; +} + static int tb_start(struct tb *tb) { struct tb_cm *tcm = tb_priv(tb); @@ -447,7 +474,9 @@ static int tb_start(struct tb *tb) tb_scan_switch(tb->root_switch); /* Find out tunnels created by the boot firmware */ tb_discover_tunnels(tb->root_switch); - tb_activate_pcie_devices(tb); + /* Make the discovered switches available to the userspace */ + device_for_each_child(&tb->root_switch->dev, NULL, + tb_scan_finalize_switch); /* Allow tb_handle_hotplug to progress events */ tcm->hotplug_active = true; @@ -502,6 +531,7 @@ static const struct tb_cm_ops tb_cm_ops = { .suspend_noirq = tb_suspend_noirq, .resume_noirq = tb_resume_noirq, .handle_event = tb_handle_event, + .approve_switch = tb_tunnel_pci, }; struct tb *tb_probe(struct tb_nhi *nhi) @@ -516,7 +546,7 @@ struct tb *tb_probe(struct tb_nhi *nhi) if (!tb) return NULL; - tb->security_level = TB_SECURITY_NONE; + tb->security_level = TB_SECURITY_USER; tb->cm_ops = &tb_cm_ops; tcm = tb_priv(tb); diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index a558adf6ff10..5b5ba8919086 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -350,6 +350,11 @@ static inline bool tb_port_has_remote(const struct tb_port *port) return true; } +static inline bool tb_port_is_pcie_down(const struct tb_port *port) +{ + return port && port->config.type == TB_TYPE_PCIE_DOWN; +} + static inline bool tb_port_is_pcie_up(const struct tb_port *port) { return port && port->config.type == TB_TYPE_PCIE_UP; @@ -532,6 +537,28 @@ static inline bool tb_switch_is_er(const struct tb_switch *sw) return sw->config.device_id == PCI_DEVICE_ID_INTEL_EAGLE_RIDGE; } +static inline bool tb_switch_is_cr(const struct tb_switch *sw) +{ + switch (sw->config.device_id) { + case PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_2C: + case PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_4C: + return true; + default: + return false; + } +} + +static inline bool tb_switch_is_fr(const struct tb_switch *sw) +{ + switch (sw->config.device_id) { + case PCI_DEVICE_ID_INTEL_FALCON_RIDGE_2C_BRIDGE: + case PCI_DEVICE_ID_INTEL_FALCON_RIDGE_4C_BRIDGE: + return true; + default: + return false; + } +} + int tb_wait_for_port(struct tb_port *port, bool wait_if_unplugged); int tb_port_add_nfc_credits(struct tb_port *port, int credits); int tb_port_clear_counter(struct tb_port *port, int counter); From 344e06430a72347b554a7fd98f3a961084f37be6 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 11 Oct 2017 17:19:54 +0300 Subject: [PATCH 102/255] thunderbolt: Scan only valid NULL adapter ports in hotplug The only way to expand Thunderbolt topology is through the NULL adapter ports (typically ports 1, 2, 3 and 4). There is no point handling Thunderbolt hotplug events on any other port. Add a helper function (tb_port_is_null()) that can be used to determine if the port is NULL port, and use it in software connection manager code when hotplug event is handled. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/tb.c | 10 ++++++---- drivers/thunderbolt/tb.h | 5 +++++ 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index cfc451c938fd..fb01396a62a9 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -356,10 +356,12 @@ static void tb_handle_hotplug(struct work_struct *work) tb_port_info(port, "got plug event for connected port, ignoring\n"); } else { - tb_port_info(port, "hotplug: scanning\n"); - tb_scan_port(port); - if (!port->remote) - tb_port_info(port, "hotplug: no switch found\n"); + if (tb_port_is_null(port)) { + tb_port_info(port, "hotplug: scanning\n"); + tb_scan_port(port); + if (!port->remote) + tb_port_info(port, "hotplug: no switch found\n"); + } } put_sw: diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 5b5ba8919086..260360ec59a9 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -350,6 +350,11 @@ static inline bool tb_port_has_remote(const struct tb_port *port) return true; } +static inline bool tb_port_is_null(const struct tb_port *port) +{ + return port && port->port && port->config.type == TB_TYPE_PORT; +} + static inline bool tb_port_is_pcie_down(const struct tb_port *port) { return port && port->config.type == TB_TYPE_PCIE_DOWN; From e78db6f08b6a2a50eea9ed4146f019026491d63c Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 12 Oct 2017 16:45:50 +0300 Subject: [PATCH 103/255] thunderbolt: Generalize port finding routines to support all port types We will be needing these routines to find Display Port adapters as well so modify them to take port type as the second parameter. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/switch.c | 16 ++++++++++++++++ drivers/thunderbolt/tb.c | 35 +++++++++++++++++------------------ drivers/thunderbolt/tb.h | 1 + 3 files changed, 34 insertions(+), 18 deletions(-) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 00aec2124f79..028e9a293382 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -730,6 +730,22 @@ struct tb_port *tb_next_port_on_path(struct tb_port *start, struct tb_port *end, return next; } +/** + * tb_port_is_enabled() - Is the adapter port enabled + * @port: Port to check + */ +bool tb_port_is_enabled(struct tb_port *port) +{ + switch (port->config.type) { + case TB_TYPE_PCIE_UP: + case TB_TYPE_PCIE_DOWN: + return tb_pci_port_is_enabled(port); + + default: + return false; + } +} + /** * tb_pci_port_is_enabled() - Is the PCIe adapter port enabled * @port: PCIe port to check diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index fb01396a62a9..903922a16d64 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -180,40 +180,39 @@ static void tb_free_unplugged_children(struct tb_switch *sw) } } - /** - * find_pci_up_port() - return the first PCIe up port on @sw or NULL + * tb_find_port() - return the first port of @type on @sw or NULL + * @sw: Switch to find the port from + * @type: Port type to look for */ -static struct tb_port *tb_find_pci_up_port(struct tb_switch *sw) +static struct tb_port *tb_find_port(struct tb_switch *sw, + enum tb_port_type type) { int i; for (i = 1; i <= sw->config.max_port_number; i++) - if (sw->ports[i].config.type == TB_TYPE_PCIE_UP) + if (sw->ports[i].config.type == type) return &sw->ports[i]; return NULL; } /** - * find_unused_down_port() - return the first inactive PCIe down port on @sw + * tb_find_unused_port() - return the first inactive port on @sw + * @sw: Switch to find the port on + * @type: Port type to look for */ -static struct tb_port *tb_find_unused_down_port(struct tb_switch *sw) +static struct tb_port *tb_find_unused_port(struct tb_switch *sw, + enum tb_port_type type) { int i; - int cap; - int res; - int data; + for (i = 1; i <= sw->config.max_port_number; i++) { if (tb_is_upstream_port(&sw->ports[i])) continue; - if (sw->ports[i].config.type != TB_TYPE_PCIE_DOWN) + if (sw->ports[i].config.type != type) continue; - cap = sw->ports[i].cap_adap; - if (!cap) + if (!sw->ports[i].cap_adap) continue; - res = tb_port_read(&sw->ports[i], &data, TB_CFG_PORT, cap, 1); - if (res < 0) - continue; - if (data & 0x80000000) + if (tb_port_is_enabled(&sw->ports[i])) continue; return &sw->ports[i]; } @@ -255,7 +254,7 @@ static struct tb_port *tb_find_pcie_down(struct tb_switch *sw, } out: - return tb_find_unused_down_port(sw); + return tb_find_unused_port(sw, TB_TYPE_PCIE_DOWN); } static int tb_tunnel_pci(struct tb *tb, struct tb_switch *sw) @@ -265,7 +264,7 @@ static int tb_tunnel_pci(struct tb *tb, struct tb_switch *sw) struct tb_switch *parent_sw; struct tb_tunnel *tunnel; - up = tb_find_pci_up_port(sw); + up = tb_find_port(sw, TB_TYPE_PCIE_UP); if (!up) return 0; diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 260360ec59a9..e6040c9f68fa 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -576,6 +576,7 @@ struct tb_port *tb_next_port_on_path(struct tb_port *start, struct tb_port *end, int tb_switch_find_vse_cap(struct tb_switch *sw, enum tb_switch_vse_cap vsec); int tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap); +bool tb_port_is_enabled(struct tb_port *port); bool tb_pci_port_is_enabled(struct tb_port *port); int tb_pci_port_enable(struct tb_port *port, bool enable); From c5ee6feb34709da96f9909b8a2e1e42875020efb Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Thu, 11 Oct 2018 11:38:22 +0300 Subject: [PATCH 104/255] thunderbolt: Rework NFC credits handling NFC (non flow control) credits is actually 20-bit field so update tb_port_add_nfc_credits() to handle this properly. This allows us to set NFC credits for Display Port path in subsequent patches. Also make sure the function does not update the hardware if the underlying switch is already unplugged. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/switch.c | 20 +++++++++++++------- drivers/thunderbolt/tb_regs.h | 3 +++ 2 files changed, 16 insertions(+), 7 deletions(-) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 028e9a293382..9462e6982061 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -537,14 +537,20 @@ int tb_wait_for_port(struct tb_port *port, bool wait_if_unplugged) */ int tb_port_add_nfc_credits(struct tb_port *port, int credits) { - if (credits == 0) + u32 nfc_credits; + + if (credits == 0 || port->sw->is_unplugged) return 0; - tb_port_info(port, - "adding %#x NFC credits (%#x -> %#x)", - credits, - port->config.nfc_credits, - port->config.nfc_credits + credits); - port->config.nfc_credits += credits; + + nfc_credits = port->config.nfc_credits & TB_PORT_NFC_CREDITS_MASK; + nfc_credits += credits; + + tb_port_dbg(port, "adding %d NFC credits to %lu", + credits, port->config.nfc_credits & TB_PORT_NFC_CREDITS_MASK); + + port->config.nfc_credits &= ~TB_PORT_NFC_CREDITS_MASK; + port->config.nfc_credits |= nfc_credits; + return tb_port_write(port, &port->config.nfc_credits, TB_CFG_PORT, 4, 1); } diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h index 75e935acade5..74c0f4a5606d 100644 --- a/drivers/thunderbolt/tb_regs.h +++ b/drivers/thunderbolt/tb_regs.h @@ -211,6 +211,9 @@ struct tb_regs_port_header { } __packed; +/* DWORD 4 */ +#define TB_PORT_NFC_CREDITS_MASK GENMASK(19, 0) + /* PCIe adapter registers */ #define TB_PCI_EN BIT(31) From 4f807e47ee9a75747d042a8eacf398f436da9452 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 17 Sep 2018 16:30:49 +0300 Subject: [PATCH 105/255] thunderbolt: Add support for Display Port tunnels Display Port tunnels are somewhat more complex than PCIe tunnels as it requires 3 tunnels (AUX Rx/Tx and Video). In addition we are not supposed to create the tunnels immediately when a DP OUT is enumerated. Instead we need to wait until we get hotplug event to that adapter port or check if the port has HPD set before tunnels can be established. This adds Display Port tunneling support to the software connection manager. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/switch.c | 111 ++++++++++++++ drivers/thunderbolt/tb.c | 129 +++++++++++++--- drivers/thunderbolt/tb.h | 17 +++ drivers/thunderbolt/tb_regs.h | 22 +++ drivers/thunderbolt/tunnel.c | 277 +++++++++++++++++++++++++++++++++- drivers/thunderbolt/tunnel.h | 23 +++ 6 files changed, 554 insertions(+), 25 deletions(-) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 9462e6982061..1de1afa24182 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -747,6 +747,10 @@ bool tb_port_is_enabled(struct tb_port *port) case TB_TYPE_PCIE_DOWN: return tb_pci_port_is_enabled(port); + case TB_TYPE_DP_HDMI_IN: + case TB_TYPE_DP_HDMI_OUT: + return tb_dp_port_is_enabled(port); + default: return false; } @@ -779,6 +783,113 @@ int tb_pci_port_enable(struct tb_port *port, bool enable) return tb_port_write(port, &word, TB_CFG_PORT, port->cap_adap, 1); } +/** + * tb_dp_port_hpd_is_active() - Is HPD already active + * @port: DP out port to check + * + * Checks if the DP OUT adapter port has HDP bit already set. + */ +int tb_dp_port_hpd_is_active(struct tb_port *port) +{ + u32 data; + int ret; + + ret = tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap + 2, 1); + if (ret) + return ret; + + return !!(data & TB_DP_HDP); +} + +/** + * tb_dp_port_hpd_clear() - Clear HPD from DP IN port + * @port: Port to clear HPD + * + * If the DP IN port has HDP set, this function can be used to clear it. + */ +int tb_dp_port_hpd_clear(struct tb_port *port) +{ + u32 data; + int ret; + + ret = tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap + 3, 1); + if (ret) + return ret; + + data |= TB_DP_HPDC; + return tb_port_write(port, &data, TB_CFG_PORT, port->cap_adap + 3, 1); +} + +/** + * tb_dp_port_set_hops() - Set video/aux Hop IDs for DP port + * @port: DP IN/OUT port to set hops + * @video: Video Hop ID + * @aux_tx: AUX TX Hop ID + * @aux_rx: AUX RX Hop ID + * + * Programs specified Hop IDs for DP IN/OUT port. + */ +int tb_dp_port_set_hops(struct tb_port *port, unsigned int video, + unsigned int aux_tx, unsigned int aux_rx) +{ + u32 data[2]; + int ret; + + ret = tb_port_read(port, data, TB_CFG_PORT, port->cap_adap, + ARRAY_SIZE(data)); + if (ret) + return ret; + + data[0] &= ~TB_DP_VIDEO_HOPID_MASK; + data[1] &= ~(TB_DP_AUX_RX_HOPID_MASK | TB_DP_AUX_TX_HOPID_MASK); + + data[0] |= (video << TB_DP_VIDEO_HOPID_SHIFT) & TB_DP_VIDEO_HOPID_MASK; + data[1] |= aux_tx & TB_DP_AUX_TX_HOPID_MASK; + data[1] |= (aux_rx << TB_DP_AUX_RX_HOPID_SHIFT) & TB_DP_AUX_RX_HOPID_MASK; + + return tb_port_write(port, data, TB_CFG_PORT, port->cap_adap, + ARRAY_SIZE(data)); +} + +/** + * tb_dp_port_is_enabled() - Is DP adapter port enabled + * @port: DP adapter port to check + */ +bool tb_dp_port_is_enabled(struct tb_port *port) +{ + u32 data; + + if (tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap, 1)) + return false; + + return !!(data & (TB_DP_VIDEO_EN | TB_DP_AUX_EN)); +} + +/** + * tb_dp_port_enable() - Enables/disables DP paths of a port + * @port: DP IN/OUT port + * @enable: Enable/disable DP path + * + * Once Hop IDs are programmed DP paths can be enabled or disabled by + * calling this function. + */ +int tb_dp_port_enable(struct tb_port *port, bool enable) +{ + u32 data; + int ret; + + ret = tb_port_read(port, &data, TB_CFG_PORT, port->cap_adap, 1); + if (ret) + return ret; + + if (enable) + data |= TB_DP_VIDEO_EN | TB_DP_AUX_EN; + else + data &= ~(TB_DP_VIDEO_EN | TB_DP_AUX_EN); + + return tb_port_write(port, &data, TB_CFG_PORT, port->cap_adap, 1); +} + /* switch utility functions */ static void tb_dump_switch(struct tb *tb, struct tb_regs_switch_header *sw) diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 903922a16d64..c5e96e7ac37a 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -28,6 +28,32 @@ struct tb_cm { bool hotplug_active; }; +struct tb_hotplug_event { + struct work_struct work; + struct tb *tb; + u64 route; + u8 port; + bool unplug; +}; + +static void tb_handle_hotplug(struct work_struct *work); + +static void tb_queue_hotplug(struct tb *tb, u64 route, u8 port, bool unplug) +{ + struct tb_hotplug_event *ev; + + ev = kmalloc(sizeof(*ev), GFP_KERNEL); + if (!ev) + return; + + ev->tb = tb; + ev->route = route; + ev->port = port; + ev->unplug = unplug; + INIT_WORK(&ev->work, tb_handle_hotplug); + queue_work(tb->wq, &ev->work); +} + /* enumeration & hot plug handling */ static void tb_discover_tunnels(struct tb_switch *sw) @@ -42,6 +68,10 @@ static void tb_discover_tunnels(struct tb_switch *sw) port = &sw->ports[i]; switch (port->config.type) { + case TB_TYPE_DP_HDMI_IN: + tunnel = tb_tunnel_discover_dp(tb, port); + break; + case TB_TYPE_PCIE_DOWN: tunnel = tb_tunnel_discover_pci(tb, port); break; @@ -50,16 +80,19 @@ static void tb_discover_tunnels(struct tb_switch *sw) break; } - if (tunnel) { + if (!tunnel) + continue; + + if (tb_tunnel_is_pci(tunnel)) { struct tb_switch *parent = tunnel->dst_port->sw; while (parent != tunnel->src_port->sw) { parent->boot = true; parent = tb_switch_parent(parent); } - - list_add_tail(&tunnel->list, &tcm->tunnel_list); } + + list_add_tail(&tunnel->list, &tcm->tunnel_list); } for (i = 1; i <= sw->config.max_port_number; i++) { @@ -91,6 +124,15 @@ static void tb_scan_port(struct tb_port *port) if (tb_is_upstream_port(port)) return; + + if (tb_port_is_dpout(port) && tb_dp_port_hpd_is_active(port) == 1 && + !tb_dp_port_is_enabled(port)) { + tb_port_dbg(port, "DP adapter HPD set, queuing hotplug\n"); + tb_queue_hotplug(port->sw->tb, tb_route(port->sw), port->port, + false); + return; + } + if (port->config.type != TB_TYPE_PORT) return; if (port->dual_link_port && port->link_nr) @@ -139,6 +181,26 @@ static void tb_scan_port(struct tb_port *port) tb_scan_switch(sw); } +static int tb_free_tunnel(struct tb *tb, enum tb_tunnel_type type, + struct tb_port *src_port, struct tb_port *dst_port) +{ + struct tb_cm *tcm = tb_priv(tb); + struct tb_tunnel *tunnel; + + list_for_each_entry(tunnel, &tcm->tunnel_list, list) { + if (tunnel->type == type && + ((src_port && src_port == tunnel->src_port) || + (dst_port && dst_port == tunnel->dst_port))) { + tb_tunnel_deactivate(tunnel); + list_del(&tunnel->list); + tb_tunnel_free(tunnel); + return 0; + } + } + + return -ENODEV; +} + /** * tb_free_invalid_tunnels() - destroy tunnels of devices that have gone away */ @@ -257,6 +319,44 @@ static struct tb_port *tb_find_pcie_down(struct tb_switch *sw, return tb_find_unused_port(sw, TB_TYPE_PCIE_DOWN); } +static int tb_tunnel_dp(struct tb *tb, struct tb_port *out) +{ + struct tb_cm *tcm = tb_priv(tb); + struct tb_switch *sw = out->sw; + struct tb_tunnel *tunnel; + struct tb_port *in; + + if (tb_port_is_enabled(out)) + return 0; + + do { + sw = tb_to_switch(sw->dev.parent); + if (!sw) + return 0; + in = tb_find_unused_port(sw, TB_TYPE_DP_HDMI_IN); + } while (!in); + + tunnel = tb_tunnel_alloc_dp(tb, in, out); + if (!tunnel) { + tb_port_dbg(out, "DP tunnel allocation failed\n"); + return -ENOMEM; + } + + if (tb_tunnel_activate(tunnel)) { + tb_port_info(out, "DP tunnel activation failed, aborting\n"); + tb_tunnel_free(tunnel); + return -EIO; + } + + list_add_tail(&tunnel->list, &tcm->tunnel_list); + return 0; +} + +static void tb_teardown_dp(struct tb *tb, struct tb_port *out) +{ + tb_free_tunnel(tb, TB_TUNNEL_DP, NULL, out); +} + static int tb_tunnel_pci(struct tb *tb, struct tb_switch *sw) { struct tb_port *up, *down, *port; @@ -295,14 +395,6 @@ static int tb_tunnel_pci(struct tb *tb, struct tb_switch *sw) /* hotplug handling */ -struct tb_hotplug_event { - struct work_struct work; - struct tb *tb; - u64 route; - u8 port; - bool unplug; -}; - /** * tb_handle_hotplug() - handle hotplug event * @@ -347,6 +439,8 @@ static void tb_handle_hotplug(struct work_struct *work) port->remote = NULL; if (port->dual_link_port) port->dual_link_port->remote = NULL; + } else if (tb_port_is_dpout(port)) { + tb_teardown_dp(tb, port); } else { tb_port_info(port, "got unplug event for disconnected port, ignoring\n"); @@ -360,6 +454,8 @@ static void tb_handle_hotplug(struct work_struct *work) tb_scan_port(port); if (!port->remote) tb_port_info(port, "hotplug: no switch found\n"); + } else if (tb_port_is_dpout(port)) { + tb_tunnel_dp(tb, port); } } @@ -379,7 +475,6 @@ static void tb_handle_event(struct tb *tb, enum tb_cfg_pkg_type type, const void *buf, size_t size) { const struct cfg_event_pkg *pkg = buf; - struct tb_hotplug_event *ev; u64 route; if (type != TB_CFG_PKG_EVENT) { @@ -395,15 +490,7 @@ static void tb_handle_event(struct tb *tb, enum tb_cfg_pkg_type type, pkg->port); } - ev = kmalloc(sizeof(*ev), GFP_KERNEL); - if (!ev) - return; - INIT_WORK(&ev->work, tb_handle_hotplug); - ev->tb = tb; - ev->route = route; - ev->port = pkg->port; - ev->unplug = pkg->unplug; - queue_work(tb->wq, &ev->work); + tb_queue_hotplug(tb, route, pkg->port, pkg->unplug); } static void tb_stop(struct tb *tb) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index e6040c9f68fa..56eed0bc3c2b 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -365,6 +365,16 @@ static inline bool tb_port_is_pcie_up(const struct tb_port *port) return port && port->config.type == TB_TYPE_PCIE_UP; } +static inline bool tb_port_is_dpin(const struct tb_port *port) +{ + return port && port->config.type == TB_TYPE_DP_HDMI_IN; +} + +static inline bool tb_port_is_dpout(const struct tb_port *port) +{ + return port && port->config.type == TB_TYPE_DP_HDMI_OUT; +} + static inline int tb_sw_read(struct tb_switch *sw, void *buffer, enum tb_cfg_space space, u32 offset, u32 length) { @@ -581,6 +591,13 @@ bool tb_port_is_enabled(struct tb_port *port); bool tb_pci_port_is_enabled(struct tb_port *port); int tb_pci_port_enable(struct tb_port *port, bool enable); +int tb_dp_port_hpd_is_active(struct tb_port *port); +int tb_dp_port_hpd_clear(struct tb_port *port); +int tb_dp_port_set_hops(struct tb_port *port, unsigned int video, + unsigned int aux_tx, unsigned int aux_rx); +bool tb_dp_port_is_enabled(struct tb_port *port); +int tb_dp_port_enable(struct tb_port *port, bool enable); + struct tb_path *tb_path_discover(struct tb_port *src, int src_hopid, struct tb_port *dst, int dst_hopid, struct tb_port **last, const char *name); diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h index 74c0f4a5606d..3ce705184e2c 100644 --- a/drivers/thunderbolt/tb_regs.h +++ b/drivers/thunderbolt/tb_regs.h @@ -213,6 +213,28 @@ struct tb_regs_port_header { /* DWORD 4 */ #define TB_PORT_NFC_CREDITS_MASK GENMASK(19, 0) +#define TB_PORT_MAX_CREDITS_SHIFT 20 +#define TB_PORT_MAX_CREDITS_MASK GENMASK(26, 20) + +/* Display Port adapter registers */ + +/* DWORD 0 */ +#define TB_DP_VIDEO_HOPID_SHIFT 16 +#define TB_DP_VIDEO_HOPID_MASK GENMASK(26, 16) +#define TB_DP_AUX_EN BIT(30) +#define TB_DP_VIDEO_EN BIT(31) +/* DWORD 1 */ +#define TB_DP_AUX_TX_HOPID_MASK GENMASK(10, 0) +#define TB_DP_AUX_RX_HOPID_SHIFT 11 +#define TB_DP_AUX_RX_HOPID_MASK GENMASK(21, 11) +/* DWORD 2 */ +#define TB_DP_HDP BIT(6) +/* DWORD 3 */ +#define TB_DP_HPDC BIT(9) +/* DWORD 4 */ +#define TB_DP_LOCAL_CAP 0x4 +/* DWORD 5 */ +#define TB_DP_REMOTE_CAP 0x5 /* PCIe adapter registers */ diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index 71c712300326..21d3393c6e9c 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -18,14 +18,26 @@ #define TB_PCI_PATH_DOWN 0 #define TB_PCI_PATH_UP 1 +/* DP adapters use HopID 8 for AUX and 9 for Video */ +#define TB_DP_AUX_TX_HOPID 8 +#define TB_DP_AUX_RX_HOPID 8 +#define TB_DP_VIDEO_HOPID 9 + +#define TB_DP_VIDEO_PATH_OUT 0 +#define TB_DP_AUX_PATH_OUT 1 +#define TB_DP_AUX_PATH_IN 2 + +static const char * const tb_tunnel_names[] = { "PCI", "DP" }; + #define __TB_TUNNEL_PRINT(level, tunnel, fmt, arg...) \ do { \ struct tb_tunnel *__tunnel = (tunnel); \ - level(__tunnel->tb, "%llx:%x <-> %llx:%x (PCI): " fmt, \ + level(__tunnel->tb, "%llx:%x <-> %llx:%x (%s): " fmt, \ tb_route(__tunnel->src_port->sw), \ __tunnel->src_port->port, \ tb_route(__tunnel->dst_port->sw), \ __tunnel->dst_port->port, \ + tb_tunnel_names[__tunnel->type], \ ## arg); \ } while (0) @@ -38,7 +50,8 @@ #define tb_tunnel_dbg(tunnel, fmt, arg...) \ __TB_TUNNEL_PRINT(tb_dbg, tunnel, fmt, ##arg) -static struct tb_tunnel *tb_tunnel_alloc(struct tb *tb, size_t npaths) +static struct tb_tunnel *tb_tunnel_alloc(struct tb *tb, size_t npaths, + enum tb_tunnel_type type) { struct tb_tunnel *tunnel; @@ -55,6 +68,7 @@ static struct tb_tunnel *tb_tunnel_alloc(struct tb *tb, size_t npaths) INIT_LIST_HEAD(&tunnel->list); tunnel->tb = tb; tunnel->npaths = npaths; + tunnel->type = type; return tunnel; } @@ -104,7 +118,7 @@ struct tb_tunnel *tb_tunnel_discover_pci(struct tb *tb, struct tb_port *down) if (!tb_pci_port_is_enabled(down)) return NULL; - tunnel = tb_tunnel_alloc(tb, 2); + tunnel = tb_tunnel_alloc(tb, 2, TB_TUNNEL_PCI); if (!tunnel) return NULL; @@ -179,7 +193,7 @@ struct tb_tunnel *tb_tunnel_alloc_pci(struct tb *tb, struct tb_port *up, struct tb_tunnel *tunnel; struct tb_path *path; - tunnel = tb_tunnel_alloc(tb, 2); + tunnel = tb_tunnel_alloc(tb, 2, TB_TUNNEL_PCI); if (!tunnel) return NULL; @@ -208,6 +222,255 @@ struct tb_tunnel *tb_tunnel_alloc_pci(struct tb *tb, struct tb_port *up, return tunnel; } +static int tb_dp_xchg_caps(struct tb_tunnel *tunnel) +{ + struct tb_port *out = tunnel->dst_port; + struct tb_port *in = tunnel->src_port; + u32 in_dp_cap, out_dp_cap; + int ret; + + /* + * Copy DP_LOCAL_CAP register to DP_REMOTE_CAP register for + * newer generation hardware. + */ + if (in->sw->generation < 2 || out->sw->generation < 2) + return 0; + + /* Read both DP_LOCAL_CAP registers */ + ret = tb_port_read(in, &in_dp_cap, TB_CFG_PORT, + in->cap_adap + TB_DP_LOCAL_CAP, 1); + if (ret) + return ret; + + ret = tb_port_read(out, &out_dp_cap, TB_CFG_PORT, + out->cap_adap + TB_DP_LOCAL_CAP, 1); + if (ret) + return ret; + + /* Write IN local caps to OUT remote caps */ + ret = tb_port_write(out, &in_dp_cap, TB_CFG_PORT, + out->cap_adap + TB_DP_REMOTE_CAP, 1); + if (ret) + return ret; + + return tb_port_write(in, &out_dp_cap, TB_CFG_PORT, + in->cap_adap + TB_DP_REMOTE_CAP, 1); +} + +static int tb_dp_activate(struct tb_tunnel *tunnel, bool active) +{ + int ret; + + if (active) { + struct tb_path **paths; + int last; + + paths = tunnel->paths; + last = paths[TB_DP_VIDEO_PATH_OUT]->path_length - 1; + + tb_dp_port_set_hops(tunnel->src_port, + paths[TB_DP_VIDEO_PATH_OUT]->hops[0].in_hop_index, + paths[TB_DP_AUX_PATH_OUT]->hops[0].in_hop_index, + paths[TB_DP_AUX_PATH_IN]->hops[last].next_hop_index); + + tb_dp_port_set_hops(tunnel->dst_port, + paths[TB_DP_VIDEO_PATH_OUT]->hops[last].next_hop_index, + paths[TB_DP_AUX_PATH_IN]->hops[0].in_hop_index, + paths[TB_DP_AUX_PATH_OUT]->hops[last].next_hop_index); + } else { + tb_dp_port_hpd_clear(tunnel->src_port); + tb_dp_port_set_hops(tunnel->src_port, 0, 0, 0); + if (tb_port_is_dpout(tunnel->dst_port)) + tb_dp_port_set_hops(tunnel->dst_port, 0, 0, 0); + } + + ret = tb_dp_port_enable(tunnel->src_port, active); + if (ret) + return ret; + + if (tb_port_is_dpout(tunnel->dst_port)) + return tb_dp_port_enable(tunnel->dst_port, active); + + return 0; +} + +static void tb_dp_init_aux_path(struct tb_path *path) +{ + int i; + + path->egress_fc_enable = TB_PATH_SOURCE | TB_PATH_INTERNAL; + path->egress_shared_buffer = TB_PATH_NONE; + path->ingress_fc_enable = TB_PATH_ALL; + path->ingress_shared_buffer = TB_PATH_NONE; + path->priority = 2; + path->weight = 1; + + for (i = 0; i < path->path_length; i++) + path->hops[i].initial_credits = 1; +} + +static void tb_dp_init_video_path(struct tb_path *path, bool discover) +{ + u32 nfc_credits = path->hops[0].in_port->config.nfc_credits; + + path->egress_fc_enable = TB_PATH_NONE; + path->egress_shared_buffer = TB_PATH_NONE; + path->ingress_fc_enable = TB_PATH_NONE; + path->ingress_shared_buffer = TB_PATH_NONE; + path->priority = 1; + path->weight = 1; + + if (discover) { + path->nfc_credits = nfc_credits & TB_PORT_NFC_CREDITS_MASK; + } else { + u32 max_credits; + + max_credits = (nfc_credits & TB_PORT_MAX_CREDITS_MASK) >> + TB_PORT_MAX_CREDITS_SHIFT; + /* Leave some credits for AUX path */ + path->nfc_credits = min(max_credits - 2, 12U); + } +} + +/** + * tb_tunnel_discover_dp() - Discover existing Display Port tunnels + * @tb: Pointer to the domain structure + * @in: DP in adapter + * + * If @in adapter is active, follows the tunnel to the DP out adapter + * and back. Returns the discovered tunnel or %NULL if there was no + * tunnel. + * + * Return: DP tunnel or %NULL if no tunnel found. + */ +struct tb_tunnel *tb_tunnel_discover_dp(struct tb *tb, struct tb_port *in) +{ + struct tb_tunnel *tunnel; + struct tb_port *port; + struct tb_path *path; + + if (!tb_dp_port_is_enabled(in)) + return NULL; + + tunnel = tb_tunnel_alloc(tb, 3, TB_TUNNEL_DP); + if (!tunnel) + return NULL; + + tunnel->init = tb_dp_xchg_caps; + tunnel->activate = tb_dp_activate; + tunnel->src_port = in; + + path = tb_path_discover(in, TB_DP_VIDEO_HOPID, NULL, -1, + &tunnel->dst_port, "Video"); + if (!path) { + /* Just disable the DP IN port */ + tb_dp_port_enable(in, false); + goto err_free; + } + tunnel->paths[TB_DP_VIDEO_PATH_OUT] = path; + tb_dp_init_video_path(tunnel->paths[TB_DP_VIDEO_PATH_OUT], true); + + path = tb_path_discover(in, TB_DP_AUX_TX_HOPID, NULL, -1, NULL, "AUX TX"); + if (!path) + goto err_deactivate; + tunnel->paths[TB_DP_AUX_PATH_OUT] = path; + tb_dp_init_aux_path(tunnel->paths[TB_DP_AUX_PATH_OUT]); + + path = tb_path_discover(tunnel->dst_port, -1, in, TB_DP_AUX_RX_HOPID, + &port, "AUX RX"); + if (!path) + goto err_deactivate; + tunnel->paths[TB_DP_AUX_PATH_IN] = path; + tb_dp_init_aux_path(tunnel->paths[TB_DP_AUX_PATH_IN]); + + /* Validate that the tunnel is complete */ + if (!tb_port_is_dpout(tunnel->dst_port)) { + tb_port_warn(in, "path does not end on a DP adapter, cleaning up\n"); + goto err_deactivate; + } + + if (!tb_dp_port_is_enabled(tunnel->dst_port)) + goto err_deactivate; + + if (!tb_dp_port_hpd_is_active(tunnel->dst_port)) + goto err_deactivate; + + if (port != tunnel->src_port) { + tb_tunnel_warn(tunnel, "path is not complete, cleaning up\n"); + goto err_deactivate; + } + + tb_tunnel_dbg(tunnel, "discovered\n"); + return tunnel; + +err_deactivate: + tb_tunnel_deactivate(tunnel); +err_free: + tb_tunnel_free(tunnel); + + return NULL; +} + +/** + * tb_tunnel_alloc_dp() - allocate a Display Port tunnel + * @tb: Pointer to the domain structure + * @in: DP in adapter port + * @out: DP out adapter port + * + * Allocates a tunnel between @in and @out that is capable of tunneling + * Display Port traffic. + * + * Return: Returns a tb_tunnel on success or NULL on failure. + */ +struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in, + struct tb_port *out) +{ + struct tb_tunnel *tunnel; + struct tb_path **paths; + struct tb_path *path; + + if (WARN_ON(!in->cap_adap || !out->cap_adap)) + return NULL; + + tunnel = tb_tunnel_alloc(tb, 3, TB_TUNNEL_DP); + if (!tunnel) + return NULL; + + tunnel->init = tb_dp_xchg_caps; + tunnel->activate = tb_dp_activate; + tunnel->src_port = in; + tunnel->dst_port = out; + + paths = tunnel->paths; + + path = tb_path_alloc(tb, in, TB_DP_VIDEO_HOPID, out, TB_DP_VIDEO_HOPID, + 1, "Video"); + if (!path) + goto err_free; + tb_dp_init_video_path(path, false); + paths[TB_DP_VIDEO_PATH_OUT] = path; + + path = tb_path_alloc(tb, in, TB_DP_AUX_TX_HOPID, out, + TB_DP_AUX_TX_HOPID, 1, "AUX TX"); + if (!path) + goto err_free; + tb_dp_init_aux_path(path); + paths[TB_DP_AUX_PATH_OUT] = path; + + path = tb_path_alloc(tb, out, TB_DP_AUX_RX_HOPID, in, + TB_DP_AUX_RX_HOPID, 1, "AUX RX"); + if (!path) + goto err_free; + tb_dp_init_aux_path(path); + paths[TB_DP_AUX_PATH_IN] = path; + + return tunnel; + +err_free: + tb_tunnel_free(tunnel); + return NULL; +} + /** * tb_tunnel_free() - free a tunnel * @tunnel: Tunnel to be freed @@ -278,6 +541,12 @@ int tb_tunnel_restart(struct tb_tunnel *tunnel) } } + if (tunnel->init) { + res = tunnel->init(tunnel); + if (res) + return res; + } + for (i = 0; i < tunnel->npaths; i++) { res = tb_path_activate(tunnel->paths[i]); if (res) diff --git a/drivers/thunderbolt/tunnel.h b/drivers/thunderbolt/tunnel.h index 07bf587bed80..0373779f43ba 100644 --- a/drivers/thunderbolt/tunnel.h +++ b/drivers/thunderbolt/tunnel.h @@ -11,6 +11,11 @@ #include "tb.h" +enum tb_tunnel_type { + TB_TUNNEL_PCI, + TB_TUNNEL_DP, +}; + /** * struct tb_tunnel - Tunnel between two ports * @tb: Pointer to the domain @@ -19,8 +24,10 @@ * tunnels may be %NULL or null adapter port instead. * @paths: All paths required by the tunnel * @npaths: Number of paths in @paths + * @init: Optional tunnel specific initialization * @activate: Optional tunnel specific activation/deactivation * @list: Tunnels are linked using this field + * @type: Type of the tunnel */ struct tb_tunnel { struct tb *tb; @@ -28,18 +35,34 @@ struct tb_tunnel { struct tb_port *dst_port; struct tb_path **paths; size_t npaths; + int (*init)(struct tb_tunnel *tunnel); int (*activate)(struct tb_tunnel *tunnel, bool activate); struct list_head list; + enum tb_tunnel_type type; }; struct tb_tunnel *tb_tunnel_discover_pci(struct tb *tb, struct tb_port *down); struct tb_tunnel *tb_tunnel_alloc_pci(struct tb *tb, struct tb_port *up, struct tb_port *down); +struct tb_tunnel *tb_tunnel_discover_dp(struct tb *tb, struct tb_port *in); +struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in, + struct tb_port *out); + void tb_tunnel_free(struct tb_tunnel *tunnel); int tb_tunnel_activate(struct tb_tunnel *tunnel); int tb_tunnel_restart(struct tb_tunnel *tunnel); void tb_tunnel_deactivate(struct tb_tunnel *tunnel); bool tb_tunnel_is_invalid(struct tb_tunnel *tunnel); +static inline bool tb_tunnel_is_pci(const struct tb_tunnel *tunnel) +{ + return tunnel->type == TB_TUNNEL_PCI; +} + +static inline bool tb_tunnel_is_dp(const struct tb_tunnel *tunnel) +{ + return tunnel->type == TB_TUNNEL_DP; +} + #endif From ab9f31cfa89ad700f83bfaf30dc8703c4f609d0f Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 6 Mar 2019 18:21:08 +0200 Subject: [PATCH 106/255] thunderbolt: Do not tear down tunnels when driver is unloaded Now that we have capability to discover existing tunnels during driver load there is no point tearing down tunnels when the driver gets unloaded. Instead we can just leave them running. If user disconnects devices while there is no Thunderbolt driver loaded, tunneled protocol hotplug happens and is handled by the corresponding driver (pciehp in case of PCIe tunnel, GFX driver in case of DP tunnel). Signed-off-by: Mika Westerberg --- drivers/thunderbolt/path.c | 10 ++++------ drivers/thunderbolt/tb.c | 4 +--- drivers/thunderbolt/tunnel.c | 10 +--------- 3 files changed, 6 insertions(+), 18 deletions(-) diff --git a/drivers/thunderbolt/path.c b/drivers/thunderbolt/path.c index 670a12e60d66..3fc92881a197 100644 --- a/drivers/thunderbolt/path.c +++ b/drivers/thunderbolt/path.c @@ -304,17 +304,15 @@ struct tb_path *tb_path_alloc(struct tb *tb, struct tb_port *src, int src_hopid, } /** - * tb_path_free() - free a deactivated path + * tb_path_free() - free a path + * @path: Path to free + * + * Frees a path. The path does not need to be deactivated. */ void tb_path_free(struct tb_path *path) { int i; - if (path->activated) { - tb_WARN(path->tb, "trying to free an activated path\n") - return; - } - for (i = 0; i < path->path_length; i++) { const struct tb_path_hop *hop = &path->hops[i]; diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index c5e96e7ac37a..8a97a4e19638 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -500,10 +500,8 @@ static void tb_stop(struct tb *tb) struct tb_tunnel *n; /* tunnels are only present after everything has been initialized */ - list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) { - tb_tunnel_deactivate(tunnel); + list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) tb_tunnel_free(tunnel); - } tb_switch_remove(tb->root_switch); tcm->hotplug_active = false; /* signal tb_handle_hotplug to quit */ } diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index 21d3393c6e9c..0bc6639c6e74 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -475,7 +475,7 @@ struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in, * tb_tunnel_free() - free a tunnel * @tunnel: Tunnel to be freed * - * The tunnel must have been deactivated. + * Frees a tunnel. The tunnel does not need to be deactivated. */ void tb_tunnel_free(struct tb_tunnel *tunnel) { @@ -484,14 +484,6 @@ void tb_tunnel_free(struct tb_tunnel *tunnel) if (!tunnel) return; - for (i = 0; i < tunnel->npaths; i++) { - if (tunnel->paths[i] && tunnel->paths[i]->activated) { - tb_tunnel_WARN(tunnel, - "trying to free an activated tunnel\n"); - return; - } - } - for (i = 0; i < tunnel->npaths; i++) { if (tunnel->paths[i]) tb_path_free(tunnel->paths[i]); From 559c1e1e013437bf190469efbcbd8bc803285853 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 22 Oct 2018 14:47:01 +0300 Subject: [PATCH 107/255] thunderbolt: Run tb_xdp_handle_request() in system workqueue We run all XDomain requests during discovery in tb->wq and since it only runs one work at the time it means that sending back reply to the other domain may be delayed too much depending whether there is an active XDomain discovery request running. To make sure we can send reply to the other domain as soon as possible run tb_xdp_handle_request() in system workqueue instead. Since the device can be hot-removed in the middle we need to make sure the domain structure is still around when the function is run so increase reference count before we schedule the reply work. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/tb.h | 7 +++++++ drivers/thunderbolt/xdomain.c | 6 ++++-- 2 files changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 56eed0bc3c2b..89b5d18f6035 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -492,6 +492,13 @@ int tb_domain_approve_xdomain_paths(struct tb *tb, struct tb_xdomain *xd); int tb_domain_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd); int tb_domain_disconnect_all_paths(struct tb *tb); +static inline struct tb *tb_domain_get(struct tb *tb) +{ + if (tb) + get_device(&tb->dev); + return tb; +} + static inline void tb_domain_put(struct tb *tb) { put_device(&tb->dev); diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index 7bae92bc486f..44d3b2e486cd 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -524,6 +524,8 @@ static void tb_xdp_handle_request(struct work_struct *work) out: kfree(xw->pkg); kfree(xw); + + tb_domain_put(tb); } static bool @@ -542,9 +544,9 @@ tb_xdp_schedule_request(struct tb *tb, const struct tb_xdp_header *hdr, kfree(xw); return false; } - xw->tb = tb; + xw->tb = tb_domain_get(tb); - queue_work(tb->wq, &xw->work); + schedule_work(&xw->work); return true; } From 3b4b3235ca5bf1b69ff15a269d9881b2604dd4fa Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 28 Sep 2018 16:30:16 +0300 Subject: [PATCH 108/255] thunderbolt: Add XDomain UUID exchange support Currently ICM has been handling XDomain UUID exchange so there was no need to have it in the driver yet. However, since now we are going to add the same capabilities to the software connection manager it needs to be handled properly. For this reason modify the driver XDomain protocol handling so that if the remote domain UUID is not filled in the core will query it first and only then start the normal property exchange flow. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/tb_msgs.h | 11 +++ drivers/thunderbolt/xdomain.c | 136 +++++++++++++++++++++++++++++++--- include/linux/thunderbolt.h | 8 ++ 3 files changed, 145 insertions(+), 10 deletions(-) diff --git a/drivers/thunderbolt/tb_msgs.h b/drivers/thunderbolt/tb_msgs.h index 02c84aa3d018..afbe1d29bb03 100644 --- a/drivers/thunderbolt/tb_msgs.h +++ b/drivers/thunderbolt/tb_msgs.h @@ -492,6 +492,17 @@ struct tb_xdp_header { u32 type; }; +struct tb_xdp_uuid { + struct tb_xdp_header hdr; +}; + +struct tb_xdp_uuid_response { + struct tb_xdp_header hdr; + uuid_t src_uuid; + u32 src_route_hi; + u32 src_route_lo; +}; + struct tb_xdp_properties { struct tb_xdp_header hdr; uuid_t src_uuid; diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index 44d3b2e486cd..5118d46702d5 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -18,6 +18,7 @@ #include "tb.h" #define XDOMAIN_DEFAULT_TIMEOUT 5000 /* ms */ +#define XDOMAIN_UUID_RETRIES 10 #define XDOMAIN_PROPERTIES_RETRIES 60 #define XDOMAIN_PROPERTIES_CHANGED_RETRIES 10 @@ -222,6 +223,50 @@ static int tb_xdp_handle_error(const struct tb_xdp_header *hdr) return 0; } +static int tb_xdp_uuid_request(struct tb_ctl *ctl, u64 route, int retry, + uuid_t *uuid) +{ + struct tb_xdp_uuid_response res; + struct tb_xdp_uuid req; + int ret; + + memset(&req, 0, sizeof(req)); + tb_xdp_fill_header(&req.hdr, route, retry % 4, UUID_REQUEST, + sizeof(req)); + + memset(&res, 0, sizeof(res)); + ret = __tb_xdomain_request(ctl, &req, sizeof(req), + TB_CFG_PKG_XDOMAIN_REQ, &res, sizeof(res), + TB_CFG_PKG_XDOMAIN_RESP, + XDOMAIN_DEFAULT_TIMEOUT); + if (ret) + return ret; + + ret = tb_xdp_handle_error(&res.hdr); + if (ret) + return ret; + + uuid_copy(uuid, &res.src_uuid); + return 0; +} + +static int tb_xdp_uuid_response(struct tb_ctl *ctl, u64 route, u8 sequence, + const uuid_t *uuid) +{ + struct tb_xdp_uuid_response res; + + memset(&res, 0, sizeof(res)); + tb_xdp_fill_header(&res.hdr, route, sequence, UUID_RESPONSE, + sizeof(res)); + + uuid_copy(&res.src_uuid, uuid); + res.src_route_hi = upper_32_bits(route); + res.src_route_lo = lower_32_bits(route); + + return __tb_xdomain_response(ctl, &res, sizeof(res), + TB_CFG_PKG_XDOMAIN_RESP); +} + static int tb_xdp_error_response(struct tb_ctl *ctl, u64 route, u8 sequence, enum tb_xdp_error error) { @@ -512,7 +557,14 @@ static void tb_xdp_handle_request(struct work_struct *work) break; } + case UUID_REQUEST_OLD: + case UUID_REQUEST: + ret = tb_xdp_uuid_response(ctl, route, sequence, uuid); + break; + default: + tb_xdp_error_response(ctl, route, sequence, + ERROR_NOT_SUPPORTED); break; } @@ -839,6 +891,55 @@ static void tb_xdomain_restore_paths(struct tb_xdomain *xd) } } +static void tb_xdomain_get_uuid(struct work_struct *work) +{ + struct tb_xdomain *xd = container_of(work, typeof(*xd), + get_uuid_work.work); + struct tb *tb = xd->tb; + uuid_t uuid; + int ret; + + ret = tb_xdp_uuid_request(tb->ctl, xd->route, xd->uuid_retries, &uuid); + if (ret < 0) { + if (xd->uuid_retries-- > 0) { + queue_delayed_work(xd->tb->wq, &xd->get_uuid_work, + msecs_to_jiffies(100)); + } else { + dev_dbg(&xd->dev, "failed to read remote UUID\n"); + } + return; + } + + if (uuid_equal(&uuid, xd->local_uuid)) { + dev_dbg(&xd->dev, "intra-domain loop detected\n"); + return; + } + + /* + * If the UUID is different, there is another domain connected + * so mark this one unplugged and wait for the connection + * manager to replace it. + */ + if (xd->remote_uuid && !uuid_equal(&uuid, xd->remote_uuid)) { + dev_dbg(&xd->dev, "remote UUID is different, unplugging\n"); + xd->is_unplugged = true; + return; + } + + /* First time fill in the missing UUID */ + if (!xd->remote_uuid) { + xd->remote_uuid = kmemdup(&uuid, sizeof(uuid_t), GFP_KERNEL); + if (!xd->remote_uuid) + return; + } + + /* Now we can start the normal properties exchange */ + queue_delayed_work(xd->tb->wq, &xd->properties_changed_work, + msecs_to_jiffies(100)); + queue_delayed_work(xd->tb->wq, &xd->get_properties_work, + msecs_to_jiffies(1000)); +} + static void tb_xdomain_get_properties(struct work_struct *work) { struct tb_xdomain *xd = container_of(work, typeof(*xd), @@ -1045,21 +1146,29 @@ static void tb_xdomain_release(struct device *dev) static void start_handshake(struct tb_xdomain *xd) { + xd->uuid_retries = XDOMAIN_UUID_RETRIES; xd->properties_retries = XDOMAIN_PROPERTIES_RETRIES; xd->properties_changed_retries = XDOMAIN_PROPERTIES_CHANGED_RETRIES; - /* Start exchanging properties with the other host */ - queue_delayed_work(xd->tb->wq, &xd->properties_changed_work, - msecs_to_jiffies(100)); - queue_delayed_work(xd->tb->wq, &xd->get_properties_work, - msecs_to_jiffies(1000)); + if (xd->needs_uuid) { + queue_delayed_work(xd->tb->wq, &xd->get_uuid_work, + msecs_to_jiffies(100)); + } else { + /* Start exchanging properties with the other host */ + queue_delayed_work(xd->tb->wq, &xd->properties_changed_work, + msecs_to_jiffies(100)); + queue_delayed_work(xd->tb->wq, &xd->get_properties_work, + msecs_to_jiffies(1000)); + } } static void stop_handshake(struct tb_xdomain *xd) { + xd->uuid_retries = 0; xd->properties_retries = 0; xd->properties_changed_retries = 0; + cancel_delayed_work_sync(&xd->get_uuid_work); cancel_delayed_work_sync(&xd->get_properties_work); cancel_delayed_work_sync(&xd->properties_changed_work); } @@ -1102,7 +1211,7 @@ EXPORT_SYMBOL_GPL(tb_xdomain_type); * other domain is reached). * @route: Route string used to reach the other domain * @local_uuid: Our local domain UUID - * @remote_uuid: UUID of the other domain + * @remote_uuid: UUID of the other domain (optional) * * Allocates new XDomain structure and returns pointer to that. The * object must be released by calling tb_xdomain_put(). @@ -1121,6 +1230,7 @@ struct tb_xdomain *tb_xdomain_alloc(struct tb *tb, struct device *parent, xd->route = route; ida_init(&xd->service_ids); mutex_init(&xd->lock); + INIT_DELAYED_WORK(&xd->get_uuid_work, tb_xdomain_get_uuid); INIT_DELAYED_WORK(&xd->get_properties_work, tb_xdomain_get_properties); INIT_DELAYED_WORK(&xd->properties_changed_work, tb_xdomain_properties_changed); @@ -1129,9 +1239,14 @@ struct tb_xdomain *tb_xdomain_alloc(struct tb *tb, struct device *parent, if (!xd->local_uuid) goto err_free; - xd->remote_uuid = kmemdup(remote_uuid, sizeof(uuid_t), GFP_KERNEL); - if (!xd->remote_uuid) - goto err_free_local_uuid; + if (remote_uuid) { + xd->remote_uuid = kmemdup(remote_uuid, sizeof(uuid_t), + GFP_KERNEL); + if (!xd->remote_uuid) + goto err_free_local_uuid; + } else { + xd->needs_uuid = true; + } device_initialize(&xd->dev); xd->dev.parent = get_device(parent); @@ -1299,7 +1414,8 @@ static struct tb_xdomain *switch_find_xdomain(struct tb_switch *sw, xd = port->xdomain; if (lookup->uuid) { - if (uuid_equal(xd->remote_uuid, lookup->uuid)) + if (xd->remote_uuid && + uuid_equal(xd->remote_uuid, lookup->uuid)) return xd; } else if (lookup->link && lookup->link == xd->link && diff --git a/include/linux/thunderbolt.h b/include/linux/thunderbolt.h index bf6ec83e60ee..2d7e012db03f 100644 --- a/include/linux/thunderbolt.h +++ b/include/linux/thunderbolt.h @@ -181,6 +181,8 @@ void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir); * @device_name: Name of the device (or %NULL if not known) * @is_unplugged: The XDomain is unplugged * @resume: The XDomain is being resumed + * @needs_uuid: If the XDomain does not have @remote_uuid it will be + * queried first * @transmit_path: HopID which the remote end expects us to transmit * @transmit_ring: Local ring (hop) where outgoing packets are pushed * @receive_path: HopID which we expect the remote end to transmit @@ -189,6 +191,9 @@ void tb_unregister_property_dir(const char *key, struct tb_property_dir *dir); * @properties: Properties exported by the remote domain * @property_block_gen: Generation of @properties * @properties_lock: Lock protecting @properties. + * @get_uuid_work: Work used to retrieve @remote_uuid + * @uuid_retries: Number of times left @remote_uuid is requested before + * giving up * @get_properties_work: Work used to get remote domain properties * @properties_retries: Number of times left to read properties * @properties_changed_work: Work used to notify the remote domain that @@ -220,6 +225,7 @@ struct tb_xdomain { const char *device_name; bool is_unplugged; bool resume; + bool needs_uuid; u16 transmit_path; u16 transmit_ring; u16 receive_path; @@ -227,6 +233,8 @@ struct tb_xdomain { struct ida service_ids; struct tb_property_dir *properties; u32 property_block_gen; + struct delayed_work get_uuid_work; + int uuid_retries; struct delayed_work get_properties_work; int properties_retries; struct delayed_work properties_changed_work; From 44242d6c9703208e7e7abd6b4dbb258a930dd01a Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 28 Sep 2018 16:35:32 +0300 Subject: [PATCH 109/255] thunderbolt: Add support for DMA tunnels In addition to PCIe and Display Port tunnels it is also possible to create tunnels that forward DMA traffic from the host interface adapter (NHI) to a NULL port that is connected to another domain through a Thunderbolt cable. These tunnels can be used to carry software messages such as networking packets. To support this we introduce another tunnel type (TB_TUNNEL_DMA) that supports paths from NHI to NULL port and back. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/path.c | 22 +++++++-- drivers/thunderbolt/switch.c | 22 +++++++++ drivers/thunderbolt/tb.h | 4 ++ drivers/thunderbolt/tb_regs.h | 3 ++ drivers/thunderbolt/tunnel.c | 93 ++++++++++++++++++++++++++++++++++- drivers/thunderbolt/tunnel.h | 10 ++++ 6 files changed, 149 insertions(+), 5 deletions(-) diff --git a/drivers/thunderbolt/path.c b/drivers/thunderbolt/path.c index 3fc92881a197..e4c22f53ef4d 100644 --- a/drivers/thunderbolt/path.c +++ b/drivers/thunderbolt/path.c @@ -341,7 +341,8 @@ static void __tb_path_deallocate_nfc(struct tb_path *path, int first_hop) } } -static int __tb_path_deactivate_hop(struct tb_port *port, int hop_index) +static int __tb_path_deactivate_hop(struct tb_port *port, int hop_index, + bool clear_fc) { struct tb_regs_hop hop; ktime_t timeout; @@ -369,8 +370,20 @@ static int __tb_path_deactivate_hop(struct tb_port *port, int hop_index) if (ret) return ret; - if (!hop.pending) + if (!hop.pending) { + if (clear_fc) { + /* Clear flow control */ + hop.ingress_fc = 0; + hop.egress_fc = 0; + hop.ingress_shared_buffer = 0; + hop.egress_shared_buffer = 0; + + return tb_port_write(port, &hop, TB_CFG_HOPS, + 2 * hop_index, 2); + } + return 0; + } usleep_range(10, 20); } while (ktime_before(ktime_get(), timeout)); @@ -384,7 +397,8 @@ static void __tb_path_deactivate_hops(struct tb_path *path, int first_hop) for (i = first_hop; i < path->path_length; i++) { res = __tb_path_deactivate_hop(path->hops[i].in_port, - path->hops[i].in_hop_index); + path->hops[i].in_hop_index, + path->clear_fc); if (res && res != -ENODEV) tb_port_warn(path->hops[i].in_port, "hop deactivation failed for hop %d, index %d\n", @@ -459,7 +473,7 @@ int tb_path_activate(struct tb_path *path) /* If it is left active deactivate it first */ __tb_path_deactivate_hop(path->hops[i].in_port, - path->hops[i].in_hop_index); + path->hops[i].in_hop_index, path->clear_fc); /* dword 0 */ hop.next_hop = path->hops[i].next_hop_index; diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 1de1afa24182..ecf53d986a5c 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -555,6 +555,28 @@ int tb_port_add_nfc_credits(struct tb_port *port, int credits) TB_CFG_PORT, 4, 1); } +/** + * tb_port_set_initial_credits() - Set initial port link credits allocated + * @port: Port to set the initial credits + * @credits: Number of credits to to allocate + * + * Set initial credits value to be used for ingress shared buffering. + */ +int tb_port_set_initial_credits(struct tb_port *port, u32 credits) +{ + u32 data; + int ret; + + ret = tb_port_read(port, &data, TB_CFG_PORT, 5, 1); + if (ret) + return ret; + + data &= ~TB_PORT_LCA_MASK; + data |= (credits << TB_PORT_LCA_SHIFT) & TB_PORT_LCA_MASK; + + return tb_port_write(port, &data, TB_CFG_PORT, 5, 1); +} + /** * tb_port_clear_counter() - clear a counter in TB_CFG_COUNTER * diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 89b5d18f6035..119a00837992 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -207,6 +207,8 @@ enum tb_path_port { * @weight: Weight of the path inside the priority group * @drop_packages: Drop packages from queue tail or head * @activated: Is the path active + * @clear_fc: Clear all flow control from the path config space entries + * when deactivating this path * @hops: Path hops * @path_length: How many hops the path uses * @@ -227,6 +229,7 @@ struct tb_path { int weight:4; bool drop_packages; bool activated; + bool clear_fc; struct tb_path_hop *hops; int path_length; }; @@ -583,6 +586,7 @@ static inline bool tb_switch_is_fr(const struct tb_switch *sw) int tb_wait_for_port(struct tb_port *port, bool wait_if_unplugged); int tb_port_add_nfc_credits(struct tb_port *port, int credits); +int tb_port_set_initial_credits(struct tb_port *port, u32 credits); int tb_port_clear_counter(struct tb_port *port, int counter); int tb_port_alloc_in_hopid(struct tb_port *port, int hopid, int max_hopid); void tb_port_release_in_hopid(struct tb_port *port, int hopid); diff --git a/drivers/thunderbolt/tb_regs.h b/drivers/thunderbolt/tb_regs.h index 3ce705184e2c..deb9d4a977b9 100644 --- a/drivers/thunderbolt/tb_regs.h +++ b/drivers/thunderbolt/tb_regs.h @@ -215,6 +215,9 @@ struct tb_regs_port_header { #define TB_PORT_NFC_CREDITS_MASK GENMASK(19, 0) #define TB_PORT_MAX_CREDITS_SHIFT 20 #define TB_PORT_MAX_CREDITS_MASK GENMASK(26, 20) +/* DWORD 5 */ +#define TB_PORT_LCA_SHIFT 22 +#define TB_PORT_LCA_MASK GENMASK(28, 22) /* Display Port adapter registers */ diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index 0bc6639c6e74..9f9b26b12d0a 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -27,7 +27,10 @@ #define TB_DP_AUX_PATH_OUT 1 #define TB_DP_AUX_PATH_IN 2 -static const char * const tb_tunnel_names[] = { "PCI", "DP" }; +#define TB_DMA_PATH_OUT 0 +#define TB_DMA_PATH_IN 1 + +static const char * const tb_tunnel_names[] = { "PCI", "DP", "DMA" }; #define __TB_TUNNEL_PRINT(level, tunnel, fmt, arg...) \ do { \ @@ -471,6 +474,94 @@ struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in, return NULL; } +static u32 tb_dma_credits(struct tb_port *nhi) +{ + u32 max_credits; + + max_credits = (nhi->config.nfc_credits & TB_PORT_MAX_CREDITS_MASK) >> + TB_PORT_MAX_CREDITS_SHIFT; + return min(max_credits, 13U); +} + +static int tb_dma_activate(struct tb_tunnel *tunnel, bool active) +{ + struct tb_port *nhi = tunnel->src_port; + u32 credits; + + credits = active ? tb_dma_credits(nhi) : 0; + return tb_port_set_initial_credits(nhi, credits); +} + +static void tb_dma_init_path(struct tb_path *path, unsigned int isb, + unsigned int efc, u32 credits) +{ + int i; + + path->egress_fc_enable = efc; + path->ingress_fc_enable = TB_PATH_ALL; + path->egress_shared_buffer = TB_PATH_NONE; + path->ingress_shared_buffer = isb; + path->priority = 5; + path->weight = 1; + path->clear_fc = true; + + for (i = 0; i < path->path_length; i++) + path->hops[i].initial_credits = credits; +} + +/** + * tb_tunnel_alloc_dma() - allocate a DMA tunnel + * @tb: Pointer to the domain structure + * @nhi: Host controller port + * @dst: Destination null port which the other domain is connected to + * @transmit_ring: NHI ring number used to send packets towards the + * other domain + * @transmit_path: HopID used for transmitting packets + * @receive_ring: NHI ring number used to receive packets from the + * other domain + * @reveive_path: HopID used for receiving packets + * + * Return: Returns a tb_tunnel on success or NULL on failure. + */ +struct tb_tunnel *tb_tunnel_alloc_dma(struct tb *tb, struct tb_port *nhi, + struct tb_port *dst, int transmit_ring, + int transmit_path, int receive_ring, + int receive_path) +{ + struct tb_tunnel *tunnel; + struct tb_path *path; + u32 credits; + + tunnel = tb_tunnel_alloc(tb, 2, TB_TUNNEL_DMA); + if (!tunnel) + return NULL; + + tunnel->activate = tb_dma_activate; + tunnel->src_port = nhi; + tunnel->dst_port = dst; + + credits = tb_dma_credits(nhi); + + path = tb_path_alloc(tb, dst, receive_path, nhi, receive_ring, 0, "DMA RX"); + if (!path) { + tb_tunnel_free(tunnel); + return NULL; + } + tb_dma_init_path(path, TB_PATH_NONE, TB_PATH_SOURCE | TB_PATH_INTERNAL, + credits); + tunnel->paths[TB_DMA_PATH_IN] = path; + + path = tb_path_alloc(tb, nhi, transmit_ring, dst, transmit_path, 0, "DMA TX"); + if (!path) { + tb_tunnel_free(tunnel); + return NULL; + } + tb_dma_init_path(path, TB_PATH_SOURCE, TB_PATH_ALL, credits); + tunnel->paths[TB_DMA_PATH_OUT] = path; + + return tunnel; +} + /** * tb_tunnel_free() - free a tunnel * @tunnel: Tunnel to be freed diff --git a/drivers/thunderbolt/tunnel.h b/drivers/thunderbolt/tunnel.h index 0373779f43ba..c68bbcd3a62c 100644 --- a/drivers/thunderbolt/tunnel.h +++ b/drivers/thunderbolt/tunnel.h @@ -14,6 +14,7 @@ enum tb_tunnel_type { TB_TUNNEL_PCI, TB_TUNNEL_DP, + TB_TUNNEL_DMA, }; /** @@ -47,6 +48,10 @@ struct tb_tunnel *tb_tunnel_alloc_pci(struct tb *tb, struct tb_port *up, struct tb_tunnel *tb_tunnel_discover_dp(struct tb *tb, struct tb_port *in); struct tb_tunnel *tb_tunnel_alloc_dp(struct tb *tb, struct tb_port *in, struct tb_port *out); +struct tb_tunnel *tb_tunnel_alloc_dma(struct tb *tb, struct tb_port *nhi, + struct tb_port *dst, int transmit_ring, + int transmit_path, int receive_ring, + int receive_path); void tb_tunnel_free(struct tb_tunnel *tunnel); int tb_tunnel_activate(struct tb_tunnel *tunnel); @@ -64,5 +69,10 @@ static inline bool tb_tunnel_is_dp(const struct tb_tunnel *tunnel) return tunnel->type == TB_TUNNEL_DP; } +static inline bool tb_tunnel_is_dma(const struct tb_tunnel *tunnel) +{ + return tunnel->type == TB_TUNNEL_DMA; +} + #endif From 444ac3844895c34ab71ffcec1b3199449d3434a4 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Sun, 30 Dec 2018 12:17:52 +0200 Subject: [PATCH 110/255] thunderbolt: Make tb_switch_alloc() return ERR_PTR() In order to detect possible connections to other domains we need to be able to find out why tb_switch_alloc() fails so make it return ERR_PTR() instead. This allows the caller to differentiate between errors such as -ENOMEM which comes from the kernel and for instance -EIO which comes from the hardware when trying to access the possible switch. Convert all the current call sites to handle this properly. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/icm.c | 6 +++--- drivers/thunderbolt/switch.c | 36 ++++++++++++++++++++---------------- drivers/thunderbolt/tb.c | 6 +++--- 3 files changed, 26 insertions(+), 22 deletions(-) diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index 805958e53c58..d1f6ec89763c 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -468,7 +468,7 @@ static void add_switch(struct tb_switch *parent_sw, u64 route, pm_runtime_get_sync(&parent_sw->dev); sw = tb_switch_alloc(parent_sw->tb, &parent_sw->dev, route); - if (!sw) + if (IS_ERR(sw)) goto out; sw->uuid = kmemdup(uuid, sizeof(*uuid), GFP_KERNEL); @@ -1848,8 +1848,8 @@ static int icm_start(struct tb *tb) tb->root_switch = tb_switch_alloc_safe_mode(tb, &tb->dev, 0); else tb->root_switch = tb_switch_alloc(tb, &tb->dev, 0); - if (!tb->root_switch) - return -ENODEV; + if (IS_ERR(tb->root_switch)) + return PTR_ERR(tb->root_switch); /* * NVM upgrade has not been tested on Apple systems and they diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index ecf53d986a5c..460f2bcad40a 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -1450,30 +1450,32 @@ static int tb_switch_get_generation(struct tb_switch *sw) * separately. The returned switch should be released by calling * tb_switch_put(). * - * Return: Pointer to the allocated switch or %NULL in case of failure + * Return: Pointer to the allocated switch or ERR_PTR() in case of + * failure. */ struct tb_switch *tb_switch_alloc(struct tb *tb, struct device *parent, u64 route) { struct tb_switch *sw; int upstream_port; - int i, cap, depth; + int i, ret, depth; /* Make sure we do not exceed maximum topology limit */ depth = tb_route_length(route); if (depth > TB_SWITCH_MAX_DEPTH) - return NULL; + return ERR_PTR(-EADDRNOTAVAIL); upstream_port = tb_cfg_get_upstream_port(tb->ctl, route); if (upstream_port < 0) - return NULL; + return ERR_PTR(upstream_port); sw = kzalloc(sizeof(*sw), GFP_KERNEL); if (!sw) - return NULL; + return ERR_PTR(-ENOMEM); sw->tb = tb; - if (tb_cfg_read(tb->ctl, &sw->config, route, 0, TB_CFG_SWITCH, 0, 5)) + ret = tb_cfg_read(tb->ctl, &sw->config, route, 0, TB_CFG_SWITCH, 0, 5); + if (ret) goto err_free_sw_ports; tb_dbg(tb, "current switch config:\n"); @@ -1489,8 +1491,10 @@ struct tb_switch *tb_switch_alloc(struct tb *tb, struct device *parent, /* initialize ports */ sw->ports = kcalloc(sw->config.max_port_number + 1, sizeof(*sw->ports), GFP_KERNEL); - if (!sw->ports) + if (!sw->ports) { + ret = -ENOMEM; goto err_free_sw_ports; + } for (i = 0; i <= sw->config.max_port_number; i++) { /* minimum setup for tb_find_cap and tb_drom_read to work */ @@ -1500,16 +1504,16 @@ struct tb_switch *tb_switch_alloc(struct tb *tb, struct device *parent, sw->generation = tb_switch_get_generation(sw); - cap = tb_switch_find_vse_cap(sw, TB_VSE_CAP_PLUG_EVENTS); - if (cap < 0) { + ret = tb_switch_find_vse_cap(sw, TB_VSE_CAP_PLUG_EVENTS); + if (ret < 0) { tb_sw_warn(sw, "cannot find TB_VSE_CAP_PLUG_EVENTS aborting\n"); goto err_free_sw_ports; } - sw->cap_plug_events = cap; + sw->cap_plug_events = ret; - cap = tb_switch_find_vse_cap(sw, TB_VSE_CAP_LINK_CONTROLLER); - if (cap > 0) - sw->cap_lc = cap; + ret = tb_switch_find_vse_cap(sw, TB_VSE_CAP_LINK_CONTROLLER); + if (ret > 0) + sw->cap_lc = ret; /* Root switch is always authorized */ if (!route) @@ -1528,7 +1532,7 @@ struct tb_switch *tb_switch_alloc(struct tb *tb, struct device *parent, kfree(sw->ports); kfree(sw); - return NULL; + return ERR_PTR(ret); } /** @@ -1543,7 +1547,7 @@ struct tb_switch *tb_switch_alloc(struct tb *tb, struct device *parent, * * The returned switch must be released by calling tb_switch_put(). * - * Return: Pointer to the allocated switch or %NULL in case of failure + * Return: Pointer to the allocated switch or ERR_PTR() in case of failure */ struct tb_switch * tb_switch_alloc_safe_mode(struct tb *tb, struct device *parent, u64 route) @@ -1552,7 +1556,7 @@ tb_switch_alloc_safe_mode(struct tb *tb, struct device *parent, u64 route) sw = kzalloc(sizeof(*sw), GFP_KERNEL); if (!sw) - return NULL; + return ERR_PTR(-ENOMEM); sw->tb = tb; sw->config.depth = tb_route_length(route); diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index 8a97a4e19638..c5e82c4dcb64 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -148,7 +148,7 @@ static void tb_scan_port(struct tb_port *port) } sw = tb_switch_alloc(port->sw->tb, &port->sw->dev, tb_downstream_route(port)); - if (!sw) + if (IS_ERR(sw)) return; if (tb_switch_configure(sw)) { @@ -533,8 +533,8 @@ static int tb_start(struct tb *tb) int ret; tb->root_switch = tb_switch_alloc(tb, &tb->dev, 0); - if (!tb->root_switch) - return -ENOMEM; + if (IS_ERR(tb->root_switch)) + return PTR_ERR(tb->root_switch); /* * ICM firmware upgrade needs running firmware and in native From 7ea4cd6b2010eecccf37ac3953ac8ecd3688300f Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Fri, 28 Sep 2018 16:41:01 +0300 Subject: [PATCH 111/255] thunderbolt: Add support for XDomain connections Two domains (hosts) can be connected through a Thunderbolt cable and in that case they can start software services such as networking over the high-speed DMA paths. Now that we have all the basic building blocks in place to create DMA tunnels over the Thunderbolt fabric we can add this support to the software connection manager as well. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/switch.c | 29 +++++- drivers/thunderbolt/tb.c | 167 ++++++++++++++++++++++++++++++++++- 2 files changed, 188 insertions(+), 8 deletions(-) diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 460f2bcad40a..a5345a6225bd 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -1845,6 +1845,8 @@ void tb_sw_set_unplugged(struct tb_switch *sw) for (i = 0; i <= sw->config.max_port_number; i++) { if (tb_port_has_remote(&sw->ports[i])) tb_sw_set_unplugged(sw->ports[i].remote->sw); + else if (sw->ports[i].xdomain) + sw->ports[i].xdomain->is_unplugged = true; } } @@ -1860,6 +1862,17 @@ int tb_switch_resume(struct tb_switch *sw) if (tb_route(sw)) { u64 uid; + /* + * Check first that we can still read the switch config + * space. It may be that there is now another domain + * connected. + */ + err = tb_cfg_get_upstream_port(sw->tb->ctl, tb_route(sw)); + if (err < 0) { + tb_sw_info(sw, "switch not present anymore\n"); + return err; + } + err = tb_drom_read_uid_only(sw, &uid); if (err) { tb_sw_warn(sw, "uid read failed\n"); @@ -1890,14 +1903,22 @@ int tb_switch_resume(struct tb_switch *sw) for (i = 1; i <= sw->config.max_port_number; i++) { struct tb_port *port = &sw->ports[i]; - if (!tb_port_has_remote(port)) + if (!tb_port_has_remote(port) && !port->xdomain) continue; - if (tb_wait_for_port(port, true) <= 0 - || tb_switch_resume(port->remote->sw)) { + if (tb_wait_for_port(port, true) <= 0) { tb_port_warn(port, "lost during suspend, disconnecting\n"); - tb_sw_set_unplugged(port->remote->sw); + if (tb_port_has_remote(port)) + tb_sw_set_unplugged(port->remote->sw); + else if (port->xdomain) + port->xdomain->is_unplugged = true; + } else if (tb_port_has_remote(port)) { + if (tb_switch_resume(port->remote->sw)) { + tb_port_warn(port, + "lost during suspend, disconnecting\n"); + tb_sw_set_unplugged(port->remote->sw); + } } } return 0; diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index c5e82c4dcb64..e39fc1e35e6b 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -101,6 +101,28 @@ static void tb_discover_tunnels(struct tb_switch *sw) } } +static void tb_scan_xdomain(struct tb_port *port) +{ + struct tb_switch *sw = port->sw; + struct tb *tb = sw->tb; + struct tb_xdomain *xd; + u64 route; + + route = tb_downstream_route(port); + xd = tb_xdomain_find_by_route(tb, route); + if (xd) { + tb_xdomain_put(xd); + return; + } + + xd = tb_xdomain_alloc(tb, &sw->dev, route, tb->root_switch->uuid, + NULL); + if (xd) { + tb_port_at(route, sw)->xdomain = xd; + tb_xdomain_add(xd); + } +} + static void tb_scan_port(struct tb_port *port); /** @@ -143,19 +165,36 @@ static void tb_scan_port(struct tb_port *port) if (tb_wait_for_port(port, false) <= 0) return; if (port->remote) { - tb_port_WARN(port, "port already has a remote!\n"); + tb_port_dbg(port, "port already has a remote\n"); return; } sw = tb_switch_alloc(port->sw->tb, &port->sw->dev, tb_downstream_route(port)); - if (IS_ERR(sw)) + if (IS_ERR(sw)) { + /* + * If there is an error accessing the connected switch + * it may be connected to another domain. Also we allow + * the other domain to be connected to a max depth switch. + */ + if (PTR_ERR(sw) == -EIO || PTR_ERR(sw) == -EADDRNOTAVAIL) + tb_scan_xdomain(port); return; + } if (tb_switch_configure(sw)) { tb_switch_put(sw); return; } + /* + * If there was previously another domain connected remove it + * first. + */ + if (port->xdomain) { + tb_xdomain_remove(port->xdomain); + port->xdomain = NULL; + } + /* * Do not send uevents until we have discovered all existing * tunnels and know which switches were authorized already by @@ -393,6 +432,65 @@ static int tb_tunnel_pci(struct tb *tb, struct tb_switch *sw) return 0; } +static int tb_approve_xdomain_paths(struct tb *tb, struct tb_xdomain *xd) +{ + struct tb_cm *tcm = tb_priv(tb); + struct tb_port *nhi_port, *dst_port; + struct tb_tunnel *tunnel; + struct tb_switch *sw; + + sw = tb_to_switch(xd->dev.parent); + dst_port = tb_port_at(xd->route, sw); + nhi_port = tb_find_port(tb->root_switch, TB_TYPE_NHI); + + mutex_lock(&tb->lock); + tunnel = tb_tunnel_alloc_dma(tb, nhi_port, dst_port, xd->transmit_ring, + xd->transmit_path, xd->receive_ring, + xd->receive_path); + if (!tunnel) { + mutex_unlock(&tb->lock); + return -ENOMEM; + } + + if (tb_tunnel_activate(tunnel)) { + tb_port_info(nhi_port, + "DMA tunnel activation failed, aborting\n"); + tb_tunnel_free(tunnel); + mutex_unlock(&tb->lock); + return -EIO; + } + + list_add_tail(&tunnel->list, &tcm->tunnel_list); + mutex_unlock(&tb->lock); + return 0; +} + +static void __tb_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd) +{ + struct tb_port *dst_port; + struct tb_switch *sw; + + sw = tb_to_switch(xd->dev.parent); + dst_port = tb_port_at(xd->route, sw); + + /* + * It is possible that the tunnel was already teared down (in + * case of cable disconnect) so it is fine if we cannot find it + * here anymore. + */ + tb_free_tunnel(tb, TB_TUNNEL_DMA, NULL, dst_port); +} + +static int tb_disconnect_xdomain_paths(struct tb *tb, struct tb_xdomain *xd) +{ + if (!xd->is_unplugged) { + mutex_lock(&tb->lock); + __tb_disconnect_xdomain_paths(tb, xd); + mutex_unlock(&tb->lock); + } + return 0; +} + /* hotplug handling */ /** @@ -432,13 +530,29 @@ static void tb_handle_hotplug(struct work_struct *work) } if (ev->unplug) { if (tb_port_has_remote(port)) { - tb_port_info(port, "unplugged\n"); + tb_port_dbg(port, "switch unplugged\n"); tb_sw_set_unplugged(port->remote->sw); tb_free_invalid_tunnels(tb); tb_switch_remove(port->remote->sw); port->remote = NULL; if (port->dual_link_port) port->dual_link_port->remote = NULL; + } else if (port->xdomain) { + struct tb_xdomain *xd = tb_xdomain_get(port->xdomain); + + tb_port_dbg(port, "xdomain unplugged\n"); + /* + * Service drivers are unbound during + * tb_xdomain_remove() so setting XDomain as + * unplugged here prevents deadlock if they call + * tb_xdomain_disable_paths(). We will tear down + * the path below. + */ + xd->is_unplugged = true; + tb_xdomain_remove(xd); + port->xdomain = NULL; + __tb_disconnect_xdomain_paths(tb, xd); + tb_xdomain_put(xd); } else if (tb_port_is_dpout(port)) { tb_teardown_dp(tb, port); } else { @@ -500,8 +614,16 @@ static void tb_stop(struct tb *tb) struct tb_tunnel *n; /* tunnels are only present after everything has been initialized */ - list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) + list_for_each_entry_safe(tunnel, n, &tcm->tunnel_list, list) { + /* + * DMA tunnels require the driver to be functional so we + * tear them down. Other protocol tunnels can be left + * intact. + */ + if (tb_tunnel_is_dma(tunnel)) + tb_tunnel_deactivate(tunnel); tb_tunnel_free(tunnel); + } tb_switch_remove(tb->root_switch); tcm->hotplug_active = false; /* signal tb_handle_hotplug to quit */ } @@ -611,13 +733,50 @@ static int tb_resume_noirq(struct tb *tb) return 0; } +static int tb_free_unplugged_xdomains(struct tb_switch *sw) +{ + int i, ret = 0; + + for (i = 1; i <= sw->config.max_port_number; i++) { + struct tb_port *port = &sw->ports[i]; + + if (tb_is_upstream_port(port)) + continue; + if (port->xdomain && port->xdomain->is_unplugged) { + tb_xdomain_remove(port->xdomain); + port->xdomain = NULL; + ret++; + } else if (port->remote) { + ret += tb_free_unplugged_xdomains(port->remote->sw); + } + } + + return ret; +} + +static void tb_complete(struct tb *tb) +{ + /* + * Release any unplugged XDomains and if there is a case where + * another domain is swapped in place of unplugged XDomain we + * need to run another rescan. + */ + mutex_lock(&tb->lock); + if (tb_free_unplugged_xdomains(tb->root_switch)) + tb_scan_switch(tb->root_switch); + mutex_unlock(&tb->lock); +} + static const struct tb_cm_ops tb_cm_ops = { .start = tb_start, .stop = tb_stop, .suspend_noirq = tb_suspend_noirq, .resume_noirq = tb_resume_noirq, + .complete = tb_complete, .handle_event = tb_handle_event, .approve_switch = tb_tunnel_pci, + .approve_xdomain_paths = tb_approve_xdomain_paths, + .disconnect_xdomain_paths = tb_disconnect_xdomain_paths, }; struct tb *tb_probe(struct tb_nhi *nhi) From b323a98f9b9b3e345e325dbfdb515900c61df312 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 6 Mar 2019 19:23:38 +0200 Subject: [PATCH 112/255] thunderbolt: Make __TB_[SW|PORT]_PRINT take const parameters The printing macros do not modify the passed object so make them const. While there make tb_route() to take const parameter as well. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/tb.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 119a00837992..15d225dcb403 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -320,7 +320,7 @@ static inline bool tb_is_upstream_port(const struct tb_port *port) return port == upstream_port || port->dual_link_port == upstream_port; } -static inline u64 tb_route(struct tb_switch *sw) +static inline u64 tb_route(const struct tb_switch *sw) { return ((u64) sw->config.route_hi) << 32 | sw->config.route_lo; } @@ -442,7 +442,7 @@ static inline int tb_port_write(struct tb_port *port, const void *buffer, #define __TB_SW_PRINT(level, sw, fmt, arg...) \ do { \ - struct tb_switch *__sw = (sw); \ + const struct tb_switch *__sw = (sw); \ level(__sw->tb, "%llx: " fmt, \ tb_route(__sw), ## arg); \ } while (0) @@ -453,7 +453,7 @@ static inline int tb_port_write(struct tb_port *port, const void *buffer, #define __TB_PORT_PRINT(level, _port, fmt, arg...) \ do { \ - struct tb_port *__port = (_port); \ + const struct tb_port *__port = (_port); \ level(__port->sw->tb, "%llx:%x: " fmt, \ tb_route(__port->sw), __port->port, ## arg); \ } while (0) From 62efe699a7f666b48e1d41511147017e13e8d230 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 17 Sep 2018 16:32:13 +0300 Subject: [PATCH 113/255] thunderbolt: Make rest of the logging to happen at debug level Now that the driver can handle every possible tunnel types there is no point to log everything as info level so turn these to happen at debug level instead. While at it remove duplicated tunnel activation log message (tb_tunnel_activate() calls tb_tunnel_restart() which print the same message) and add one missing '\n' termination. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/ctl.c | 2 +- drivers/thunderbolt/icm.c | 2 +- drivers/thunderbolt/path.c | 6 +++--- drivers/thunderbolt/switch.c | 19 +++++++++---------- drivers/thunderbolt/tb.c | 11 +++++------ drivers/thunderbolt/tunnel.c | 6 ++---- 6 files changed, 21 insertions(+), 25 deletions(-) diff --git a/drivers/thunderbolt/ctl.c b/drivers/thunderbolt/ctl.c index 73b386de4d15..2427d73be731 100644 --- a/drivers/thunderbolt/ctl.c +++ b/drivers/thunderbolt/ctl.c @@ -720,7 +720,7 @@ int tb_cfg_error(struct tb_ctl *ctl, u64 route, u32 port, .port = port, .error = error, }; - tb_ctl_info(ctl, "resetting error on %llx:%x.\n", route, port); + tb_ctl_dbg(ctl, "resetting error on %llx:%x.\n", route, port); return tb_ctl_tx(ctl, &pkg, sizeof(pkg), TB_CFG_PKG_ERROR); } diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index d1f6ec89763c..597507bbd8ed 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -1568,7 +1568,7 @@ static int icm_firmware_start(struct tb *tb, struct tb_nhi *nhi) if (val & REG_FW_STS_ICM_EN) return 0; - dev_info(&nhi->pdev->dev, "starting ICM firmware\n"); + dev_dbg(&nhi->pdev->dev, "starting ICM firmware\n"); ret = icm_firmware_reset(tb, nhi); if (ret) diff --git a/drivers/thunderbolt/path.c b/drivers/thunderbolt/path.c index e4c22f53ef4d..273e0cae9a98 100644 --- a/drivers/thunderbolt/path.c +++ b/drivers/thunderbolt/path.c @@ -500,8 +500,8 @@ int tb_path_activate(struct tb_path *path) & out_mask; hop.unknown3 = 0; - tb_port_info(path->hops[i].in_port, "Writing hop %d, index %d", - i, path->hops[i].in_hop_index); + tb_port_dbg(path->hops[i].in_port, "Writing hop %d, index %d\n", + i, path->hops[i].in_hop_index); tb_dump_hop(path->hops[i].in_port, &hop); res = tb_port_write(path->hops[i].in_port, &hop, TB_CFG_HOPS, 2 * path->hops[i].in_hop_index, 2); @@ -512,7 +512,7 @@ int tb_path_activate(struct tb_path *path) } } path->activated = true; - tb_info(path->tb, "path activation complete\n"); + tb_dbg(path->tb, "path activation complete\n"); return 0; err: tb_WARN(path->tb, "path activation failed\n"); diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index a5345a6225bd..c1b016574fb4 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -493,23 +493,22 @@ int tb_wait_for_port(struct tb_port *port, bool wait_if_unplugged) if (state < 0) return state; if (state == TB_PORT_DISABLED) { - tb_port_info(port, "is disabled (state: 0)\n"); + tb_port_dbg(port, "is disabled (state: 0)\n"); return 0; } if (state == TB_PORT_UNPLUGGED) { if (wait_if_unplugged) { /* used during resume */ - tb_port_info(port, - "is unplugged (state: 7), retrying...\n"); + tb_port_dbg(port, + "is unplugged (state: 7), retrying...\n"); msleep(100); continue; } - tb_port_info(port, "is unplugged (state: 7)\n"); + tb_port_dbg(port, "is unplugged (state: 7)\n"); return 0; } if (state == TB_PORT_UP) { - tb_port_info(port, - "is connected, link is up (state: 2)\n"); + tb_port_dbg(port, "is connected, link is up (state: 2)\n"); return 1; } @@ -517,9 +516,9 @@ int tb_wait_for_port(struct tb_port *port, bool wait_if_unplugged) * After plug-in the state is TB_PORT_CONNECTING. Give it some * time. */ - tb_port_info(port, - "is connected, link is not up (state: %d), retrying...\n", - state); + tb_port_dbg(port, + "is connected, link is not up (state: %d), retrying...\n", + state); msleep(100); } tb_port_warn(port, @@ -585,7 +584,7 @@ int tb_port_set_initial_credits(struct tb_port *port, u32 credits) int tb_port_clear_counter(struct tb_port *port, int counter) { u32 zero[3] = { 0, 0, 0 }; - tb_port_info(port, "clearing counter %d\n", counter); + tb_port_dbg(port, "clearing counter %d\n", counter); return tb_port_write(port, zero, TB_CFG_COUNTERS, 3 * counter, 3); } diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index e39fc1e35e6b..1f7a9e1cc09c 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -556,18 +556,17 @@ static void tb_handle_hotplug(struct work_struct *work) } else if (tb_port_is_dpout(port)) { tb_teardown_dp(tb, port); } else { - tb_port_info(port, - "got unplug event for disconnected port, ignoring\n"); + tb_port_dbg(port, + "got unplug event for disconnected port, ignoring\n"); } } else if (port->remote) { - tb_port_info(port, - "got plug event for connected port, ignoring\n"); + tb_port_dbg(port, "got plug event for connected port, ignoring\n"); } else { if (tb_port_is_null(port)) { - tb_port_info(port, "hotplug: scanning\n"); + tb_port_dbg(port, "hotplug: scanning\n"); tb_scan_port(port); if (!port->remote) - tb_port_info(port, "hotplug: no switch found\n"); + tb_port_dbg(port, "hotplug: no switch found\n"); } else if (tb_port_is_dpout(port)) { tb_tunnel_dp(tb, port); } diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c index 9f9b26b12d0a..31d0234837e4 100644 --- a/drivers/thunderbolt/tunnel.c +++ b/drivers/thunderbolt/tunnel.c @@ -611,7 +611,7 @@ int tb_tunnel_restart(struct tb_tunnel *tunnel) { int res, i; - tb_tunnel_info(tunnel, "activating\n"); + tb_tunnel_dbg(tunnel, "activating\n"); /* * Make sure all paths are properly disabled before enabling @@ -660,8 +660,6 @@ int tb_tunnel_activate(struct tb_tunnel *tunnel) { int i; - tb_tunnel_info(tunnel, "activating\n"); - for (i = 0; i < tunnel->npaths; i++) { if (tunnel->paths[i]->activated) { tb_tunnel_WARN(tunnel, @@ -681,7 +679,7 @@ void tb_tunnel_deactivate(struct tb_tunnel *tunnel) { int i; - tb_tunnel_info(tunnel, "deactivating\n"); + tb_tunnel_dbg(tunnel, "deactivating\n"); if (tunnel->activate) tunnel->activate(tunnel, false); From 6755156abc8886f4d1c22e4e5a281f4b9768db7d Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Wed, 6 Mar 2019 19:33:23 +0200 Subject: [PATCH 114/255] thunderbolt: Reword output of tb_dump_hop() While tb_dump_hop() prints out necessary information it is in format that is quite hard to read from the logs especially when one needs to follow the path to see that the setup is correct. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/path.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/drivers/thunderbolt/path.c b/drivers/thunderbolt/path.c index 273e0cae9a98..afe5f8391ebf 100644 --- a/drivers/thunderbolt/path.c +++ b/drivers/thunderbolt/path.c @@ -13,21 +13,22 @@ #include "tb.h" -static void tb_dump_hop(struct tb_port *port, struct tb_regs_hop *hop) +static void tb_dump_hop(const struct tb_path_hop *hop, const struct tb_regs_hop *regs) { - tb_port_dbg(port, " Hop through port %d to hop %d (%s)\n", - hop->out_port, hop->next_hop, - hop->enable ? "enabled" : "disabled"); + const struct tb_port *port = hop->in_port; + + tb_port_dbg(port, " In HopID: %d => Out port: %d Out HopID: %d\n", + hop->in_hop_index, regs->out_port, regs->next_hop); tb_port_dbg(port, " Weight: %d Priority: %d Credits: %d Drop: %d\n", - hop->weight, hop->priority, - hop->initial_credits, hop->drop_packages); + regs->weight, regs->priority, + regs->initial_credits, regs->drop_packages); tb_port_dbg(port, " Counter enabled: %d Counter index: %d\n", - hop->counter_enable, hop->counter); + regs->counter_enable, regs->counter); tb_port_dbg(port, " Flow Control (In/Eg): %d/%d Shared Buffer (In/Eg): %d/%d\n", - hop->ingress_fc, hop->egress_fc, - hop->ingress_shared_buffer, hop->egress_shared_buffer); + regs->ingress_fc, regs->egress_fc, + regs->ingress_shared_buffer, regs->egress_shared_buffer); tb_port_dbg(port, " Unknown1: %#x Unknown2: %#x Unknown3: %#x\n", - hop->unknown1, hop->unknown2, hop->unknown3); + regs->unknown1, regs->unknown2, regs->unknown3); } static struct tb_port *tb_path_find_dst_port(struct tb_port *src, int src_hopid, @@ -500,9 +501,8 @@ int tb_path_activate(struct tb_path *path) & out_mask; hop.unknown3 = 0; - tb_port_dbg(path->hops[i].in_port, "Writing hop %d, index %d\n", - i, path->hops[i].in_hop_index); - tb_dump_hop(path->hops[i].in_port, &hop); + tb_port_dbg(path->hops[i].in_port, "Writing hop %d\n", i); + tb_dump_hop(&path->hops[i], &hop); res = tb_port_write(path->hops[i].in_port, &hop, TB_CFG_HOPS, 2 * path->hops[i].in_hop_index, 2); if (res) { From c4630d6ae6e33b76fedde5c15bdfc7fa579eac32 Mon Sep 17 00:00:00 2001 From: Mika Westerberg Date: Mon, 21 Jan 2019 16:41:27 +0300 Subject: [PATCH 115/255] thunderbolt: Start firmware on Titan Ridge Apple systems Titan Ridge flow to start the firmware is the same as Alpine Ridge so we can do the same on Titan Ridge based Apple systems. Signed-off-by: Mika Westerberg --- drivers/thunderbolt/icm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index 597507bbd8ed..f1c10378fa3e 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -1199,6 +1199,8 @@ static struct pci_dev *get_upstream_port(struct pci_dev *pdev) case PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_LP_BRIDGE: case PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_C_4C_BRIDGE: case PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_C_2C_BRIDGE: + case PCI_DEVICE_ID_INTEL_TITAN_RIDGE_2C_BRIDGE: + case PCI_DEVICE_ID_INTEL_TITAN_RIDGE_4C_BRIDGE: return parent; } From 883c2459a57d93efbcb974bea1d2d506db3ae9ab Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sun, 21 Apr 2019 10:48:41 +0300 Subject: [PATCH 116/255] habanalabs: re-factor goya_parse_cb_no_ext_queue() This patch re-factors goya_parse_cb_no_ext_queue() to make it more readable by inverting the check inside the first if statement so the bulk of the function won't be inside an if statement. The patch also fixes a spelling error in the name of the function. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 43 ++++++++++++++--------------- 1 file changed, 21 insertions(+), 22 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index bde11fc2c251..3f707e8c408a 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -3858,36 +3858,35 @@ static int goya_parse_cb_no_mmu(struct hl_device *hdev, return rc; } -static int goya_parse_cb_no_ext_quque(struct hl_device *hdev, +static int goya_parse_cb_no_ext_queue(struct hl_device *hdev, struct hl_cs_parser *parser) { struct asic_fixed_properties *asic_prop = &hdev->asic_prop; struct goya_device *goya = hdev->asic_specific; - if (!(goya->hw_cap_initialized & HW_CAP_MMU)) { - /* For internal queue jobs, just check if cb address is valid */ - if (hl_mem_area_inside_range( - (u64) (uintptr_t) parser->user_cb, - parser->user_cb_size, - asic_prop->sram_user_base_address, - asic_prop->sram_end_address)) - return 0; + if (goya->hw_cap_initialized & HW_CAP_MMU) + return 0; - if (hl_mem_area_inside_range( - (u64) (uintptr_t) parser->user_cb, - parser->user_cb_size, - asic_prop->dram_user_base_address, - asic_prop->dram_end_address)) - return 0; + /* For internal queue jobs, just check if CB address is valid */ + if (hl_mem_area_inside_range( + (u64) (uintptr_t) parser->user_cb, + parser->user_cb_size, + asic_prop->sram_user_base_address, + asic_prop->sram_end_address)) + return 0; - dev_err(hdev->dev, - "Internal CB address %px + 0x%x is not in SRAM nor in DRAM\n", - parser->user_cb, parser->user_cb_size); + if (hl_mem_area_inside_range( + (u64) (uintptr_t) parser->user_cb, + parser->user_cb_size, + asic_prop->dram_user_base_address, + asic_prop->dram_end_address)) + return 0; - return -EFAULT; - } + dev_err(hdev->dev, + "Internal CB address %px + 0x%x is not in SRAM nor in DRAM\n", + parser->user_cb, parser->user_cb_size); - return 0; + return -EFAULT; } int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser) @@ -3895,7 +3894,7 @@ int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser) struct goya_device *goya = hdev->asic_specific; if (!parser->ext_queue) - return goya_parse_cb_no_ext_quque(hdev, parser); + return goya_parse_cb_no_ext_queue(hdev, parser); if ((goya->hw_cap_initialized & HW_CAP_MMU) && parser->use_virt_addr) return goya_parse_cb_mmu(hdev, parser); From d691171d61b635fa36860ca65c4f8fde718abd09 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sun, 21 Apr 2019 16:20:46 +0300 Subject: [PATCH 117/255] uapi/habanalabs: add missing fields in bmon params This patch adds missing fields of start address 0 and 1 in the bmon parameter structure that is received from the user in the debug IOCTL. Without these fields, the functionality of the bmon trace is broken, because there is no configuration of the base address of the filter of the bus monitor. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya_coresight.c | 16 ++++++++++++---- include/uapi/misc/habanalabs.h | 9 ++++++--- 2 files changed, 18 insertions(+), 7 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya_coresight.c b/drivers/misc/habanalabs/goya/goya_coresight.c index 68726fb4c56a..1ac951f52d1e 100644 --- a/drivers/misc/habanalabs/goya/goya_coresight.c +++ b/drivers/misc/habanalabs/goya/goya_coresight.c @@ -459,10 +459,14 @@ static int goya_config_bmon(struct hl_device *hdev, if (!input) return -EINVAL; - WREG32(base_reg + 0x208, lower_32_bits(input->addr_range0)); - WREG32(base_reg + 0x20C, upper_32_bits(input->addr_range0)); - WREG32(base_reg + 0x248, lower_32_bits(input->addr_range1)); - WREG32(base_reg + 0x24C, upper_32_bits(input->addr_range1)); + WREG32(base_reg + 0x200, lower_32_bits(input->start_addr0)); + WREG32(base_reg + 0x204, upper_32_bits(input->start_addr0)); + WREG32(base_reg + 0x208, lower_32_bits(input->addr_mask0)); + WREG32(base_reg + 0x20C, upper_32_bits(input->addr_mask0)); + WREG32(base_reg + 0x240, lower_32_bits(input->start_addr1)); + WREG32(base_reg + 0x244, upper_32_bits(input->start_addr1)); + WREG32(base_reg + 0x248, lower_32_bits(input->addr_mask1)); + WREG32(base_reg + 0x24C, upper_32_bits(input->addr_mask1)); WREG32(base_reg + 0x224, 0); WREG32(base_reg + 0x234, 0); WREG32(base_reg + 0x30C, input->bw_win); @@ -482,8 +486,12 @@ static int goya_config_bmon(struct hl_device *hdev, WREG32(base_reg + 0x100, 0x11); WREG32(base_reg + 0x304, 0x1); } else { + WREG32(base_reg + 0x200, 0); + WREG32(base_reg + 0x204, 0); WREG32(base_reg + 0x208, 0xFFFFFFFF); WREG32(base_reg + 0x20C, 0xFFFFFFFF); + WREG32(base_reg + 0x240, 0); + WREG32(base_reg + 0x244, 0); WREG32(base_reg + 0x248, 0xFFFFFFFF); WREG32(base_reg + 0x24C, 0xFFFFFFFF); WREG32(base_reg + 0x224, 0xFFFFFFFF); diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h index 613d431da783..8ac292cf4d00 100644 --- a/include/uapi/misc/habanalabs.h +++ b/include/uapi/misc/habanalabs.h @@ -374,9 +374,12 @@ struct hl_debug_params_stm { }; struct hl_debug_params_bmon { - /* Transaction address filter */ - __u64 addr_range0; - __u64 addr_range1; + /* Two address ranges that the user can request to filter */ + __u64 start_addr0; + __u64 addr_mask0; + + __u64 start_addr1; + __u64 addr_mask1; /* Capture window configuration */ __u32 bw_win; From b2377e032f17c3dd87739a97699f144ed00edf05 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Mon, 22 Apr 2019 11:49:06 +0300 Subject: [PATCH 118/255] habanalabs: use ASIC functions interface for rreg/wreg This patch slightly changes the macros of RREG32 and WREG32, which are used when reading or writing from registers. Instead of directly calling a function in the common code from these macros, the new code calls a function from the ASIC functions interface. This change allows us to share much more code between real ASICs and simulators, which in turn reduces the maintenance burden and the chances for forgetting to port code between the ASIC files. The patch also implements the hl_poll_timeout macro, instead of calling the generic readl_poll_timeout macro. This is required to allow use of this macro in the simulator files. As a result from this change, more functions in goya.c are shared with the simulator and therefore, should not be defined as static. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 43 +++++++++++----------------- drivers/misc/habanalabs/goya/goyaP.h | 40 ++++++++++++++++++-------- drivers/misc/habanalabs/habanalabs.h | 32 +++++++++++++++++---- 3 files changed, 71 insertions(+), 44 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 3f707e8c408a..8ee3b00b0fab 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -297,7 +297,7 @@ static u32 goya_all_events[] = { GOYA_ASYNC_EVENT_ID_DMA_BM_CH4 }; -static void goya_get_fixed_properties(struct hl_device *hdev) +void goya_get_fixed_properties(struct hl_device *hdev) { struct asic_fixed_properties *prop = &hdev->asic_prop; int i; @@ -542,14 +542,7 @@ static void goya_fetch_psoc_frequency(struct hl_device *hdev) prop->psoc_pci_pll_div_factor = RREG32(mmPSOC_PCI_PLL_DIV_FACTOR_1); } -/* - * goya_late_init - GOYA late initialization code - * - * @hdev: pointer to hl_device structure - * - * Get ArmCP info and send message to CPU to enable PCI access - */ -static int goya_late_init(struct hl_device *hdev) +int goya_late_init(struct hl_device *hdev) { struct asic_fixed_properties *prop = &hdev->asic_prop; int rc; @@ -648,9 +641,6 @@ static int goya_sw_init(struct hl_device *hdev) goya->tpc_clk = GOYA_PLL_FREQ_LOW; goya->ic_clk = GOYA_PLL_FREQ_LOW; - goya->mmu_prepare_reg = goya_mmu_prepare_reg; - goya->qman0_set_security = goya_qman0_set_security; - hdev->asic_specific = goya; /* Create DMA pool for small allocations */ @@ -815,7 +805,7 @@ static void goya_init_dma_ch(struct hl_device *hdev, int dma_id) * Initialize the H/W registers of the QMAN DMA channels * */ -static void goya_init_dma_qmans(struct hl_device *hdev) +void goya_init_dma_qmans(struct hl_device *hdev) { struct goya_device *goya = hdev->asic_specific; struct hl_hw_queue *q; @@ -968,7 +958,7 @@ static int goya_stop_external_queues(struct hl_device *hdev) * Returns 0 on success * */ -static int goya_init_cpu_queues(struct hl_device *hdev) +int goya_init_cpu_queues(struct hl_device *hdev) { struct goya_device *goya = hdev->asic_specific; struct hl_eq *eq; @@ -1549,7 +1539,7 @@ static void goya_init_mme_cmdq(struct hl_device *hdev) WREG32(mmMME_CMDQ_GLBL_CFG0, CMDQ_MME_ENABLE); } -static void goya_init_mme_qmans(struct hl_device *hdev) +void goya_init_mme_qmans(struct hl_device *hdev) { struct goya_device *goya = hdev->asic_specific; u32 so_base_lo, so_base_hi; @@ -1656,7 +1646,7 @@ static void goya_init_tpc_cmdq(struct hl_device *hdev, int tpc_id) WREG32(mmTPC0_CMDQ_GLBL_CFG0 + reg_off, CMDQ_TPC_ENABLE); } -static void goya_init_tpc_qmans(struct hl_device *hdev) +void goya_init_tpc_qmans(struct hl_device *hdev) { struct goya_device *goya = hdev->asic_specific; u32 so_base_lo, so_base_hi; @@ -2373,7 +2363,7 @@ static int goya_mmu_update_asid_hop0_addr(struct hl_device *hdev, u32 asid, return 0; } -static int goya_mmu_init(struct hl_device *hdev) +int goya_mmu_init(struct hl_device *hdev) { struct asic_fixed_properties *prop = &hdev->asic_prop; struct goya_device *goya = hdev->asic_specific; @@ -2649,7 +2639,7 @@ static int goya_cb_mmap(struct hl_device *hdev, struct vm_area_struct *vma, return rc; } -static void goya_ring_doorbell(struct hl_device *hdev, u32 hw_queue_id, u32 pi) +void goya_ring_doorbell(struct hl_device *hdev, u32 hw_queue_id, u32 pi) { u32 db_reg_offset, db_value; bool invalid_queue = false; @@ -2816,7 +2806,6 @@ void *goya_get_int_queue_base(struct hl_device *hdev, u32 queue_id, static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) { - struct goya_device *goya = hdev->asic_specific; struct packet_msg_prot *fence_pkt; u32 *fence_ptr; dma_addr_t fence_dma_addr; @@ -2847,7 +2836,7 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) *fence_ptr = 0; - goya->qman0_set_security(hdev, true); + goya_qman0_set_security(hdev, true); /* * goya cs parser saves space for 2xpacket_msg_prot at end of CB. For @@ -2889,7 +2878,7 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) hdev->asic_funcs->dma_pool_free(hdev, (void *) fence_ptr, fence_dma_addr); - goya->qman0_set_security(hdev, false); + goya_qman0_set_security(hdev, false); return rc; } @@ -3927,12 +3916,12 @@ void goya_add_end_of_cb_packets(u64 kernel_address, u32 len, u64 cq_addr, cq_pkt->addr = cpu_to_le64(CFG_BASE + mmPCIE_DBI_MSIX_DOORBELL_OFF); } -static void goya_update_eq_ci(struct hl_device *hdev, u32 val) +void goya_update_eq_ci(struct hl_device *hdev, u32 val) { WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_6, val); } -static void goya_restore_phase_topology(struct hl_device *hdev) +void goya_restore_phase_topology(struct hl_device *hdev) { int i, num_of_sob_in_longs, num_of_mon_in_longs; @@ -4494,7 +4483,7 @@ static int goya_memset_device_memory(struct hl_device *hdev, u64 addr, u32 size, return rc; } -static int goya_context_switch(struct hl_device *hdev, u32 asid) +int goya_context_switch(struct hl_device *hdev, u32 asid) { struct asic_fixed_properties *prop = &hdev->asic_prop; u64 addr = prop->sram_base_address; @@ -4556,7 +4545,7 @@ void goya_mmu_prepare(struct hl_device *hdev, u32 asid) /* zero the MMBP and ASID bits and then set the ASID */ for (i = 0 ; i < GOYA_MMU_REGS_NUM ; i++) - goya->mmu_prepare_reg(hdev, goya_mmu_regs[i], asid); + goya_mmu_prepare_reg(hdev, goya_mmu_regs[i], asid); } static void goya_mmu_invalidate_cache(struct hl_device *hdev, bool is_hard) @@ -4829,7 +4818,9 @@ static const struct hl_asic_funcs goya_funcs = { .get_hw_state = goya_get_hw_state, .pci_bars_map = goya_pci_bars_map, .set_dram_bar_base = goya_set_ddr_bar_base, - .init_iatu = goya_init_iatu + .init_iatu = goya_init_iatu, + .rreg = hl_rreg, + .wreg = hl_wreg }; /* diff --git a/drivers/misc/habanalabs/goya/goyaP.h b/drivers/misc/habanalabs/goya/goyaP.h index b572e0263ac5..14e216cb3668 100644 --- a/drivers/misc/habanalabs/goya/goyaP.h +++ b/drivers/misc/habanalabs/goya/goyaP.h @@ -147,9 +147,6 @@ enum goya_fw_component { }; struct goya_device { - void (*mmu_prepare_reg)(struct hl_device *hdev, u64 reg, u32 asid); - void (*qman0_set_security)(struct hl_device *hdev, bool secure); - /* TODO: remove hw_queues_lock after moving to scheduler code */ spinlock_t hw_queues_lock; @@ -162,13 +159,34 @@ struct goya_device { u32 hw_cap_initialized; }; +void goya_get_fixed_properties(struct hl_device *hdev); +int goya_mmu_init(struct hl_device *hdev); +void goya_init_dma_qmans(struct hl_device *hdev); +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); +int goya_late_init(struct hl_device *hdev); +void goya_late_fini(struct hl_device *hdev); + +void goya_ring_doorbell(struct hl_device *hdev, u32 hw_queue_id, u32 pi); +void goya_flush_pq_write(struct hl_device *hdev, u64 *pq, u64 exp_val); +void goya_update_eq_ci(struct hl_device *hdev, u32 val); +void goya_restore_phase_topology(struct hl_device *hdev); +int goya_context_switch(struct hl_device *hdev, u32 asid); + int goya_debugfs_i2c_read(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr, u8 i2c_reg, u32 *val); int goya_debugfs_i2c_write(struct hl_device *hdev, u8 i2c_bus, u8 i2c_addr, u8 i2c_reg, u32 val); +void goya_debugfs_led_set(struct hl_device *hdev, u8 led, u8 state); + +int goya_test_queue(struct hl_device *hdev, u32 hw_queue_id); +int goya_test_queues(struct hl_device *hdev); int goya_test_cpu_queue(struct hl_device *hdev); int goya_send_cpu_message(struct hl_device *hdev, u32 *msg, u16 len, u32 timeout, long *result); + long goya_get_temperature(struct hl_device *hdev, int sensor_index, u32 attr); long goya_get_voltage(struct hl_device *hdev, int sensor_index, u32 attr); long goya_get_current(struct hl_device *hdev, int sensor_index, u32 attr); @@ -176,33 +194,31 @@ long goya_get_fan_speed(struct hl_device *hdev, int sensor_index, u32 attr); long goya_get_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr); void goya_set_pwm_info(struct hl_device *hdev, int sensor_index, u32 attr, long value); -void goya_debugfs_led_set(struct hl_device *hdev, u8 led, u8 state); +u64 goya_get_max_power(struct hl_device *hdev); +void goya_set_max_power(struct hl_device *hdev, u64 value); + void goya_set_pll_profile(struct hl_device *hdev, enum hl_pll_frequency freq); void goya_add_device_attr(struct hl_device *hdev, struct attribute_group *dev_attr_grp); int goya_armcp_info_get(struct hl_device *hdev); -void goya_init_security(struct hl_device *hdev); int goya_debug_coresight(struct hl_device *hdev, void *data); -u64 goya_get_max_power(struct hl_device *hdev); -void goya_set_max_power(struct hl_device *hdev, u64 value); -int goya_test_queues(struct hl_device *hdev); + void goya_mmu_prepare(struct hl_device *hdev, u32 asid); int goya_mmu_clear_pgt_range(struct hl_device *hdev); int goya_mmu_set_dram_default_page(struct hl_device *hdev); -void goya_late_fini(struct hl_device *hdev); int goya_suspend(struct hl_device *hdev); int goya_resume(struct hl_device *hdev); -void goya_flush_pq_write(struct hl_device *hdev, u64 *pq, u64 exp_val); + void goya_handle_eqe(struct hl_device *hdev, struct hl_eq_entry *eq_entry); void *goya_get_events_stat(struct hl_device *hdev, u32 *size); + void goya_add_end_of_cb_packets(u64 kernel_address, u32 len, u64 cq_addr, u32 cq_val, u32 msix_vec); int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser); void *goya_get_int_queue_base(struct hl_device *hdev, u32 queue_id, - dma_addr_t *dma_handle, u16 *queue_len); + dma_addr_t *dma_handle, u16 *queue_len); u32 goya_get_dma_desc_list_size(struct hl_device *hdev, struct sg_table *sgt); -int goya_test_queue(struct hl_device *hdev, u32 hw_queue_id); int goya_send_heartbeat(struct hl_device *hdev); void *goya_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size, dma_addr_t *dma_handle); diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 86bd5298efd6..e8bbaf0f26c1 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -489,6 +489,8 @@ enum hl_pll_frequency { * @pci_bars_map: Map PCI BARs. * @set_dram_bar_base: Set DRAM BAR to map specific device address. * @init_iatu: Initialize the iATU unit inside the PCI controller. + * @rreg: Read a register. Needed for simulator support. + * @wreg: Write a register. Needed for simulator support. */ struct hl_asic_funcs { int (*early_init)(struct hl_device *hdev); @@ -564,6 +566,8 @@ struct hl_asic_funcs { int (*pci_bars_map)(struct hl_device *hdev); int (*set_dram_bar_base)(struct hl_device *hdev, u64 addr); int (*init_iatu)(struct hl_device *hdev); + u32 (*rreg)(struct hl_device *hdev, u32 reg); + void (*wreg)(struct hl_device *hdev, u32 reg, u32 val); }; @@ -1007,13 +1011,10 @@ struct hl_dbg_device_entry { u32 hl_rreg(struct hl_device *hdev, u32 reg); void hl_wreg(struct hl_device *hdev, u32 reg, u32 val); -#define hl_poll_timeout(hdev, addr, val, cond, sleep_us, timeout_us) \ - readl_poll_timeout(hdev->rmmio + addr, val, cond, sleep_us, timeout_us) - -#define RREG32(reg) hl_rreg(hdev, (reg)) -#define WREG32(reg, v) hl_wreg(hdev, (reg), (v)) +#define RREG32(reg) hdev->asic_funcs->rreg(hdev, (reg)) +#define WREG32(reg, v) hdev->asic_funcs->wreg(hdev, (reg), (v)) #define DREG32(reg) pr_info("REGISTER: " #reg " : 0x%08X\n", \ - hl_rreg(hdev, (reg))) + hdev->asic_funcs->rreg(hdev, (reg))) #define WREG32_P(reg, val, mask) \ do { \ @@ -1031,6 +1032,25 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val); WREG32(mm##reg, (RREG32(mm##reg) & ~REG_FIELD_MASK(reg, field)) | \ (val) << REG_FIELD_SHIFT(reg, field)) +#define hl_poll_timeout(hdev, addr, val, cond, sleep_us, timeout_us) \ +({ \ + ktime_t __timeout = ktime_add_us(ktime_get(), timeout_us); \ + might_sleep_if(sleep_us); \ + for (;;) { \ + (val) = RREG32(addr); \ + if (cond) \ + break; \ + if (timeout_us && ktime_compare(ktime_get(), __timeout) > 0) { \ + (val) = RREG32(addr); \ + break; \ + } \ + if (sleep_us) \ + usleep_range((sleep_us >> 2) + 1, sleep_us); \ + } \ + (cond) ? 0 : -ETIMEDOUT; \ +}) + + #define HL_ENG_BUSY(buf, size, fmt, ...) ({ \ if (buf) \ snprintf(buf, size, fmt, ##__VA_ARGS__); \ From 37209783c73a47692dbf1e6b2dba0d07f6ce24b3 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 24 Apr 2019 11:34:13 -0700 Subject: [PATCH 119/255] thunderbolt: Make priority unsigned in struct tb_path Clang warns: drivers/thunderbolt/tunnel.c:504:17: warning: implicit truncation from 'int' to bit-field changes value from 5 to -3 [-Wbitfield-constant-conversion] path->priority = 5; ^ ~ 1 warning generated. The priority member in struct tb_path is only ever assigned a positive number: $ rg -n priority drivers/thunderbolt/path.c drivers/thunderbolt/tunnel.c:99: path->priority = 3; drivers/thunderbolt/tunnel.c:308: path->priority = 2; drivers/thunderbolt/tunnel.c:323: path->priority = 1; drivers/thunderbolt/tunnel.c:504: path->priority = 5; Furthermore, that value is only assigned to an unsigned integer in tb_path_activate (the priority member in struct tb_regs_hop). Fixes: 44242d6c9703 ("thunderbolt: Add support for DMA tunnels") Link: https://github.com/ClangBuiltLinux/linux/issues/454 Signed-off-by: Nathan Chancellor Reviewed-by: Nick Desaulniers Signed-off-by: Mika Westerberg --- drivers/thunderbolt/tb.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index 15d225dcb403..b12c8f33d89c 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -225,7 +225,7 @@ struct tb_path { enum tb_path_port ingress_fc_enable; enum tb_path_port egress_fc_enable; - int priority:3; + unsigned int priority:3; int weight:4; bool drop_packages; bool activated; From 027d35d0b6999c02de4c1ef86d0df4b5f4119167 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Thu, 25 Apr 2019 20:15:42 +0300 Subject: [PATCH 120/255] habanalabs: rename restore to ctx_switch when appropriate This patch only does renaming of certain variables and structure members, and their accompanied comments. This is done to better reflect the actions these variables and members represent. There is no functional change in this patch. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/command_submission.c | 16 ++++++++-------- drivers/misc/habanalabs/context.c | 4 ++-- drivers/misc/habanalabs/device.c | 6 +++--- drivers/misc/habanalabs/habanalabs.h | 17 +++++++++-------- 4 files changed, 22 insertions(+), 21 deletions(-) diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index 02c48da0b645..c4ab694b51b5 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -601,7 +601,7 @@ int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data) void __user *chunks; u32 num_chunks; u64 cs_seq = ULONG_MAX; - int rc, do_restore; + int rc, do_ctx_switch; bool need_soft_reset = false; if (hl_device_disabled_or_in_reset(hdev)) { @@ -612,9 +612,9 @@ int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data) goto out; } - do_restore = atomic_cmpxchg(&ctx->thread_restore_token, 1, 0); + do_ctx_switch = atomic_cmpxchg(&ctx->thread_ctx_switch_token, 1, 0); - if (do_restore || (args->in.cs_flags & HL_CS_FLAGS_FORCE_RESTORE)) { + if (do_ctx_switch || (args->in.cs_flags & HL_CS_FLAGS_FORCE_RESTORE)) { long ret; chunks = (void __user *)(uintptr_t)args->in.chunks_restore; @@ -622,7 +622,7 @@ int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data) mutex_lock(&hpriv->restore_phase_mutex); - if (do_restore) { + if (do_ctx_switch) { rc = hdev->asic_funcs->context_switch(hdev, ctx->asid); if (rc) { dev_err_ratelimited(hdev->dev, @@ -678,18 +678,18 @@ int hl_cs_ioctl(struct hl_fpriv *hpriv, void *data) } } - ctx->thread_restore_wait_token = 1; - } else if (!ctx->thread_restore_wait_token) { + ctx->thread_ctx_switch_wait_token = 1; + } else if (!ctx->thread_ctx_switch_wait_token) { u32 tmp; rc = hl_poll_timeout_memory(hdev, - (u64) (uintptr_t) &ctx->thread_restore_wait_token, + (u64) (uintptr_t) &ctx->thread_ctx_switch_wait_token, jiffies_to_usecs(hdev->timeout_jiffies), &tmp); if (rc || !tmp) { dev_err(hdev->dev, - "restore phase hasn't finished in time\n"); + "context switch phase didn't finish in time\n"); rc = -ETIMEDOUT; goto out; } diff --git a/drivers/misc/habanalabs/context.c b/drivers/misc/habanalabs/context.c index 619ace1c4ef7..4804cdcf4c48 100644 --- a/drivers/misc/habanalabs/context.c +++ b/drivers/misc/habanalabs/context.c @@ -106,8 +106,8 @@ int hl_ctx_init(struct hl_device *hdev, struct hl_ctx *ctx, bool is_kernel_ctx) ctx->cs_sequence = 1; spin_lock_init(&ctx->cs_lock); - atomic_set(&ctx->thread_restore_token, 1); - ctx->thread_restore_wait_token = 0; + atomic_set(&ctx->thread_ctx_switch_token, 1); + ctx->thread_ctx_switch_wait_token = 0; if (is_kernel_ctx) { ctx->asid = HL_KERNEL_ASID_ID; /* KMD gets ASID 0 */ diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index a88f7be23c7f..0e0b9ec71c80 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -710,10 +710,10 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset, for (i = 0 ; i < hdev->asic_prop.completion_queues_count ; i++) hl_cq_reset(hdev, &hdev->completion_queue[i]); - /* Make sure the setup phase for the user context will run again */ + /* Make sure the context switch phase will run again */ if (hdev->user_ctx) { - atomic_set(&hdev->user_ctx->thread_restore_token, 1); - hdev->user_ctx->thread_restore_wait_token = 0; + atomic_set(&hdev->user_ctx->thread_ctx_switch_token, 1); + hdev->user_ctx->thread_ctx_switch_wait_token = 0; } /* Finished tear-down, starting to re-initialize */ diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index e8bbaf0f26c1..a624d1e1e1e5 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -615,12 +615,13 @@ struct hl_va_range { * DRAM mapping. * @cs_lock: spinlock to protect cs_sequence. * @dram_phys_mem: amount of used physical DRAM memory by this context. - * @thread_restore_token: token to prevent multiple threads of the same context - * from running the restore phase. Only one thread - * should run it. - * @thread_restore_wait_token: token to prevent the threads that didn't run - * the restore phase from moving to their execution - * phase before the restore phase has finished. + * @thread_ctx_switch_token: token to prevent multiple threads of the same + * context from running the context switch phase. + * Only a single thread should run it. + * @thread_ctx_switch_wait_token: token to prevent the threads that didn't run + * the context switch phase from moving to their + * execution phase before the context switch phase + * has finished. * @asid: context's unique address space ID in the device's MMU. */ struct hl_ctx { @@ -640,8 +641,8 @@ struct hl_ctx { u64 *dram_default_hops; spinlock_t cs_lock; atomic64_t dram_phys_mem; - atomic_t thread_restore_token; - u32 thread_restore_wait_token; + atomic_t thread_ctx_switch_token; + u32 thread_ctx_switch_wait_token; u32 asid; }; From 28703c6ef6228635f7c8b248c1d846511a2b60a3 Mon Sep 17 00:00:00 2001 From: Patrick Venture Date: Mon, 8 Apr 2019 07:42:16 -0700 Subject: [PATCH 121/255] dt-bindings: misc: aspeed-p2a-ctrl: add support Document the ast2400, ast2500 PCI-to-AHB bridge control driver bindings. Signed-off-by: Patrick Venture Reviewed-by: Rob Herring Reviewed-by: Andrew Jeffery Signed-off-by: Greg Kroah-Hartman --- .../bindings/misc/aspeed-p2a-ctrl.txt | 47 +++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 Documentation/devicetree/bindings/misc/aspeed-p2a-ctrl.txt diff --git a/Documentation/devicetree/bindings/misc/aspeed-p2a-ctrl.txt b/Documentation/devicetree/bindings/misc/aspeed-p2a-ctrl.txt new file mode 100644 index 000000000000..854bd67ffec6 --- /dev/null +++ b/Documentation/devicetree/bindings/misc/aspeed-p2a-ctrl.txt @@ -0,0 +1,47 @@ +====================================================================== +Device tree bindings for Aspeed AST2400/AST2500 PCI-to-AHB Bridge Control Driver +====================================================================== + +The bridge is available on platforms with the VGA enabled on the Aspeed device. +In this case, the host has access to a 64KiB window into all of the BMC's +memory. The BMC can disable this bridge. If the bridge is enabled, the host +has read access to all the regions of memory, however the host only has read +and write access depending on a register controlled by the BMC. + +Required properties: +=================== + + - compatible: must be one of: + - "aspeed,ast2400-p2a-ctrl" + - "aspeed,ast2500-p2a-ctrl" + +Optional properties: +=================== + +- memory-region: A phandle to a reserved_memory region to be used for the PCI + to AHB mapping + +The p2a-control node should be the child of a syscon node with the required +property: + +- compatible : Should be one of the following: + "aspeed,ast2400-scu", "syscon", "simple-mfd" + "aspeed,g4-scu", "syscon", "simple-mfd" + "aspeed,ast2500-scu", "syscon", "simple-mfd" + "aspeed,g5-scu", "syscon", "simple-mfd" + +Example +=================== + +g4 Example +---------- + +syscon: scu@1e6e2000 { + compatible = "aspeed,ast2400-scu", "syscon", "simple-mfd"; + reg = <0x1e6e2000 0x1a8>; + + p2a: p2a-control { + compatible = "aspeed,ast2400-p2a-ctrl"; + memory-region = <&reserved_memory>; + }; +}; From 01c60dcea9f7a97ed0e94245e425002a8ddd6c17 Mon Sep 17 00:00:00 2001 From: Patrick Venture Date: Mon, 8 Apr 2019 07:42:39 -0700 Subject: [PATCH 122/255] drivers/misc: Add Aspeed P2A control driver The ASPEED AST2400, and AST2500 in some configurations include a PCI-to-AHB MMIO bridge. This bridge allows a server to read and write in the BMC's physical address space. This feature is especially useful when using this bridge to send large files to the BMC. The host may use this to send down a firmware image by staging data at a specific memory address, and in a coordinated effort with the BMC's software stack and kernel, transmit the bytes. This driver enables the BMC to unlock the PCI bridge on demand, and configure it via ioctl to allow the host to write bytes to an agreed upon location. In the primary use-case, the region to use is known apriori on the BMC, and the host requests this information. Once this request is received, the BMC's software stack will enable the bridge and the region and then using some software flow control (possibly via IPMI packets), copy the bytes down. Once the process is complete, the BMC will disable the bridge and unset any region involved. The default behavior of this bridge when present is: enabled and all regions marked read-write. This driver will fix the regions to be read-only and then disable the bridge entirely. The memory regions protected are: * BMC flash MMIO window * System flash MMIO windows * SOC IO (peripheral MMIO) * DRAM The DRAM region itself is all of DRAM and cannot be further specified. Once the PCI bridge is enabled, the host can read all of DRAM, and if the DRAM section is write-enabled, then it can write to all of it. Signed-off-by: Patrick Venture Reviewed-by: Andrew Jeffery Signed-off-by: Greg Kroah-Hartman --- drivers/misc/Kconfig | 8 + drivers/misc/Makefile | 1 + drivers/misc/aspeed-p2a-ctrl.c | 443 +++++++++++++++++++++++++++ include/uapi/linux/aspeed-p2a-ctrl.h | 62 ++++ 4 files changed, 514 insertions(+) create mode 100644 drivers/misc/aspeed-p2a-ctrl.c create mode 100644 include/uapi/linux/aspeed-p2a-ctrl.h diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index 42ab8ec92a04..3209ee020b15 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -496,6 +496,14 @@ config VEXPRESS_SYSCFG bus. System Configuration interface is one of the possible means of generating transactions on this bus. +config ASPEED_P2A_CTRL + depends on (ARCH_ASPEED || COMPILE_TEST) && REGMAP && MFD_SYSCON + tristate "Aspeed ast2400/2500 HOST P2A VGA MMIO to BMC bridge control" + help + Control Aspeed ast2400/2500 HOST P2A VGA MMIO to BMC mappings through + ioctl()s, the driver also provides an interface for userspace mappings to + a pre-defined region. + config ASPEED_LPC_CTRL depends on (ARCH_ASPEED || COMPILE_TEST) && REGMAP && MFD_SYSCON tristate "Aspeed ast2400/2500 HOST LPC to BMC bridge control" diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index d5b7d3404dc7..c36239573a5c 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -56,6 +56,7 @@ obj-$(CONFIG_VEXPRESS_SYSCFG) += vexpress-syscfg.o obj-$(CONFIG_CXL_BASE) += cxl/ obj-$(CONFIG_ASPEED_LPC_CTRL) += aspeed-lpc-ctrl.o obj-$(CONFIG_ASPEED_LPC_SNOOP) += aspeed-lpc-snoop.o +obj-$(CONFIG_ASPEED_P2A_CTRL) += aspeed-p2a-ctrl.o obj-$(CONFIG_PCI_ENDPOINT_TEST) += pci_endpoint_test.o obj-$(CONFIG_OCXL) += ocxl/ obj-y += cardreader/ diff --git a/drivers/misc/aspeed-p2a-ctrl.c b/drivers/misc/aspeed-p2a-ctrl.c new file mode 100644 index 000000000000..c0521b2ffc6a --- /dev/null +++ b/drivers/misc/aspeed-p2a-ctrl.c @@ -0,0 +1,443 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2019 Google Inc + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Provides a simple driver to control the ASPEED P2A interface which allows + * the host to read and write to various regions of the BMC's memory. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#define DEVICE_NAME "aspeed-p2a-ctrl" + +/* SCU2C is a Misc. Control Register. */ +#define SCU2C 0x2c +/* SCU180 is the PCIe Configuration Setting Control Register. */ +#define SCU180 0x180 +/* Bit 1 controls the P2A bridge, while bit 0 controls the entire VGA device + * on the PCI bus. + */ +#define SCU180_ENP2A BIT(1) + +/* The ast2400/2500 both have six ranges. */ +#define P2A_REGION_COUNT 6 + +struct region { + u64 min; + u64 max; + u32 bit; +}; + +struct aspeed_p2a_model_data { + /* min, max, bit */ + struct region regions[P2A_REGION_COUNT]; +}; + +struct aspeed_p2a_ctrl { + struct miscdevice miscdev; + struct regmap *regmap; + + const struct aspeed_p2a_model_data *config; + + /* Access to these needs to be locked, held via probe, mapping ioctl, + * and release, remove. + */ + struct mutex tracking; + u32 readers; + u32 readerwriters[P2A_REGION_COUNT]; + + phys_addr_t mem_base; + resource_size_t mem_size; +}; + +struct aspeed_p2a_user { + struct file *file; + struct aspeed_p2a_ctrl *parent; + + /* The entire memory space is opened for reading once the bridge is + * enabled, therefore this needs only to be tracked once per user. + * If any user has it open for read, the bridge must stay enabled. + */ + u32 read; + + /* Each entry of the array corresponds to a P2A Region. If the user + * opens for read or readwrite, the reference goes up here. On + * release, this array is walked and references adjusted accordingly. + */ + u32 readwrite[P2A_REGION_COUNT]; +}; + +static void aspeed_p2a_enable_bridge(struct aspeed_p2a_ctrl *p2a_ctrl) +{ + regmap_update_bits(p2a_ctrl->regmap, + SCU180, SCU180_ENP2A, SCU180_ENP2A); +} + +static void aspeed_p2a_disable_bridge(struct aspeed_p2a_ctrl *p2a_ctrl) +{ + regmap_update_bits(p2a_ctrl->regmap, SCU180, SCU180_ENP2A, 0); +} + +static int aspeed_p2a_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct aspeed_p2a_user *priv = file->private_data; + struct aspeed_p2a_ctrl *ctrl = priv->parent; + + if (ctrl->mem_base == 0 && ctrl->mem_size == 0) + return -EINVAL; + + unsigned long vsize = vma->vm_end - vma->vm_start; + pgprot_t prot = vma->vm_page_prot; + + if (vma->vm_pgoff + vsize > ctrl->mem_base + ctrl->mem_size) + return -EINVAL; + + /* ast2400/2500 AHB accesses are not cache coherent */ + prot = pgprot_noncached(prot); + + if (remap_pfn_range(vma, vma->vm_start, + (ctrl->mem_base >> PAGE_SHIFT) + vma->vm_pgoff, + vsize, prot)) + return -EAGAIN; + + return 0; +} + +static bool aspeed_p2a_region_acquire(struct aspeed_p2a_user *priv, + struct aspeed_p2a_ctrl *ctrl, + struct aspeed_p2a_ctrl_mapping *map) +{ + int i; + u64 base, end; + bool matched = false; + + base = map->addr; + end = map->addr + (map->length - 1); + + /* If the value is a legal u32, it will find a match. */ + for (i = 0; i < P2A_REGION_COUNT; i++) { + const struct region *curr = &ctrl->config->regions[i]; + + /* If the top of this region is lower than your base, skip it. + */ + if (curr->max < base) + continue; + + /* If the bottom of this region is higher than your end, bail. + */ + if (curr->min > end) + break; + + /* Lock this and update it, therefore it someone else is + * closing their file out, this'll preserve the increment. + */ + mutex_lock(&ctrl->tracking); + ctrl->readerwriters[i] += 1; + mutex_unlock(&ctrl->tracking); + + /* Track with the user, so when they close their file, we can + * decrement properly. + */ + priv->readwrite[i] += 1; + + /* Enable the region as read-write. */ + regmap_update_bits(ctrl->regmap, SCU2C, curr->bit, 0); + matched = true; + } + + return matched; +} + +static long aspeed_p2a_ioctl(struct file *file, unsigned int cmd, + unsigned long data) +{ + struct aspeed_p2a_user *priv = file->private_data; + struct aspeed_p2a_ctrl *ctrl = priv->parent; + void __user *arg = (void __user *)data; + struct aspeed_p2a_ctrl_mapping map; + + if (copy_from_user(&map, arg, sizeof(map))) + return -EFAULT; + + switch (cmd) { + case ASPEED_P2A_CTRL_IOCTL_SET_WINDOW: + /* If they want a region to be read-only, since the entire + * region is read-only once enabled, we just need to track this + * user wants to read from the bridge, and if it's not enabled. + * Enable it. + */ + if (map.flags == ASPEED_P2A_CTRL_READ_ONLY) { + mutex_lock(&ctrl->tracking); + ctrl->readers += 1; + mutex_unlock(&ctrl->tracking); + + /* Track with the user, so when they close their file, + * we can decrement properly. + */ + priv->read += 1; + } else if (map.flags == ASPEED_P2A_CTRL_READWRITE) { + /* If we don't acquire any region return error. */ + if (!aspeed_p2a_region_acquire(priv, ctrl, &map)) { + return -EINVAL; + } + } else { + /* Invalid map flags. */ + return -EINVAL; + } + + aspeed_p2a_enable_bridge(ctrl); + return 0; + case ASPEED_P2A_CTRL_IOCTL_GET_MEMORY_CONFIG: + /* This is a request for the memory-region and corresponding + * length that is used by the driver for mmap. + */ + + map.flags = 0; + map.addr = ctrl->mem_base; + map.length = ctrl->mem_size; + + return copy_to_user(arg, &map, sizeof(map)) ? -EFAULT : 0; + } + + return -EINVAL; +} + + +/* + * When a user opens this file, we create a structure to track their mappings. + * + * A user can map a region as read-only (bridge enabled), or read-write (bit + * flipped, and bridge enabled). Either way, this tracking is used, s.t. when + * they release the device references are handled. + * + * The bridge is not enabled until a user calls an ioctl to map a region, + * simply opening the device does not enable it. + */ +static int aspeed_p2a_open(struct inode *inode, struct file *file) +{ + struct aspeed_p2a_user *priv; + + priv = kmalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->file = file; + priv->read = 0; + memset(priv->readwrite, 0, sizeof(priv->readwrite)); + + /* The file's private_data is initialized to the p2a_ctrl. */ + priv->parent = file->private_data; + + /* Set the file's private_data to the user's data. */ + file->private_data = priv; + + return 0; +} + +/* + * This will close the users mappings. It will go through what they had opened + * for readwrite, and decrement those counts. If at the end, this is the last + * user, it'll close the bridge. + */ +static int aspeed_p2a_release(struct inode *inode, struct file *file) +{ + int i; + u32 value; + u32 bits = 0; + bool open_regions = false; + struct aspeed_p2a_user *priv = file->private_data; + + /* Lock others from changing these values until everything is updated + * in one pass. + */ + mutex_lock(&priv->parent->tracking); + + priv->parent->readers -= priv->read; + + for (i = 0; i < P2A_REGION_COUNT; i++) { + priv->parent->readerwriters[i] -= priv->readwrite[i]; + + if (priv->parent->readerwriters[i] > 0) + open_regions = true; + else + bits |= priv->parent->config->regions[i].bit; + } + + /* Setting a bit to 1 disables the region, so let's just OR with the + * above to disable any. + */ + + /* Note, if another user is trying to ioctl, they can't grab tracking, + * and therefore can't grab either register mutex. + * If another user is trying to close, they can't grab tracking either. + */ + regmap_update_bits(priv->parent->regmap, SCU2C, bits, bits); + + /* If parent->readers is zero and open windows is 0, disable the + * bridge. + */ + if (!open_regions && priv->parent->readers == 0) + aspeed_p2a_disable_bridge(priv->parent); + + mutex_unlock(&priv->parent->tracking); + + kfree(priv); + + return 0; +} + +static const struct file_operations aspeed_p2a_ctrl_fops = { + .owner = THIS_MODULE, + .mmap = aspeed_p2a_mmap, + .unlocked_ioctl = aspeed_p2a_ioctl, + .open = aspeed_p2a_open, + .release = aspeed_p2a_release, +}; + +/* The regions are controlled by SCU2C */ +static void aspeed_p2a_disable_all(struct aspeed_p2a_ctrl *p2a_ctrl) +{ + int i; + u32 value = 0; + + for (i = 0; i < P2A_REGION_COUNT; i++) + value |= p2a_ctrl->config->regions[i].bit; + + regmap_update_bits(p2a_ctrl->regmap, SCU2C, value, value); + + /* Disable the bridge. */ + aspeed_p2a_disable_bridge(p2a_ctrl); +} + +static int aspeed_p2a_ctrl_probe(struct platform_device *pdev) +{ + struct aspeed_p2a_ctrl *misc_ctrl; + struct device *dev; + struct resource *res, resm; + struct device_node *node; + int rc = 0; + + dev = &pdev->dev; + + misc_ctrl = devm_kzalloc(dev, sizeof(*misc_ctrl), GFP_KERNEL); + if (!misc_ctrl) + return -ENOMEM; + + mutex_init(&misc_ctrl->tracking); + + /* optional. */ + node = of_parse_phandle(dev->of_node, "memory-region", 0); + if (node) { + rc = of_address_to_resource(node, 0, &resm); + of_node_put(node); + if (rc) { + dev_err(dev, "Couldn't address to resource for reserved memory\n"); + return -ENODEV; + } + + misc_ctrl->mem_size = resource_size(&resm); + misc_ctrl->mem_base = resm.start; + } + + misc_ctrl->regmap = syscon_node_to_regmap(pdev->dev.parent->of_node); + if (IS_ERR(misc_ctrl->regmap)) { + dev_err(dev, "Couldn't get regmap\n"); + return -ENODEV; + } + + misc_ctrl->config = of_device_get_match_data(dev); + + dev_set_drvdata(&pdev->dev, misc_ctrl); + + aspeed_p2a_disable_all(misc_ctrl); + + misc_ctrl->miscdev.minor = MISC_DYNAMIC_MINOR; + misc_ctrl->miscdev.name = DEVICE_NAME; + misc_ctrl->miscdev.fops = &aspeed_p2a_ctrl_fops; + misc_ctrl->miscdev.parent = dev; + + rc = misc_register(&misc_ctrl->miscdev); + if (rc) + dev_err(dev, "Unable to register device\n"); + + return rc; +} + +static int aspeed_p2a_ctrl_remove(struct platform_device *pdev) +{ + struct aspeed_p2a_ctrl *p2a_ctrl = dev_get_drvdata(&pdev->dev); + + misc_deregister(&p2a_ctrl->miscdev); + + return 0; +} + +#define SCU2C_DRAM BIT(25) +#define SCU2C_SPI BIT(24) +#define SCU2C_SOC BIT(23) +#define SCU2C_FLASH BIT(22) + +static const struct aspeed_p2a_model_data ast2400_model_data = { + .regions = { + {0x00000000, 0x17FFFFFF, SCU2C_FLASH}, + {0x18000000, 0x1FFFFFFF, SCU2C_SOC}, + {0x20000000, 0x2FFFFFFF, SCU2C_FLASH}, + {0x30000000, 0x3FFFFFFF, SCU2C_SPI}, + {0x40000000, 0x5FFFFFFF, SCU2C_DRAM}, + {0x60000000, 0xFFFFFFFF, SCU2C_SOC}, + } +}; + +static const struct aspeed_p2a_model_data ast2500_model_data = { + .regions = { + {0x00000000, 0x0FFFFFFF, SCU2C_FLASH}, + {0x10000000, 0x1FFFFFFF, SCU2C_SOC}, + {0x20000000, 0x3FFFFFFF, SCU2C_FLASH}, + {0x40000000, 0x5FFFFFFF, SCU2C_SOC}, + {0x60000000, 0x7FFFFFFF, SCU2C_SPI}, + {0x80000000, 0xFFFFFFFF, SCU2C_DRAM}, + } +}; + +static const struct of_device_id aspeed_p2a_ctrl_match[] = { + { .compatible = "aspeed,ast2400-p2a-ctrl", + .data = &ast2400_model_data }, + { .compatible = "aspeed,ast2500-p2a-ctrl", + .data = &ast2500_model_data }, + { }, +}; + +static struct platform_driver aspeed_p2a_ctrl_driver = { + .driver = { + .name = DEVICE_NAME, + .of_match_table = aspeed_p2a_ctrl_match, + }, + .probe = aspeed_p2a_ctrl_probe, + .remove = aspeed_p2a_ctrl_remove, +}; + +module_platform_driver(aspeed_p2a_ctrl_driver); + +MODULE_DEVICE_TABLE(of, aspeed_p2a_ctrl_match); +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Patrick Venture "); +MODULE_DESCRIPTION("Control for aspeed 2400/2500 P2A VGA HOST to BMC mappings"); diff --git a/include/uapi/linux/aspeed-p2a-ctrl.h b/include/uapi/linux/aspeed-p2a-ctrl.h new file mode 100644 index 000000000000..033355552a6e --- /dev/null +++ b/include/uapi/linux/aspeed-p2a-ctrl.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Copyright 2019 Google Inc + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Provides a simple driver to control the ASPEED P2A interface which allows + * the host to read and write to various regions of the BMC's memory. + */ + +#ifndef _UAPI_LINUX_ASPEED_P2A_CTRL_H +#define _UAPI_LINUX_ASPEED_P2A_CTRL_H + +#include +#include + +#define ASPEED_P2A_CTRL_READ_ONLY 0 +#define ASPEED_P2A_CTRL_READWRITE 1 + +/* + * This driver provides a mechanism for enabling or disabling the read-write + * property of specific windows into the ASPEED BMC's memory. + * + * A user can map a region of the BMC's memory as read-only or read-write, with + * the caveat that once any region is mapped, all regions are unlocked for + * reading. + */ + +/* + * Unlock a region of BMC physical memory for access from the host. + * + * Also used to read back the optional memory-region configuration for the + * driver. + */ +struct aspeed_p2a_ctrl_mapping { + __u64 addr; + __u32 length; + __u32 flags; +}; + +#define __ASPEED_P2A_CTRL_IOCTL_MAGIC 0xb3 + +/* + * This IOCTL is meant to configure a region or regions of memory given a + * starting address and length to be readable by the host, or + * readable-writeable. + */ +#define ASPEED_P2A_CTRL_IOCTL_SET_WINDOW _IOW(__ASPEED_P2A_CTRL_IOCTL_MAGIC, \ + 0x00, struct aspeed_p2a_ctrl_mapping) + +/* + * This IOCTL is meant to read back to the user the base address and length of + * the memory-region specified to the driver for use with mmap. + */ +#define ASPEED_P2A_CTRL_IOCTL_GET_MEMORY_CONFIG \ + _IOWR(__ASPEED_P2A_CTRL_IOCTL_MAGIC, \ + 0x01, struct aspeed_p2a_ctrl_mapping) + +#endif /* _UAPI_LINUX_ASPEED_P2A_CTRL_H */ From d65bf04200da3891b1c2e6779323287b25c223f7 Mon Sep 17 00:00:00 2001 From: Tomas Winkler Date: Mon, 22 Apr 2019 09:51:06 +0300 Subject: [PATCH 123/255] mei: hdcp: use own Kconfig file The mei/hdcp module have its own Makefile so naturally it should have associated Kconfig in the same directory. Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- drivers/misc/mei/Kconfig | 10 +--------- drivers/misc/mei/hdcp/Kconfig | 13 +++++++++++++ 2 files changed, 14 insertions(+), 9 deletions(-) create mode 100644 drivers/misc/mei/hdcp/Kconfig diff --git a/drivers/misc/mei/Kconfig b/drivers/misc/mei/Kconfig index 132b07151f42..9d7b3719bfa0 100644 --- a/drivers/misc/mei/Kconfig +++ b/drivers/misc/mei/Kconfig @@ -46,12 +46,4 @@ config INTEL_MEI_TXE Supported SoCs: Intel Bay Trail -config INTEL_MEI_HDCP - tristate "Intel HDCP2.2 services of ME Interface" - select INTEL_MEI_ME - depends on DRM_I915 - help - MEI Support for HDCP2.2 Services on Intel platforms. - - Enables the ME FW services required for HDCP2.2 support through - I915 display driver of Intel. +source "drivers/misc/mei/hdcp/Kconfig" diff --git a/drivers/misc/mei/hdcp/Kconfig b/drivers/misc/mei/hdcp/Kconfig new file mode 100644 index 000000000000..95b2d6d37f10 --- /dev/null +++ b/drivers/misc/mei/hdcp/Kconfig @@ -0,0 +1,13 @@ + +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2019, Intel Corporation. All rights reserved. +# +config INTEL_MEI_HDCP + tristate "Intel HDCP2.2 services of ME Interface" + select INTEL_MEI_ME + depends on DRM_I915 + help + MEI Support for HDCP2.2 Services on Intel platforms. + + Enables the ME FW services required for HDCP2.2 support through + I915 display driver of Intel. From 43b8a7ed4739a86c1e8543489bf5524780f66284 Mon Sep 17 00:00:00 2001 From: Alexander Usyskin Date: Mon, 22 Apr 2019 09:51:07 +0300 Subject: [PATCH 124/255] mei: expose device state in sysfs Expose mei device state to user-space through sysfs. This gives indication to applications that driver is in transition, usefully mostly to detect link reset state. Signed-off-by: Alexander Usyskin Signed-off-by: Tomas Winkler Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-class-mei | 15 ++++++ drivers/misc/mei/client.c | 2 +- drivers/misc/mei/init.c | 20 +++---- drivers/misc/mei/main.c | 65 ++++++++++++++++++++--- drivers/misc/mei/mei_dev.h | 3 +- 5 files changed, 87 insertions(+), 18 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-class-mei b/Documentation/ABI/testing/sysfs-class-mei index 17d7444a2397..a92d844f806e 100644 --- a/Documentation/ABI/testing/sysfs-class-mei +++ b/Documentation/ABI/testing/sysfs-class-mei @@ -65,3 +65,18 @@ Description: Display the ME firmware version. :.... There can be up to three such blocks for different FW components. + +What: /sys/class/mei/meiN/dev_state +Date: Mar 2019 +KernelVersion: 5.1 +Contact: Tomas Winkler +Description: Display the ME device state. + + The device state can have following values: + INITIALIZING + INIT_CLIENTS + ENABLED + RESETTING + DISABLED + POWER_DOWN + POWER_UP diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 88b83c4bc5b7..1e3edbbacb1e 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -669,7 +669,7 @@ int mei_cl_unlink(struct mei_cl *cl) void mei_host_client_init(struct mei_device *dev) { - dev->dev_state = MEI_DEV_ENABLED; + mei_set_devstate(dev, MEI_DEV_ENABLED); dev->reset_count = 0; schedule_work(&dev->bus_rescan_work); diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c index cc359ae968ce..b9fef773e71b 100644 --- a/drivers/misc/mei/init.c +++ b/drivers/misc/mei/init.c @@ -123,12 +123,12 @@ int mei_reset(struct mei_device *dev) /* enter reset flow */ interrupts_enabled = state != MEI_DEV_POWER_DOWN; - dev->dev_state = MEI_DEV_RESETTING; + mei_set_devstate(dev, MEI_DEV_RESETTING); dev->reset_count++; if (dev->reset_count > MEI_MAX_CONSEC_RESET) { dev_err(dev->dev, "reset: reached maximal consecutive resets: disabling the device\n"); - dev->dev_state = MEI_DEV_DISABLED; + mei_set_devstate(dev, MEI_DEV_DISABLED); return -ENODEV; } @@ -150,7 +150,7 @@ int mei_reset(struct mei_device *dev) if (state == MEI_DEV_POWER_DOWN) { dev_dbg(dev->dev, "powering down: end of reset\n"); - dev->dev_state = MEI_DEV_DISABLED; + mei_set_devstate(dev, MEI_DEV_DISABLED); return 0; } @@ -162,11 +162,11 @@ int mei_reset(struct mei_device *dev) dev_dbg(dev->dev, "link is established start sending messages.\n"); - dev->dev_state = MEI_DEV_INIT_CLIENTS; + mei_set_devstate(dev, MEI_DEV_INIT_CLIENTS); ret = mei_hbm_start_req(dev); if (ret) { dev_err(dev->dev, "hbm_start failed ret = %d\n", ret); - dev->dev_state = MEI_DEV_RESETTING; + mei_set_devstate(dev, MEI_DEV_RESETTING); return ret; } @@ -196,7 +196,7 @@ int mei_start(struct mei_device *dev) dev->reset_count = 0; do { - dev->dev_state = MEI_DEV_INITIALIZING; + mei_set_devstate(dev, MEI_DEV_INITIALIZING); ret = mei_reset(dev); if (ret == -ENODEV || dev->dev_state == MEI_DEV_DISABLED) { @@ -231,7 +231,7 @@ int mei_start(struct mei_device *dev) return 0; err: dev_err(dev->dev, "link layer initialization failed.\n"); - dev->dev_state = MEI_DEV_DISABLED; + mei_set_devstate(dev, MEI_DEV_DISABLED); mutex_unlock(&dev->device_lock); return -ENODEV; } @@ -250,7 +250,7 @@ int mei_restart(struct mei_device *dev) mutex_lock(&dev->device_lock); - dev->dev_state = MEI_DEV_POWER_UP; + mei_set_devstate(dev, MEI_DEV_POWER_UP); dev->reset_count = 0; err = mei_reset(dev); @@ -301,7 +301,7 @@ void mei_stop(struct mei_device *dev) dev_dbg(dev->dev, "stopping the device.\n"); mutex_lock(&dev->device_lock); - dev->dev_state = MEI_DEV_POWER_DOWN; + mei_set_devstate(dev, MEI_DEV_POWER_DOWN); mutex_unlock(&dev->device_lock); mei_cl_bus_remove_devices(dev); @@ -314,7 +314,7 @@ void mei_stop(struct mei_device *dev) mei_reset(dev); /* move device to disabled state unconditionally */ - dev->dev_state = MEI_DEV_DISABLED; + mei_set_devstate(dev, MEI_DEV_DISABLED); mutex_unlock(&dev->device_lock); } diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c index b454df214dde..ad02097d7fee 100644 --- a/drivers/misc/mei/main.c +++ b/drivers/misc/mei/main.c @@ -28,6 +28,12 @@ #include "mei_dev.h" #include "client.h" +static struct class *mei_class; +static dev_t mei_devt; +#define MEI_MAX_DEVS MINORMASK +static DEFINE_MUTEX(mei_minor_lock); +static DEFINE_IDR(mei_idr); + /** * mei_open - the open function * @@ -829,12 +835,65 @@ static ssize_t fw_ver_show(struct device *device, } static DEVICE_ATTR_RO(fw_ver); +/** + * dev_state_show - display device state + * + * @device: device pointer + * @attr: attribute pointer + * @buf: char out buffer + * + * Return: number of the bytes printed into buf or error + */ +static ssize_t dev_state_show(struct device *device, + struct device_attribute *attr, char *buf) +{ + struct mei_device *dev = dev_get_drvdata(device); + enum mei_dev_state dev_state; + + mutex_lock(&dev->device_lock); + dev_state = dev->dev_state; + mutex_unlock(&dev->device_lock); + + return sprintf(buf, "%s", mei_dev_state_str(dev_state)); +} +static DEVICE_ATTR_RO(dev_state); + +static int match_devt(struct device *dev, const void *data) +{ + const dev_t *devt = data; + + return dev->devt == *devt; +} + +/** + * dev_set_devstate: set to new device state and notify sysfs file. + * + * @dev: mei_device + * @state: new device state + */ +void mei_set_devstate(struct mei_device *dev, enum mei_dev_state state) +{ + struct device *clsdev; + + if (dev->dev_state == state) + return; + + dev->dev_state = state; + + clsdev = class_find_device(mei_class, NULL, &dev->cdev.dev, match_devt); + if (clsdev) { + sysfs_notify(&clsdev->kobj, NULL, "dev_state"); + put_device(clsdev); + } +} + static struct attribute *mei_attrs[] = { &dev_attr_fw_status.attr, &dev_attr_hbm_ver.attr, &dev_attr_hbm_ver_drv.attr, &dev_attr_tx_queue_limit.attr, &dev_attr_fw_ver.attr, + &dev_attr_dev_state.attr, NULL }; ATTRIBUTE_GROUPS(mei); @@ -858,12 +917,6 @@ static const struct file_operations mei_fops = { .llseek = no_llseek }; -static struct class *mei_class; -static dev_t mei_devt; -#define MEI_MAX_DEVS MINORMASK -static DEFINE_MUTEX(mei_minor_lock); -static DEFINE_IDR(mei_idr); - /** * mei_minor_get - obtain next free device minor number * diff --git a/drivers/misc/mei/mei_dev.h b/drivers/misc/mei/mei_dev.h index 3146df37ffb0..fca832fcac57 100644 --- a/drivers/misc/mei/mei_dev.h +++ b/drivers/misc/mei/mei_dev.h @@ -525,7 +525,6 @@ struct mei_device { struct dentry *dbgfs_dir; #endif /* CONFIG_DEBUG_FS */ - const struct mei_hw_ops *ops; char hw[0] __aligned(sizeof(void *)); }; @@ -584,6 +583,8 @@ int mei_restart(struct mei_device *dev); void mei_stop(struct mei_device *dev); void mei_cancel_work(struct mei_device *dev); +void mei_set_devstate(struct mei_device *dev, enum mei_dev_state state); + int mei_dmam_ring_alloc(struct mei_device *dev); void mei_dmam_ring_free(struct mei_device *dev); bool mei_dma_ring_is_allocated(struct mei_device *dev); From 49695ac46861180baf2b2b92c62da8619b6bf28f Mon Sep 17 00:00:00 2001 From: Jean-Francois Dagenais Date: Thu, 28 Mar 2019 12:41:11 -0400 Subject: [PATCH 125/255] w1: ds2408: reset on output_write retry with readback When we have success in 'Channel Access Write' but reading back latch states fails, a write is retried without doing a proper slave reset. This leads to protocol errors as the slave treats the next 'Channel Access Write' as the continuation of previous command. This commit is fixing this by making sure if the retry loop re-runs, a reset is performed, whatever the failure (CONFIRM_BYTE or the read back). The loop was quite due for a cleanup and this change mandated it. By isolating the CONFIG_W1_SLAVE_DS2408_READBACK case into it's own function, we vastly reduce the visual and branching(runtime and compile-time) noise. Reported-by: Mariusz Bialonczyk Tested-by: Mariusz Bialonczyk Signed-off-by: Jean-Francois Dagenais Signed-off-by: Greg Kroah-Hartman --- drivers/w1/slaves/w1_ds2408.c | 76 ++++++++++++++++++----------------- 1 file changed, 39 insertions(+), 37 deletions(-) diff --git a/drivers/w1/slaves/w1_ds2408.c b/drivers/w1/slaves/w1_ds2408.c index b535d5ec35b6..92e8f0755b9a 100644 --- a/drivers/w1/slaves/w1_ds2408.c +++ b/drivers/w1/slaves/w1_ds2408.c @@ -138,14 +138,37 @@ static ssize_t status_control_read(struct file *filp, struct kobject *kobj, W1_F29_REG_CONTROL_AND_STATUS, buf); } +#ifdef fCONFIG_W1_SLAVE_DS2408_READBACK +static bool optional_read_back_valid(struct w1_slave *sl, u8 expected) +{ + u8 w1_buf[3]; + + if (w1_reset_resume_command(sl->master)) + return false; + + w1_buf[0] = W1_F29_FUNC_READ_PIO_REGS; + w1_buf[1] = W1_F29_REG_OUTPUT_LATCH_STATE; + w1_buf[2] = 0; + + w1_write_block(sl->master, w1_buf, 3); + + return (w1_read_8(sl->master) == expected); +} +#else +static bool optional_read_back_valid(struct w1_slave *sl, u8 expected) +{ + return true; +} +#endif + static ssize_t output_write(struct file *filp, struct kobject *kobj, struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) { struct w1_slave *sl = kobj_to_w1_slave(kobj); u8 w1_buf[3]; - u8 readBack; unsigned int retries = W1_F29_RETRIES; + ssize_t bytes_written = -EIO; if (count != 1 || off != 0) return -EFAULT; @@ -155,54 +178,33 @@ static ssize_t output_write(struct file *filp, struct kobject *kobj, dev_dbg(&sl->dev, "mutex locked"); if (w1_reset_select_slave(sl)) - goto error; + goto out; - while (retries--) { + do { w1_buf[0] = W1_F29_FUNC_CHANN_ACCESS_WRITE; w1_buf[1] = *buf; w1_buf[2] = ~(*buf); + w1_write_block(sl->master, w1_buf, 3); - readBack = w1_read_8(sl->master); - - if (readBack != W1_F29_SUCCESS_CONFIRM_BYTE) { - if (w1_reset_resume_command(sl->master)) - goto error; - /* try again, the slave is ready for a command */ - continue; + if (w1_read_8(sl->master) == W1_F29_SUCCESS_CONFIRM_BYTE && + optional_read_back_valid(sl, *buf)) { + bytes_written = 1; + goto out; } -#ifdef CONFIG_W1_SLAVE_DS2408_READBACK - /* here the master could read another byte which - would be the PIO reg (the actual pin logic state) - since in this driver we don't know which pins are - in and outs, there's no value to read the state and - compare. with (*buf) so end this command abruptly: */ if (w1_reset_resume_command(sl->master)) - goto error; + goto out; /* unrecoverable error */ + /* try again, the slave is ready for a command */ + } while (--retries); - /* go read back the output latches */ - /* (the direct effect of the write above) */ - w1_buf[0] = W1_F29_FUNC_READ_PIO_REGS; - w1_buf[1] = W1_F29_REG_OUTPUT_LATCH_STATE; - w1_buf[2] = 0; - w1_write_block(sl->master, w1_buf, 3); - /* read the result of the READ_PIO_REGS command */ - if (w1_read_8(sl->master) == *buf) -#endif - { - /* success! */ - mutex_unlock(&sl->master->bus_mutex); - dev_dbg(&sl->dev, - "mutex unlocked, retries:%d", retries); - return 1; - } - } -error: +out: mutex_unlock(&sl->master->bus_mutex); - dev_dbg(&sl->dev, "mutex unlocked in error, retries:%d", retries); - return -EIO; + dev_dbg(&sl->dev, "%s, mutex unlocked retries:%d\n", + (bytes_written > 0) ? "succeeded" : "error", retries); + + return bytes_written; } From b0a69f05b9633a593c14d7837ae6b299851d5539 Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 29 Mar 2019 15:20:44 +0000 Subject: [PATCH 126/255] parport: ieee1284: mark expected switch fall-through MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch fixes the following warning: drivers/parport/ieee1284.c: In function ‘parport_read’: drivers/parport/ieee1284.c:722:6: warning: this statement may fall through [-Wimplicit-fallthrough=] if (parport_negotiate (port, IEEE1284_MODE_NIBBLE)) { ^ drivers/parport/ieee1284.c:726:2: note: here case IEEE1284_MODE_NIBBLE: ^~~~ Warning level 3 was used: -Wimplicit-fallthrough=3 Notice that, in this particular case, the code comment is modified in accordance with what GCC is expecting to find. This patch is part of the ongoing efforts to enable -Wimplicit-fallthrough. Signed-off-by: Gustavo A. R. Silva Signed-off-by: Sudip Mukherjee Signed-off-by: Greg Kroah-Hartman --- drivers/parport/ieee1284.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/parport/ieee1284.c b/drivers/parport/ieee1284.c index f12b9da69255..90fb73575495 100644 --- a/drivers/parport/ieee1284.c +++ b/drivers/parport/ieee1284.c @@ -722,7 +722,7 @@ ssize_t parport_read (struct parport *port, void *buffer, size_t len) if (parport_negotiate (port, IEEE1284_MODE_NIBBLE)) { return -EIO; } - /* fall through to NIBBLE */ + /* fall through - to NIBBLE */ case IEEE1284_MODE_NIBBLE: DPRINTK (KERN_DEBUG "%s: Using nibble mode\n", port->name); fn = port->ops->nibble_read_data; From 38e7b6efe997c4eb9a5a809dc2b2fe6c759b7c4b Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Sat, 13 Apr 2019 11:32:47 +0100 Subject: [PATCH 127/255] nvmem: imx-ocotp: add support for imx8mq The i.MX8MQ uses the same OCOTP block as the i.MX7D, but with fourfold increase in fuse banks. Signed-off-by: Lucas Stach Reviewed-by: Abel Vesa Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/imx-ocotp.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c index 08a9b1ef8ae4..e0b22b6c045b 100644 --- a/drivers/nvmem/imx-ocotp.c +++ b/drivers/nvmem/imx-ocotp.c @@ -444,6 +444,12 @@ static const struct ocotp_params imx7ulp_params = { .bank_address_words = 0, }; +static const struct ocotp_params imx8mq_params = { + .nregs = 256, + .bank_address_words = 4, + .set_timing = imx_ocotp_set_imx7_timing, +}; + static const struct of_device_id imx_ocotp_dt_ids[] = { { .compatible = "fsl,imx6q-ocotp", .data = &imx6q_params }, { .compatible = "fsl,imx6sl-ocotp", .data = &imx6sl_params }, @@ -453,6 +459,7 @@ static const struct of_device_id imx_ocotp_dt_ids[] = { { .compatible = "fsl,imx7d-ocotp", .data = &imx7d_params }, { .compatible = "fsl,imx6sll-ocotp", .data = &imx6sll_params }, { .compatible = "fsl,imx7ulp-ocotp", .data = &imx7ulp_params }, + { .compatible = "fsl,imx8mq-ocotp", .data = &imx8mq_params }, { }, }; MODULE_DEVICE_TABLE(of, imx_ocotp_dt_ids); From dd4c1047b1d6e05f28a1318aa1c4df627f2e91d4 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Sat, 13 Apr 2019 11:32:48 +0100 Subject: [PATCH 128/255] nvmem: imx-ocotp: broaden Kconfig dependency The i.MX OCOTP controller is used in numerous Freescale/NXP SoCs from the MXC family, so the strict dependency on the i.MX6 SoC is too narrow. Broaden it to cover all the MXC familiy members. Signed-off-by: Lucas Stach Reviewed-by: Abel Vesa Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig index 530d570724c9..9e1d83643e9c 100644 --- a/drivers/nvmem/Kconfig +++ b/drivers/nvmem/Kconfig @@ -25,8 +25,8 @@ config NVMEM_IMX_IIM will be called nvmem-imx-iim. config NVMEM_IMX_OCOTP - tristate "i.MX6 On-Chip OTP Controller support" - depends on SOC_IMX6 || SOC_IMX7D || COMPILE_TEST + tristate "i.MX 6/7/8 On-Chip OTP Controller support" + depends on ARCH_MXC || COMPILE_TEST depends on HAS_IOMEM help This is a driver for the On-Chip OTP Controller (OCOTP) available on From 9c4adfb5dc1326f94d3e212a8b5dfb238839b9ae Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sat, 13 Apr 2019 11:32:49 +0100 Subject: [PATCH 129/255] nvmem: sunxi_sid: Read out SID for randomness without looping Since the reg_read callbacks already support arbitrary, but 4-byte aligned. offsets and lengths into the SID, there is no need for another for loop just to use it to read 1 byte at a time. Read out the whole SID block in one go. Signed-off-by: Chen-Yu Tsai Acked-by: Maxime Ripard Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/sunxi_sid.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/drivers/nvmem/sunxi_sid.c b/drivers/nvmem/sunxi_sid.c index 570a2e354f30..704c35edf796 100644 --- a/drivers/nvmem/sunxi_sid.c +++ b/drivers/nvmem/sunxi_sid.c @@ -154,7 +154,7 @@ static int sunxi_sid_probe(struct platform_device *pdev) struct resource *res; struct nvmem_device *nvmem; struct sunxi_sid *sid; - int i, size; + int size; char *randomness; const struct sunxi_sid_cfg *cfg; @@ -189,8 +189,7 @@ static int sunxi_sid_probe(struct platform_device *pdev) if (!randomness) return -ENOMEM; - for (i = 0; i < size; i++) - econfig.reg_read(sid, i, &randomness[i], 1); + econfig.reg_read(sid, 0, randomness, size); add_device_randomness(randomness, size); kfree(randomness); From de2a3eaea552f2d562fae46bd495eb83298a1b3c Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sat, 13 Apr 2019 11:32:50 +0100 Subject: [PATCH 130/255] nvmem: sunxi_sid: Optimize register read-out method SID cells are 32-bit aligned, and a multiple of 32 bits in length. The only outlier is the thermal sensor calibration data, which is 16 bits per sensor. However a whole 64 bits is allocated for this purpose, so we could consider it conforming to the rule above. Also, the register read-out method assumes native endian, unlike the direct MMIO method, which assumes big endian. Thus no endian conversion is involved. Under these assumptions, the register read-out method can be slightly optimized. Instead of reading one word then discarding 3 bytes, read the whole word directly into the buffer. However, for reads under 4 bytes or trailing bytes, we still use a scratch buffer to extract the requested bytes. We could go one step further if .word_size was 4, but changing that would affect the sysfs interface's behavior. Signed-off-by: Chen-Yu Tsai Acked-by: Maxime Ripard Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/sunxi_sid.c | 38 ++++++++++++++++++-------------------- 1 file changed, 18 insertions(+), 20 deletions(-) diff --git a/drivers/nvmem/sunxi_sid.c b/drivers/nvmem/sunxi_sid.c index 704c35edf796..15fbfab62595 100644 --- a/drivers/nvmem/sunxi_sid.c +++ b/drivers/nvmem/sunxi_sid.c @@ -115,36 +115,34 @@ static int sun8i_sid_register_readout(const struct sunxi_sid *sid, * to be not reliable at all. * Read by the registers instead. */ -static int sun8i_sid_read_byte_by_reg(const struct sunxi_sid *sid, - const unsigned int offset, - u8 *out) -{ - u32 word; - int ret; - - ret = sun8i_sid_register_readout(sid, offset & ~0x03, &word); - - if (ret) - return ret; - - *out = (word >> ((offset & 0x3) * 8)) & 0xff; - - return 0; -} - static int sun8i_sid_read_by_reg(void *context, unsigned int offset, void *val, size_t bytes) { struct sunxi_sid *sid = context; - u8 *buf = val; + u32 word; int ret; - while (bytes--) { - ret = sun8i_sid_read_byte_by_reg(sid, offset++, buf++); + /* .stride = 4 so offset is guaranteed to be aligned */ + while (bytes >= 4) { + ret = sun8i_sid_register_readout(sid, offset, val); if (ret) return ret; + + val += 4; + offset += 4; + bytes -= 4; } + if (!bytes) + return 0; + + /* Handle any trailing bytes */ + ret = sun8i_sid_register_readout(sid, offset, &word); + if (ret) + return ret; + + memcpy(val, &word, bytes); + return 0; } From 7fa5ad23dbb02fc9832ef303adbca06f425250d5 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sat, 13 Apr 2019 11:32:51 +0100 Subject: [PATCH 131/255] nvmem: sunxi_sid: Dynamically allocate nvmem_config structure The sunxi_sid driver currently uses a statically allocated nvmem_config structure that is updated at probe time. This is sub-optimal as it limits the driver to one instance, and also takes up space even if the device is not present. Modify the driver to allocate the nvmem_config structure at probe time, plugging in the desired parameters along the way. Signed-off-by: Chen-Yu Tsai Acked-by: Maxime Ripard Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/sunxi_sid.c | 32 +++++++++++++++++--------------- 1 file changed, 17 insertions(+), 15 deletions(-) diff --git a/drivers/nvmem/sunxi_sid.c b/drivers/nvmem/sunxi_sid.c index 15fbfab62595..75c1f48cb3d0 100644 --- a/drivers/nvmem/sunxi_sid.c +++ b/drivers/nvmem/sunxi_sid.c @@ -35,13 +35,6 @@ #define SUN8I_SID_OP_LOCK (0xAC << 8) #define SUN8I_SID_READ BIT(1) -static struct nvmem_config econfig = { - .name = "sunxi-sid", - .read_only = true, - .stride = 4, - .word_size = 1, -}; - struct sunxi_sid_cfg { u32 value_offset; u32 size; @@ -150,6 +143,7 @@ static int sunxi_sid_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct resource *res; + struct nvmem_config *nvmem_cfg; struct nvmem_device *nvmem; struct sunxi_sid *sid; int size; @@ -172,14 +166,23 @@ static int sunxi_sid_probe(struct platform_device *pdev) size = cfg->size; - econfig.size = size; - econfig.dev = dev; + nvmem_cfg = devm_kzalloc(dev, sizeof(*nvmem_cfg), GFP_KERNEL); + if (!nvmem_cfg) + return -ENOMEM; + + nvmem_cfg->dev = dev; + nvmem_cfg->name = "sunxi-sid"; + nvmem_cfg->read_only = true; + nvmem_cfg->size = cfg->size; + nvmem_cfg->word_size = 1; + nvmem_cfg->stride = 4; + nvmem_cfg->priv = sid; if (cfg->need_register_readout) - econfig.reg_read = sun8i_sid_read_by_reg; + nvmem_cfg->reg_read = sun8i_sid_read_by_reg; else - econfig.reg_read = sunxi_sid_read; - econfig.priv = sid; - nvmem = devm_nvmem_register(dev, &econfig); + nvmem_cfg->reg_read = sunxi_sid_read; + + nvmem = devm_nvmem_register(dev, nvmem_cfg); if (IS_ERR(nvmem)) return PTR_ERR(nvmem); @@ -187,8 +190,7 @@ static int sunxi_sid_probe(struct platform_device *pdev) if (!randomness) return -ENOMEM; - econfig.reg_read(sid, 0, randomness, size); - + nvmem_cfg->reg_read(sid, 0, randomness, size); add_device_randomness(randomness, size); kfree(randomness); From 273a474ee843fe6f77c3fef365306018bac9c96d Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sat, 13 Apr 2019 11:32:52 +0100 Subject: [PATCH 132/255] nvmem: sunxi_sid: Read out data in native format Originally the SID e-fuses were thought to be in big-endian format. Later sources show that they are in fact native or little-endian. The most compelling evidence is the thermal sensor calibration data, which is a set of one to three 16-bit values. In native-endian they are in 16-bit cells with increasing offsets, whereas with big-endian they are in the wrong order, and a gap with no data will show if there are one or three cells. Switch to a native endian representation for the nvmem device. For the H3, the register read-out method was already returning data in native endian. This only affects the other SoCs. Signed-off-by: Chen-Yu Tsai Acked-by: Maxime Ripard Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/sunxi_sid.c | 23 +---------------------- 1 file changed, 1 insertion(+), 22 deletions(-) diff --git a/drivers/nvmem/sunxi_sid.c b/drivers/nvmem/sunxi_sid.c index 75c1f48cb3d0..14c114620ed6 100644 --- a/drivers/nvmem/sunxi_sid.c +++ b/drivers/nvmem/sunxi_sid.c @@ -46,33 +46,12 @@ struct sunxi_sid { u32 value_offset; }; -/* We read the entire key, due to a 32 bit read alignment requirement. Since we - * want to return the requested byte, this results in somewhat slower code and - * uses 4 times more reads as needed but keeps code simpler. Since the SID is - * only very rarely probed, this is not really an issue. - */ -static u8 sunxi_sid_read_byte(const struct sunxi_sid *sid, - const unsigned int offset) -{ - u32 sid_key; - - sid_key = ioread32be(sid->base + round_down(offset, 4)); - sid_key >>= (offset % 4) * 8; - - return sid_key; /* Only return the last byte */ -} - static int sunxi_sid_read(void *context, unsigned int offset, void *val, size_t bytes) { struct sunxi_sid *sid = context; - u8 *buf = val; - /* Offset the read operation to the real position of SID */ - offset += sid->value_offset; - - while (bytes--) - *buf++ = sunxi_sid_read_byte(sid, offset++); + memcpy_fromio(val, sid->base + sid->value_offset + offset, bytes); return 0; } From da75b8909756160b8e785104ba421a20b756c975 Mon Sep 17 00:00:00 2001 From: Chen-Yu Tsai Date: Sat, 13 Apr 2019 11:32:53 +0100 Subject: [PATCH 133/255] nvmem: sunxi_sid: Support SID on A83T and H5 The device tree binding already lists compatible strings for these two SoCs. They don't have the defect as seen on the H3, and the size and register layout is the same as the A64. Furthermore, the driver does not include nvmem cell definitions. Add support for these two compatible strings, re-using the config for the A64. Signed-off-by: Chen-Yu Tsai Acked-by: Maxime Ripard Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/sunxi_sid.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/nvmem/sunxi_sid.c b/drivers/nvmem/sunxi_sid.c index 14c114620ed6..e7936380ce89 100644 --- a/drivers/nvmem/sunxi_sid.c +++ b/drivers/nvmem/sunxi_sid.c @@ -200,8 +200,10 @@ static const struct sunxi_sid_cfg sun50i_a64_cfg = { static const struct of_device_id sunxi_sid_of_match[] = { { .compatible = "allwinner,sun4i-a10-sid", .data = &sun4i_a10_cfg }, { .compatible = "allwinner,sun7i-a20-sid", .data = &sun7i_a20_cfg }, + { .compatible = "allwinner,sun8i-a83t-sid", .data = &sun50i_a64_cfg }, { .compatible = "allwinner,sun8i-h3-sid", .data = &sun8i_h3_cfg }, { .compatible = "allwinner,sun50i-a64-sid", .data = &sun50i_a64_cfg }, + { .compatible = "allwinner,sun50i-h5-sid", .data = &sun50i_a64_cfg }, {/* sentinel */}, }; MODULE_DEVICE_TABLE(of, sunxi_sid_of_match); From 4f4cb173d811ba37aab3048b70583b6c73803d42 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Sat, 13 Apr 2019 11:32:54 +0100 Subject: [PATCH 134/255] dt-bindings: nvmem: Add STM32 factory-programmed romem Add documentation for STMicroelectronics STM32 Factory-programmed read only memory area. Signed-off-by: Fabrice Gasnier Reviewed-by: Rob Herring Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- .../bindings/nvmem/st,stm32-romem.txt | 31 +++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 Documentation/devicetree/bindings/nvmem/st,stm32-romem.txt diff --git a/Documentation/devicetree/bindings/nvmem/st,stm32-romem.txt b/Documentation/devicetree/bindings/nvmem/st,stm32-romem.txt new file mode 100644 index 000000000000..142a51d5a9be --- /dev/null +++ b/Documentation/devicetree/bindings/nvmem/st,stm32-romem.txt @@ -0,0 +1,31 @@ +STMicroelectronics STM32 Factory-programmed data device tree bindings + +This represents STM32 Factory-programmed read only non-volatile area: locked +flash, OTP, read-only HW regs... This contains various information such as: +analog calibration data for temperature sensor (e.g. TS_CAL1, TS_CAL2), +internal vref (VREFIN_CAL), unique device ID... + +Required properties: +- compatible: Should be one of: + "st,stm32f4-otp" + "st,stm32mp15-bsec" +- reg: Offset and length of factory-programmed area. +- #address-cells: Should be '<1>'. +- #size-cells: Should be '<1>'. + +Optional Data cells: +- Must be child nodes as described in nvmem.txt. + +Example on stm32f4: + romem: nvmem@1fff7800 { + compatible = "st,stm32f4-otp"; + reg = <0x1fff7800 0x400>; + #address-cells = <1>; + #size-cells = <1>; + + /* Data cells: ts_cal1 at 0x1fff7a2c */ + ts_cal1: calib@22c { + reg = <0x22c 0x2>; + }; + ... + }; From ded1b7fc2cf5a4ae3b902b0e46f592ab724b7828 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Sat, 13 Apr 2019 11:32:55 +0100 Subject: [PATCH 135/255] nvmem: Add driver for STM32 factory-programmed read only mem Add a read only nvmem driver for STM32 factory-programmed memory area (on-chip non-volatile storage). Signed-off-by: Fabrice Gasnier Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/Kconfig | 10 +++++ drivers/nvmem/Makefile | 2 + drivers/nvmem/stm32-romem.c | 78 +++++++++++++++++++++++++++++++++++++ 3 files changed, 90 insertions(+) create mode 100644 drivers/nvmem/stm32-romem.c diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig index 9e1d83643e9c..a90e9a1ebe55 100644 --- a/drivers/nvmem/Kconfig +++ b/drivers/nvmem/Kconfig @@ -113,6 +113,16 @@ config NVMEM_BCM_OCOTP This driver can also be built as a module. If so, the module will be called nvmem-bcm-ocotp. +config NVMEM_STM32_ROMEM + tristate "STMicroelectronics STM32 factory-programmed memory support" + depends on ARCH_STM32 || COMPILE_TEST + help + Say y here to enable read-only access for STMicroelectronics STM32 + factory-programmed memory area. + + This driver can also be built as a module. If so, the module + will be called nvmem-stm32-romem. + config NVMEM_SUNXI_SID tristate "Allwinner SoCs SID support" depends on ARCH_SUNXI diff --git a/drivers/nvmem/Makefile b/drivers/nvmem/Makefile index 2ece8ffffdda..4c7ba12a7005 100644 --- a/drivers/nvmem/Makefile +++ b/drivers/nvmem/Makefile @@ -26,6 +26,8 @@ nvmem_qfprom-y := qfprom.o obj-$(CONFIG_ROCKCHIP_EFUSE) += nvmem_rockchip_efuse.o nvmem_rockchip_efuse-y := rockchip-efuse.o obj-$(CONFIG_NVMEM_SUNXI_SID) += nvmem_sunxi_sid.o +nvmem_stm32_romem-y := stm32-romem.o +obj-$(CONFIG_NVMEM_STM32_ROMEM) += nvmem_stm32_romem.o nvmem_sunxi_sid-y := sunxi_sid.o obj-$(CONFIG_UNIPHIER_EFUSE) += nvmem-uniphier-efuse.o nvmem-uniphier-efuse-y := uniphier-efuse.o diff --git a/drivers/nvmem/stm32-romem.c b/drivers/nvmem/stm32-romem.c new file mode 100644 index 000000000000..07e98b53b391 --- /dev/null +++ b/drivers/nvmem/stm32-romem.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * STM32 Factory-programmed memory read access driver + * + * Copyright (C) 2017, STMicroelectronics - All Rights Reserved + * Author: Fabrice Gasnier for STMicroelectronics. + */ + +#include +#include +#include +#include + +struct stm32_romem_priv { + void __iomem *base; + struct nvmem_config cfg; +}; + +static int stm32_romem_read(void *context, unsigned int offset, void *buf, + size_t bytes) +{ + struct stm32_romem_priv *priv = context; + u8 *buf8 = buf; + int i; + + for (i = offset; i < offset + bytes; i++) + *buf8++ = readb_relaxed(priv->base + i); + + return 0; +} + +static int stm32_romem_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct stm32_romem_priv *priv; + struct resource *res; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + priv->base = devm_ioremap_resource(dev, res); + if (IS_ERR(priv->base)) + return PTR_ERR(priv->base); + + priv->cfg.name = "stm32-romem"; + priv->cfg.read_only = true; + priv->cfg.word_size = 1; + priv->cfg.stride = 1; + priv->cfg.size = resource_size(res); + priv->cfg.reg_read = stm32_romem_read; + priv->cfg.dev = dev; + priv->cfg.priv = priv; + priv->cfg.owner = THIS_MODULE; + + return PTR_ERR_OR_ZERO(devm_nvmem_register(dev, &priv->cfg)); +} + +static const struct of_device_id stm32_romem_of_match[] = { + { .compatible = "st,stm32f4-otp", }, + {}, +}; +MODULE_DEVICE_TABLE(of, stm32_romem_of_match); + +static struct platform_driver stm32_romem_driver = { + .probe = stm32_romem_probe, + .driver = { + .name = "stm32-romem", + .of_match_table = of_match_ptr(stm32_romem_of_match), + }, +}; +module_platform_driver(stm32_romem_driver); + +MODULE_AUTHOR("Fabrice Gasnier "); +MODULE_DESCRIPTION("STMicroelectronics STM32 RO-MEM"); +MODULE_ALIAS("platform:nvmem-stm32-romem"); +MODULE_LICENSE("GPL v2"); From 7c1cd8fda8fbcc3701f372003ef0a3b6d31e11f4 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Sat, 13 Apr 2019 11:32:56 +0100 Subject: [PATCH 136/255] nvmem: stm32: add support for STM32MP15 BSEC to control OTP data On STM32MP15, OTP area may be read/written by using BSEC (boot, security and OTP control). BSEC registers set is composed of various regions, among which control registers and OTP shadow registers. Secure monitor calls are involved in this process to allow (or deny) access to the full range of OTP data. This adds support for reading and writing OTP data using SMC services. Data content can be aligned on 16-bits or 8-bits. Then take care of it, since BSEC data is 32-bits wide. Signed-off-by: Fabrice Gasnier Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/stm32-romem.c | 134 ++++++++++++++++++++++++++++++++++-- 1 file changed, 129 insertions(+), 5 deletions(-) diff --git a/drivers/nvmem/stm32-romem.c b/drivers/nvmem/stm32-romem.c index 07e98b53b391..354be526897f 100644 --- a/drivers/nvmem/stm32-romem.c +++ b/drivers/nvmem/stm32-romem.c @@ -6,11 +6,29 @@ * Author: Fabrice Gasnier for STMicroelectronics. */ +#include #include #include #include #include +/* BSEC secure service access from non-secure */ +#define STM32_SMC_BSEC 0x82001003 +#define STM32_SMC_READ_SHADOW 0x01 +#define STM32_SMC_PROG_OTP 0x02 +#define STM32_SMC_WRITE_SHADOW 0x03 +#define STM32_SMC_READ_OTP 0x04 + +/* shadow registers offest */ +#define STM32MP15_BSEC_DATA0 0x200 + +/* 32 (x 32-bits) lower shadow registers */ +#define STM32MP15_BSEC_NUM_LOWER 32 + +struct stm32_romem_cfg { + int size; +}; + struct stm32_romem_priv { void __iomem *base; struct nvmem_config cfg; @@ -29,8 +47,98 @@ static int stm32_romem_read(void *context, unsigned int offset, void *buf, return 0; } +static int stm32_bsec_smc(u8 op, u32 otp, u32 data, u32 *result) +{ +#if IS_ENABLED(CONFIG_HAVE_ARM_SMCCC) + struct arm_smccc_res res; + + arm_smccc_smc(STM32_SMC_BSEC, op, otp, data, 0, 0, 0, 0, &res); + if (res.a0) + return -EIO; + + if (result) + *result = (u32)res.a1; + + return 0; +#else + return -ENXIO; +#endif +} + +static int stm32_bsec_read(void *context, unsigned int offset, void *buf, + size_t bytes) +{ + struct stm32_romem_priv *priv = context; + struct device *dev = priv->cfg.dev; + u32 roffset, rbytes, val; + u8 *buf8 = buf, *val8 = (u8 *)&val; + int i, j = 0, ret, skip_bytes, size; + + /* Round unaligned access to 32-bits */ + roffset = rounddown(offset, 4); + skip_bytes = offset & 0x3; + rbytes = roundup(bytes + skip_bytes, 4); + + if (roffset + rbytes > priv->cfg.size) + return -EINVAL; + + for (i = roffset; (i < roffset + rbytes); i += 4) { + u32 otp = i >> 2; + + if (otp < STM32MP15_BSEC_NUM_LOWER) { + /* read lower data from shadow registers */ + val = readl_relaxed( + priv->base + STM32MP15_BSEC_DATA0 + i); + } else { + ret = stm32_bsec_smc(STM32_SMC_READ_SHADOW, otp, 0, + &val); + if (ret) { + dev_err(dev, "Can't read data%d (%d)\n", otp, + ret); + return ret; + } + } + /* skip first bytes in case of unaligned read */ + if (skip_bytes) + size = min(bytes, (size_t)(4 - skip_bytes)); + else + size = min(bytes, (size_t)4); + memcpy(&buf8[j], &val8[skip_bytes], size); + bytes -= size; + j += size; + skip_bytes = 0; + } + + return 0; +} + +static int stm32_bsec_write(void *context, unsigned int offset, void *buf, + size_t bytes) +{ + struct stm32_romem_priv *priv = context; + struct device *dev = priv->cfg.dev; + u32 *buf32 = buf; + int ret, i; + + /* Allow only writing complete 32-bits aligned words */ + if ((bytes % 4) || (offset % 4)) + return -EINVAL; + + for (i = offset; i < offset + bytes; i += 4) { + ret = stm32_bsec_smc(STM32_SMC_PROG_OTP, i >> 2, *buf32++, + NULL); + if (ret) { + dev_err(dev, "Can't write data%d (%d)\n", i >> 2, ret); + return ret; + } + } + + return 0; +} + static int stm32_romem_probe(struct platform_device *pdev) { + const struct stm32_romem_cfg *cfg; struct device *dev = &pdev->dev; struct stm32_romem_priv *priv; struct resource *res; @@ -45,21 +153,37 @@ static int stm32_romem_probe(struct platform_device *pdev) return PTR_ERR(priv->base); priv->cfg.name = "stm32-romem"; - priv->cfg.read_only = true; priv->cfg.word_size = 1; priv->cfg.stride = 1; - priv->cfg.size = resource_size(res); - priv->cfg.reg_read = stm32_romem_read; priv->cfg.dev = dev; priv->cfg.priv = priv; priv->cfg.owner = THIS_MODULE; + cfg = (const struct stm32_romem_cfg *) + of_match_device(dev->driver->of_match_table, dev)->data; + if (!cfg) { + priv->cfg.read_only = true; + priv->cfg.size = resource_size(res); + priv->cfg.reg_read = stm32_romem_read; + } else { + priv->cfg.size = cfg->size; + priv->cfg.reg_read = stm32_bsec_read; + priv->cfg.reg_write = stm32_bsec_write; + } + return PTR_ERR_OR_ZERO(devm_nvmem_register(dev, &priv->cfg)); } +static const struct stm32_romem_cfg stm32mp15_bsec_cfg = { + .size = 384, /* 96 x 32-bits data words */ +}; + static const struct of_device_id stm32_romem_of_match[] = { - { .compatible = "st,stm32f4-otp", }, - {}, + { .compatible = "st,stm32f4-otp", }, { + .compatible = "st,stm32mp15-bsec", + .data = (void *)&stm32mp15_bsec_cfg, + }, { + }, }; MODULE_DEVICE_TABLE(of, stm32_romem_of_match); From 0a9b2d1ce42210d087d32b1979d3ada343537708 Mon Sep 17 00:00:00 2001 From: Fabrice Gasnier Date: Sat, 13 Apr 2019 11:32:57 +0100 Subject: [PATCH 137/255] nvmem: core: add nvmem_cell_read_u16 Add nvmem_cell_read_u16() helper to ease read of an u16 value on consumer side. This is inspired by nvmem_cell_read_u32() function. This helper is useful on stm32 that has 16 bits data cells stored in non volatile memory. Signed-off-by: Fabrice Gasnier Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 37 ++++++++++++++++++++++++++++++++++ include/linux/nvmem-consumer.h | 7 +++++++ 2 files changed, 44 insertions(+) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index f24008b66826..1d00f5671368 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -1334,6 +1334,43 @@ int nvmem_cell_write(struct nvmem_cell *cell, void *buf, size_t len) } EXPORT_SYMBOL_GPL(nvmem_cell_write); +/** + * nvmem_cell_read_u16() - Read a cell value as an u16 + * + * @dev: Device that requests the nvmem cell. + * @cell_id: Name of nvmem cell to read. + * @val: pointer to output value. + * + * Return: 0 on success or negative errno. + */ +int nvmem_cell_read_u16(struct device *dev, const char *cell_id, u16 *val) +{ + struct nvmem_cell *cell; + void *buf; + size_t len; + + cell = nvmem_cell_get(dev, cell_id); + if (IS_ERR(cell)) + return PTR_ERR(cell); + + buf = nvmem_cell_read(cell, &len); + if (IS_ERR(buf)) { + nvmem_cell_put(cell); + return PTR_ERR(buf); + } + if (len != sizeof(*val)) { + kfree(buf); + nvmem_cell_put(cell); + return -EINVAL; + } + memcpy(val, buf, sizeof(*val)); + kfree(buf); + nvmem_cell_put(cell); + + return 0; +} +EXPORT_SYMBOL_GPL(nvmem_cell_read_u16); + /** * nvmem_cell_read_u32() - Read a cell value as an u32 * diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h index 312bfa5efd80..8f8be5b00060 100644 --- a/include/linux/nvmem-consumer.h +++ b/include/linux/nvmem-consumer.h @@ -61,6 +61,7 @@ void nvmem_cell_put(struct nvmem_cell *cell); void devm_nvmem_cell_put(struct device *dev, struct nvmem_cell *cell); void *nvmem_cell_read(struct nvmem_cell *cell, size_t *len); int nvmem_cell_write(struct nvmem_cell *cell, void *buf, size_t len); +int nvmem_cell_read_u16(struct device *dev, const char *cell_id, u16 *val); int nvmem_cell_read_u32(struct device *dev, const char *cell_id, u32 *val); /* direct nvmem device read/write interface */ @@ -122,6 +123,12 @@ static inline int nvmem_cell_write(struct nvmem_cell *cell, return -EOPNOTSUPP; } +static inline int nvmem_cell_read_u16(struct device *dev, + const char *cell_id, u16 *val) +{ + return -EOPNOTSUPP; +} + static inline int nvmem_cell_read_u32(struct device *dev, const char *cell_id, u32 *val) { From 2fe518fecb3a4727393be286db9804cd82ee2d91 Mon Sep 17 00:00:00 2001 From: Jorge Ramirez-Ortiz Date: Sat, 13 Apr 2019 11:32:58 +0100 Subject: [PATCH 138/255] nvmem: core: fix read buffer in place When the bit_offset in the cell is zero, the pointer to the msb will not be properly initialized (ie, will still be pointing to the first byte in the buffer). This being the case, if there are bits to clear in the msb, those will be left untouched while the mask will incorrectly clear bit positions on the first byte. This commit also makes sure that any byte unused in the cell is cleared. Signed-off-by: Jorge Ramirez-Ortiz Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/core.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 1d00f5671368..5abebf2128b8 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -1166,7 +1166,7 @@ EXPORT_SYMBOL_GPL(nvmem_cell_put); static void nvmem_shift_read_buffer_in_place(struct nvmem_cell *cell, void *buf) { u8 *p, *b; - int i, bit_offset = cell->bit_offset; + int i, extra, bit_offset = cell->bit_offset; p = b = buf; if (bit_offset) { @@ -1181,11 +1181,16 @@ static void nvmem_shift_read_buffer_in_place(struct nvmem_cell *cell, void *buf) p = b; *b++ >>= bit_offset; } - - /* result fits in less bytes */ - if (cell->bytes != DIV_ROUND_UP(cell->nbits, BITS_PER_BYTE)) - *p-- = 0; + } else { + /* point to the msb */ + p += cell->bytes - 1; } + + /* result fits in less bytes */ + extra = cell->bytes - DIV_ROUND_UP(cell->nbits, BITS_PER_BYTE); + while (--extra >= 0) + *p-- = 0; + /* clear msb bits if any leftover in the last byte */ *p &= GENMASK((cell->nbits%BITS_PER_BYTE) - 1, 0); } From 3b26cd885853764aed83828429f5c50787cfc55a Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Sat, 13 Apr 2019 11:32:59 +0100 Subject: [PATCH 139/255] nvmem: imx-ocotp: use devm_platform_ioremap_resource() to simplify code Use the new helper devm_platform_ioremap_resource() which wraps the platform_get_resource() and devm_ioremap_resource() together, to simplify the code. Signed-off-by: Anson Huang Reviewed-by: Mukesh Ojha Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/imx-ocotp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/nvmem/imx-ocotp.c b/drivers/nvmem/imx-ocotp.c index e0b22b6c045b..4cf7b61e4bf5 100644 --- a/drivers/nvmem/imx-ocotp.c +++ b/drivers/nvmem/imx-ocotp.c @@ -467,7 +467,6 @@ MODULE_DEVICE_TABLE(of, imx_ocotp_dt_ids); static int imx_ocotp_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - struct resource *res; struct ocotp_priv *priv; struct nvmem_device *nvmem; @@ -477,8 +476,7 @@ static int imx_ocotp_probe(struct platform_device *pdev) priv->dev = dev; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->base = devm_ioremap_resource(dev, res); + priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) return PTR_ERR(priv->base); From 794a1e229b92a4327ed536dd55a22d5a52762b39 Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Sat, 13 Apr 2019 11:33:00 +0100 Subject: [PATCH 140/255] nvmem: mxs-ocotp: use devm_platform_ioremap_resource() to simplify code Use the new helper devm_platform_ioremap_resource() which wraps the platform_get_resource() and devm_ioremap_resource() together, to simplify the code. Signed-off-by: Anson Huang Reviewed-by: Mukesh Ojha Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/mxs-ocotp.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/nvmem/mxs-ocotp.c b/drivers/nvmem/mxs-ocotp.c index 53122f59c4b2..fbb7db6ee1f5 100644 --- a/drivers/nvmem/mxs-ocotp.c +++ b/drivers/nvmem/mxs-ocotp.c @@ -145,7 +145,6 @@ static int mxs_ocotp_probe(struct platform_device *pdev) struct device *dev = &pdev->dev; const struct mxs_data *data; struct mxs_ocotp *otp; - struct resource *res; const struct of_device_id *match; int ret; @@ -157,8 +156,7 @@ static int mxs_ocotp_probe(struct platform_device *pdev) if (!otp) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - otp->base = devm_ioremap_resource(dev, res); + otp->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(otp->base)) return PTR_ERR(otp->base); From ededa0457b67ebb73d2c24b71822dad8c66a4715 Mon Sep 17 00:00:00 2001 From: Anson Huang Date: Sat, 13 Apr 2019 11:33:01 +0100 Subject: [PATCH 141/255] nvmem: imx-iim: use devm_platform_ioremap_resource() to simplify code Use the new helper devm_platform_ioremap_resource() which wraps the platform_get_resource() and devm_ioremap_resource() together, to simplify the code. Signed-off-by: Anson Huang Reviewed-by: Mukesh Ojha Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/imx-iim.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/drivers/nvmem/imx-iim.c b/drivers/nvmem/imx-iim.c index 6651e4cdc002..34582293b985 100644 --- a/drivers/nvmem/imx-iim.c +++ b/drivers/nvmem/imx-iim.c @@ -104,7 +104,6 @@ static int imx_iim_probe(struct platform_device *pdev) { const struct of_device_id *of_id; struct device *dev = &pdev->dev; - struct resource *res; struct iim_priv *iim; struct nvmem_device *nvmem; struct nvmem_config cfg = {}; @@ -114,8 +113,7 @@ static int imx_iim_probe(struct platform_device *pdev) if (!iim) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - iim->base = devm_ioremap_resource(dev, res); + iim->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(iim->base)) return PTR_ERR(iim->base); From b8371fc104d3acb87b04dbc70e75eda4714931e6 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Sat, 13 Apr 2019 11:33:02 +0100 Subject: [PATCH 142/255] nvmem: sunxi-sid: fix wrong description in kernel doc qfprom->sunxi-sid Acked-by: Maxime Ripard Reviewed-by: Rob Herring Signed-off-by: Yangtao Li Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/nvmem/allwinner,sunxi-sid.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/nvmem/allwinner,sunxi-sid.txt b/Documentation/devicetree/bindings/nvmem/allwinner,sunxi-sid.txt index 99c4ba6a3f61..d37017e343b1 100644 --- a/Documentation/devicetree/bindings/nvmem/allwinner,sunxi-sid.txt +++ b/Documentation/devicetree/bindings/nvmem/allwinner,sunxi-sid.txt @@ -12,7 +12,7 @@ Required properties: - reg: Should contain registers location and length = Data cells = -Are child nodes of qfprom, bindings of which as described in +Are child nodes of sunxi-sid, bindings of which as described in bindings/nvmem/nvmem.txt Example for sun4i: From f6edbb38ea8369bf366475924ba02178e4c25183 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Sat, 13 Apr 2019 11:33:03 +0100 Subject: [PATCH 143/255] nvmem: sunxi-sid: add binding for H6's SID controller Add a binding for H6's SID controller. Acked-by: Maxime Ripard Reviewed-by: Rob Herring Signed-off-by: Yangtao Li Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/nvmem/allwinner,sunxi-sid.txt | 1 + 1 file changed, 1 insertion(+) diff --git a/Documentation/devicetree/bindings/nvmem/allwinner,sunxi-sid.txt b/Documentation/devicetree/bindings/nvmem/allwinner,sunxi-sid.txt index d37017e343b1..cfb18b4ef8f7 100644 --- a/Documentation/devicetree/bindings/nvmem/allwinner,sunxi-sid.txt +++ b/Documentation/devicetree/bindings/nvmem/allwinner,sunxi-sid.txt @@ -8,6 +8,7 @@ Required properties: "allwinner,sun8i-h3-sid" "allwinner,sun50i-a64-sid" "allwinner,sun50i-h5-sid" + "allwinner,sun50i-h6-sid" - reg: Should contain registers location and length From 055f5df53f28fce845d5c0ae3a14deee756d99a6 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Sat, 13 Apr 2019 11:33:04 +0100 Subject: [PATCH 144/255] nvmem: sunxi-sid: convert to SPDX license tags Updates license to use SPDX-License-Identifier. Acked-by: Maxime Ripard Signed-off-by: Yangtao Li Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/sunxi_sid.c | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/drivers/nvmem/sunxi_sid.c b/drivers/nvmem/sunxi_sid.c index e7936380ce89..7013f9cc43c7 100644 --- a/drivers/nvmem/sunxi_sid.c +++ b/drivers/nvmem/sunxi_sid.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Allwinner sunXi SoCs Security ID support. * * Copyright (c) 2013 Oliver Schinagl * Copyright (C) 2014 Maxime Ripard - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #include From fc1eb6ebbd55e20819e8ec5f07a2bf71e3bea5f1 Mon Sep 17 00:00:00 2001 From: Yangtao Li Date: Sat, 13 Apr 2019 11:33:05 +0100 Subject: [PATCH 145/255] nvmem: sunxi_sid: Support SID on H6 Add support for H6's SID controller. It supports 4K-bit EFUSE, bigger than before. Signed-off-by: Yangtao Li Acked-by: Maxime Ripard Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/nvmem/sunxi_sid.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/nvmem/sunxi_sid.c b/drivers/nvmem/sunxi_sid.c index 7013f9cc43c7..a079a80ddf2c 100644 --- a/drivers/nvmem/sunxi_sid.c +++ b/drivers/nvmem/sunxi_sid.c @@ -188,6 +188,11 @@ static const struct sunxi_sid_cfg sun50i_a64_cfg = { .size = 0x100, }; +static const struct sunxi_sid_cfg sun50i_h6_cfg = { + .value_offset = 0x200, + .size = 0x200, +}; + static const struct of_device_id sunxi_sid_of_match[] = { { .compatible = "allwinner,sun4i-a10-sid", .data = &sun4i_a10_cfg }, { .compatible = "allwinner,sun7i-a20-sid", .data = &sun7i_a20_cfg }, @@ -195,6 +200,7 @@ static const struct of_device_id sunxi_sid_of_match[] = { { .compatible = "allwinner,sun8i-h3-sid", .data = &sun8i_h3_cfg }, { .compatible = "allwinner,sun50i-a64-sid", .data = &sun50i_a64_cfg }, { .compatible = "allwinner,sun50i-h5-sid", .data = &sun50i_a64_cfg }, + { .compatible = "allwinner,sun50i-h6-sid", .data = &sun50i_h6_cfg }, {/* sentinel */}, }; MODULE_DEVICE_TABLE(of, sunxi_sid_of_match); From ae0c2d725512f32a0d1a25f0cf2f07616d33a72e Mon Sep 17 00:00:00 2001 From: Srinivas Kandagatla Date: Tue, 16 Apr 2019 10:59:24 +0100 Subject: [PATCH 146/255] nvmem: core: add NVMEM_SYSFS Kconfig Many nvmem providers are not very keen on having default sysfs nvmem entry, as most of the usecases for them are inside kernel itself. And in some cases read/writes to some areas in nvmem are restricted and trapped at secure monitor level, so accessing them from userspace would result in board reboots. This patch adds new NVMEM_SYSFS Kconfig to make binary sysfs entry an optional one. This provision will give more flexibility to users. This patch also moves existing sysfs code to a new file so that its not compiled in when its not really required. Signed-off-by: Srinivas Kandagatla Reviewed-by: Mika Westerberg Reviewed-by: Gaurav Kohli Tested-by: Gaurav Kohli Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/stable/sysfs-bus-nvmem | 2 + drivers/nvmem/Kconfig | 10 + drivers/nvmem/Makefile | 3 + drivers/nvmem/core.c | 264 +---------------------- drivers/nvmem/nvmem-sysfs.c | 256 ++++++++++++++++++++++ drivers/nvmem/nvmem.h | 62 ++++++ 6 files changed, 337 insertions(+), 260 deletions(-) create mode 100644 drivers/nvmem/nvmem-sysfs.c create mode 100644 drivers/nvmem/nvmem.h diff --git a/Documentation/ABI/stable/sysfs-bus-nvmem b/Documentation/ABI/stable/sysfs-bus-nvmem index 5923ab4620c5..9ffba8576f7b 100644 --- a/Documentation/ABI/stable/sysfs-bus-nvmem +++ b/Documentation/ABI/stable/sysfs-bus-nvmem @@ -6,6 +6,8 @@ Description: This file allows user to read/write the raw NVMEM contents. Permissions for write to this file depends on the nvmem provider configuration. + Note: This file is only present if CONFIG_NVMEM_SYSFS + is enabled ex: hexdump /sys/bus/nvmem/devices/qfprom0/nvmem diff --git a/drivers/nvmem/Kconfig b/drivers/nvmem/Kconfig index a90e9a1ebe55..6b2c4254c2fb 100644 --- a/drivers/nvmem/Kconfig +++ b/drivers/nvmem/Kconfig @@ -13,6 +13,16 @@ menuconfig NVMEM if NVMEM +config NVMEM_SYSFS + bool "/sys/bus/nvmem/devices/*/nvmem (sysfs interface)" + depends on SYSFS + default y + help + Say Y here to add a sysfs interface for NVMEM. + + This interface is mostly used by userspace applications to + read/write directly into nvmem. + config NVMEM_IMX_IIM tristate "i.MX IC Identification Module support" depends on ARCH_MXC || COMPILE_TEST diff --git a/drivers/nvmem/Makefile b/drivers/nvmem/Makefile index 4c7ba12a7005..c1fe4768dfef 100644 --- a/drivers/nvmem/Makefile +++ b/drivers/nvmem/Makefile @@ -6,6 +6,9 @@ obj-$(CONFIG_NVMEM) += nvmem_core.o nvmem_core-y := core.o +obj-$(CONFIG_NVMEM_SYSFS) += nvmem_sysfs.o +nvmem_sysfs-y := nvmem-sysfs.o + # Devices obj-$(CONFIG_NVMEM_BCM_OCOTP) += nvmem-bcm-ocotp.o nvmem-bcm-ocotp-y := bcm-ocotp.o diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c index 5abebf2128b8..c7892c3da91f 100644 --- a/drivers/nvmem/core.c +++ b/drivers/nvmem/core.c @@ -17,27 +17,7 @@ #include #include #include - -struct nvmem_device { - struct module *owner; - struct device dev; - int stride; - int word_size; - int id; - struct kref refcnt; - size_t size; - bool read_only; - int flags; - enum nvmem_type type; - struct bin_attribute eeprom; - struct device *base_dev; - struct list_head cells; - nvmem_reg_read_t reg_read; - nvmem_reg_write_t reg_write; - void *priv; -}; - -#define FLAG_COMPAT BIT(0) +#include "nvmem.h" struct nvmem_cell { const char *name; @@ -61,18 +41,7 @@ static LIST_HEAD(nvmem_lookup_list); static BLOCKING_NOTIFIER_HEAD(nvmem_notifier); -static const char * const nvmem_type_str[] = { - [NVMEM_TYPE_UNKNOWN] = "Unknown", - [NVMEM_TYPE_EEPROM] = "EEPROM", - [NVMEM_TYPE_OTP] = "OTP", - [NVMEM_TYPE_BATTERY_BACKED] = "Battery backed", -}; -#ifdef CONFIG_DEBUG_LOCK_ALLOC -static struct lock_class_key eeprom_lock_key; -#endif - -#define to_nvmem_device(d) container_of(d, struct nvmem_device, dev) static int nvmem_reg_read(struct nvmem_device *nvmem, unsigned int offset, void *val, size_t bytes) { @@ -91,187 +60,6 @@ static int nvmem_reg_write(struct nvmem_device *nvmem, unsigned int offset, return -EINVAL; } -static ssize_t type_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct nvmem_device *nvmem = to_nvmem_device(dev); - - return sprintf(buf, "%s\n", nvmem_type_str[nvmem->type]); -} - -static DEVICE_ATTR_RO(type); - -static struct attribute *nvmem_attrs[] = { - &dev_attr_type.attr, - NULL, -}; - -static ssize_t bin_attr_nvmem_read(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, - char *buf, loff_t pos, size_t count) -{ - struct device *dev; - struct nvmem_device *nvmem; - int rc; - - if (attr->private) - dev = attr->private; - else - dev = container_of(kobj, struct device, kobj); - nvmem = to_nvmem_device(dev); - - /* Stop the user from reading */ - if (pos >= nvmem->size) - return 0; - - if (count < nvmem->word_size) - return -EINVAL; - - if (pos + count > nvmem->size) - count = nvmem->size - pos; - - count = round_down(count, nvmem->word_size); - - rc = nvmem_reg_read(nvmem, pos, buf, count); - - if (rc) - return rc; - - return count; -} - -static ssize_t bin_attr_nvmem_write(struct file *filp, struct kobject *kobj, - struct bin_attribute *attr, - char *buf, loff_t pos, size_t count) -{ - struct device *dev; - struct nvmem_device *nvmem; - int rc; - - if (attr->private) - dev = attr->private; - else - dev = container_of(kobj, struct device, kobj); - nvmem = to_nvmem_device(dev); - - /* Stop the user from writing */ - if (pos >= nvmem->size) - return -EFBIG; - - if (count < nvmem->word_size) - return -EINVAL; - - if (pos + count > nvmem->size) - count = nvmem->size - pos; - - count = round_down(count, nvmem->word_size); - - rc = nvmem_reg_write(nvmem, pos, buf, count); - - if (rc) - return rc; - - return count; -} - -/* default read/write permissions */ -static struct bin_attribute bin_attr_rw_nvmem = { - .attr = { - .name = "nvmem", - .mode = 0644, - }, - .read = bin_attr_nvmem_read, - .write = bin_attr_nvmem_write, -}; - -static struct bin_attribute *nvmem_bin_rw_attributes[] = { - &bin_attr_rw_nvmem, - NULL, -}; - -static const struct attribute_group nvmem_bin_rw_group = { - .bin_attrs = nvmem_bin_rw_attributes, - .attrs = nvmem_attrs, -}; - -static const struct attribute_group *nvmem_rw_dev_groups[] = { - &nvmem_bin_rw_group, - NULL, -}; - -/* read only permission */ -static struct bin_attribute bin_attr_ro_nvmem = { - .attr = { - .name = "nvmem", - .mode = 0444, - }, - .read = bin_attr_nvmem_read, -}; - -static struct bin_attribute *nvmem_bin_ro_attributes[] = { - &bin_attr_ro_nvmem, - NULL, -}; - -static const struct attribute_group nvmem_bin_ro_group = { - .bin_attrs = nvmem_bin_ro_attributes, - .attrs = nvmem_attrs, -}; - -static const struct attribute_group *nvmem_ro_dev_groups[] = { - &nvmem_bin_ro_group, - NULL, -}; - -/* default read/write permissions, root only */ -static struct bin_attribute bin_attr_rw_root_nvmem = { - .attr = { - .name = "nvmem", - .mode = 0600, - }, - .read = bin_attr_nvmem_read, - .write = bin_attr_nvmem_write, -}; - -static struct bin_attribute *nvmem_bin_rw_root_attributes[] = { - &bin_attr_rw_root_nvmem, - NULL, -}; - -static const struct attribute_group nvmem_bin_rw_root_group = { - .bin_attrs = nvmem_bin_rw_root_attributes, - .attrs = nvmem_attrs, -}; - -static const struct attribute_group *nvmem_rw_root_dev_groups[] = { - &nvmem_bin_rw_root_group, - NULL, -}; - -/* read only permission, root only */ -static struct bin_attribute bin_attr_ro_root_nvmem = { - .attr = { - .name = "nvmem", - .mode = 0400, - }, - .read = bin_attr_nvmem_read, -}; - -static struct bin_attribute *nvmem_bin_ro_root_attributes[] = { - &bin_attr_ro_root_nvmem, - NULL, -}; - -static const struct attribute_group nvmem_bin_ro_root_group = { - .bin_attrs = nvmem_bin_ro_root_attributes, - .attrs = nvmem_attrs, -}; - -static const struct attribute_group *nvmem_ro_root_dev_groups[] = { - &nvmem_bin_ro_root_group, - NULL, -}; - static void nvmem_release(struct device *dev) { struct nvmem_device *nvmem = to_nvmem_device(dev); @@ -422,43 +210,6 @@ static int nvmem_add_cells(struct nvmem_device *nvmem, return rval; } -/* - * nvmem_setup_compat() - Create an additional binary entry in - * drivers sys directory, to be backwards compatible with the older - * drivers/misc/eeprom drivers. - */ -static int nvmem_setup_compat(struct nvmem_device *nvmem, - const struct nvmem_config *config) -{ - int rval; - - if (!config->base_dev) - return -EINVAL; - - if (nvmem->read_only) - nvmem->eeprom = bin_attr_ro_root_nvmem; - else - nvmem->eeprom = bin_attr_rw_root_nvmem; - nvmem->eeprom.attr.name = "eeprom"; - nvmem->eeprom.size = nvmem->size; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - nvmem->eeprom.attr.key = &eeprom_lock_key; -#endif - nvmem->eeprom.private = &nvmem->dev; - nvmem->base_dev = config->base_dev; - - rval = device_create_bin_file(nvmem->base_dev, &nvmem->eeprom); - if (rval) { - dev_err(&nvmem->dev, - "Failed to create eeprom binary file %d\n", rval); - return rval; - } - - nvmem->flags |= FLAG_COMPAT; - - return 0; -} - /** * nvmem_register_notifier() - Register a notifier block for nvmem events. * @@ -651,14 +402,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem->read_only = device_property_present(config->dev, "read-only") || config->read_only || !nvmem->reg_write; - if (config->root_only) - nvmem->dev.groups = nvmem->read_only ? - nvmem_ro_root_dev_groups : - nvmem_rw_root_dev_groups; - else - nvmem->dev.groups = nvmem->read_only ? - nvmem_ro_dev_groups : - nvmem_rw_dev_groups; + nvmem->dev.groups = nvmem_sysfs_get_groups(nvmem, config); device_initialize(&nvmem->dev); @@ -669,7 +413,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) goto err_put_device; if (config->compat) { - rval = nvmem_setup_compat(nvmem, config); + rval = nvmem_sysfs_setup_compat(nvmem, config); if (rval) goto err_device_del; } @@ -696,7 +440,7 @@ struct nvmem_device *nvmem_register(const struct nvmem_config *config) nvmem_device_remove_all_cells(nvmem); err_teardown_compat: if (config->compat) - device_remove_bin_file(nvmem->base_dev, &nvmem->eeprom); + nvmem_sysfs_remove_compat(nvmem, config); err_device_del: device_del(&nvmem->dev); err_put_device: diff --git a/drivers/nvmem/nvmem-sysfs.c b/drivers/nvmem/nvmem-sysfs.c new file mode 100644 index 000000000000..6f303b91f6e7 --- /dev/null +++ b/drivers/nvmem/nvmem-sysfs.c @@ -0,0 +1,256 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2019, Linaro Limited + */ +#include "nvmem.h" + +static const char * const nvmem_type_str[] = { + [NVMEM_TYPE_UNKNOWN] = "Unknown", + [NVMEM_TYPE_EEPROM] = "EEPROM", + [NVMEM_TYPE_OTP] = "OTP", + [NVMEM_TYPE_BATTERY_BACKED] = "Battery backed", +}; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +static struct lock_class_key eeprom_lock_key; +#endif + +static ssize_t type_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvmem_device *nvmem = to_nvmem_device(dev); + + return sprintf(buf, "%s\n", nvmem_type_str[nvmem->type]); +} + +static DEVICE_ATTR_RO(type); + +static struct attribute *nvmem_attrs[] = { + &dev_attr_type.attr, + NULL, +}; + +static ssize_t bin_attr_nvmem_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t pos, size_t count) +{ + struct device *dev; + struct nvmem_device *nvmem; + int rc; + + if (attr->private) + dev = attr->private; + else + dev = container_of(kobj, struct device, kobj); + nvmem = to_nvmem_device(dev); + + /* Stop the user from reading */ + if (pos >= nvmem->size) + return 0; + + if (count < nvmem->word_size) + return -EINVAL; + + if (pos + count > nvmem->size) + count = nvmem->size - pos; + + count = round_down(count, nvmem->word_size); + + rc = nvmem->reg_read(nvmem->priv, pos, buf, count); + + if (rc) + return rc; + + return count; +} + +static ssize_t bin_attr_nvmem_write(struct file *filp, struct kobject *kobj, + struct bin_attribute *attr, + char *buf, loff_t pos, size_t count) +{ + struct device *dev; + struct nvmem_device *nvmem; + int rc; + + if (attr->private) + dev = attr->private; + else + dev = container_of(kobj, struct device, kobj); + nvmem = to_nvmem_device(dev); + + /* Stop the user from writing */ + if (pos >= nvmem->size) + return -EFBIG; + + if (count < nvmem->word_size) + return -EINVAL; + + if (pos + count > nvmem->size) + count = nvmem->size - pos; + + count = round_down(count, nvmem->word_size); + + rc = nvmem->reg_write(nvmem->priv, pos, buf, count); + + if (rc) + return rc; + + return count; +} + +/* default read/write permissions */ +static struct bin_attribute bin_attr_rw_nvmem = { + .attr = { + .name = "nvmem", + .mode = 0644, + }, + .read = bin_attr_nvmem_read, + .write = bin_attr_nvmem_write, +}; + +static struct bin_attribute *nvmem_bin_rw_attributes[] = { + &bin_attr_rw_nvmem, + NULL, +}; + +static const struct attribute_group nvmem_bin_rw_group = { + .bin_attrs = nvmem_bin_rw_attributes, + .attrs = nvmem_attrs, +}; + +static const struct attribute_group *nvmem_rw_dev_groups[] = { + &nvmem_bin_rw_group, + NULL, +}; + +/* read only permission */ +static struct bin_attribute bin_attr_ro_nvmem = { + .attr = { + .name = "nvmem", + .mode = 0444, + }, + .read = bin_attr_nvmem_read, +}; + +static struct bin_attribute *nvmem_bin_ro_attributes[] = { + &bin_attr_ro_nvmem, + NULL, +}; + +static const struct attribute_group nvmem_bin_ro_group = { + .bin_attrs = nvmem_bin_ro_attributes, + .attrs = nvmem_attrs, +}; + +static const struct attribute_group *nvmem_ro_dev_groups[] = { + &nvmem_bin_ro_group, + NULL, +}; + +/* default read/write permissions, root only */ +static struct bin_attribute bin_attr_rw_root_nvmem = { + .attr = { + .name = "nvmem", + .mode = 0600, + }, + .read = bin_attr_nvmem_read, + .write = bin_attr_nvmem_write, +}; + +static struct bin_attribute *nvmem_bin_rw_root_attributes[] = { + &bin_attr_rw_root_nvmem, + NULL, +}; + +static const struct attribute_group nvmem_bin_rw_root_group = { + .bin_attrs = nvmem_bin_rw_root_attributes, + .attrs = nvmem_attrs, +}; + +static const struct attribute_group *nvmem_rw_root_dev_groups[] = { + &nvmem_bin_rw_root_group, + NULL, +}; + +/* read only permission, root only */ +static struct bin_attribute bin_attr_ro_root_nvmem = { + .attr = { + .name = "nvmem", + .mode = 0400, + }, + .read = bin_attr_nvmem_read, +}; + +static struct bin_attribute *nvmem_bin_ro_root_attributes[] = { + &bin_attr_ro_root_nvmem, + NULL, +}; + +static const struct attribute_group nvmem_bin_ro_root_group = { + .bin_attrs = nvmem_bin_ro_root_attributes, + .attrs = nvmem_attrs, +}; + +static const struct attribute_group *nvmem_ro_root_dev_groups[] = { + &nvmem_bin_ro_root_group, + NULL, +}; + +const struct attribute_group **nvmem_sysfs_get_groups( + struct nvmem_device *nvmem, + const struct nvmem_config *config) +{ + if (config->root_only) + return nvmem->read_only ? + nvmem_ro_root_dev_groups : + nvmem_rw_root_dev_groups; + + return nvmem->read_only ? nvmem_ro_dev_groups : nvmem_rw_dev_groups; +} + +/* + * nvmem_setup_compat() - Create an additional binary entry in + * drivers sys directory, to be backwards compatible with the older + * drivers/misc/eeprom drivers. + */ +int nvmem_sysfs_setup_compat(struct nvmem_device *nvmem, + const struct nvmem_config *config) +{ + int rval; + + if (!config->compat) + return 0; + + if (!config->base_dev) + return -EINVAL; + + if (nvmem->read_only) + nvmem->eeprom = bin_attr_ro_root_nvmem; + else + nvmem->eeprom = bin_attr_rw_root_nvmem; + nvmem->eeprom.attr.name = "eeprom"; + nvmem->eeprom.size = nvmem->size; +#ifdef CONFIG_DEBUG_LOCK_ALLOC + nvmem->eeprom.attr.key = &eeprom_lock_key; +#endif + nvmem->eeprom.private = &nvmem->dev; + nvmem->base_dev = config->base_dev; + + rval = device_create_bin_file(nvmem->base_dev, &nvmem->eeprom); + if (rval) { + dev_err(&nvmem->dev, + "Failed to create eeprom binary file %d\n", rval); + return rval; + } + + nvmem->flags |= FLAG_COMPAT; + + return 0; +} + +void nvmem_sysfs_remove_compat(struct nvmem_device *nvmem, + const struct nvmem_config *config) +{ + if (config->compat) + device_remove_bin_file(nvmem->base_dev, &nvmem->eeprom); +} diff --git a/drivers/nvmem/nvmem.h b/drivers/nvmem/nvmem.h new file mode 100644 index 000000000000..eb8ed7121fa3 --- /dev/null +++ b/drivers/nvmem/nvmem.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _DRIVERS_NVMEM_H +#define _DRIVERS_NVMEM_H + +#include +#include +#include +#include +#include +#include + +struct nvmem_device { + struct module *owner; + struct device dev; + int stride; + int word_size; + int id; + struct kref refcnt; + size_t size; + bool read_only; + int flags; + enum nvmem_type type; + struct bin_attribute eeprom; + struct device *base_dev; + struct list_head cells; + nvmem_reg_read_t reg_read; + nvmem_reg_write_t reg_write; + void *priv; +}; + +#define to_nvmem_device(d) container_of(d, struct nvmem_device, dev) +#define FLAG_COMPAT BIT(0) + +#ifdef CONFIG_NVMEM_SYSFS +const struct attribute_group **nvmem_sysfs_get_groups( + struct nvmem_device *nvmem, + const struct nvmem_config *config); +int nvmem_sysfs_setup_compat(struct nvmem_device *nvmem, + const struct nvmem_config *config); +void nvmem_sysfs_remove_compat(struct nvmem_device *nvmem, + const struct nvmem_config *config); +#else +static inline const struct attribute_group **nvmem_sysfs_get_groups( + struct nvmem_device *nvmem, + const struct nvmem_config *config) +{ + return NULL; +} + +static inline int nvmem_sysfs_setup_compat(struct nvmem_device *nvmem, + const struct nvmem_config *config) +{ + return -ENOSYS; +} +static inline void nvmem_sysfs_remove_compat(struct nvmem_device *nvmem, + const struct nvmem_config *config) +{ +} +#endif /* CONFIG_NVMEM_SYSFS */ + +#endif /* _DRIVERS_NVMEM_H */ From ba2e544075c282a5bb21df7752efad3b42d6077b Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Tue, 16 Apr 2019 17:27:20 +1000 Subject: [PATCH 147/255] lib/siphash.c: mark expected switch fall-throughs In preparation to enabling -Wimplicit-fallthrough, mark switch cases where we are expecting to fall through. This patch aims to suppress up to 18 missing-break-in-switch false positives on some architectures. Cc: Gustavo A. R. Silva Cc: Kees Cook Signed-off-by: Stephen Rothwell Reviewed-by: Jason A. Donenfeld Signed-off-by: Greg Kroah-Hartman --- lib/siphash.c | 36 ++++++++++++++++++------------------ 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/lib/siphash.c b/lib/siphash.c index 3ae58b4edad6..c47bb6ff2149 100644 --- a/lib/siphash.c +++ b/lib/siphash.c @@ -68,11 +68,11 @@ u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key) bytemask_from_count(left))); #else switch (left) { - case 7: b |= ((u64)end[6]) << 48; - case 6: b |= ((u64)end[5]) << 40; - case 5: b |= ((u64)end[4]) << 32; + case 7: b |= ((u64)end[6]) << 48; /* fall through */ + case 6: b |= ((u64)end[5]) << 40; /* fall through */ + case 5: b |= ((u64)end[4]) << 32; /* fall through */ case 4: b |= le32_to_cpup(data); break; - case 3: b |= ((u64)end[2]) << 16; + case 3: b |= ((u64)end[2]) << 16; /* fall through */ case 2: b |= le16_to_cpup(data); break; case 1: b |= end[0]; } @@ -101,11 +101,11 @@ u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key) bytemask_from_count(left))); #else switch (left) { - case 7: b |= ((u64)end[6]) << 48; - case 6: b |= ((u64)end[5]) << 40; - case 5: b |= ((u64)end[4]) << 32; + case 7: b |= ((u64)end[6]) << 48; /* fall through */ + case 6: b |= ((u64)end[5]) << 40; /* fall through */ + case 5: b |= ((u64)end[4]) << 32; /* fall through */ case 4: b |= get_unaligned_le32(end); break; - case 3: b |= ((u64)end[2]) << 16; + case 3: b |= ((u64)end[2]) << 16; /* fall through */ case 2: b |= get_unaligned_le16(end); break; case 1: b |= end[0]; } @@ -268,11 +268,11 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) bytemask_from_count(left))); #else switch (left) { - case 7: b |= ((u64)end[6]) << 48; - case 6: b |= ((u64)end[5]) << 40; - case 5: b |= ((u64)end[4]) << 32; + case 7: b |= ((u64)end[6]) << 48; /* fall through */ + case 6: b |= ((u64)end[5]) << 40; /* fall through */ + case 5: b |= ((u64)end[4]) << 32; /* fall through */ case 4: b |= le32_to_cpup(data); break; - case 3: b |= ((u64)end[2]) << 16; + case 3: b |= ((u64)end[2]) << 16; /* fall through */ case 2: b |= le16_to_cpup(data); break; case 1: b |= end[0]; } @@ -301,11 +301,11 @@ u32 __hsiphash_unaligned(const void *data, size_t len, bytemask_from_count(left))); #else switch (left) { - case 7: b |= ((u64)end[6]) << 48; - case 6: b |= ((u64)end[5]) << 40; - case 5: b |= ((u64)end[4]) << 32; + case 7: b |= ((u64)end[6]) << 48; /* fall through */ + case 6: b |= ((u64)end[5]) << 40; /* fall through */ + case 5: b |= ((u64)end[4]) << 32; /* fall through */ case 4: b |= get_unaligned_le32(end); break; - case 3: b |= ((u64)end[2]) << 16; + case 3: b |= ((u64)end[2]) << 16; /* fall through */ case 2: b |= get_unaligned_le16(end); break; case 1: b |= end[0]; } @@ -431,7 +431,7 @@ u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key) v0 ^= m; } switch (left) { - case 3: b |= ((u32)end[2]) << 16; + case 3: b |= ((u32)end[2]) << 16; /* fall through */ case 2: b |= le16_to_cpup(data); break; case 1: b |= end[0]; } @@ -454,7 +454,7 @@ u32 __hsiphash_unaligned(const void *data, size_t len, v0 ^= m; } switch (left) { - case 3: b |= ((u32)end[2]) << 16; + case 3: b |= ((u32)end[2]) << 16; /* fall through */ case 2: b |= get_unaligned_le16(end); break; case 1: b |= end[0]; } From d2f4a83fe3f7fcc2a8a10a39e367c5d1c6670327 Mon Sep 17 00:00:00 2001 From: Fuqian Huang Date: Sun, 21 Apr 2019 19:47:48 +0800 Subject: [PATCH 148/255] misc: genwqe: Fix misuse of %x The pointer should be printed with %p or %px rather than cast to long long type and printed with %016llx. Change %x to %p to print the pointer. Signed-off-by: Fuqian Huang Signed-off-by: Greg Kroah-Hartman --- drivers/misc/genwqe/card_debugfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/misc/genwqe/card_debugfs.c b/drivers/misc/genwqe/card_debugfs.c index 7c713e01d198..6f7e39f07811 100644 --- a/drivers/misc/genwqe/card_debugfs.c +++ b/drivers/misc/genwqe/card_debugfs.c @@ -227,7 +227,7 @@ static int ddcb_info_show(struct seq_file *s, void *unused) seq_puts(s, "DDCB QUEUE:\n"); seq_printf(s, " ddcb_max: %d\n" " ddcb_daddr: %016llx - %016llx\n" - " ddcb_vaddr: %016llx\n" + " ddcb_vaddr: %p\n" " ddcbs_in_flight: %u\n" " ddcbs_max_in_flight: %u\n" " ddcbs_completed: %u\n" @@ -237,7 +237,7 @@ static int ddcb_info_show(struct seq_file *s, void *unused) queue->ddcb_max, (long long)queue->ddcb_daddr, (long long)queue->ddcb_daddr + (queue->ddcb_max * DDCB_LENGTH), - (long long)queue->ddcb_vaddr, queue->ddcbs_in_flight, + queue->ddcb_vaddr, queue->ddcbs_in_flight, queue->ddcbs_max_in_flight, queue->ddcbs_completed, queue->return_on_busy, queue->wait_on_busy, cd->irqs_processed); From 0b0509508beff65c1d50541861bc0d4973487dc5 Mon Sep 17 00:00:00 2001 From: Todd Kjos Date: Wed, 24 Apr 2019 12:31:18 -0700 Subject: [PATCH 149/255] binder: check for overflow when alloc for security context When allocating space in the target buffer for the security context, make sure the extra_buffers_size doesn't overflow. This can only happen if the given size is invalid, but an overflow can turn it into a valid size. Fail the transaction if an overflow is detected. Signed-off-by: Todd Kjos Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 4b9c7ca492e6..6f0712f0767c 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -3121,6 +3121,7 @@ static void binder_transaction(struct binder_proc *proc, if (target_node && target_node->txn_security_ctx) { u32 secid; + size_t added_size; security_task_getsecid(proc->tsk, &secid); ret = security_secid_to_secctx(secid, &secctx, &secctx_sz); @@ -3130,7 +3131,15 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_get_secctx_failed; } - extra_buffers_size += ALIGN(secctx_sz, sizeof(u64)); + added_size = ALIGN(secctx_sz, sizeof(u64)); + extra_buffers_size += added_size; + if (extra_buffers_size < added_size) { + /* integer overflow of extra_buffers_size */ + return_error = BR_FAILED_REPLY; + return_error_param = EINVAL; + return_error_line = __LINE__; + goto err_bad_extra_size; + } } trace_binder_transaction(reply, t, target_node); @@ -3480,6 +3489,7 @@ static void binder_transaction(struct binder_proc *proc, t->buffer->transaction = NULL; binder_alloc_free_buf(&target_proc->alloc, t->buffer); err_binder_alloc_buf_failed: +err_bad_extra_size: if (secctx) security_release_secctx(secctx, secctx_sz); err_get_secctx_failed: From cf4f2ad6b87dda2dbe0573b1ebeb0273f8d4aac6 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Thu, 4 Apr 2019 14:39:09 +0200 Subject: [PATCH 150/255] virt: vbox: Sanity-check parameter types for hgcm-calls coming from userspace Userspace can make host function calls, called hgcm-calls through the /dev/vboxguest device. In this case we should not accept all hgcm-function-parameter-types, some are only valid for in kernel calls. This commit adds proper hgcm-function-parameter-type validation to the ioctl for doing a hgcm-call from userspace. Cc: stable@vger.kernel.org Signed-off-by: Hans de Goede Signed-off-by: Greg Kroah-Hartman --- drivers/virt/vboxguest/vboxguest_core.c | 31 +++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/drivers/virt/vboxguest/vboxguest_core.c b/drivers/virt/vboxguest/vboxguest_core.c index 8ca333f21292..2307b0329aec 100644 --- a/drivers/virt/vboxguest/vboxguest_core.c +++ b/drivers/virt/vboxguest/vboxguest_core.c @@ -1298,6 +1298,20 @@ static int vbg_ioctl_hgcm_disconnect(struct vbg_dev *gdev, return ret; } +static bool vbg_param_valid(enum vmmdev_hgcm_function_parameter_type type) +{ + switch (type) { + case VMMDEV_HGCM_PARM_TYPE_32BIT: + case VMMDEV_HGCM_PARM_TYPE_64BIT: + case VMMDEV_HGCM_PARM_TYPE_LINADDR: + case VMMDEV_HGCM_PARM_TYPE_LINADDR_IN: + case VMMDEV_HGCM_PARM_TYPE_LINADDR_OUT: + return true; + default: + return false; + } +} + static int vbg_ioctl_hgcm_call(struct vbg_dev *gdev, struct vbg_session *session, bool f32bit, struct vbg_ioctl_hgcm_call *call) @@ -1333,6 +1347,23 @@ static int vbg_ioctl_hgcm_call(struct vbg_dev *gdev, } call->hdr.size_out = actual_size; + /* Validate parameter types */ + if (f32bit) { + struct vmmdev_hgcm_function_parameter32 *parm = + VBG_IOCTL_HGCM_CALL_PARMS32(call); + + for (i = 0; i < call->parm_count; i++) + if (!vbg_param_valid(parm[i].type)) + return -EINVAL; + } else { + struct vmmdev_hgcm_function_parameter *parm = + VBG_IOCTL_HGCM_CALL_PARMS(call); + + for (i = 0; i < call->parm_count; i++) + if (!vbg_param_valid(parm[i].type)) + return -EINVAL; + } + /* * Validate the client id. */ From 59d63de076607a9334b11628b5c3ddda1d8f56cd Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 25 Apr 2019 13:52:39 -0600 Subject: [PATCH 151/255] coresight: catu: fix clang build warning Clang points out a syntax error, as the etr_catu_buf_ops structure is declared 'static' before the type is known: In file included from drivers/hwtracing/coresight/coresight-tmc-etr.c:12: drivers/hwtracing/coresight/coresight-catu.h:116:40: warning: tentative definition of variable with internal linkage has incomplete non-array type 'const struct etr_buf_operations' [-Wtentative-definition-incomplete-type] static const struct etr_buf_operations etr_catu_buf_ops; ^ drivers/hwtracing/coresight/coresight-catu.h:116:21: note: forward declaration of 'struct etr_buf_operations' static const struct etr_buf_operations etr_catu_buf_ops; This seems worth fixing in the code, so replace pointer to the empty constant structure with a NULL pointer. We need an extra NULL pointer check here, but the result should be better object code otherwise, avoiding the silly empty structure. Fixes: 434d611cddef ("coresight: catu: Plug in CATU as a backend for ETR buffer") Signed-off-by: Arnd Bergmann Reviewed-by: Suzuki K Poulose [Fixed line over 80 characters] Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-catu.h | 5 ----- drivers/hwtracing/coresight/coresight-tmc-etr.c | 5 +++-- 2 files changed, 3 insertions(+), 7 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-catu.h b/drivers/hwtracing/coresight/coresight-catu.h index 1b281f0dcccc..1d2ad183fd92 100644 --- a/drivers/hwtracing/coresight/coresight-catu.h +++ b/drivers/hwtracing/coresight/coresight-catu.h @@ -109,11 +109,6 @@ static inline bool coresight_is_catu_device(struct coresight_device *csdev) return true; } -#ifdef CONFIG_CORESIGHT_CATU extern const struct etr_buf_operations etr_catu_buf_ops; -#else -/* Dummy declaration for the CATU ops */ -static const struct etr_buf_operations etr_catu_buf_ops; -#endif #endif diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index f684283890d3..cf7a32ce209d 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -772,7 +772,8 @@ static inline void tmc_etr_disable_catu(struct tmc_drvdata *drvdata) static const struct etr_buf_operations *etr_buf_ops[] = { [ETR_MODE_FLAT] = &etr_flat_buf_ops, [ETR_MODE_ETR_SG] = &etr_sg_buf_ops, - [ETR_MODE_CATU] = &etr_catu_buf_ops, + [ETR_MODE_CATU] = IS_ENABLED(CONFIG_CORESIGHT_CATU) + ? &etr_catu_buf_ops : NULL, }; static inline int tmc_etr_mode_alloc_buf(int mode, @@ -786,7 +787,7 @@ static inline int tmc_etr_mode_alloc_buf(int mode, case ETR_MODE_FLAT: case ETR_MODE_ETR_SG: case ETR_MODE_CATU: - if (etr_buf_ops[mode]->alloc) + if (etr_buf_ops[mode] && etr_buf_ops[mode]->alloc) rc = etr_buf_ops[mode]->alloc(drvdata, etr_buf, node, pages); if (!rc) From 61810404b43fb0f7195cd947aef903ac90ea6989 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Thu, 25 Apr 2019 13:52:40 -0600 Subject: [PATCH 152/255] coresight: catu: Make catu_helper_ops and catu_ops static Fix sparse warnings: drivers/hwtracing/coresight/coresight-catu.c:488:35: warning: symbol 'catu_helper_ops' was not declared. Should it be static? drivers/hwtracing/coresight/coresight-catu.c:493:28: warning: symbol 'catu_ops' was not declared. Should it be static? Signed-off-by: YueHaibing Reviewed-by: Mukesh Ojha Reviewed-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-catu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-catu.c b/drivers/hwtracing/coresight/coresight-catu.c index 170fbb66bda2..057627a0753d 100644 --- a/drivers/hwtracing/coresight/coresight-catu.c +++ b/drivers/hwtracing/coresight/coresight-catu.c @@ -485,12 +485,12 @@ static int catu_disable(struct coresight_device *csdev, void *__unused) return rc; } -const struct coresight_ops_helper catu_helper_ops = { +static const struct coresight_ops_helper catu_helper_ops = { .enable = catu_enable, .disable = catu_disable, }; -const struct coresight_ops catu_ops = { +static const struct coresight_ops catu_ops = { .helper_ops = &catu_helper_ops, }; From 08be874775f13a0acffff864440d10b8b1397912 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 25 Apr 2019 13:52:41 -0600 Subject: [PATCH 153/255] coresight: tmc: Report DMA setup failures If we failed to setup the DMA mask for TMC-ETR, report the error before failing the probe. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-tmc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c index 2a02da3d630f..647b6aa93554 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.c +++ b/drivers/hwtracing/coresight/coresight-tmc.c @@ -340,6 +340,8 @@ static inline bool tmc_etr_can_use_sg(struct tmc_drvdata *drvdata) static int tmc_etr_setup_caps(struct tmc_drvdata *drvdata, u32 devid, void *dev_caps) { + int rc; + u32 dma_mask = 0; /* Set the unadvertised capabilities */ @@ -369,7 +371,10 @@ static int tmc_etr_setup_caps(struct tmc_drvdata *drvdata, dma_mask = 40; } - return dma_set_mask_and_coherent(drvdata->dev, DMA_BIT_MASK(dma_mask)); + rc = dma_set_mask_and_coherent(drvdata->dev, DMA_BIT_MASK(dma_mask)); + if (rc) + dev_err(drvdata->dev, "Failed to setup DMA mask: %d\n", rc); + return rc; } static int tmc_probe(struct amba_device *adev, const struct amba_id *id) From ee8146aad87cd8eeb5963856ac0b9a9176392e3a Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 25 Apr 2019 13:52:42 -0600 Subject: [PATCH 154/255] coresight: dynamic-replicator: Clean up error handling We fail to disable the clock in case of a failure during the probe. Clean this up. Also, we are supposed to drop the pm reference only when the probing is successful. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- .../coresight/coresight-dynamic-replicator.c | 24 ++++++++++++------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c b/drivers/hwtracing/coresight/coresight-dynamic-replicator.c index 299667b887fc..fe176b987685 100644 --- a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c +++ b/drivers/hwtracing/coresight/coresight-dynamic-replicator.c @@ -150,7 +150,7 @@ static const struct attribute_group *replicator_groups[] = { static int replicator_probe(struct amba_device *adev, const struct amba_id *id) { - int ret; + int ret = 0; struct device *dev = &adev->dev; struct resource *res = &adev->res; struct coresight_platform_data *pdata = NULL; @@ -180,12 +180,13 @@ static int replicator_probe(struct amba_device *adev, const struct amba_id *id) /* Validity for the resource is already checked by the AMBA core */ base = devm_ioremap_resource(dev, res); - if (IS_ERR(base)) - return PTR_ERR(base); + if (IS_ERR(base)) { + ret = PTR_ERR(base); + goto out_disable_clk; + } drvdata->base = base; dev_set_drvdata(dev, drvdata); - pm_runtime_put(&adev->dev); desc.type = CORESIGHT_DEV_TYPE_LINK; desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT; @@ -195,11 +196,18 @@ static int replicator_probe(struct amba_device *adev, const struct amba_id *id) desc.groups = replicator_groups; drvdata->csdev = coresight_register(&desc); - if (!IS_ERR(drvdata->csdev)) { - replicator_reset(drvdata); - return 0; + if (IS_ERR(drvdata->csdev)) { + ret = PTR_ERR(drvdata->csdev); + goto out_disable_clk; } - return PTR_ERR(drvdata->csdev); + + replicator_reset(drvdata); + pm_runtime_put(&adev->dev); + +out_disable_clk: + if (ret && !IS_ERR_OR_NULL(drvdata->atclk)) + clk_disable_unprepare(drvdata->atclk); + return ret; } #ifdef CONFIG_PM From eb6934b5c1bb53ca3b31527945cb1b8d02e9864c Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 25 Apr 2019 13:52:43 -0600 Subject: [PATCH 155/255] coresight: replicator: Prepare for merging with dynamic-replicator As a preparatory step to merge the separate drivers for static and dynamic replicators, annotate the static replicator specific details. Also refactor the probe routine to make it generic in order to merge the drivers easily. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- .../coresight/coresight-replicator.c | 62 +++++++++++-------- 1 file changed, 36 insertions(+), 26 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c index feac98315471..43cbcf1e7be8 100644 --- a/drivers/hwtracing/coresight/coresight-replicator.c +++ b/drivers/hwtracing/coresight/coresight-replicator.c @@ -56,58 +56,68 @@ static const struct coresight_ops replicator_cs_ops = { .link_ops = &replicator_link_ops, }; -static int replicator_probe(struct platform_device *pdev) +static int replicator_probe(struct device *dev) { - int ret; - struct device *dev = &pdev->dev; + int ret = 0; struct coresight_platform_data *pdata = NULL; struct replicator_drvdata *drvdata; struct coresight_desc desc = { 0 }; - struct device_node *np = pdev->dev.of_node; + struct device_node *np = dev->of_node; if (np) { pdata = of_get_coresight_platform_data(dev, np); if (IS_ERR(pdata)) return PTR_ERR(pdata); - pdev->dev.platform_data = pdata; + dev->platform_data = pdata; } drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); if (!drvdata) return -ENOMEM; - drvdata->dev = &pdev->dev; - drvdata->atclk = devm_clk_get(&pdev->dev, "atclk"); /* optional */ + drvdata->dev = dev; + drvdata->atclk = devm_clk_get(dev, "atclk"); /* optional */ if (!IS_ERR(drvdata->atclk)) { ret = clk_prepare_enable(drvdata->atclk); if (ret) return ret; } - pm_runtime_get_noresume(&pdev->dev); - pm_runtime_set_active(&pdev->dev); - pm_runtime_enable(&pdev->dev); - platform_set_drvdata(pdev, drvdata); + + dev_set_drvdata(dev, drvdata); desc.type = CORESIGHT_DEV_TYPE_LINK; desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT; desc.ops = &replicator_cs_ops; - desc.pdata = pdev->dev.platform_data; - desc.dev = &pdev->dev; + desc.pdata = dev->platform_data; + desc.dev = dev; drvdata->csdev = coresight_register(&desc); if (IS_ERR(drvdata->csdev)) { ret = PTR_ERR(drvdata->csdev); - goto out_disable_pm; + goto out_disable_clk; } - pm_runtime_put(&pdev->dev); + pm_runtime_put(dev); - return 0; - -out_disable_pm: - if (!IS_ERR(drvdata->atclk)) +out_disable_clk: + if (ret && !IS_ERR_OR_NULL(drvdata->atclk)) clk_disable_unprepare(drvdata->atclk); - pm_runtime_put_noidle(&pdev->dev); - pm_runtime_disable(&pdev->dev); + return ret; +} + +static int static_replicator_probe(struct platform_device *pdev) +{ + int ret; + + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + ret = replicator_probe(&pdev->dev); + + if (ret) { + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_disable(&pdev->dev); + } return ret; } @@ -139,18 +149,18 @@ static const struct dev_pm_ops replicator_dev_pm_ops = { replicator_runtime_resume, NULL) }; -static const struct of_device_id replicator_match[] = { +static const struct of_device_id static_replicator_match[] = { {.compatible = "arm,coresight-replicator"}, {} }; -static struct platform_driver replicator_driver = { - .probe = replicator_probe, +static struct platform_driver static_replicator_driver = { + .probe = static_replicator_probe, .driver = { .name = "coresight-replicator", - .of_match_table = replicator_match, + .of_match_table = static_replicator_match, .pm = &replicator_dev_pm_ops, .suppress_bind_attrs = true, }, }; -builtin_platform_driver(replicator_driver); +builtin_platform_driver(static_replicator_driver); From c827db65666b781df3fbdc7b7645856d3101080e Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 25 Apr 2019 13:52:44 -0600 Subject: [PATCH 156/255] coresight: dynamic-replicator: Prepare for merging with static replicator Rename the dynamic replicator specific routines for merging with the replicator driver. Also re-arrange the probe routine to make it easier to merge. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- .../coresight/coresight-dynamic-replicator.c | 104 +++++++++++------- 1 file changed, 63 insertions(+), 41 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c b/drivers/hwtracing/coresight/coresight-dynamic-replicator.c index fe176b987685..b7d7c4146f9a 100644 --- a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c +++ b/drivers/hwtracing/coresight/coresight-dynamic-replicator.c @@ -21,13 +21,13 @@ #define REPLICATOR_IDFILTER1 0x004 /** - * struct replicator_state - specifics associated to a replicator component + * struct replicator_drvdata - specifics associated to a replicator component * @base: memory mapped base address for this component. * @dev: the device entity associated with this component * @atclk: optional clock for the core parts of the replicator. * @csdev: component vitals needed by the framework */ -struct replicator_state { +struct replicator_drvdata { void __iomem *base; struct device *dev; struct clk *atclk; @@ -35,9 +35,9 @@ struct replicator_state { }; /* - * replicator_reset : Reset the replicator configuration to sane values. + * dynamic_replicator_reset : Reset the replicator configuration to sane values. */ -static void replicator_reset(struct replicator_state *drvdata) +static void dynamic_replicator_reset(struct replicator_drvdata *drvdata) { CS_UNLOCK(drvdata->base); @@ -50,12 +50,11 @@ static void replicator_reset(struct replicator_state *drvdata) CS_LOCK(drvdata->base); } -static int replicator_enable(struct coresight_device *csdev, int inport, - int outport) +static int dynamic_replicator_enable(struct replicator_drvdata *drvdata, + int inport, int outport) { int rc = 0; u32 reg; - struct replicator_state *drvdata = dev_get_drvdata(csdev->dev.parent); switch (outport) { case 0: @@ -76,21 +75,28 @@ static int replicator_enable(struct coresight_device *csdev, int inport, rc = coresight_claim_device_unlocked(drvdata->base); /* Ensure that the outport is enabled. */ - if (!rc) { + if (!rc) writel_relaxed(0x00, drvdata->base + reg); - dev_dbg(drvdata->dev, "REPLICATOR enabled\n"); - } - CS_LOCK(drvdata->base); return rc; } -static void replicator_disable(struct coresight_device *csdev, int inport, - int outport) +static int replicator_enable(struct coresight_device *csdev, int inport, + int outport) +{ + int rc = 0; + struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + rc = dynamic_replicator_enable(drvdata, inport, outport); + dev_dbg(drvdata->dev, "REPLICATOR enabled\n"); + return rc; +} + +static void dynamic_replicator_disable(struct replicator_drvdata *drvdata, + int inport, int outport) { u32 reg; - struct replicator_state *drvdata = dev_get_drvdata(csdev->dev.parent); switch (outport) { case 0: @@ -113,7 +119,14 @@ static void replicator_disable(struct coresight_device *csdev, int inport, (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff)) coresight_disclaim_device_unlocked(drvdata->base); CS_LOCK(drvdata->base); +} +static void replicator_disable(struct coresight_device *csdev, int inport, + int outport) +{ + struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + + dynamic_replicator_disable(drvdata, inport, outport); dev_dbg(drvdata->dev, "REPLICATOR disabled\n"); } @@ -127,7 +140,7 @@ static const struct coresight_ops replicator_cs_ops = { }; #define coresight_replicator_reg(name, offset) \ - coresight_simple_reg32(struct replicator_state, name, offset) + coresight_simple_reg32(struct replicator_drvdata, name, offset) coresight_replicator_reg(idfilter0, REPLICATOR_IDFILTER0); coresight_replicator_reg(idfilter1, REPLICATOR_IDFILTER1); @@ -148,52 +161,55 @@ static const struct attribute_group *replicator_groups[] = { NULL, }; -static int replicator_probe(struct amba_device *adev, const struct amba_id *id) +static int replicator_probe(struct device *dev, struct resource *res) { int ret = 0; - struct device *dev = &adev->dev; - struct resource *res = &adev->res; struct coresight_platform_data *pdata = NULL; - struct replicator_state *drvdata; + struct replicator_drvdata *drvdata; struct coresight_desc desc = { 0 }; - struct device_node *np = adev->dev.of_node; + struct device_node *np = dev->of_node; void __iomem *base; if (np) { pdata = of_get_coresight_platform_data(dev, np); if (IS_ERR(pdata)) return PTR_ERR(pdata); - adev->dev.platform_data = pdata; + dev->platform_data = pdata; } drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); if (!drvdata) return -ENOMEM; - drvdata->dev = &adev->dev; - drvdata->atclk = devm_clk_get(&adev->dev, "atclk"); /* optional */ + drvdata->dev = dev; + drvdata->atclk = devm_clk_get(dev, "atclk"); /* optional */ if (!IS_ERR(drvdata->atclk)) { ret = clk_prepare_enable(drvdata->atclk); if (ret) return ret; } - /* Validity for the resource is already checked by the AMBA core */ - base = devm_ioremap_resource(dev, res); - if (IS_ERR(base)) { - ret = PTR_ERR(base); - goto out_disable_clk; + /* + * Map the device base for dynamic-replicator, which has been + * validated by AMBA core + */ + if (res) { + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) { + ret = PTR_ERR(base); + goto out_disable_clk; + } + drvdata->base = base; + desc.groups = replicator_groups; } - drvdata->base = base; dev_set_drvdata(dev, drvdata); desc.type = CORESIGHT_DEV_TYPE_LINK; desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT; desc.ops = &replicator_cs_ops; - desc.pdata = adev->dev.platform_data; - desc.dev = &adev->dev; - desc.groups = replicator_groups; + desc.pdata = dev->platform_data; + desc.dev = dev; drvdata->csdev = coresight_register(&desc); if (IS_ERR(drvdata->csdev)) { @@ -201,8 +217,8 @@ static int replicator_probe(struct amba_device *adev, const struct amba_id *id) goto out_disable_clk; } - replicator_reset(drvdata); - pm_runtime_put(&adev->dev); + dynamic_replicator_reset(drvdata); + pm_runtime_put(dev); out_disable_clk: if (ret && !IS_ERR_OR_NULL(drvdata->atclk)) @@ -210,10 +226,16 @@ static int replicator_probe(struct amba_device *adev, const struct amba_id *id) return ret; } +static int dynamic_replicator_probe(struct amba_device *adev, + const struct amba_id *id) +{ + return replicator_probe(&adev->dev, &adev->res); +} + #ifdef CONFIG_PM static int replicator_runtime_suspend(struct device *dev) { - struct replicator_state *drvdata = dev_get_drvdata(dev); + struct replicator_drvdata *drvdata = dev_get_drvdata(dev); if (drvdata && !IS_ERR(drvdata->atclk)) clk_disable_unprepare(drvdata->atclk); @@ -223,7 +245,7 @@ static int replicator_runtime_suspend(struct device *dev) static int replicator_runtime_resume(struct device *dev) { - struct replicator_state *drvdata = dev_get_drvdata(dev); + struct replicator_drvdata *drvdata = dev_get_drvdata(dev); if (drvdata && !IS_ERR(drvdata->atclk)) clk_prepare_enable(drvdata->atclk); @@ -238,7 +260,7 @@ static const struct dev_pm_ops replicator_dev_pm_ops = { NULL) }; -static const struct amba_id replicator_ids[] = { +static const struct amba_id dynamic_replicator_ids[] = { { .id = 0x000bb909, .mask = 0x000fffff, @@ -251,13 +273,13 @@ static const struct amba_id replicator_ids[] = { { 0, 0 }, }; -static struct amba_driver replicator_driver = { +static struct amba_driver dynamic_replicator_driver = { .drv = { .name = "coresight-dynamic-replicator", .pm = &replicator_dev_pm_ops, .suppress_bind_attrs = true, }, - .probe = replicator_probe, - .id_table = replicator_ids, + .probe = dynamic_replicator_probe, + .id_table = dynamic_replicator_ids, }; -builtin_amba_driver(replicator_driver); +builtin_amba_driver(dynamic_replicator_driver); From 455328b1772a190e27fe7ef3a2416dfee6234317 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 25 Apr 2019 13:52:45 -0600 Subject: [PATCH 157/255] coresight: Merge the static and dynamic replicator drivers Merge the drivers for the two varieties of replicators into a singel one. The dynamic replicator has programming base which can be programmed to filter the trace data. The driver detects the type based on the "base" address value of the device, which is NULL for the static device. Also, while at it, remove the now obsolete DYNAMIC_REPLICATOR config entry. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/Kconfig | 8 - drivers/hwtracing/coresight/Makefile | 1 - .../coresight/coresight-dynamic-replicator.c | 285 ------------------ .../coresight/coresight-replicator.c | 174 ++++++++++- 4 files changed, 169 insertions(+), 299 deletions(-) delete mode 100644 drivers/hwtracing/coresight/coresight-dynamic-replicator.c diff --git a/drivers/hwtracing/coresight/Kconfig b/drivers/hwtracing/coresight/Kconfig index ad34380cac49..a40d796f0a4b 100644 --- a/drivers/hwtracing/coresight/Kconfig +++ b/drivers/hwtracing/coresight/Kconfig @@ -81,14 +81,6 @@ config CORESIGHT_SOURCE_ETM4X for instruction level tracing. Depending on the implemented version data tracing may also be available. -config CORESIGHT_DYNAMIC_REPLICATOR - bool "CoreSight Programmable Replicator driver" - depends on CORESIGHT_LINKS_AND_SINKS - help - This enables support for dynamic CoreSight replicator link driver. - The programmable ATB replicator allows independent filtering of the - trace data based on the traceid. - config CORESIGHT_STM bool "CoreSight System Trace Macrocell driver" depends on (ARM && !(CPU_32v3 || CPU_32v4 || CPU_32v4T)) || ARM64 diff --git a/drivers/hwtracing/coresight/Makefile b/drivers/hwtracing/coresight/Makefile index 41870ded51a3..3b435aa42af5 100644 --- a/drivers/hwtracing/coresight/Makefile +++ b/drivers/hwtracing/coresight/Makefile @@ -15,7 +15,6 @@ obj-$(CONFIG_CORESIGHT_SOURCE_ETM3X) += coresight-etm3x.o coresight-etm-cp14.o \ coresight-etm3x-sysfs.o obj-$(CONFIG_CORESIGHT_SOURCE_ETM4X) += coresight-etm4x.o \ coresight-etm4x-sysfs.o -obj-$(CONFIG_CORESIGHT_DYNAMIC_REPLICATOR) += coresight-dynamic-replicator.o obj-$(CONFIG_CORESIGHT_STM) += coresight-stm.o obj-$(CONFIG_CORESIGHT_CPU_DEBUG) += coresight-cpu-debug.o obj-$(CONFIG_CORESIGHT_CATU) += coresight-catu.o diff --git a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c b/drivers/hwtracing/coresight/coresight-dynamic-replicator.c deleted file mode 100644 index b7d7c4146f9a..000000000000 --- a/drivers/hwtracing/coresight/coresight-dynamic-replicator.c +++ /dev/null @@ -1,285 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved. - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "coresight-priv.h" - -#define REPLICATOR_IDFILTER0 0x000 -#define REPLICATOR_IDFILTER1 0x004 - -/** - * struct replicator_drvdata - specifics associated to a replicator component - * @base: memory mapped base address for this component. - * @dev: the device entity associated with this component - * @atclk: optional clock for the core parts of the replicator. - * @csdev: component vitals needed by the framework - */ -struct replicator_drvdata { - void __iomem *base; - struct device *dev; - struct clk *atclk; - struct coresight_device *csdev; -}; - -/* - * dynamic_replicator_reset : Reset the replicator configuration to sane values. - */ -static void dynamic_replicator_reset(struct replicator_drvdata *drvdata) -{ - CS_UNLOCK(drvdata->base); - - if (!coresight_claim_device_unlocked(drvdata->base)) { - writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER0); - writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER1); - coresight_disclaim_device_unlocked(drvdata->base); - } - - CS_LOCK(drvdata->base); -} - -static int dynamic_replicator_enable(struct replicator_drvdata *drvdata, - int inport, int outport) -{ - int rc = 0; - u32 reg; - - switch (outport) { - case 0: - reg = REPLICATOR_IDFILTER0; - break; - case 1: - reg = REPLICATOR_IDFILTER1; - break; - default: - WARN_ON(1); - return -EINVAL; - } - - CS_UNLOCK(drvdata->base); - - if ((readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0) == 0xff) && - (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff)) - rc = coresight_claim_device_unlocked(drvdata->base); - - /* Ensure that the outport is enabled. */ - if (!rc) - writel_relaxed(0x00, drvdata->base + reg); - CS_LOCK(drvdata->base); - - return rc; -} - -static int replicator_enable(struct coresight_device *csdev, int inport, - int outport) -{ - int rc = 0; - struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - rc = dynamic_replicator_enable(drvdata, inport, outport); - dev_dbg(drvdata->dev, "REPLICATOR enabled\n"); - return rc; -} - -static void dynamic_replicator_disable(struct replicator_drvdata *drvdata, - int inport, int outport) -{ - u32 reg; - - switch (outport) { - case 0: - reg = REPLICATOR_IDFILTER0; - break; - case 1: - reg = REPLICATOR_IDFILTER1; - break; - default: - WARN_ON(1); - return; - } - - CS_UNLOCK(drvdata->base); - - /* disable the flow of ATB data through port */ - writel_relaxed(0xff, drvdata->base + reg); - - if ((readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0) == 0xff) && - (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff)) - coresight_disclaim_device_unlocked(drvdata->base); - CS_LOCK(drvdata->base); -} - -static void replicator_disable(struct coresight_device *csdev, int inport, - int outport) -{ - struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - - dynamic_replicator_disable(drvdata, inport, outport); - dev_dbg(drvdata->dev, "REPLICATOR disabled\n"); -} - -static const struct coresight_ops_link replicator_link_ops = { - .enable = replicator_enable, - .disable = replicator_disable, -}; - -static const struct coresight_ops replicator_cs_ops = { - .link_ops = &replicator_link_ops, -}; - -#define coresight_replicator_reg(name, offset) \ - coresight_simple_reg32(struct replicator_drvdata, name, offset) - -coresight_replicator_reg(idfilter0, REPLICATOR_IDFILTER0); -coresight_replicator_reg(idfilter1, REPLICATOR_IDFILTER1); - -static struct attribute *replicator_mgmt_attrs[] = { - &dev_attr_idfilter0.attr, - &dev_attr_idfilter1.attr, - NULL, -}; - -static const struct attribute_group replicator_mgmt_group = { - .attrs = replicator_mgmt_attrs, - .name = "mgmt", -}; - -static const struct attribute_group *replicator_groups[] = { - &replicator_mgmt_group, - NULL, -}; - -static int replicator_probe(struct device *dev, struct resource *res) -{ - int ret = 0; - struct coresight_platform_data *pdata = NULL; - struct replicator_drvdata *drvdata; - struct coresight_desc desc = { 0 }; - struct device_node *np = dev->of_node; - void __iomem *base; - - if (np) { - pdata = of_get_coresight_platform_data(dev, np); - if (IS_ERR(pdata)) - return PTR_ERR(pdata); - dev->platform_data = pdata; - } - - drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); - if (!drvdata) - return -ENOMEM; - - drvdata->dev = dev; - drvdata->atclk = devm_clk_get(dev, "atclk"); /* optional */ - if (!IS_ERR(drvdata->atclk)) { - ret = clk_prepare_enable(drvdata->atclk); - if (ret) - return ret; - } - - /* - * Map the device base for dynamic-replicator, which has been - * validated by AMBA core - */ - if (res) { - base = devm_ioremap_resource(dev, res); - if (IS_ERR(base)) { - ret = PTR_ERR(base); - goto out_disable_clk; - } - drvdata->base = base; - desc.groups = replicator_groups; - } - - dev_set_drvdata(dev, drvdata); - - desc.type = CORESIGHT_DEV_TYPE_LINK; - desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_SPLIT; - desc.ops = &replicator_cs_ops; - desc.pdata = dev->platform_data; - desc.dev = dev; - drvdata->csdev = coresight_register(&desc); - - if (IS_ERR(drvdata->csdev)) { - ret = PTR_ERR(drvdata->csdev); - goto out_disable_clk; - } - - dynamic_replicator_reset(drvdata); - pm_runtime_put(dev); - -out_disable_clk: - if (ret && !IS_ERR_OR_NULL(drvdata->atclk)) - clk_disable_unprepare(drvdata->atclk); - return ret; -} - -static int dynamic_replicator_probe(struct amba_device *adev, - const struct amba_id *id) -{ - return replicator_probe(&adev->dev, &adev->res); -} - -#ifdef CONFIG_PM -static int replicator_runtime_suspend(struct device *dev) -{ - struct replicator_drvdata *drvdata = dev_get_drvdata(dev); - - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_disable_unprepare(drvdata->atclk); - - return 0; -} - -static int replicator_runtime_resume(struct device *dev) -{ - struct replicator_drvdata *drvdata = dev_get_drvdata(dev); - - if (drvdata && !IS_ERR(drvdata->atclk)) - clk_prepare_enable(drvdata->atclk); - - return 0; -} -#endif - -static const struct dev_pm_ops replicator_dev_pm_ops = { - SET_RUNTIME_PM_OPS(replicator_runtime_suspend, - replicator_runtime_resume, - NULL) -}; - -static const struct amba_id dynamic_replicator_ids[] = { - { - .id = 0x000bb909, - .mask = 0x000fffff, - }, - { - /* Coresight SoC-600 */ - .id = 0x000bb9ec, - .mask = 0x000fffff, - }, - { 0, 0 }, -}; - -static struct amba_driver dynamic_replicator_driver = { - .drv = { - .name = "coresight-dynamic-replicator", - .pm = &replicator_dev_pm_ops, - .suppress_bind_attrs = true, - }, - .probe = dynamic_replicator_probe, - .id_table = dynamic_replicator_ids, -}; -builtin_amba_driver(dynamic_replicator_driver); diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c index 43cbcf1e7be8..4e0da85efd2d 100644 --- a/drivers/hwtracing/coresight/coresight-replicator.c +++ b/drivers/hwtracing/coresight/coresight-replicator.c @@ -1,10 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright (c) 2011-2012, The Linux Foundation. All rights reserved. + * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved. * * Description: CoreSight Replicator driver */ +#include #include #include #include @@ -18,25 +19,117 @@ #include "coresight-priv.h" +#define REPLICATOR_IDFILTER0 0x000 +#define REPLICATOR_IDFILTER1 0x004 + /** * struct replicator_drvdata - specifics associated to a replicator component + * @base: memory mapped base address for this component. Also indicates + * whether this one is programmable or not. * @dev: the device entity associated with this component * @atclk: optional clock for the core parts of the replicator. * @csdev: component vitals needed by the framework */ struct replicator_drvdata { + void __iomem *base; struct device *dev; struct clk *atclk; struct coresight_device *csdev; }; +static void dynamic_replicator_reset(struct replicator_drvdata *drvdata) +{ + CS_UNLOCK(drvdata->base); + + if (!coresight_claim_device_unlocked(drvdata->base)) { + writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER0); + writel_relaxed(0xff, drvdata->base + REPLICATOR_IDFILTER1); + coresight_disclaim_device_unlocked(drvdata->base); + } + + CS_LOCK(drvdata->base); +} + +/* + * replicator_reset : Reset the replicator configuration to sane values. + */ +static inline void replicator_reset(struct replicator_drvdata *drvdata) +{ + if (drvdata->base) + dynamic_replicator_reset(drvdata); +} + +static int dynamic_replicator_enable(struct replicator_drvdata *drvdata, + int inport, int outport) +{ + int rc = 0; + u32 reg; + + switch (outport) { + case 0: + reg = REPLICATOR_IDFILTER0; + break; + case 1: + reg = REPLICATOR_IDFILTER1; + break; + default: + WARN_ON(1); + return -EINVAL; + } + + CS_UNLOCK(drvdata->base); + + if ((readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0) == 0xff) && + (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff)) + rc = coresight_claim_device_unlocked(drvdata->base); + + /* Ensure that the outport is enabled. */ + if (!rc) + writel_relaxed(0x00, drvdata->base + reg); + CS_LOCK(drvdata->base); + + return rc; +} + static int replicator_enable(struct coresight_device *csdev, int inport, int outport) { + int rc = 0; struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - dev_dbg(drvdata->dev, "REPLICATOR enabled\n"); - return 0; + if (drvdata->base) + rc = dynamic_replicator_enable(drvdata, inport, outport); + if (!rc) + dev_dbg(drvdata->dev, "REPLICATOR enabled\n"); + return rc; +} + +static void dynamic_replicator_disable(struct replicator_drvdata *drvdata, + int inport, int outport) +{ + u32 reg; + + switch (outport) { + case 0: + reg = REPLICATOR_IDFILTER0; + break; + case 1: + reg = REPLICATOR_IDFILTER1; + break; + default: + WARN_ON(1); + return; + } + + CS_UNLOCK(drvdata->base); + + /* disable the flow of ATB data through port */ + writel_relaxed(0xff, drvdata->base + reg); + + if ((readl_relaxed(drvdata->base + REPLICATOR_IDFILTER0) == 0xff) && + (readl_relaxed(drvdata->base + REPLICATOR_IDFILTER1) == 0xff)) + coresight_disclaim_device_unlocked(drvdata->base); + CS_LOCK(drvdata->base); } static void replicator_disable(struct coresight_device *csdev, int inport, @@ -44,6 +137,8 @@ static void replicator_disable(struct coresight_device *csdev, int inport, { struct replicator_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + if (drvdata->base) + dynamic_replicator_disable(drvdata, inport, outport); dev_dbg(drvdata->dev, "REPLICATOR disabled\n"); } @@ -56,13 +151,36 @@ static const struct coresight_ops replicator_cs_ops = { .link_ops = &replicator_link_ops, }; -static int replicator_probe(struct device *dev) +#define coresight_replicator_reg(name, offset) \ + coresight_simple_reg32(struct replicator_drvdata, name, offset) + +coresight_replicator_reg(idfilter0, REPLICATOR_IDFILTER0); +coresight_replicator_reg(idfilter1, REPLICATOR_IDFILTER1); + +static struct attribute *replicator_mgmt_attrs[] = { + &dev_attr_idfilter0.attr, + &dev_attr_idfilter1.attr, + NULL, +}; + +static const struct attribute_group replicator_mgmt_group = { + .attrs = replicator_mgmt_attrs, + .name = "mgmt", +}; + +static const struct attribute_group *replicator_groups[] = { + &replicator_mgmt_group, + NULL, +}; + +static int replicator_probe(struct device *dev, struct resource *res) { int ret = 0; struct coresight_platform_data *pdata = NULL; struct replicator_drvdata *drvdata; struct coresight_desc desc = { 0 }; struct device_node *np = dev->of_node; + void __iomem *base; if (np) { pdata = of_get_coresight_platform_data(dev, np); @@ -83,6 +201,20 @@ static int replicator_probe(struct device *dev) return ret; } + /* + * Map the device base for dynamic-replicator, which has been + * validated by AMBA core + */ + if (res) { + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) { + ret = PTR_ERR(base); + goto out_disable_clk; + } + drvdata->base = base; + desc.groups = replicator_groups; + } + dev_set_drvdata(dev, drvdata); desc.type = CORESIGHT_DEV_TYPE_LINK; @@ -96,6 +228,7 @@ static int replicator_probe(struct device *dev) goto out_disable_clk; } + replicator_reset(drvdata); pm_runtime_put(dev); out_disable_clk: @@ -112,7 +245,8 @@ static int static_replicator_probe(struct platform_device *pdev) pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); - ret = replicator_probe(&pdev->dev); + /* Static replicators do not have programming base */ + ret = replicator_probe(&pdev->dev, NULL); if (ret) { pm_runtime_put_noidle(&pdev->dev); @@ -164,3 +298,33 @@ static struct platform_driver static_replicator_driver = { }, }; builtin_platform_driver(static_replicator_driver); + +static int dynamic_replicator_probe(struct amba_device *adev, + const struct amba_id *id) +{ + return replicator_probe(&adev->dev, &adev->res); +} + +static const struct amba_id dynamic_replicator_ids[] = { + { + .id = 0x000bb909, + .mask = 0x000fffff, + }, + { + /* Coresight SoC-600 */ + .id = 0x000bb9ec, + .mask = 0x000fffff, + }, + { 0, 0 }, +}; + +static struct amba_driver dynamic_replicator_driver = { + .drv = { + .name = "coresight-dynamic-replicator", + .pm = &replicator_dev_pm_ops, + .suppress_bind_attrs = true, + }, + .probe = dynamic_replicator_probe, + .id_table = dynamic_replicator_ids, +}; +builtin_amba_driver(dynamic_replicator_driver); From 1b015ef28a443a89985db2a67080bf7c660d66d2 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 25 Apr 2019 13:52:46 -0600 Subject: [PATCH 158/255] coresight: Fix freeing up the coresight connections With commit c2c729415b2d2132 ("coresight: platform: Cleanup coresight connection handling"), we switched to re-using coresight_connections for the coresight_device. However, that introduced a mismatch in the alloc/free of the connections. The allocation is made using devm_*, while we use kfree() to release the memory when a device is released (even though we don't support this at the moment). Fix this by leaving it to the automatic freeing of the memory. Fixes: c2c729415b2d2132 ("coresight: platform: Cleanup coresight connection handling") Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index 29cef898afba..55204dd47479 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -973,7 +973,6 @@ static void coresight_device_release(struct device *dev) { struct coresight_device *csdev = to_coresight_device(dev); - kfree(csdev->conns); kfree(csdev->refcnt); kfree(csdev); } From 850ccfe3e891b668605a663c7024c3f187443c76 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 25 Apr 2019 13:52:47 -0600 Subject: [PATCH 159/255] coresight: etb10: Cleanup power management We drop the power before we complete the probe successfully. We are supposed to drop it only when we are successful. Also, probing the etb_buffer_length happens with the power turned up. So we don't need to do that again in the helper. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etb10.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 105782ea64c7..13c0a601d3be 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -93,17 +93,9 @@ struct etb_drvdata { static int etb_set_buffer(struct coresight_device *csdev, struct perf_output_handle *handle); -static unsigned int etb_get_buffer_depth(struct etb_drvdata *drvdata) +static inline unsigned int etb_get_buffer_depth(struct etb_drvdata *drvdata) { - u32 depth = 0; - - pm_runtime_get_sync(drvdata->dev); - - /* RO registers don't need locking */ - depth = readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG); - - pm_runtime_put(drvdata->dev); - return depth; + return readl_relaxed(drvdata->base + ETB_RAM_DEPTH_REG); } static void __etb_enable_hw(struct etb_drvdata *drvdata) @@ -720,7 +712,6 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id) spin_lock_init(&drvdata->spinlock); drvdata->buffer_depth = etb_get_buffer_depth(drvdata); - pm_runtime_put(&adev->dev); if (drvdata->buffer_depth & 0x80000000) return -EINVAL; @@ -747,6 +738,7 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id) if (ret) goto err_misc_register; + pm_runtime_put(&adev->dev); return 0; err_misc_register: From 0bfc53b30eacbc5623f4981e04a55d3ad9393a87 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 25 Apr 2019 13:52:48 -0600 Subject: [PATCH 160/255] coresight: tpiu: Cleanup power management Drop the power only when we have successfully probed. Otherwise leave it to the amba probe to do the rest. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose [Removed extra newline left after original modification] Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-tpiu.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c index b2f72a1fa402..93e2ef34e734 100644 --- a/drivers/hwtracing/coresight/coresight-tpiu.c +++ b/drivers/hwtracing/coresight/coresight-tpiu.c @@ -153,8 +153,6 @@ static int tpiu_probe(struct amba_device *adev, const struct amba_id *id) /* Disable tpiu to support older devices */ tpiu_disable_hw(drvdata); - pm_runtime_put(&adev->dev); - desc.type = CORESIGHT_DEV_TYPE_SINK; desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_PORT; desc.ops = &tpiu_cs_ops; @@ -162,7 +160,12 @@ static int tpiu_probe(struct amba_device *adev, const struct amba_id *id) desc.dev = dev; drvdata->csdev = coresight_register(&desc); - return PTR_ERR_OR_ZERO(drvdata->csdev); + if (!IS_ERR(drvdata->csdev)) { + pm_runtime_put(&adev->dev); + return 0; + } + + return PTR_ERR(drvdata->csdev); } #ifdef CONFIG_PM From 2390d4586475e2e4fdff1ad281fb33e73b41b5cc Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 25 Apr 2019 13:52:49 -0600 Subject: [PATCH 161/255] coresight: catu: Cleanup power management Drop the power handle only if we were successful. Otherwise the AMBA bus code would do the rest. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-catu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/hwtracing/coresight/coresight-catu.c b/drivers/hwtracing/coresight/coresight-catu.c index 057627a0753d..4ea68a3522e9 100644 --- a/drivers/hwtracing/coresight/coresight-catu.c +++ b/drivers/hwtracing/coresight/coresight-catu.c @@ -557,8 +557,9 @@ static int catu_probe(struct amba_device *adev, const struct amba_id *id) drvdata->csdev = coresight_register(&catu_desc); if (IS_ERR(drvdata->csdev)) ret = PTR_ERR(drvdata->csdev); + else + pm_runtime_put(&adev->dev); out: - pm_runtime_put(&adev->dev); return ret; } From 263556950f2ad764bad4f98fbc5a9d711fd653a6 Mon Sep 17 00:00:00 2001 From: Suzuki K Poulose Date: Thu, 25 Apr 2019 13:52:50 -0600 Subject: [PATCH 162/255] coresight: tmc: Cleanup power management Drop the power only if we were successful in probing the device. Cc: Mathieu Poirier Signed-off-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-tmc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c index 647b6aa93554..c6a5462ebf27 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.c +++ b/drivers/hwtracing/coresight/coresight-tmc.c @@ -432,8 +432,6 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) drvdata->size = readl_relaxed(drvdata->base + TMC_RSZ) * 4; } - pm_runtime_put(&adev->dev); - desc.pdata = pdata; desc.dev = dev; desc.groups = coresight_tmc_groups; @@ -476,6 +474,8 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) ret = misc_register(&drvdata->miscdev); if (ret) coresight_unregister(drvdata->csdev); + else + pm_runtime_put(&adev->dev); out: return ret; } From 6fcdba33ab0d43e5fcb557897c1c81541927f615 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:52:51 -0600 Subject: [PATCH 163/255] coresight: pmu: Adding ITRACE property to cs_etm PMU Add to the capabilities the ITRACE property so that ITRACE START events are generated when the PMU is switched on by the core. Signed-off-by: Mathieu Poirier Acked-by: Suzuki K Poulose Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etm-perf.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 4d5a2b9f9d6a..25ae56e924bb 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -566,7 +566,8 @@ static int __init etm_perf_init(void) { int ret; - etm_pmu.capabilities = PERF_PMU_CAP_EXCLUSIVE; + etm_pmu.capabilities = (PERF_PMU_CAP_EXCLUSIVE | + PERF_PMU_CAP_ITRACE); etm_pmu.attr_groups = etm_pmu_attr_groups; etm_pmu.task_ctx_nr = perf_sw_context; From 82500a810ee26ac542d128499d7adae163e61adb Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:52:52 -0600 Subject: [PATCH 164/255] coresight: etm4x: Add kernel configuration for CONTEXTID Set the proper bit in the configuration register when contextID tracing has been requested by user space. That way PE_CONTEXT elements are generated by the tracers when a process is installed on a CPU. Signed-off-by: Mathieu Poirier Reviewed-by: Suzuki K Poulose Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/Kconfig | 1 + drivers/hwtracing/coresight/coresight-etm-perf.c | 2 ++ drivers/hwtracing/coresight/coresight-etm4x.c | 5 +++++ include/linux/coresight-pmu.h | 2 ++ tools/include/linux/coresight-pmu.h | 2 ++ 5 files changed, 12 insertions(+) diff --git a/drivers/hwtracing/coresight/Kconfig b/drivers/hwtracing/coresight/Kconfig index a40d796f0a4b..18e8d03321d6 100644 --- a/drivers/hwtracing/coresight/Kconfig +++ b/drivers/hwtracing/coresight/Kconfig @@ -75,6 +75,7 @@ config CORESIGHT_SOURCE_ETM4X bool "CoreSight Embedded Trace Macrocell 4.x driver" depends on ARM64 select CORESIGHT_LINKS_AND_SINKS + select PID_IN_CONTEXTIDR help This driver provides support for the ETM4.x tracer module, tracing the instructions that a processor is executing. This is primarily useful diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 25ae56e924bb..bbfed70b3402 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -29,6 +29,7 @@ static DEFINE_PER_CPU(struct coresight_device *, csdev_src); /* ETMv3.5/PTM's ETMCR is 'config' */ PMU_FORMAT_ATTR(cycacc, "config:" __stringify(ETM_OPT_CYCACC)); +PMU_FORMAT_ATTR(contextid, "config:" __stringify(ETM_OPT_CTXTID)); PMU_FORMAT_ATTR(timestamp, "config:" __stringify(ETM_OPT_TS)); PMU_FORMAT_ATTR(retstack, "config:" __stringify(ETM_OPT_RETSTK)); /* Sink ID - same for all ETMs */ @@ -36,6 +37,7 @@ PMU_FORMAT_ATTR(sinkid, "config2:0-31"); static struct attribute *etm_config_formats_attr[] = { &format_attr_cycacc.attr, + &format_attr_contextid.attr, &format_attr_timestamp.attr, &format_attr_retstack.attr, &format_attr_sinkid.attr, diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c index 08ce37c9475d..732ae12fca9b 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.c +++ b/drivers/hwtracing/coresight/coresight-etm4x.c @@ -239,6 +239,11 @@ static int etm4_parse_event_config(struct etmv4_drvdata *drvdata, if (attr->config & BIT(ETM_OPT_TS)) /* bit[11], Global timestamp tracing bit */ config->cfg |= BIT(11); + + if (attr->config & BIT(ETM_OPT_CTXTID)) + /* bit[6], Context ID tracing bit */ + config->cfg |= BIT(ETM4_CFG_BIT_CTXTID); + /* return stack - enable if selected and supported */ if ((attr->config & BIT(ETM_OPT_RETSTK)) && drvdata->retstack) /* bit[12], Return stack enable bit */ diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h index a1a959ba24ff..b0e35eec6499 100644 --- a/include/linux/coresight-pmu.h +++ b/include/linux/coresight-pmu.h @@ -12,11 +12,13 @@ /* ETMv3.5/PTM's ETMCR config bit */ #define ETM_OPT_CYCACC 12 +#define ETM_OPT_CTXTID 14 #define ETM_OPT_TS 28 #define ETM_OPT_RETSTK 29 /* ETMv4 CONFIGR programming bits for the ETM OPTs */ #define ETM4_CFG_BIT_CYCACC 4 +#define ETM4_CFG_BIT_CTXTID 6 #define ETM4_CFG_BIT_TS 11 #define ETM4_CFG_BIT_RETSTK 12 diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h index a1a959ba24ff..b0e35eec6499 100644 --- a/tools/include/linux/coresight-pmu.h +++ b/tools/include/linux/coresight-pmu.h @@ -12,11 +12,13 @@ /* ETMv3.5/PTM's ETMCR config bit */ #define ETM_OPT_CYCACC 12 +#define ETM_OPT_CTXTID 14 #define ETM_OPT_TS 28 #define ETM_OPT_RETSTK 29 /* ETMv4 CONFIGR programming bits for the ETM OPTs */ #define ETM4_CFG_BIT_CYCACC 4 +#define ETM4_CFG_BIT_CTXTID 6 #define ETM4_CFG_BIT_TS 11 #define ETM4_CFG_BIT_RETSTK 12 From 8013f32a1b352f810cc2acfb00317df2ae3c5dee Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:52:53 -0600 Subject: [PATCH 165/255] coresight: etm4x: Skip selector pair 0 Resource selector pair 0 is always implemented and reserved. As such it should not be explicitly programmed. Signed-off-by: Mathieu Poirier Reviewed-by: Suzuki K Poulose Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etm4x.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c index 732ae12fca9b..d64192c29860 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.c +++ b/drivers/hwtracing/coresight/coresight-etm4x.c @@ -138,8 +138,11 @@ static int etm4_enable_hw(struct etmv4_drvdata *drvdata) drvdata->base + TRCCNTVRn(i)); } - /* Resource selector pair 0 is always implemented and reserved */ - for (i = 0; i < drvdata->nr_resource * 2; i++) + /* + * Resource selector pair 0 is always implemented and reserved. As + * such start at 2. + */ + for (i = 2; i < drvdata->nr_resource * 2; i++) writel_relaxed(config->res_ctrl[i], drvdata->base + TRCRSCTLRn(i)); From a54e14f810f257d782ddf2fde1df5f3819e612a8 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:52:54 -0600 Subject: [PATCH 166/255] coresight: etm4x: Configure tracers to emit timestamps Configure timestamps to be emitted at regular intervals in the trace stream to temporally correlate instructions executed on different CPUs. Signed-off-by: Mathieu Poirier Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etm4x.c | 102 +++++++++++++++++- 1 file changed, 101 insertions(+), 1 deletion(-) diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c index d64192c29860..8bb0092c7ec2 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.c +++ b/drivers/hwtracing/coresight/coresight-etm4x.c @@ -204,6 +204,91 @@ static void etm4_enable_hw_smp_call(void *info) arg->rc = etm4_enable_hw(arg->drvdata); } +/* + * The goal of function etm4_config_timestamp_event() is to configure a + * counter that will tell the tracer to emit a timestamp packet when it + * reaches zero. This is done in order to get a more fine grained idea + * of when instructions are executed so that they can be correlated + * with execution on other CPUs. + * + * To do this the counter itself is configured to self reload and + * TRCRSCTLR1 (always true) used to get the counter to decrement. From + * there a resource selector is configured with the counter and the + * timestamp control register to use the resource selector to trigger the + * event that will insert a timestamp packet in the stream. + */ +static int etm4_config_timestamp_event(struct etmv4_drvdata *drvdata) +{ + int ctridx, ret = -EINVAL; + int counter, rselector; + u32 val = 0; + struct etmv4_config *config = &drvdata->config; + + /* No point in trying if we don't have at least one counter */ + if (!drvdata->nr_cntr) + goto out; + + /* Find a counter that hasn't been initialised */ + for (ctridx = 0; ctridx < drvdata->nr_cntr; ctridx++) + if (config->cntr_val[ctridx] == 0) + break; + + /* All the counters have been configured already, bail out */ + if (ctridx == drvdata->nr_cntr) { + pr_debug("%s: no available counter found\n", __func__); + ret = -ENOSPC; + goto out; + } + + /* + * Searching for an available resource selector to use, starting at + * '2' since every implementation has at least 2 resource selector. + * ETMIDR4 gives the number of resource selector _pairs_, + * hence multiply by 2. + */ + for (rselector = 2; rselector < drvdata->nr_resource * 2; rselector++) + if (!config->res_ctrl[rselector]) + break; + + if (rselector == drvdata->nr_resource * 2) { + pr_debug("%s: no available resource selector found\n", + __func__); + ret = -ENOSPC; + goto out; + } + + /* Remember what counter we used */ + counter = 1 << ctridx; + + /* + * Initialise original and reload counter value to the smallest + * possible value in order to get as much precision as we can. + */ + config->cntr_val[ctridx] = 1; + config->cntrldvr[ctridx] = 1; + + /* Set the trace counter control register */ + val = 0x1 << 16 | /* Bit 16, reload counter automatically */ + 0x0 << 7 | /* Select single resource selector */ + 0x1; /* Resource selector 1, i.e always true */ + + config->cntr_ctrl[ctridx] = val; + + val = 0x2 << 16 | /* Group 0b0010 - Counter and sequencers */ + counter << 0; /* Counter to use */ + + config->res_ctrl[rselector] = val; + + val = 0x0 << 7 | /* Select single resource selector */ + rselector; /* Resource selector */ + + config->ts_ctrl = val; + + ret = 0; +out: + return ret; +} + static int etm4_parse_event_config(struct etmv4_drvdata *drvdata, struct perf_event *event) { @@ -239,9 +324,24 @@ static int etm4_parse_event_config(struct etmv4_drvdata *drvdata, /* TRM: Must program this for cycacc to work */ config->ccctlr = ETM_CYC_THRESHOLD_DEFAULT; } - if (attr->config & BIT(ETM_OPT_TS)) + if (attr->config & BIT(ETM_OPT_TS)) { + /* + * Configure timestamps to be emitted at regular intervals in + * order to correlate instructions executed on different CPUs + * (CPU-wide trace scenarios). + */ + ret = etm4_config_timestamp_event(drvdata); + + /* + * No need to go further if timestamp intervals can't + * be configured. + */ + if (ret) + goto out; + /* bit[11], Global timestamp tracing bit */ config->cfg |= BIT(11); + } if (attr->config & BIT(ETM_OPT_CTXTID)) /* bit[6], Context ID tracing bit */ From 6c817a95d84b8388e97d4e2b6ee361a660e244e9 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:52:55 -0600 Subject: [PATCH 167/255] coresight: Adding return code to sink::disable() operation In preparation to handle device reference counting inside of the sink drivers, add a return code to the sink::disable() operation so that proper action can be taken if a sink has not been disabled. Signed-off-by: Mathieu Poirier Reviewed-by: Suzuki K Poulose Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etb10.c | 3 ++- drivers/hwtracing/coresight/coresight-tmc-etf.c | 5 +++-- drivers/hwtracing/coresight/coresight-tmc-etr.c | 5 +++-- drivers/hwtracing/coresight/coresight-tpiu.c | 3 ++- drivers/hwtracing/coresight/coresight.c | 6 +++++- include/linux/coresight.h | 2 +- 6 files changed, 16 insertions(+), 8 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 13c0a601d3be..23b049cef19a 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -317,7 +317,7 @@ static void etb_disable_hw(struct etb_drvdata *drvdata) coresight_disclaim_device(drvdata->base); } -static void etb_disable(struct coresight_device *csdev) +static int etb_disable(struct coresight_device *csdev) { struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); unsigned long flags; @@ -332,6 +332,7 @@ static void etb_disable(struct coresight_device *csdev) spin_unlock_irqrestore(&drvdata->spinlock, flags); dev_dbg(drvdata->dev, "ETB disabled\n"); + return 0; } static void *etb_alloc_buffer(struct coresight_device *csdev, int cpu, diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index a5f053f2db2c..d4213e7c2c45 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -273,7 +273,7 @@ static int tmc_enable_etf_sink(struct coresight_device *csdev, return 0; } -static void tmc_disable_etf_sink(struct coresight_device *csdev) +static int tmc_disable_etf_sink(struct coresight_device *csdev) { unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); @@ -281,7 +281,7 @@ static void tmc_disable_etf_sink(struct coresight_device *csdev) spin_lock_irqsave(&drvdata->spinlock, flags); if (drvdata->reading) { spin_unlock_irqrestore(&drvdata->spinlock, flags); - return; + return -EBUSY; } /* Disable the TMC only if it needs to */ @@ -293,6 +293,7 @@ static void tmc_disable_etf_sink(struct coresight_device *csdev) spin_unlock_irqrestore(&drvdata->spinlock, flags); dev_dbg(drvdata->dev, "TMC-ETB/ETF disabled\n"); + return 0; } static int tmc_enable_etf_link(struct coresight_device *csdev, diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index cf7a32ce209d..c6a0f5897684 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -1393,7 +1393,7 @@ static int tmc_enable_etr_sink(struct coresight_device *csdev, return -EINVAL; } -static void tmc_disable_etr_sink(struct coresight_device *csdev) +static int tmc_disable_etr_sink(struct coresight_device *csdev) { unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); @@ -1401,7 +1401,7 @@ static void tmc_disable_etr_sink(struct coresight_device *csdev) spin_lock_irqsave(&drvdata->spinlock, flags); if (drvdata->reading) { spin_unlock_irqrestore(&drvdata->spinlock, flags); - return; + return -EBUSY; } /* Disable the TMC only if it needs to */ @@ -1413,6 +1413,7 @@ static void tmc_disable_etr_sink(struct coresight_device *csdev) spin_unlock_irqrestore(&drvdata->spinlock, flags); dev_dbg(drvdata->dev, "TMC-ETR disabled\n"); + return 0; } static const struct coresight_ops_sink tmc_etr_sink_ops = { diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c index 93e2ef34e734..c1b77e3c3187 100644 --- a/drivers/hwtracing/coresight/coresight-tpiu.c +++ b/drivers/hwtracing/coresight/coresight-tpiu.c @@ -94,13 +94,14 @@ static void tpiu_disable_hw(struct tpiu_drvdata *drvdata) CS_LOCK(drvdata->base); } -static void tpiu_disable(struct coresight_device *csdev) +static int tpiu_disable(struct coresight_device *csdev) { struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); tpiu_disable_hw(drvdata); dev_dbg(drvdata->dev, "TPIU disabled\n"); + return 0; } static const struct coresight_ops_sink tpiu_sink_ops = { diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index 55204dd47479..66c25b0a785e 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -239,9 +239,13 @@ static int coresight_enable_sink(struct coresight_device *csdev, static void coresight_disable_sink(struct coresight_device *csdev) { + int ret; + if (atomic_dec_return(csdev->refcnt) == 0) { if (sink_ops(csdev)->disable) { - sink_ops(csdev)->disable(csdev); + ret = sink_ops(csdev)->disable(csdev); + if (ret) + return; csdev->enable = false; } } diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 7b87965f7a65..189cc6ddc92b 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -192,7 +192,7 @@ struct coresight_device { */ struct coresight_ops_sink { int (*enable)(struct coresight_device *csdev, u32 mode, void *data); - void (*disable)(struct coresight_device *csdev); + int (*disable)(struct coresight_device *csdev); void *(*alloc_buffer)(struct coresight_device *csdev, int cpu, void **pages, int nr_pages, bool overwrite); void (*free_buffer)(void *config); From f973d88b75703719d39c4d5145079199aaf442b2 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:52:56 -0600 Subject: [PATCH 168/255] coresight: Move reference counting inside sink drivers When operating in CPU-wide mode with an N:1 source/sink HW topology, multiple CPUs can access a sink concurrently. As such reference counting needs to happen when the device's spinlock is held to avoid racing with other operations (start(), update(), stop()), such as: session A Session B ----- ------- enable_sink atomic_inc(refcount) = 1 ... atomic_dec(refcount) = 0 enable_sink if (refcount == 0) disable_sink atomic_inc() Signed-off-by: Mathieu Poirier Reviewed-by: Suzuki K Poulose Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etb10.c | 21 ++++++++++---- .../hwtracing/coresight/coresight-tmc-etf.c | 21 +++++++++++--- .../hwtracing/coresight/coresight-tmc-etr.c | 19 +++++++++++-- drivers/hwtracing/coresight/coresight-tpiu.c | 6 +++- drivers/hwtracing/coresight/coresight.c | 28 +++++++++---------- 5 files changed, 66 insertions(+), 29 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 23b049cef19a..8e63863cf950 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -5,6 +5,7 @@ * Description: CoreSight Embedded Trace Buffer driver */ +#include #include #include #include @@ -151,14 +152,15 @@ static int etb_enable_sysfs(struct coresight_device *csdev) goto out; } - /* Nothing to do, the tracer is already enabled. */ - if (drvdata->mode == CS_MODE_SYSFS) - goto out; + if (drvdata->mode == CS_MODE_DISABLED) { + ret = etb_enable_hw(drvdata); + if (ret) + goto out; - ret = etb_enable_hw(drvdata); - if (!ret) drvdata->mode = CS_MODE_SYSFS; + } + atomic_inc(csdev->refcnt); out: spin_unlock_irqrestore(&drvdata->spinlock, flags); return ret; @@ -188,8 +190,10 @@ static int etb_enable_perf(struct coresight_device *csdev, void *data) goto out; ret = etb_enable_hw(drvdata); - if (!ret) + if (!ret) { drvdata->mode = CS_MODE_PERF; + atomic_inc(csdev->refcnt); + } out: spin_unlock_irqrestore(&drvdata->spinlock, flags); @@ -324,6 +328,11 @@ static int etb_disable(struct coresight_device *csdev) spin_lock_irqsave(&drvdata->spinlock, flags); + if (atomic_dec_return(csdev->refcnt)) { + spin_unlock_irqrestore(&drvdata->spinlock, flags); + return -EBUSY; + } + /* Disable the ETB only if it needs to */ if (drvdata->mode != CS_MODE_DISABLED) { etb_disable_hw(drvdata); diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index d4213e7c2c45..d50a608a60f1 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -4,6 +4,7 @@ * Author: Mathieu Poirier */ +#include #include #include #include @@ -180,8 +181,10 @@ static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev) * sink is already enabled no memory is needed and the HW need not be * touched. */ - if (drvdata->mode == CS_MODE_SYSFS) + if (drvdata->mode == CS_MODE_SYSFS) { + atomic_inc(csdev->refcnt); goto out; + } /* * If drvdata::buf isn't NULL, memory was allocated for a previous @@ -200,11 +203,13 @@ static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev) } ret = tmc_etb_enable_hw(drvdata); - if (!ret) + if (!ret) { drvdata->mode = CS_MODE_SYSFS; - else + atomic_inc(csdev->refcnt); + } else { /* Free up the buffer if we failed to enable */ used = false; + } out: spin_unlock_irqrestore(&drvdata->spinlock, flags); @@ -239,8 +244,10 @@ static int tmc_enable_etf_sink_perf(struct coresight_device *csdev, void *data) if (ret) break; ret = tmc_etb_enable_hw(drvdata); - if (!ret) + if (!ret) { drvdata->mode = CS_MODE_PERF; + atomic_inc(csdev->refcnt); + } } while (0); spin_unlock_irqrestore(&drvdata->spinlock, flags); @@ -279,11 +286,17 @@ static int tmc_disable_etf_sink(struct coresight_device *csdev) struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); spin_lock_irqsave(&drvdata->spinlock, flags); + if (drvdata->reading) { spin_unlock_irqrestore(&drvdata->spinlock, flags); return -EBUSY; } + if (atomic_dec_return(csdev->refcnt)) { + spin_unlock_irqrestore(&drvdata->spinlock, flags); + return -EBUSY; + } + /* Disable the TMC only if it needs to */ if (drvdata->mode != CS_MODE_DISABLED) { tmc_etb_disable_hw(drvdata); diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index c6a0f5897684..6a8f39d03de3 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -4,6 +4,7 @@ * Author: Mathieu Poirier */ +#include #include #include #include @@ -1125,8 +1126,10 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev) * sink is already enabled no memory is needed and the HW need not be * touched, even if the buffer size has changed. */ - if (drvdata->mode == CS_MODE_SYSFS) + if (drvdata->mode == CS_MODE_SYSFS) { + atomic_inc(csdev->refcnt); goto out; + } /* * If we don't have a buffer or it doesn't match the requested size, @@ -1139,8 +1142,10 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev) } ret = tmc_etr_enable_hw(drvdata, drvdata->sysfs_buf); - if (!ret) + if (!ret) { drvdata->mode = CS_MODE_SYSFS; + atomic_inc(csdev->refcnt); + } out: spin_unlock_irqrestore(&drvdata->spinlock, flags); @@ -1371,8 +1376,10 @@ static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data) etr_perf->head = PERF_IDX2OFF(handle->head, etr_perf); drvdata->perf_data = etr_perf; rc = tmc_etr_enable_hw(drvdata, etr_perf->etr_buf); - if (!rc) + if (!rc) { drvdata->mode = CS_MODE_PERF; + atomic_inc(csdev->refcnt); + } unlock_out: spin_unlock_irqrestore(&drvdata->spinlock, flags); @@ -1399,11 +1406,17 @@ static int tmc_disable_etr_sink(struct coresight_device *csdev) struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); spin_lock_irqsave(&drvdata->spinlock, flags); + if (drvdata->reading) { spin_unlock_irqrestore(&drvdata->spinlock, flags); return -EBUSY; } + if (atomic_dec_return(csdev->refcnt)) { + spin_unlock_irqrestore(&drvdata->spinlock, flags); + return -EBUSY; + } + /* Disable the TMC only if it needs to */ if (drvdata->mode != CS_MODE_DISABLED) { tmc_etr_disable_hw(drvdata); diff --git a/drivers/hwtracing/coresight/coresight-tpiu.c b/drivers/hwtracing/coresight/coresight-tpiu.c index c1b77e3c3187..63d9af31f57f 100644 --- a/drivers/hwtracing/coresight/coresight-tpiu.c +++ b/drivers/hwtracing/coresight/coresight-tpiu.c @@ -5,6 +5,7 @@ * Description: CoreSight Trace Port Interface Unit driver */ +#include #include #include #include @@ -73,7 +74,7 @@ static int tpiu_enable(struct coresight_device *csdev, u32 mode, void *__unused) struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); tpiu_enable_hw(drvdata); - + atomic_inc(csdev->refcnt); dev_dbg(drvdata->dev, "TPIU enabled\n"); return 0; } @@ -98,6 +99,9 @@ static int tpiu_disable(struct coresight_device *csdev) { struct tpiu_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + if (atomic_dec_return(csdev->refcnt)) + return -EBUSY; + tpiu_disable_hw(drvdata); dev_dbg(drvdata->dev, "TPIU disabled\n"); diff --git a/drivers/hwtracing/coresight/coresight.c b/drivers/hwtracing/coresight/coresight.c index 66c25b0a785e..4b130281236a 100644 --- a/drivers/hwtracing/coresight/coresight.c +++ b/drivers/hwtracing/coresight/coresight.c @@ -225,14 +225,13 @@ static int coresight_enable_sink(struct coresight_device *csdev, * We need to make sure the "new" session is compatible with the * existing "mode" of operation. */ - if (sink_ops(csdev)->enable) { - ret = sink_ops(csdev)->enable(csdev, mode, data); - if (ret) - return ret; - csdev->enable = true; - } + if (!sink_ops(csdev)->enable) + return -EINVAL; - atomic_inc(csdev->refcnt); + ret = sink_ops(csdev)->enable(csdev, mode, data); + if (ret) + return ret; + csdev->enable = true; return 0; } @@ -241,14 +240,13 @@ static void coresight_disable_sink(struct coresight_device *csdev) { int ret; - if (atomic_dec_return(csdev->refcnt) == 0) { - if (sink_ops(csdev)->disable) { - ret = sink_ops(csdev)->disable(csdev); - if (ret) - return; - csdev->enable = false; - } - } + if (!sink_ops(csdev)->disable) + return; + + ret = sink_ops(csdev)->disable(csdev); + if (ret) + return; + csdev->enable = false; } static int coresight_enable_link(struct coresight_device *csdev, From 12dfc9e022aa4e8768d127416bf841c169f8c57e Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:52:57 -0600 Subject: [PATCH 169/255] coresight: Properly address errors in sink::disable() functions When disabling a sink the reference counter ensures the operation goes through if nobody else is using it. As such if drvdata::mode is already set do CS_MODE_DISABLED, it is an error and should be reported as such. Signed-off-by: Mathieu Poirier Reviewed-by: Suzuki K Poulose Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etb10.c | 9 ++++----- drivers/hwtracing/coresight/coresight-tmc-etf.c | 9 ++++----- drivers/hwtracing/coresight/coresight-tmc-etr.c | 9 ++++----- 3 files changed, 12 insertions(+), 15 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 8e63863cf950..6b73bc2e0dbd 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -333,11 +333,10 @@ static int etb_disable(struct coresight_device *csdev) return -EBUSY; } - /* Disable the ETB only if it needs to */ - if (drvdata->mode != CS_MODE_DISABLED) { - etb_disable_hw(drvdata); - drvdata->mode = CS_MODE_DISABLED; - } + /* Complain if we (somehow) got out of sync */ + WARN_ON_ONCE(drvdata->mode == CS_MODE_DISABLED); + etb_disable_hw(drvdata); + drvdata->mode = CS_MODE_DISABLED; spin_unlock_irqrestore(&drvdata->spinlock, flags); dev_dbg(drvdata->dev, "ETB disabled\n"); diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index d50a608a60f1..30f868676540 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -297,11 +297,10 @@ static int tmc_disable_etf_sink(struct coresight_device *csdev) return -EBUSY; } - /* Disable the TMC only if it needs to */ - if (drvdata->mode != CS_MODE_DISABLED) { - tmc_etb_disable_hw(drvdata); - drvdata->mode = CS_MODE_DISABLED; - } + /* Complain if we (somehow) got out of sync */ + WARN_ON_ONCE(drvdata->mode == CS_MODE_DISABLED); + tmc_etb_disable_hw(drvdata); + drvdata->mode = CS_MODE_DISABLED; spin_unlock_irqrestore(&drvdata->spinlock, flags); diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 6a8f39d03de3..9a0b346be58b 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -1417,11 +1417,10 @@ static int tmc_disable_etr_sink(struct coresight_device *csdev) return -EBUSY; } - /* Disable the TMC only if it needs to */ - if (drvdata->mode != CS_MODE_DISABLED) { - tmc_etr_disable_hw(drvdata); - drvdata->mode = CS_MODE_DISABLED; - } + /* Complain if we (somehow) got out of sync */ + WARN_ON_ONCE(drvdata->mode == CS_MODE_DISABLED); + tmc_etr_disable_hw(drvdata); + drvdata->mode = CS_MODE_DISABLED; spin_unlock_irqrestore(&drvdata->spinlock, flags); From 0916447c8728ed1ffa2bf9feee220f01d802b37e Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:52:58 -0600 Subject: [PATCH 170/255] coresight: Properly address concurrency in sink::update() functions When operating in CPU-wide trace scenarios and working with an N:1 source/sink HW topology, update() functions need to be made atomic in order to avoid racing with start and stop operations. Signed-off-by: Mathieu Poirier Reviewed-by: Suzuki K Poulose Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etb10.c | 4 +++- drivers/hwtracing/coresight/coresight-tmc-etf.c | 4 +++- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 6b73bc2e0dbd..00d664c6a401 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -405,7 +405,7 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, const u32 *barrier; u32 read_ptr, write_ptr, capacity; u32 status, read_data; - unsigned long offset, to_read; + unsigned long offset, to_read, flags; struct cs_buffers *buf = sink_config; struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); @@ -414,6 +414,7 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, capacity = drvdata->buffer_depth * ETB_FRAME_SIZE_WORDS; + spin_lock_irqsave(&drvdata->spinlock, flags); __etb_disable_hw(drvdata); CS_UNLOCK(drvdata->base); @@ -524,6 +525,7 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, } __etb_enable_hw(drvdata); CS_LOCK(drvdata->base); + spin_unlock_irqrestore(&drvdata->spinlock, flags); return to_read; } diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index 30f868676540..a38ad2b0d95a 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -413,7 +413,7 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, u32 *buf_ptr; u64 read_ptr, write_ptr; u32 status; - unsigned long offset, to_read; + unsigned long offset, to_read, flags; struct cs_buffers *buf = sink_config; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); @@ -424,6 +424,7 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, if (WARN_ON_ONCE(drvdata->mode != CS_MODE_PERF)) return 0; + spin_lock_irqsave(&drvdata->spinlock, flags); CS_UNLOCK(drvdata->base); tmc_flush_and_stop(drvdata); @@ -517,6 +518,7 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, to_read = buf->nr_pages << PAGE_SHIFT; } CS_LOCK(drvdata->base); + spin_unlock_irqrestore(&drvdata->spinlock, flags); return to_read; } From 02d5c897a091f8e064f022a5383978182751d7fb Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:52:59 -0600 Subject: [PATCH 171/255] coresight: perf: Clean up function etm_setup_aux() There is no point in allocating sink memory for a trace session if there is not a way to free it once it is no longer needed. As such make sure the sink API function to allocate and free memory have been implemented before moving ahead with the establishment of a trace session. Signed-off-by: Mathieu Poirier Reviewed-by: Suzuki K Poulose Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etm-perf.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index bbfed70b3402..b8ca3800b56b 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -134,8 +134,7 @@ static void free_event_data(struct work_struct *work) if (event_data->snk_config && !WARN_ON(cpumask_empty(mask))) { cpu = cpumask_first(mask); sink = coresight_get_sink(etm_event_cpu_path(event_data, cpu)); - if (sink_ops(sink)->free_buffer) - sink_ops(sink)->free_buffer(event_data->snk_config); + sink_ops(sink)->free_buffer(event_data->snk_config); } for_each_cpu(cpu, mask) { @@ -215,7 +214,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, sink = coresight_get_enabled_sink(true); } - if (!sink || !sink_ops(sink)->alloc_buffer) + if (!sink) goto err; mask = &event_data->mask; @@ -261,6 +260,9 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, if (cpu >= nr_cpu_ids) goto err; + if (!sink_ops(sink)->alloc_buffer || !sink_ops(sink)->free_buffer) + goto err; + /* Allocate the sink buffer for this session */ event_data->snk_config = sink_ops(sink)->alloc_buffer(sink, cpu, pages, From f5200aa9831f38271c8104565fdcae4401658475 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:53:00 -0600 Subject: [PATCH 172/255] coresight: perf: Refactor function free_event_data() Function free_event_data() is already busy and is bound to become worse with the addition of CPU-wide trace scenarios. As such spin off a new function to strickly take care of the sink buffers. Signed-off-by: Mathieu Poirier Reviewed-by: Suzuki K Poulose Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- .../hwtracing/coresight/coresight-etm-perf.c | 24 ++++++++++++++----- 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index b8ca3800b56b..806b3dd5872d 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -120,22 +120,34 @@ static int etm_event_init(struct perf_event *event) return ret; } +static void free_sink_buffer(struct etm_event_data *event_data) +{ + int cpu; + cpumask_t *mask = &event_data->mask; + struct coresight_device *sink; + + if (WARN_ON(cpumask_empty(mask))) + return; + + if (!event_data->snk_config) + return; + + cpu = cpumask_first(mask); + sink = coresight_get_sink(etm_event_cpu_path(event_data, cpu)); + sink_ops(sink)->free_buffer(event_data->snk_config); +} + static void free_event_data(struct work_struct *work) { int cpu; cpumask_t *mask; struct etm_event_data *event_data; - struct coresight_device *sink; event_data = container_of(work, struct etm_event_data, work); mask = &event_data->mask; /* Free the sink buffers, if there are any */ - if (event_data->snk_config && !WARN_ON(cpumask_empty(mask))) { - cpu = cpumask_first(mask); - sink = coresight_get_sink(etm_event_cpu_path(event_data, cpu)); - sink_ops(sink)->free_buffer(event_data->snk_config); - } + free_sink_buffer(event_data); for_each_cpu(cpu, mask) { struct list_head **ppath; From a0f08a6a9fee0ce3f2d36e3e30799e4c1ec171f4 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:53:01 -0600 Subject: [PATCH 173/255] coresight: Communicate perf event to sink buffer allocation functions Make struct perf_event available to sink buffer allocation functions in order to use the pid they carry to allocate and free buffer memory along with regimenting access to what source a sink can collect data for. Signed-off-by: Mathieu Poirier Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etb10.c | 7 ++++--- .../hwtracing/coresight/coresight-etm-perf.c | 2 +- .../hwtracing/coresight/coresight-tmc-etf.c | 7 ++++--- .../hwtracing/coresight/coresight-tmc-etr.c | 18 ++++++++++-------- include/linux/coresight.h | 5 +++-- 5 files changed, 22 insertions(+), 17 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index 00d664c6a401..eeae375c7aed 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -343,10 +343,11 @@ static int etb_disable(struct coresight_device *csdev) return 0; } -static void *etb_alloc_buffer(struct coresight_device *csdev, int cpu, - void **pages, int nr_pages, bool overwrite) +static void *etb_alloc_buffer(struct coresight_device *csdev, + struct perf_event *event, void **pages, + int nr_pages, bool overwrite) { - int node; + int node, cpu = event->cpu; struct cs_buffers *buf; if (cpu == -1) diff --git a/drivers/hwtracing/coresight/coresight-etm-perf.c b/drivers/hwtracing/coresight/coresight-etm-perf.c index 806b3dd5872d..3c6294432748 100644 --- a/drivers/hwtracing/coresight/coresight-etm-perf.c +++ b/drivers/hwtracing/coresight/coresight-etm-perf.c @@ -277,7 +277,7 @@ static void *etm_setup_aux(struct perf_event *event, void **pages, /* Allocate the sink buffer for this session */ event_data->snk_config = - sink_ops(sink)->alloc_buffer(sink, cpu, pages, + sink_ops(sink)->alloc_buffer(sink, event, pages, nr_pages, overwrite); if (!event_data->snk_config) goto err; diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index a38ad2b0d95a..1df1f8fade71 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -350,10 +350,11 @@ static void tmc_disable_etf_link(struct coresight_device *csdev, dev_dbg(drvdata->dev, "TMC-ETF disabled\n"); } -static void *tmc_alloc_etf_buffer(struct coresight_device *csdev, int cpu, - void **pages, int nr_pages, bool overwrite) +static void *tmc_alloc_etf_buffer(struct coresight_device *csdev, + struct perf_event *event, void **pages, + int nr_pages, bool overwrite) { - int node; + int node, cpu = event->cpu; struct cs_buffers *buf; if (cpu == -1) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 9a0b346be58b..55ee0aca321c 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -1167,13 +1167,18 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev) * reaches a minimum limit (1M), beyond which we give up. */ static struct etr_perf_buffer * -tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, int node, int nr_pages, - void **pages, bool snapshot) +tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, struct perf_event *event, + int nr_pages, void **pages, bool snapshot) { + int node, cpu = event->cpu; struct etr_buf *etr_buf; struct etr_perf_buffer *etr_perf; unsigned long size; + if (cpu == -1) + cpu = smp_processor_id(); + node = cpu_to_node(cpu); + etr_perf = kzalloc_node(sizeof(*etr_perf), GFP_KERNEL, node); if (!etr_perf) return ERR_PTR(-ENOMEM); @@ -1211,16 +1216,13 @@ tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, int node, int nr_pages, static void *tmc_alloc_etr_buffer(struct coresight_device *csdev, - int cpu, void **pages, int nr_pages, - bool snapshot) + struct perf_event *event, void **pages, + int nr_pages, bool snapshot) { struct etr_perf_buffer *etr_perf; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - if (cpu == -1) - cpu = smp_processor_id(); - - etr_perf = tmc_etr_setup_perf_buf(drvdata, cpu_to_node(cpu), + etr_perf = tmc_etr_setup_perf_buf(drvdata, event, nr_pages, pages, snapshot); if (IS_ERR(etr_perf)) { dev_dbg(drvdata->dev, "Unable to allocate ETR buffer\n"); diff --git a/include/linux/coresight.h b/include/linux/coresight.h index 189cc6ddc92b..62a520df8add 100644 --- a/include/linux/coresight.h +++ b/include/linux/coresight.h @@ -193,8 +193,9 @@ struct coresight_device { struct coresight_ops_sink { int (*enable)(struct coresight_device *csdev, u32 mode, void *data); int (*disable)(struct coresight_device *csdev); - void *(*alloc_buffer)(struct coresight_device *csdev, int cpu, - void **pages, int nr_pages, bool overwrite); + void *(*alloc_buffer)(struct coresight_device *csdev, + struct perf_event *event, void **pages, + int nr_pages, bool overwrite); void (*free_buffer)(void *config); unsigned long (*update_buffer)(struct coresight_device *csdev, struct perf_output_handle *handle, From 855ab61c16bf70b646fa9c84e7b07d14a003cd42 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:53:02 -0600 Subject: [PATCH 174/255] coresight: tmc-etr: Refactor function tmc_etr_setup_perf_buf() Refactoring function tmc_etr_setup_perf_buf() so that it only deals with the high level etr_perf_buffer, leaving the allocation of the backend buffer (i.e etr_buf) to another function. That way the backend buffer allocation function can decide if it wants to reuse an existing buffer (CPU-wide trace scenarios) or simply create a new one. Signed-off-by: Mathieu Poirier Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- .../hwtracing/coresight/coresight-tmc-etr.c | 39 ++++++++++++++----- 1 file changed, 30 insertions(+), 9 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 55ee0aca321c..e1d2128ee757 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -1160,29 +1160,24 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev) } /* - * tmc_etr_setup_perf_buf: Allocate ETR buffer for use by perf. + * alloc_etr_buf: Allocate ETR buffer for use by perf. * The size of the hardware buffer is dependent on the size configured * via sysfs and the perf ring buffer size. We prefer to allocate the * largest possible size, scaling down the size by half until it * reaches a minimum limit (1M), beyond which we give up. */ -static struct etr_perf_buffer * -tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, struct perf_event *event, - int nr_pages, void **pages, bool snapshot) +static struct etr_buf * +alloc_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event, + int nr_pages, void **pages, bool snapshot) { int node, cpu = event->cpu; struct etr_buf *etr_buf; - struct etr_perf_buffer *etr_perf; unsigned long size; if (cpu == -1) cpu = smp_processor_id(); node = cpu_to_node(cpu); - etr_perf = kzalloc_node(sizeof(*etr_perf), GFP_KERNEL, node); - if (!etr_perf) - return ERR_PTR(-ENOMEM); - /* * Try to match the perf ring buffer size if it is larger * than the size requested via sysfs. @@ -1206,6 +1201,32 @@ tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, struct perf_event *event, size /= 2; } while (size >= TMC_ETR_PERF_MIN_BUF_SIZE); + return ERR_PTR(-ENOMEM); + +done: + return etr_buf; +} + +static struct etr_perf_buffer * +tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, struct perf_event *event, + int nr_pages, void **pages, bool snapshot) +{ + int node, cpu = event->cpu; + struct etr_buf *etr_buf; + struct etr_perf_buffer *etr_perf; + + if (cpu == -1) + cpu = smp_processor_id(); + node = cpu_to_node(cpu); + + etr_perf = kzalloc_node(sizeof(*etr_perf), GFP_KERNEL, node); + if (!etr_perf) + return ERR_PTR(-ENOMEM); + + etr_buf = alloc_etr_buf(drvdata, event, nr_pages, pages, snapshot); + if (!IS_ERR(etr_buf)) + goto done; + kfree(etr_perf); return ERR_PTR(-ENOMEM); From e553a8aef4c300530844fe096c10975548ea26cb Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:53:03 -0600 Subject: [PATCH 175/255] coresight: tmc-etr: Create per-thread buffer allocation function Buffer allocation is different when dealing with per-thread and CPU-wide sessions. In preparation to support CPU-wide trace scenarios simplify things by keeping allocation functions for both type separate. Signed-off-by: Mathieu Poirier Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- .../hwtracing/coresight/coresight-tmc-etr.c | 29 ++++++++++++++++++- 1 file changed, 28 insertions(+), 1 deletion(-) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index e1d2128ee757..bca1b2d9ef2e 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -1207,6 +1207,33 @@ alloc_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event, return etr_buf; } +static struct etr_buf * +get_perf_etr_buf_per_thread(struct tmc_drvdata *drvdata, + struct perf_event *event, int nr_pages, + void **pages, bool snapshot) +{ + struct etr_buf *etr_buf; + + /* + * In per-thread mode the etr_buf isn't shared, so just go ahead + * with memory allocation. + */ + etr_buf = alloc_etr_buf(drvdata, event, nr_pages, pages, snapshot); + + return etr_buf; +} + +static struct etr_buf * +get_perf_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event, + int nr_pages, void **pages, bool snapshot) +{ + if (event->cpu == -1) + return get_perf_etr_buf_per_thread(drvdata, event, nr_pages, + pages, snapshot); + + return ERR_PTR(-ENOENT); +} + static struct etr_perf_buffer * tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, struct perf_event *event, int nr_pages, void **pages, bool snapshot) @@ -1223,7 +1250,7 @@ tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, struct perf_event *event, if (!etr_perf) return ERR_PTR(-ENOMEM); - etr_buf = alloc_etr_buf(drvdata, event, nr_pages, pages, snapshot); + etr_buf = get_perf_etr_buf(drvdata, event, nr_pages, pages, snapshot); if (!IS_ERR(etr_buf)) goto done; From ef848e463ac9052be620757579cfa0aa975e97ea Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:53:04 -0600 Subject: [PATCH 176/255] coresight: tmc-etr: Introduce the notion of process ID to ETR devices In preparation to support CPU-wide trace scenarios, introduce the notion of process ID to ETR devices. That way events monitoring the same process can use the same etr_buf, allowing multiple CPUs to use the same sink. Signed-off-by: Mathieu Poirier Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-tmc-etr.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index bca1b2d9ef2e..1acad42184e6 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include "coresight-catu.h" #include "coresight-etm-perf.h" @@ -25,6 +26,7 @@ struct etr_flat_buf { /* * etr_perf_buffer - Perf buffer used for ETR * @etr_buf - Actual buffer used by the ETR + * @pid - The PID this etr_perf_buffer belongs to. * @snaphost - Perf session mode * @head - handle->head at the beginning of the session. * @nr_pages - Number of pages in the ring buffer. @@ -32,6 +34,7 @@ struct etr_flat_buf { */ struct etr_perf_buffer { struct etr_buf *etr_buf; + pid_t pid; bool snapshot; unsigned long head; int nr_pages; @@ -1277,6 +1280,7 @@ static void *tmc_alloc_etr_buffer(struct coresight_device *csdev, return NULL; } + etr_perf->pid = task_pid_nr(event->owner); etr_perf->snapshot = snapshot; etr_perf->nr_pages = nr_pages; etr_perf->pages = pages; From 57549999b9a0d0c72900d2413ef1e3168bd2e817 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:53:05 -0600 Subject: [PATCH 177/255] coresight: tmc-etr: Introduce the notion of reference counting to ETR devices This patch adds reference counting to struct etr_buf so that, in CPU-wide trace scenarios, shared buffers can be disposed of when no longer used. Signed-off-by: Mathieu Poirier Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-tmc-etr.c | 5 +++++ drivers/hwtracing/coresight/coresight-tmc.h | 3 +++ 2 files changed, 8 insertions(+) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 1acad42184e6..de33c0391186 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -1222,7 +1223,11 @@ get_perf_etr_buf_per_thread(struct tmc_drvdata *drvdata, * with memory allocation. */ etr_buf = alloc_etr_buf(drvdata, event, nr_pages, pages, snapshot); + if (IS_ERR(etr_buf)) + goto out; + refcount_set(&etr_buf->refcount, 1); +out: return etr_buf; } diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h index 487c53701e9c..ee44906dffe8 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.h +++ b/drivers/hwtracing/coresight/coresight-tmc.h @@ -9,6 +9,7 @@ #include #include +#include #define TMC_RSZ 0x004 #define TMC_STS 0x00c @@ -133,6 +134,7 @@ struct etr_buf_operations; /** * struct etr_buf - Details of the buffer used by ETR + * refcount ; Number of sources currently using this etr_buf. * @mode : Mode of the ETR buffer, contiguous, Scatter Gather etc. * @full : Trace data overflow * @size : Size of the buffer. @@ -143,6 +145,7 @@ struct etr_buf_operations; * @private : Backend specific information for the buf */ struct etr_buf { + refcount_t refcount; enum etr_mode mode; bool full; ssize_t size; From c5ff734462b1d32f793db717ef222cd05e6232d5 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:53:06 -0600 Subject: [PATCH 178/255] coresight: tmc-etr: Introduce the notion of IDR to ETR devices In CPU-wide scenarios with an N:1 source/sink topology, sources share the same sink. In order to reuse the same sink for all sources an IDR is needed to archive events that have already been accounted for. Signed-off-by: Mathieu Poirier Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-tmc.c | 4 ++++ drivers/hwtracing/coresight/coresight-tmc.h | 6 ++++++ 2 files changed, 10 insertions(+) diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c index c6a5462ebf27..9f9b2c514566 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.c +++ b/drivers/hwtracing/coresight/coresight-tmc.c @@ -8,10 +8,12 @@ #include #include #include +#include #include #include #include #include +#include #include #include #include @@ -450,6 +452,8 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) coresight_get_uci_data(id)); if (ret) goto out; + idr_init(&drvdata->idr); + mutex_init(&drvdata->idr_mutex); break; case TMC_CONFIG_TYPE_ETF: desc.type = CORESIGHT_DEV_TYPE_LINKSINK; diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h index ee44906dffe8..c1b1700b2df7 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.h +++ b/drivers/hwtracing/coresight/coresight-tmc.h @@ -8,7 +8,9 @@ #define _CORESIGHT_TMC_H #include +#include #include +#include #include #define TMC_RSZ 0x004 @@ -173,6 +175,8 @@ struct etr_buf { * @trigger_cntr: amount of words to store after a trigger. * @etr_caps: Bitmask of capabilities of the TMC ETR, inferred from the * device configuration register (DEVID) + * @idr: Holds etr_bufs allocated for this ETR. + * @idr_mutex: Access serialisation for idr. * @perf_data: PERF buffer for ETR. * @sysfs_data: SYSFS buffer for ETR. */ @@ -194,6 +198,8 @@ struct tmc_drvdata { enum tmc_mem_intf_width memwidth; u32 trigger_cntr; u32 etr_caps; + struct idr idr; + struct mutex idr_mutex; struct etr_buf *sysfs_buf; void *perf_data; }; From 3147da92a8a81fc304e6e9d7ac75b68d6a54d9f7 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:53:07 -0600 Subject: [PATCH 179/255] coresight: tmc-etr: Allocate and free ETR memory buffers for CPU-wide scenarios This patch uses the PID of the process being traced to allocate and free ETR memory buffers for CPU-wide scenarios. The implementation is tailored to handle both N:1 and 1:1 source/sink HW topologies. Signed-off-by: Mathieu Poirier Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- .../hwtracing/coresight/coresight-tmc-etr.c | 107 +++++++++++++++++- 1 file changed, 104 insertions(+), 3 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index de33c0391186..8c75800003d2 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -8,6 +8,8 @@ #include #include #include +#include +#include #include #include #include @@ -26,6 +28,7 @@ struct etr_flat_buf { /* * etr_perf_buffer - Perf buffer used for ETR + * @drvdata - The ETR drvdaga this buffer has been allocated for. * @etr_buf - Actual buffer used by the ETR * @pid - The PID this etr_perf_buffer belongs to. * @snaphost - Perf session mode @@ -34,6 +37,7 @@ struct etr_flat_buf { * @pages - Array of Pages in the ring buffer. */ struct etr_perf_buffer { + struct tmc_drvdata *drvdata; struct etr_buf *etr_buf; pid_t pid; bool snapshot; @@ -1211,6 +1215,72 @@ alloc_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event, return etr_buf; } +static struct etr_buf * +get_perf_etr_buf_cpu_wide(struct tmc_drvdata *drvdata, + struct perf_event *event, int nr_pages, + void **pages, bool snapshot) +{ + int ret; + pid_t pid = task_pid_nr(event->owner); + struct etr_buf *etr_buf; + +retry: + /* + * An etr_perf_buffer is associated with an event and holds a reference + * to the AUX ring buffer that was created for that event. In CPU-wide + * N:1 mode multiple events (one per CPU), each with its own AUX ring + * buffer, share a sink. As such an etr_perf_buffer is created for each + * event but a single etr_buf associated with the ETR is shared between + * them. The last event in a trace session will copy the content of the + * etr_buf to its AUX ring buffer. Ring buffer associated to other + * events are simply not used an freed as events are destoyed. We still + * need to allocate a ring buffer for each event since we don't know + * which event will be last. + */ + + /* + * The first thing to do here is check if an etr_buf has already been + * allocated for this session. If so it is shared with this event, + * otherwise it is created. + */ + mutex_lock(&drvdata->idr_mutex); + etr_buf = idr_find(&drvdata->idr, pid); + if (etr_buf) { + refcount_inc(&etr_buf->refcount); + mutex_unlock(&drvdata->idr_mutex); + return etr_buf; + } + + /* If we made it here no buffer has been allocated, do so now. */ + mutex_unlock(&drvdata->idr_mutex); + + etr_buf = alloc_etr_buf(drvdata, event, nr_pages, pages, snapshot); + if (IS_ERR(etr_buf)) + return etr_buf; + + refcount_set(&etr_buf->refcount, 1); + + /* Now that we have a buffer, add it to the IDR. */ + mutex_lock(&drvdata->idr_mutex); + ret = idr_alloc(&drvdata->idr, etr_buf, pid, pid + 1, GFP_KERNEL); + mutex_unlock(&drvdata->idr_mutex); + + /* Another event with this session ID has allocated this buffer. */ + if (ret == -ENOSPC) { + tmc_free_etr_buf(etr_buf); + goto retry; + } + + /* The IDR can't allocate room for a new session, abandon ship. */ + if (ret == -ENOMEM) { + tmc_free_etr_buf(etr_buf); + return ERR_PTR(ret); + } + + + return etr_buf; +} + static struct etr_buf * get_perf_etr_buf_per_thread(struct tmc_drvdata *drvdata, struct perf_event *event, int nr_pages, @@ -1239,7 +1309,8 @@ get_perf_etr_buf(struct tmc_drvdata *drvdata, struct perf_event *event, return get_perf_etr_buf_per_thread(drvdata, event, nr_pages, pages, snapshot); - return ERR_PTR(-ENOENT); + return get_perf_etr_buf_cpu_wide(drvdata, event, nr_pages, + pages, snapshot); } static struct etr_perf_buffer * @@ -1266,7 +1337,13 @@ tmc_etr_setup_perf_buf(struct tmc_drvdata *drvdata, struct perf_event *event, return ERR_PTR(-ENOMEM); done: + /* + * Keep a reference to the ETR this buffer has been allocated for + * in order to have access to the IDR in tmc_free_etr_buffer(). + */ + etr_perf->drvdata = drvdata; etr_perf->etr_buf = etr_buf; + return etr_perf; } @@ -1296,9 +1373,33 @@ static void *tmc_alloc_etr_buffer(struct coresight_device *csdev, static void tmc_free_etr_buffer(void *config) { struct etr_perf_buffer *etr_perf = config; + struct tmc_drvdata *drvdata = etr_perf->drvdata; + struct etr_buf *buf, *etr_buf = etr_perf->etr_buf; - if (etr_perf->etr_buf) - tmc_free_etr_buf(etr_perf->etr_buf); + if (!etr_buf) + goto free_etr_perf_buffer; + + mutex_lock(&drvdata->idr_mutex); + /* If we are not the last one to use the buffer, don't touch it. */ + if (!refcount_dec_and_test(&etr_buf->refcount)) { + mutex_unlock(&drvdata->idr_mutex); + goto free_etr_perf_buffer; + } + + /* We are the last one, remove from the IDR and free the buffer. */ + buf = idr_remove(&drvdata->idr, etr_perf->pid); + mutex_unlock(&drvdata->idr_mutex); + + /* + * Something went very wrong if the buffer associated with this ID + * is not the same in the IDR. Leak to avoid use after free. + */ + if (buf && WARN_ON(buf != etr_buf)) + goto free_etr_perf_buffer; + + tmc_free_etr_buf(etr_perf->etr_buf); + +free_etr_perf_buffer: kfree(etr_perf); } From 8d03cfd16a7283e9e7a5aeb7dc0742ceb66d2d23 Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:53:08 -0600 Subject: [PATCH 180/255] coresight: tmc-etr: Add support for CPU-wide trace scenarios This patch adds support for CPU-wide trace scenarios by making sure that only the sources monitoring the same process have access to a common sink. Because the sink is shared between sources, the first source to use the sink switches it on while the last one does the cleanup. Any attempt to modify the HW is overlooked for as long as more than one source is using a sink. Signed-off-by: Mathieu Poirier Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- .../hwtracing/coresight/coresight-tmc-etr.c | 38 ++++++++++++++++--- drivers/hwtracing/coresight/coresight-tmc.c | 2 + drivers/hwtracing/coresight/coresight-tmc.h | 3 ++ 3 files changed, 38 insertions(+), 5 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 8c75800003d2..df6e4b0b84e9 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -1474,6 +1474,13 @@ tmc_update_etr_buffer(struct coresight_device *csdev, struct etr_buf *etr_buf = etr_perf->etr_buf; spin_lock_irqsave(&drvdata->spinlock, flags); + + /* Don't do anything if another tracer is using this sink */ + if (atomic_read(csdev->refcnt) != 1) { + spin_unlock_irqrestore(&drvdata->spinlock, flags); + goto out; + } + if (WARN_ON(drvdata->perf_data != etr_perf)) { lost = true; spin_unlock_irqrestore(&drvdata->spinlock, flags); @@ -1513,17 +1520,15 @@ tmc_update_etr_buffer(struct coresight_device *csdev, static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data) { int rc = 0; + pid_t pid; unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); struct perf_output_handle *handle = data; struct etr_perf_buffer *etr_perf = etm_perf_sink_config(handle); spin_lock_irqsave(&drvdata->spinlock, flags); - /* - * There can be only one writer per sink in perf mode. If the sink - * is already open in SYSFS mode, we can't use it. - */ - if (drvdata->mode != CS_MODE_DISABLED || WARN_ON(drvdata->perf_data)) { + /* Don't use this sink if it is already claimed by sysFS */ + if (drvdata->mode == CS_MODE_SYSFS) { rc = -EBUSY; goto unlock_out; } @@ -1533,10 +1538,31 @@ static int tmc_enable_etr_sink_perf(struct coresight_device *csdev, void *data) goto unlock_out; } + /* Get a handle on the pid of the process to monitor */ + pid = etr_perf->pid; + + /* Do not proceed if this device is associated with another session */ + if (drvdata->pid != -1 && drvdata->pid != pid) { + rc = -EBUSY; + goto unlock_out; + } + etr_perf->head = PERF_IDX2OFF(handle->head, etr_perf); drvdata->perf_data = etr_perf; + + /* + * No HW configuration is needed if the sink is already in + * use for this session. + */ + if (drvdata->pid == pid) { + atomic_inc(csdev->refcnt); + goto unlock_out; + } + rc = tmc_etr_enable_hw(drvdata, etr_perf->etr_buf); if (!rc) { + /* Associate with monitored process. */ + drvdata->pid = pid; drvdata->mode = CS_MODE_PERF; atomic_inc(csdev->refcnt); } @@ -1580,6 +1606,8 @@ static int tmc_disable_etr_sink(struct coresight_device *csdev) /* Complain if we (somehow) got out of sync */ WARN_ON_ONCE(drvdata->mode == CS_MODE_DISABLED); tmc_etr_disable_hw(drvdata); + /* Dissociate from monitored process. */ + drvdata->pid = -1; drvdata->mode = CS_MODE_DISABLED; spin_unlock_irqrestore(&drvdata->spinlock, flags); diff --git a/drivers/hwtracing/coresight/coresight-tmc.c b/drivers/hwtracing/coresight/coresight-tmc.c index 9f9b2c514566..3f718729d741 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.c +++ b/drivers/hwtracing/coresight/coresight-tmc.c @@ -422,6 +422,8 @@ static int tmc_probe(struct amba_device *adev, const struct amba_id *id) devid = readl_relaxed(drvdata->base + CORESIGHT_DEVID); drvdata->config_type = BMVAL(devid, 6, 7); drvdata->memwidth = tmc_get_memwidth(devid); + /* This device is not associated with a session */ + drvdata->pid = -1; if (drvdata->config_type == TMC_CONFIG_TYPE_ETR) { if (np) diff --git a/drivers/hwtracing/coresight/coresight-tmc.h b/drivers/hwtracing/coresight/coresight-tmc.h index c1b1700b2df7..503f1b3a3741 100644 --- a/drivers/hwtracing/coresight/coresight-tmc.h +++ b/drivers/hwtracing/coresight/coresight-tmc.h @@ -165,6 +165,8 @@ struct etr_buf { * @csdev: component vitals needed by the framework. * @miscdev: specifics to handle "/dev/xyz.tmc" entry. * @spinlock: only one at a time pls. + * @pid: Process ID of the process being monitored by the session + * that is using this component. * @buf: Snapshot of the trace data for ETF/ETB. * @etr_buf: details of buffer used in TMC-ETR * @len: size of the available trace for ETF/ETB. @@ -186,6 +188,7 @@ struct tmc_drvdata { struct coresight_device *csdev; struct miscdevice miscdev; spinlock_t spinlock; + pid_t pid; bool reading; union { char *buf; /* TMC ETB */ From 880af782c6e81cccf507f5a1cf4b23fbb471c39f Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:53:09 -0600 Subject: [PATCH 181/255] coresight: tmc-etf: Add support for CPU-wide trace scenarios This patch adds support for CPU-wide trace scenarios by making sure that only the sources monitoring the same process have access to a common sink. Because the sink is shared between sources, the first source to use the sink switches it on while the last one does the cleanup. Any attempt to modify the HW is overlooked for as long as more than one source is using a sink. Signed-off-by: Mathieu Poirier Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- .../hwtracing/coresight/coresight-tmc-etf.c | 40 ++++++++++++++++--- 1 file changed, 35 insertions(+), 5 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-tmc-etf.c b/drivers/hwtracing/coresight/coresight-tmc-etf.c index 1df1f8fade71..2527b5d3b65e 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etf.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etf.c @@ -223,6 +223,7 @@ static int tmc_enable_etf_sink_sysfs(struct coresight_device *csdev) static int tmc_enable_etf_sink_perf(struct coresight_device *csdev, void *data) { int ret = 0; + pid_t pid; unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); struct perf_output_handle *handle = data; @@ -233,18 +234,39 @@ static int tmc_enable_etf_sink_perf(struct coresight_device *csdev, void *data) if (drvdata->reading) break; /* - * In Perf mode there can be only one writer per sink. There - * is also no need to continue if the ETB/ETF is already - * operated from sysFS. + * No need to continue if the ETB/ETF is already operated + * from sysFS. */ - if (drvdata->mode != CS_MODE_DISABLED) + if (drvdata->mode == CS_MODE_SYSFS) { + ret = -EBUSY; break; + } + + /* Get a handle on the pid of the process to monitor */ + pid = task_pid_nr(handle->event->owner); + + if (drvdata->pid != -1 && drvdata->pid != pid) { + ret = -EBUSY; + break; + } ret = tmc_set_etf_buffer(csdev, handle); if (ret) break; + + /* + * No HW configuration is needed if the sink is already in + * use for this session. + */ + if (drvdata->pid == pid) { + atomic_inc(csdev->refcnt); + break; + } + ret = tmc_etb_enable_hw(drvdata); if (!ret) { + /* Associate with monitored process. */ + drvdata->pid = pid; drvdata->mode = CS_MODE_PERF; atomic_inc(csdev->refcnt); } @@ -300,6 +322,8 @@ static int tmc_disable_etf_sink(struct coresight_device *csdev) /* Complain if we (somehow) got out of sync */ WARN_ON_ONCE(drvdata->mode == CS_MODE_DISABLED); tmc_etb_disable_hw(drvdata); + /* Dissociate from monitored process. */ + drvdata->pid = -1; drvdata->mode = CS_MODE_DISABLED; spin_unlock_irqrestore(&drvdata->spinlock, flags); @@ -414,7 +438,7 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, u32 *buf_ptr; u64 read_ptr, write_ptr; u32 status; - unsigned long offset, to_read, flags; + unsigned long offset, to_read = 0, flags; struct cs_buffers *buf = sink_config; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); @@ -426,6 +450,11 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, return 0; spin_lock_irqsave(&drvdata->spinlock, flags); + + /* Don't do anything if another tracer is using this sink */ + if (atomic_read(csdev->refcnt) != 1) + goto out; + CS_UNLOCK(drvdata->base); tmc_flush_and_stop(drvdata); @@ -519,6 +548,7 @@ static unsigned long tmc_update_etf_buffer(struct coresight_device *csdev, to_read = buf->nr_pages << PAGE_SHIFT; } CS_LOCK(drvdata->base); +out: spin_unlock_irqrestore(&drvdata->spinlock, flags); return to_read; From 75d7dbd3882450c7b6602d234b3b31864dbc356d Mon Sep 17 00:00:00 2001 From: Mathieu Poirier Date: Thu, 25 Apr 2019 13:53:10 -0600 Subject: [PATCH 182/255] coresight: etb10: Add support for CPU-wide trace scenarios This patch adds support for CPU-wide trace scenarios by making sure that only the sources monitoring the same process have access to a common sink. Because the sink is shared between sources, the first source to use the sink switches it on while the last one does the cleanup. Any attempt to modify the HW is overlooked for as long as more than one source is using a sink. Signed-off-by: Mathieu Poirier Tested-by: Leo Yan Tested-by: Robert Walker Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-etb10.c | 43 +++++++++++++++++-- 1 file changed, 39 insertions(+), 4 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-etb10.c b/drivers/hwtracing/coresight/coresight-etb10.c index eeae375c7aed..4ee4c80a4354 100644 --- a/drivers/hwtracing/coresight/coresight-etb10.c +++ b/drivers/hwtracing/coresight/coresight-etb10.c @@ -72,6 +72,8 @@ * @miscdev: specifics to handle "/dev/xyz.etb" entry. * @spinlock: only one at a time pls. * @reading: synchronise user space access to etb buffer. + * @pid: Process ID of the process being monitored by the session + * that is using this component. * @buf: area of memory where ETB buffer content gets sent. * @mode: this ETB is being used. * @buffer_depth: size of @buf. @@ -85,6 +87,7 @@ struct etb_drvdata { struct miscdevice miscdev; spinlock_t spinlock; local_t reading; + pid_t pid; u8 *buf; u32 mode; u32 buffer_depth; @@ -169,28 +172,49 @@ static int etb_enable_sysfs(struct coresight_device *csdev) static int etb_enable_perf(struct coresight_device *csdev, void *data) { int ret = 0; + pid_t pid; unsigned long flags; struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); + struct perf_output_handle *handle = data; spin_lock_irqsave(&drvdata->spinlock, flags); - /* No need to continue if the component is already in use. */ - if (drvdata->mode != CS_MODE_DISABLED) { + /* No need to continue if the component is already in used by sysFS. */ + if (drvdata->mode == CS_MODE_SYSFS) { ret = -EBUSY; goto out; } + /* Get a handle on the pid of the process to monitor */ + pid = task_pid_nr(handle->event->owner); + + if (drvdata->pid != -1 && drvdata->pid != pid) { + ret = -EBUSY; + goto out; + } + + /* + * No HW configuration is needed if the sink is already in + * use for this session. + */ + if (drvdata->pid == pid) { + atomic_inc(csdev->refcnt); + goto out; + } + /* * We don't have an internal state to clean up if we fail to setup * the perf buffer. So we can perform the step before we turn the * ETB on and leave without cleaning up. */ - ret = etb_set_buffer(csdev, (struct perf_output_handle *)data); + ret = etb_set_buffer(csdev, handle); if (ret) goto out; ret = etb_enable_hw(drvdata); if (!ret) { + /* Associate with monitored process. */ + drvdata->pid = pid; drvdata->mode = CS_MODE_PERF; atomic_inc(csdev->refcnt); } @@ -336,6 +360,8 @@ static int etb_disable(struct coresight_device *csdev) /* Complain if we (somehow) got out of sync */ WARN_ON_ONCE(drvdata->mode == CS_MODE_DISABLED); etb_disable_hw(drvdata); + /* Dissociate from monitored process. */ + drvdata->pid = -1; drvdata->mode = CS_MODE_DISABLED; spin_unlock_irqrestore(&drvdata->spinlock, flags); @@ -406,7 +432,7 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, const u32 *barrier; u32 read_ptr, write_ptr, capacity; u32 status, read_data; - unsigned long offset, to_read, flags; + unsigned long offset, to_read = 0, flags; struct cs_buffers *buf = sink_config; struct etb_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); @@ -416,6 +442,11 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, capacity = drvdata->buffer_depth * ETB_FRAME_SIZE_WORDS; spin_lock_irqsave(&drvdata->spinlock, flags); + + /* Don't do anything if another tracer is using this sink */ + if (atomic_read(csdev->refcnt) != 1) + goto out; + __etb_disable_hw(drvdata); CS_UNLOCK(drvdata->base); @@ -526,6 +557,7 @@ static unsigned long etb_update_buffer(struct coresight_device *csdev, } __etb_enable_hw(drvdata); CS_LOCK(drvdata->base); +out: spin_unlock_irqrestore(&drvdata->spinlock, flags); return to_read; @@ -733,6 +765,9 @@ static int etb_probe(struct amba_device *adev, const struct amba_id *id) if (!drvdata->buf) return -ENOMEM; + /* This device is not associated with a session */ + drvdata->pid = -1; + desc.type = CORESIGHT_DEV_TYPE_SINK; desc.subtype.sink_subtype = CORESIGHT_DEV_SUBTYPE_SINK_BUFFER; desc.ops = &etb_cs_ops; From 15235f1f495efc5ed435cf6fff95066ba85c5328 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Sat, 13 Apr 2019 11:32:46 +0100 Subject: [PATCH 183/255] dt-bindings: imx-ocotp: Add i.MX8MQ compatible Add compatible for i.MX8MQ and add i.MX7D/S, i.MX7ULP and i.M8MQ to the description. Signed-off-by: Lucas Stach Reviewed-by: Rob Herring Reviewed-by: Abel Vesa Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/nvmem/imx-ocotp.txt | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/nvmem/imx-ocotp.txt b/Documentation/devicetree/bindings/nvmem/imx-ocotp.txt index 7a999a135e56..68f7d6fdd140 100644 --- a/Documentation/devicetree/bindings/nvmem/imx-ocotp.txt +++ b/Documentation/devicetree/bindings/nvmem/imx-ocotp.txt @@ -1,7 +1,8 @@ Freescale i.MX6 On-Chip OTP Controller (OCOTP) device tree bindings This binding represents the on-chip eFuse OTP controller found on -i.MX6Q/D, i.MX6DL/S, i.MX6SL, i.MX6SX, i.MX6UL, i.MX6ULL/ULZ and i.MX6SLL SoCs. +i.MX6Q/D, i.MX6DL/S, i.MX6SL, i.MX6SX, i.MX6UL, i.MX6ULL/ULZ, i.MX6SLL, +i.MX7D/S, i.MX7ULP and i.MX8MQ SoCs. Required properties: - compatible: should be one of @@ -13,6 +14,7 @@ Required properties: "fsl,imx7d-ocotp" (i.MX7D/S), "fsl,imx6sll-ocotp" (i.MX6SLL), "fsl,imx7ulp-ocotp" (i.MX7ULP), + "fsl,imx8mq-ocotp" (i.MX8MQ), followed by "syscon". - #address-cells : Should be 1 - #size-cells : Should be 1 From b281218ad4311a0342a40cb02fb17a363df08b48 Mon Sep 17 00:00:00 2001 From: Young Xiao Date: Fri, 12 Apr 2019 15:45:06 +0800 Subject: [PATCH 184/255] Drivers: misc: fix out-of-bounds access in function param_set_kgdbts_var There is an out-of-bounds access to "config[len - 1]" array when the variable "len" is zero. See commit dada6a43b040 ("kgdboc: fix KASAN global-out-of-bounds bug in param_set_kgdboc_var()") for details. Signed-off-by: Young Xiao Signed-off-by: Greg Kroah-Hartman --- drivers/misc/kgdbts.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/misc/kgdbts.c b/drivers/misc/kgdbts.c index de20bdaa148d..8b01257783dd 100644 --- a/drivers/misc/kgdbts.c +++ b/drivers/misc/kgdbts.c @@ -1135,7 +1135,7 @@ static void kgdbts_put_char(u8 chr) static int param_set_kgdbts_var(const char *kmessage, const struct kernel_param *kp) { - int len = strlen(kmessage); + size_t len = strlen(kmessage); if (len >= MAX_CONFIG_LEN) { printk(KERN_ERR "kgdbts: config string too long\n"); @@ -1155,7 +1155,7 @@ static int param_set_kgdbts_var(const char *kmessage, strcpy(config, kmessage); /* Chop out \n char as a result of echo */ - if (config[len - 1] == '\n') + if (len && config[len - 1] == '\n') config[len - 1] = '\0'; /* Go and configure with the new params. */ From 06d5d6b7f9948a89543e1160ef852d57892c750d Mon Sep 17 00:00:00 2001 From: Kangjie Lu Date: Sat, 13 Apr 2019 11:34:47 +0100 Subject: [PATCH 185/255] slimbus: fix a potential NULL pointer dereference in of_qcom_slim_ngd_register In case platform_device_alloc fails, the fix returns an error code to avoid the NULL pointer dereference. Signed-off-by: Kangjie Lu Signed-off-by: Srinivas Kandagatla Signed-off-by: Greg Kroah-Hartman --- drivers/slimbus/qcom-ngd-ctrl.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/slimbus/qcom-ngd-ctrl.c b/drivers/slimbus/qcom-ngd-ctrl.c index 71f094c9ec68..f3585777324c 100644 --- a/drivers/slimbus/qcom-ngd-ctrl.c +++ b/drivers/slimbus/qcom-ngd-ctrl.c @@ -1342,6 +1342,10 @@ static int of_qcom_slim_ngd_register(struct device *parent, return -ENOMEM; ngd->pdev = platform_device_alloc(QCOM_SLIM_NGD_DRV_NAME, id); + if (!ngd->pdev) { + kfree(ngd); + return -ENOMEM; + } ngd->id = id; ngd->pdev->dev.parent = parent; ngd->pdev->driver_override = QCOM_SLIM_NGD_DRV_NAME; From 2d1c31cb642b44e3d621643b8d30e15e5e4df4e4 Mon Sep 17 00:00:00 2001 From: Patrick Venture Date: Thu, 25 Apr 2019 13:23:47 -0700 Subject: [PATCH 186/255] drivers/misc: Add Aspeed P2A control driver Fixup compiler warnings: - 108 warning: ISO C90 forbids mixed declarations and code - 264 warning: unused variable 'value' - 335 warning: unused variable 'res' Reported-by: kbuild test robot Signed-off-by: Patrick Venture Signed-off-by: Greg Kroah-Hartman --- drivers/misc/aspeed-p2a-ctrl.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/misc/aspeed-p2a-ctrl.c b/drivers/misc/aspeed-p2a-ctrl.c index c0521b2ffc6a..9736821972ef 100644 --- a/drivers/misc/aspeed-p2a-ctrl.c +++ b/drivers/misc/aspeed-p2a-ctrl.c @@ -99,13 +99,14 @@ static void aspeed_p2a_disable_bridge(struct aspeed_p2a_ctrl *p2a_ctrl) static int aspeed_p2a_mmap(struct file *file, struct vm_area_struct *vma) { + unsigned long vsize; struct aspeed_p2a_user *priv = file->private_data; struct aspeed_p2a_ctrl *ctrl = priv->parent; if (ctrl->mem_base == 0 && ctrl->mem_size == 0) return -EINVAL; - unsigned long vsize = vma->vm_end - vma->vm_start; + vsize = vma->vm_end - vma->vm_start; pgprot_t prot = vma->vm_page_prot; if (vma->vm_pgoff + vsize > ctrl->mem_base + ctrl->mem_size) @@ -261,7 +262,6 @@ static int aspeed_p2a_open(struct inode *inode, struct file *file) static int aspeed_p2a_release(struct inode *inode, struct file *file) { int i; - u32 value; u32 bits = 0; bool open_regions = false; struct aspeed_p2a_user *priv = file->private_data; @@ -332,7 +332,7 @@ static int aspeed_p2a_ctrl_probe(struct platform_device *pdev) { struct aspeed_p2a_ctrl *misc_ctrl; struct device *dev; - struct resource *res, resm; + struct resource resm; struct device_node *node; int rc = 0; From 94001602d6bb21adbb4fa991d42b0c5d8a69db48 Mon Sep 17 00:00:00 2001 From: Patrick Venture Date: Fri, 26 Apr 2019 09:56:55 -0700 Subject: [PATCH 187/255] misc: aspeed-p2a-ctrl: fix mixed declarations Fix up mixed declarations and code in aspeed_p2a_mmap. Tested: Verified the build had the error and that this patch resolved it and there were no other warnings or build errors associated with compilation of this driver. Reported-by: Stephen Rothwell Signed-off-by: Patrick Venture Signed-off-by: Greg Kroah-Hartman --- drivers/misc/aspeed-p2a-ctrl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/misc/aspeed-p2a-ctrl.c b/drivers/misc/aspeed-p2a-ctrl.c index 9736821972ef..b60fbeaffcbd 100644 --- a/drivers/misc/aspeed-p2a-ctrl.c +++ b/drivers/misc/aspeed-p2a-ctrl.c @@ -100,6 +100,7 @@ static void aspeed_p2a_disable_bridge(struct aspeed_p2a_ctrl *p2a_ctrl) static int aspeed_p2a_mmap(struct file *file, struct vm_area_struct *vma) { unsigned long vsize; + pgprot_t prot; struct aspeed_p2a_user *priv = file->private_data; struct aspeed_p2a_ctrl *ctrl = priv->parent; @@ -107,7 +108,7 @@ static int aspeed_p2a_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; vsize = vma->vm_end - vma->vm_start; - pgprot_t prot = vma->vm_page_prot; + prot = vma->vm_page_prot; if (vma->vm_pgoff + vsize > ctrl->mem_base + ctrl->mem_size) return -EINVAL; From 62909da8aca048ecf9fbd7e484e5100608f40a63 Mon Sep 17 00:00:00 2001 From: Mariusz Bialonczyk Date: Thu, 21 Mar 2019 11:52:55 +0100 Subject: [PATCH 188/255] w1: fix the resume command API >From the DS2408 datasheet [1]: "Resume Command function checks the status of the RC flag and, if it is set, directly transfers control to the control functions, similar to a Skip ROM command. The only way to set the RC flag is through successfully executing the Match ROM, Search ROM, Conditional Search ROM, or Overdrive-Match ROM command" The function currently works perfectly fine in a multidrop bus, but when we have only a single slave connected, then only a Skip ROM is used and Match ROM is not called at all. This is leading to problems e.g. with single one DS2408 connected, as the Resume Command is not working properly and the device is responding with failing results after the Resume Command. This commit is fixing this by using a Skip ROM instead in those cases. The bandwidth / performance advantage is exactly the same. Refs: [1] https://datasheets.maximintegrated.com/en/ds/DS2408.pdf Signed-off-by: Mariusz Bialonczyk Reviewed-by: Jean-Francois Dagenais Signed-off-by: Greg Kroah-Hartman --- drivers/w1/w1_io.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/w1/w1_io.c b/drivers/w1/w1_io.c index 0364d3329c52..3516ce6718d9 100644 --- a/drivers/w1/w1_io.c +++ b/drivers/w1/w1_io.c @@ -432,8 +432,7 @@ int w1_reset_resume_command(struct w1_master *dev) if (w1_reset_bus(dev)) return -1; - /* This will make only the last matched slave perform a skip ROM. */ - w1_write_8(dev, W1_RESUME_CMD); + w1_write_8(dev, dev->slave_count > 1 ? W1_RESUME_CMD : W1_SKIP_ROM); return 0; } EXPORT_SYMBOL_GPL(w1_reset_resume_command); From a38693d77576145673a7b3d4d771d992282ad13b Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Sun, 28 Apr 2019 10:18:35 +0300 Subject: [PATCH 189/255] habanalabs: return old dram bar address upon change This patch changes the ASIC interface function that changes the DRAM bar window. The change is to return the old address that the DRAM bar pointed to instead of an error code. This simplifies the code that use this function (mainly in debugfs) to restore the bar to the old setting. This is also needed for easier support in future ASICs. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 60 +++++++++++++--------------- drivers/misc/habanalabs/habanalabs.h | 5 ++- drivers/misc/habanalabs/pci.c | 5 ++- 3 files changed, 35 insertions(+), 35 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 8ee3b00b0fab..04e4ed8a0be6 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -389,33 +389,26 @@ static int goya_pci_bars_map(struct hl_device *hdev) return 0; } -/* - * goya_set_ddr_bar_base - set DDR bar to map specific device address - * - * @hdev: pointer to hl_device structure - * @addr: address in DDR. Must be aligned to DDR bar size - * - * This function configures the iATU so that the DDR bar will start at the - * specified addr. - * - */ -static int goya_set_ddr_bar_base(struct hl_device *hdev, u64 addr) +static u64 goya_set_ddr_bar_base(struct hl_device *hdev, u64 addr) { struct goya_device *goya = hdev->asic_specific; + u64 old_addr = addr; int rc; if ((goya) && (goya->ddr_bar_cur_addr == addr)) - return 0; + return old_addr; /* Inbound Region 1 - Bar 4 - Point to DDR */ rc = hl_pci_set_dram_bar_base(hdev, 1, 4, addr); if (rc) - return rc; + return U64_MAX; - if (goya) + if (goya) { + old_addr = goya->ddr_bar_cur_addr; goya->ddr_bar_cur_addr = addr; + } - return 0; + return old_addr; } /* @@ -2215,11 +2208,10 @@ static int goya_init_cpu(struct hl_device *hdev, u32 cpu_timeout) * Before pushing u-boot/linux to device, need to set the ddr bar to * base address of dram */ - rc = goya_set_ddr_bar_base(hdev, DRAM_PHYS_BASE); - if (rc) { + if (goya_set_ddr_bar_base(hdev, DRAM_PHYS_BASE) == U64_MAX) { dev_err(hdev->dev, "failed to map DDR bar to DRAM base address\n"); - return rc; + return -EIO; } if (hdev->pldm) { @@ -2454,12 +2446,12 @@ static int goya_hw_init(struct hl_device *hdev) * After CPU initialization is finished, change DDR bar mapping inside * iATU to point to the start address of the MMU page tables */ - rc = goya_set_ddr_bar_base(hdev, DRAM_PHYS_BASE + - (MMU_PAGE_TABLES_ADDR & ~(prop->dram_pci_bar_size - 0x1ull))); - if (rc) { + if (goya_set_ddr_bar_base(hdev, DRAM_PHYS_BASE + + (MMU_PAGE_TABLES_ADDR & + ~(prop->dram_pci_bar_size - 0x1ull))) == U64_MAX) { dev_err(hdev->dev, "failed to map DDR bar to MMU page tables\n"); - return rc; + return -EIO; } rc = goya_mmu_init(hdev); @@ -3958,6 +3950,7 @@ void goya_restore_phase_topology(struct hl_device *hdev) static int goya_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val) { struct asic_fixed_properties *prop = &hdev->asic_prop; + u64 ddr_bar_addr; int rc = 0; if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) { @@ -3975,15 +3968,16 @@ static int goya_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val) u64 bar_base_addr = DRAM_PHYS_BASE + (addr & ~(prop->dram_pci_bar_size - 0x1ull)); - rc = goya_set_ddr_bar_base(hdev, bar_base_addr); - if (!rc) { + ddr_bar_addr = goya_set_ddr_bar_base(hdev, bar_base_addr); + if (ddr_bar_addr != U64_MAX) { *val = readl(hdev->pcie_bar[DDR_BAR_ID] + (addr - bar_base_addr)); - rc = goya_set_ddr_bar_base(hdev, DRAM_PHYS_BASE + - (MMU_PAGE_TABLES_ADDR & - ~(prop->dram_pci_bar_size - 0x1ull))); + ddr_bar_addr = goya_set_ddr_bar_base(hdev, + ddr_bar_addr); } + if (ddr_bar_addr == U64_MAX) + rc = -EIO; } else { rc = -EFAULT; } @@ -4008,6 +4002,7 @@ static int goya_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val) static int goya_debugfs_write32(struct hl_device *hdev, u64 addr, u32 val) { struct asic_fixed_properties *prop = &hdev->asic_prop; + u64 ddr_bar_addr; int rc = 0; if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) { @@ -4025,15 +4020,16 @@ static int goya_debugfs_write32(struct hl_device *hdev, u64 addr, u32 val) u64 bar_base_addr = DRAM_PHYS_BASE + (addr & ~(prop->dram_pci_bar_size - 0x1ull)); - rc = goya_set_ddr_bar_base(hdev, bar_base_addr); - if (!rc) { + ddr_bar_addr = goya_set_ddr_bar_base(hdev, bar_base_addr); + if (ddr_bar_addr != U64_MAX) { writel(val, hdev->pcie_bar[DDR_BAR_ID] + (addr - bar_base_addr)); - rc = goya_set_ddr_bar_base(hdev, DRAM_PHYS_BASE + - (MMU_PAGE_TABLES_ADDR & - ~(prop->dram_pci_bar_size - 0x1ull))); + ddr_bar_addr = goya_set_ddr_bar_base(hdev, + ddr_bar_addr); } + if (ddr_bar_addr == U64_MAX) + rc = -EIO; } else { rc = -EFAULT; } diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index a624d1e1e1e5..65717e4055da 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -487,7 +487,8 @@ enum hl_pll_frequency { * @send_cpu_message: send buffer to ArmCP. * @get_hw_state: retrieve the H/W state * @pci_bars_map: Map PCI BARs. - * @set_dram_bar_base: Set DRAM BAR to map specific device address. + * @set_dram_bar_base: Set DRAM BAR to map specific device address. Returns + * old address the bar pointed to or U64_MAX for failure * @init_iatu: Initialize the iATU unit inside the PCI controller. * @rreg: Read a register. Needed for simulator support. * @wreg: Write a register. Needed for simulator support. @@ -564,7 +565,7 @@ struct hl_asic_funcs { u16 len, u32 timeout, long *result); enum hl_device_hw_state (*get_hw_state)(struct hl_device *hdev); int (*pci_bars_map)(struct hl_device *hdev); - int (*set_dram_bar_base)(struct hl_device *hdev, u64 addr); + u64 (*set_dram_bar_base)(struct hl_device *hdev, u64 addr); int (*init_iatu)(struct hl_device *hdev); u32 (*rreg)(struct hl_device *hdev, u32 reg); void (*wreg)(struct hl_device *hdev, u32 reg, u32 val); diff --git a/drivers/misc/habanalabs/pci.c b/drivers/misc/habanalabs/pci.c index d472d02a8e6e..5278f086d65d 100644 --- a/drivers/misc/habanalabs/pci.c +++ b/drivers/misc/habanalabs/pci.c @@ -259,7 +259,10 @@ int hl_pci_init_iatu(struct hl_device *hdev, u64 sram_base_address, /* Point to DRAM */ if (!hdev->asic_funcs->set_dram_bar_base) return -EINVAL; - rc |= hdev->asic_funcs->set_dram_bar_base(hdev, dram_base_address); + if (hdev->asic_funcs->set_dram_bar_base(hdev, dram_base_address) == + U64_MAX) + return -EIO; + /* Outbound Region 0 - Point to Host */ host_phys_end_addr = prop->host_phys_base_address + host_phys_size - 1; From 03d5f641dc711eb93145ded91ed68b4be729be4d Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Sun, 28 Apr 2019 19:17:38 +0300 Subject: [PATCH 190/255] habanalabs: Use single pool for CPU accessible host memory The device's CPU accessible memory on host is managed in a dedicated pool, except for 2 regions - Primary Queue (PQ) and Event Queue (EQ) - which are allocated from generic DMA pools. Due to address length limitations of the CPU, the addresses of all these memory regions must have the same MSBs starting at bit 40. This patch modifies the allocation of the PQ and EQ to be also from the dedicated pool, to ensure compliance with the limitation. Signed-off-by: Tomer Tayar Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/habanalabs.h | 12 +++++++ drivers/misc/habanalabs/hw_queue.c | 40 ++++++++++++++++------ drivers/misc/habanalabs/include/armcp_if.h | 8 ----- drivers/misc/habanalabs/irq.c | 10 +++--- 4 files changed, 48 insertions(+), 22 deletions(-) diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 65717e4055da..687651db614c 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -321,6 +321,18 @@ struct hl_cs_job; #define HL_EQ_LENGTH 64 #define HL_EQ_SIZE_IN_BYTES (HL_EQ_LENGTH * HL_EQ_ENTRY_SIZE) +#define HL_CPU_PKT_SHIFT 5 +#define HL_CPU_PKT_SIZE (1 << HL_CPU_PKT_SHIFT) +#define HL_CPU_PKT_MASK (~((1 << HL_CPU_PKT_SHIFT) - 1)) +#define HL_CPU_MAX_PKTS_IN_CB 32 +#define HL_CPU_CB_SIZE (HL_CPU_PKT_SIZE * \ + HL_CPU_MAX_PKTS_IN_CB) +#define HL_CPU_CB_QUEUE_SIZE (HL_QUEUE_LENGTH * HL_CPU_CB_SIZE) + +/* KMD <-> ArmCP shared memory size (EQ + PQ + CPU CB queue) */ +#define HL_CPU_ACCESSIBLE_MEM_SIZE (HL_EQ_SIZE_IN_BYTES + \ + HL_QUEUE_SIZE_IN_BYTES + \ + HL_CPU_CB_QUEUE_SIZE) /** * struct hl_hw_queue - describes a H/W transport queue. diff --git a/drivers/misc/habanalabs/hw_queue.c b/drivers/misc/habanalabs/hw_queue.c index ef3bb6951360..a1ee52cfd505 100644 --- a/drivers/misc/habanalabs/hw_queue.c +++ b/drivers/misc/habanalabs/hw_queue.c @@ -415,14 +415,20 @@ void hl_hw_queue_inc_ci_kernel(struct hl_device *hdev, u32 hw_queue_id) } static int ext_and_cpu_hw_queue_init(struct hl_device *hdev, - struct hl_hw_queue *q) + struct hl_hw_queue *q, bool is_cpu_queue) { void *p; int rc; - p = hdev->asic_funcs->dma_alloc_coherent(hdev, - HL_QUEUE_SIZE_IN_BYTES, - &q->bus_address, GFP_KERNEL | __GFP_ZERO); + if (is_cpu_queue) + p = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, + HL_QUEUE_SIZE_IN_BYTES, + &q->bus_address); + else + p = hdev->asic_funcs->dma_alloc_coherent(hdev, + HL_QUEUE_SIZE_IN_BYTES, + &q->bus_address, + GFP_KERNEL | __GFP_ZERO); if (!p) return -ENOMEM; @@ -446,8 +452,15 @@ static int ext_and_cpu_hw_queue_init(struct hl_device *hdev, return 0; free_queue: - hdev->asic_funcs->dma_free_coherent(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address, q->bus_address); + if (is_cpu_queue) + hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, + HL_QUEUE_SIZE_IN_BYTES, + (void *) (uintptr_t) q->kernel_address); + else + hdev->asic_funcs->dma_free_coherent(hdev, + HL_QUEUE_SIZE_IN_BYTES, + (void *) (uintptr_t) q->kernel_address, + q->bus_address); return rc; } @@ -474,12 +487,12 @@ static int int_hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q) static int cpu_hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q) { - return ext_and_cpu_hw_queue_init(hdev, q); + return ext_and_cpu_hw_queue_init(hdev, q, true); } static int ext_hw_queue_init(struct hl_device *hdev, struct hl_hw_queue *q) { - return ext_and_cpu_hw_queue_init(hdev, q); + return ext_and_cpu_hw_queue_init(hdev, q, false); } /* @@ -569,8 +582,15 @@ static void hw_queue_fini(struct hl_device *hdev, struct hl_hw_queue *q) kfree(q->shadow_queue); - hdev->asic_funcs->dma_free_coherent(hdev, HL_QUEUE_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address, q->bus_address); + if (q->queue_type == QUEUE_TYPE_CPU) + hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, + HL_QUEUE_SIZE_IN_BYTES, + (void *) (uintptr_t) q->kernel_address); + else + hdev->asic_funcs->dma_free_coherent(hdev, + HL_QUEUE_SIZE_IN_BYTES, + (void *) (uintptr_t) q->kernel_address, + q->bus_address); } int hl_hw_queues_create(struct hl_device *hdev) diff --git a/drivers/misc/habanalabs/include/armcp_if.h b/drivers/misc/habanalabs/include/armcp_if.h index c8f28cadc335..1f1e35e86d84 100644 --- a/drivers/misc/habanalabs/include/armcp_if.h +++ b/drivers/misc/habanalabs/include/armcp_if.h @@ -300,14 +300,6 @@ enum armcp_pwm_attributes { armcp_pwm_enable }; -#define HL_CPU_PKT_SHIFT 5 -#define HL_CPU_PKT_SIZE (1 << HL_CPU_PKT_SHIFT) -#define HL_CPU_PKT_MASK (~((1 << HL_CPU_PKT_SHIFT) - 1)) -#define HL_CPU_MAX_PKTS_IN_CB 32 -#define HL_CPU_CB_SIZE (HL_CPU_PKT_SIZE * \ - HL_CPU_MAX_PKTS_IN_CB) -#define HL_CPU_ACCESSIBLE_MEM_SIZE (HL_QUEUE_LENGTH * HL_CPU_CB_SIZE) - /* Event Queue Packets */ struct eq_generic_event { diff --git a/drivers/misc/habanalabs/irq.c b/drivers/misc/habanalabs/irq.c index e69a09c10e3f..86a8ad57f1ca 100644 --- a/drivers/misc/habanalabs/irq.c +++ b/drivers/misc/habanalabs/irq.c @@ -284,8 +284,9 @@ int hl_eq_init(struct hl_device *hdev, struct hl_eq *q) BUILD_BUG_ON(HL_EQ_SIZE_IN_BYTES > HL_PAGE_SIZE); - p = hdev->asic_funcs->dma_alloc_coherent(hdev, HL_EQ_SIZE_IN_BYTES, - &q->bus_address, GFP_KERNEL | __GFP_ZERO); + p = hdev->asic_funcs->cpu_accessible_dma_pool_alloc(hdev, + HL_EQ_SIZE_IN_BYTES, + &q->bus_address); if (!p) return -ENOMEM; @@ -308,8 +309,9 @@ void hl_eq_fini(struct hl_device *hdev, struct hl_eq *q) { flush_workqueue(hdev->eq_wq); - hdev->asic_funcs->dma_free_coherent(hdev, HL_EQ_SIZE_IN_BYTES, - (void *) (uintptr_t) q->kernel_address, q->bus_address); + hdev->asic_funcs->cpu_accessible_dma_pool_free(hdev, + HL_EQ_SIZE_IN_BYTES, + (void *) (uintptr_t) q->kernel_address); } void hl_eq_reset(struct hl_device *hdev, struct hl_eq *q) From 3706b47006a9c8aa867d314f913d3b1310163d63 Mon Sep 17 00:00:00 2001 From: Dalit Ben Zoor Date: Tue, 30 Apr 2019 15:22:14 +0300 Subject: [PATCH 191/255] habanalabs: remove call to cs_parser() There is no need to parse the command submission when doing memset of the device memory using the DMA engine because only the driver calls the memset function and therefore, the CS is trusted and doesn't require validation and patching. Signed-off-by: Dalit Ben Zoor Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 27 +++------------------------ 1 file changed, 3 insertions(+), 24 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 04e4ed8a0be6..9fc8b6e1369d 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -4398,7 +4398,6 @@ static int goya_memset_device_memory(struct hl_device *hdev, u64 addr, u32 size, u64 val, bool is_dram) { struct packet_lin_dma *lin_dma_pkt; - struct hl_cs_parser parser; struct hl_cs_job *job; u32 cb_size, ctl; struct hl_cb *cb; @@ -4438,36 +4437,16 @@ static int goya_memset_device_memory(struct hl_device *hdev, u64 addr, u32 size, job->user_cb->cs_cnt++; job->user_cb_size = cb_size; job->hw_queue_id = GOYA_QUEUE_ID_DMA_0; + job->patched_cb = job->user_cb; + job->job_cb_size = job->user_cb_size + + sizeof(struct packet_msg_prot) * 2; hl_debugfs_add_job(hdev, job); - parser.ctx_id = HL_KERNEL_ASID_ID; - parser.cs_sequence = 0; - parser.job_id = job->id; - parser.hw_queue_id = job->hw_queue_id; - parser.job_userptr_list = &job->userptr_list; - parser.user_cb = job->user_cb; - parser.user_cb_size = job->user_cb_size; - parser.ext_queue = job->ext_queue; - parser.use_virt_addr = hdev->mmu_enable; - - rc = hdev->asic_funcs->cs_parser(hdev, &parser); - if (rc) { - dev_err(hdev->dev, "Failed to parse kernel CB\n"); - goto free_job; - } - - job->patched_cb = parser.patched_cb; - job->job_cb_size = parser.patched_cb_size; - job->patched_cb->cs_cnt++; - rc = goya_send_job_on_qman0(hdev, job); - job->patched_cb->cs_cnt--; hl_cb_put(job->patched_cb); -free_job: - hl_userptr_delete_list(hdev, &job->userptr_list); hl_debugfs_remove_job(hdev, job); kfree(job); cb->cs_cnt--; From d9c3aa8038c391f38a391289989ca0ac356a9501 Mon Sep 17 00:00:00 2001 From: Oded Gabbay Date: Wed, 1 May 2019 11:47:04 +0300 Subject: [PATCH 192/255] habanalabs: rename functions to improve code readability This patch renames four functions in the ASIC-specific functions section, so it will be easier to differentiate them from the generic kernel functions with the same name. This will help in future code reviews, to make sure we don't use the kernel functions directly. Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/command_buffer.c | 6 ++--- drivers/misc/habanalabs/goya/goya.c | 28 ++++++++++++---------- drivers/misc/habanalabs/habanalabs.h | 30 ++++++++++++------------ drivers/misc/habanalabs/hw_queue.c | 6 ++--- drivers/misc/habanalabs/irq.c | 4 ++-- 5 files changed, 38 insertions(+), 36 deletions(-) diff --git a/drivers/misc/habanalabs/command_buffer.c b/drivers/misc/habanalabs/command_buffer.c index b1ffca47d748..e495f44064fa 100644 --- a/drivers/misc/habanalabs/command_buffer.c +++ b/drivers/misc/habanalabs/command_buffer.c @@ -13,7 +13,7 @@ static void cb_fini(struct hl_device *hdev, struct hl_cb *cb) { - hdev->asic_funcs->dma_free_coherent(hdev, cb->size, + hdev->asic_funcs->asic_dma_free_coherent(hdev, cb->size, (void *) (uintptr_t) cb->kernel_address, cb->bus_address); kfree(cb); @@ -66,10 +66,10 @@ static struct hl_cb *hl_cb_alloc(struct hl_device *hdev, u32 cb_size, return NULL; if (ctx_id == HL_KERNEL_ASID_ID) - p = hdev->asic_funcs->dma_alloc_coherent(hdev, cb_size, + p = hdev->asic_funcs->asic_dma_alloc_coherent(hdev, cb_size, &cb->bus_address, GFP_ATOMIC); else - p = hdev->asic_funcs->dma_alloc_coherent(hdev, cb_size, + p = hdev->asic_funcs->asic_dma_alloc_coherent(hdev, cb_size, &cb->bus_address, GFP_USER | __GFP_ZERO); if (!p) { diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 9fc8b6e1369d..8e18c80a22e7 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -646,7 +646,7 @@ static int goya_sw_init(struct hl_device *hdev) } hdev->cpu_accessible_dma_mem = - hdev->asic_funcs->dma_alloc_coherent(hdev, + hdev->asic_funcs->asic_dma_alloc_coherent(hdev, HL_CPU_ACCESSIBLE_MEM_SIZE, &hdev->cpu_accessible_dma_address, GFP_KERNEL | __GFP_ZERO); @@ -681,7 +681,8 @@ static int goya_sw_init(struct hl_device *hdev) free_cpu_pq_pool: gen_pool_destroy(hdev->cpu_accessible_dma_pool); free_cpu_pq_dma_mem: - hdev->asic_funcs->dma_free_coherent(hdev, HL_CPU_ACCESSIBLE_MEM_SIZE, + hdev->asic_funcs->asic_dma_free_coherent(hdev, + HL_CPU_ACCESSIBLE_MEM_SIZE, hdev->cpu_accessible_dma_mem, hdev->cpu_accessible_dma_address); free_dma_pool: @@ -704,7 +705,8 @@ static int goya_sw_fini(struct hl_device *hdev) gen_pool_destroy(hdev->cpu_accessible_dma_pool); - hdev->asic_funcs->dma_free_coherent(hdev, HL_CPU_ACCESSIBLE_MEM_SIZE, + hdev->asic_funcs->asic_dma_free_coherent(hdev, + HL_CPU_ACCESSIBLE_MEM_SIZE, hdev->cpu_accessible_dma_mem, hdev->cpu_accessible_dma_address); @@ -2818,7 +2820,7 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) return -EBUSY; } - fence_ptr = hdev->asic_funcs->dma_pool_zalloc(hdev, 4, GFP_KERNEL, + fence_ptr = hdev->asic_funcs->asic_dma_pool_zalloc(hdev, 4, GFP_KERNEL, &fence_dma_addr); if (!fence_ptr) { dev_err(hdev->dev, @@ -2867,7 +2869,7 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) } free_fence_ptr: - hdev->asic_funcs->dma_pool_free(hdev, (void *) fence_ptr, + hdev->asic_funcs->asic_dma_pool_free(hdev, (void *) fence_ptr, fence_dma_addr); goya_qman0_set_security(hdev, false); @@ -2901,7 +2903,7 @@ int goya_test_queue(struct hl_device *hdev, u32 hw_queue_id) fence_val = GOYA_QMAN0_FENCE_VAL; - fence_ptr = hdev->asic_funcs->dma_pool_zalloc(hdev, 4, GFP_KERNEL, + fence_ptr = hdev->asic_funcs->asic_dma_pool_zalloc(hdev, 4, GFP_KERNEL, &fence_dma_addr); if (!fence_ptr) { dev_err(hdev->dev, @@ -2911,7 +2913,7 @@ int goya_test_queue(struct hl_device *hdev, u32 hw_queue_id) *fence_ptr = 0; - fence_pkt = hdev->asic_funcs->dma_pool_zalloc(hdev, + fence_pkt = hdev->asic_funcs->asic_dma_pool_zalloc(hdev, sizeof(struct packet_msg_prot), GFP_KERNEL, &pkt_dma_addr); if (!fence_pkt) { @@ -2955,10 +2957,10 @@ int goya_test_queue(struct hl_device *hdev, u32 hw_queue_id) } free_pkt: - hdev->asic_funcs->dma_pool_free(hdev, (void *) fence_pkt, + hdev->asic_funcs->asic_dma_pool_free(hdev, (void *) fence_pkt, pkt_dma_addr); free_fence_ptr: - hdev->asic_funcs->dma_pool_free(hdev, (void *) fence_ptr, + hdev->asic_funcs->asic_dma_pool_free(hdev, (void *) fence_ptr, fence_dma_addr); return rc; } @@ -4755,12 +4757,12 @@ static const struct hl_asic_funcs goya_funcs = { .cb_mmap = goya_cb_mmap, .ring_doorbell = goya_ring_doorbell, .flush_pq_write = goya_flush_pq_write, - .dma_alloc_coherent = goya_dma_alloc_coherent, - .dma_free_coherent = goya_dma_free_coherent, + .asic_dma_alloc_coherent = goya_dma_alloc_coherent, + .asic_dma_free_coherent = goya_dma_free_coherent, .get_int_queue_base = goya_get_int_queue_base, .test_queues = goya_test_queues, - .dma_pool_zalloc = goya_dma_pool_zalloc, - .dma_pool_free = goya_dma_pool_free, + .asic_dma_pool_zalloc = goya_dma_pool_zalloc, + .asic_dma_pool_free = goya_dma_pool_free, .cpu_accessible_dma_pool_alloc = goya_cpu_accessible_dma_pool_alloc, .cpu_accessible_dma_pool_free = goya_cpu_accessible_dma_pool_free, .hl_dma_unmap_sg = goya_dma_unmap_sg, diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 687651db614c..b64594be6dbd 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -453,19 +453,19 @@ enum hl_pll_frequency { * @cb_mmap: maps a CB. * @ring_doorbell: increment PI on a given QMAN. * @flush_pq_write: flush PQ entry write if necessary, WARN if flushing failed. - * @dma_alloc_coherent: Allocate coherent DMA memory by calling - * dma_alloc_coherent(). This is ASIC function because its - * implementation is not trivial when the driver is loaded - * in simulation mode (not upstreamed). - * @dma_free_coherent: Free coherent DMA memory by calling dma_free_coherent(). - * This is ASIC function because its implementation is not - * trivial when the driver is loaded in simulation mode - * (not upstreamed). + * @asic_dma_alloc_coherent: Allocate coherent DMA memory by calling + * dma_alloc_coherent(). This is ASIC function because + * its implementation is not trivial when the driver + * is loaded in simulation mode (not upstreamed). + * @asic_dma_free_coherent: Free coherent DMA memory by calling + * dma_free_coherent(). This is ASIC function because + * its implementation is not trivial when the driver + * is loaded in simulation mode (not upstreamed). * @get_int_queue_base: get the internal queue base address. * @test_queues: run simple test on all queues for sanity check. - * @dma_pool_zalloc: small DMA allocation of coherent memory from DMA pool. - * size of allocation is HL_DMA_POOL_BLK_SIZE. - * @dma_pool_free: free small DMA allocation from pool. + * @asic_dma_pool_zalloc: small DMA allocation of coherent memory from DMA pool. + * size of allocation is HL_DMA_POOL_BLK_SIZE. + * @asic_dma_pool_free: free small DMA allocation from pool. * @cpu_accessible_dma_pool_alloc: allocate CPU PQ packet from DMA pool. * @cpu_accessible_dma_pool_free: free CPU PQ packet from DMA pool. * @hl_dma_unmap_sg: DMA unmap scatter-gather list. @@ -521,16 +521,16 @@ struct hl_asic_funcs { u64 kaddress, phys_addr_t paddress, u32 size); void (*ring_doorbell)(struct hl_device *hdev, u32 hw_queue_id, u32 pi); void (*flush_pq_write)(struct hl_device *hdev, u64 *pq, u64 exp_val); - void* (*dma_alloc_coherent)(struct hl_device *hdev, size_t size, + void* (*asic_dma_alloc_coherent)(struct hl_device *hdev, size_t size, dma_addr_t *dma_handle, gfp_t flag); - void (*dma_free_coherent)(struct hl_device *hdev, size_t size, + void (*asic_dma_free_coherent)(struct hl_device *hdev, size_t size, void *cpu_addr, dma_addr_t dma_handle); void* (*get_int_queue_base)(struct hl_device *hdev, u32 queue_id, dma_addr_t *dma_handle, u16 *queue_len); int (*test_queues)(struct hl_device *hdev); - void* (*dma_pool_zalloc)(struct hl_device *hdev, size_t size, + void* (*asic_dma_pool_zalloc)(struct hl_device *hdev, size_t size, gfp_t mem_flags, dma_addr_t *dma_handle); - void (*dma_pool_free)(struct hl_device *hdev, void *vaddr, + void (*asic_dma_pool_free)(struct hl_device *hdev, void *vaddr, dma_addr_t dma_addr); void* (*cpu_accessible_dma_pool_alloc)(struct hl_device *hdev, size_t size, dma_addr_t *dma_handle); diff --git a/drivers/misc/habanalabs/hw_queue.c b/drivers/misc/habanalabs/hw_queue.c index a1ee52cfd505..6cdaa117fc40 100644 --- a/drivers/misc/habanalabs/hw_queue.c +++ b/drivers/misc/habanalabs/hw_queue.c @@ -425,7 +425,7 @@ static int ext_and_cpu_hw_queue_init(struct hl_device *hdev, HL_QUEUE_SIZE_IN_BYTES, &q->bus_address); else - p = hdev->asic_funcs->dma_alloc_coherent(hdev, + p = hdev->asic_funcs->asic_dma_alloc_coherent(hdev, HL_QUEUE_SIZE_IN_BYTES, &q->bus_address, GFP_KERNEL | __GFP_ZERO); @@ -457,7 +457,7 @@ static int ext_and_cpu_hw_queue_init(struct hl_device *hdev, HL_QUEUE_SIZE_IN_BYTES, (void *) (uintptr_t) q->kernel_address); else - hdev->asic_funcs->dma_free_coherent(hdev, + hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_QUEUE_SIZE_IN_BYTES, (void *) (uintptr_t) q->kernel_address, q->bus_address); @@ -587,7 +587,7 @@ static void hw_queue_fini(struct hl_device *hdev, struct hl_hw_queue *q) HL_QUEUE_SIZE_IN_BYTES, (void *) (uintptr_t) q->kernel_address); else - hdev->asic_funcs->dma_free_coherent(hdev, + hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_QUEUE_SIZE_IN_BYTES, (void *) (uintptr_t) q->kernel_address, q->bus_address); diff --git a/drivers/misc/habanalabs/irq.c b/drivers/misc/habanalabs/irq.c index 86a8ad57f1ca..ea9f72ff456c 100644 --- a/drivers/misc/habanalabs/irq.c +++ b/drivers/misc/habanalabs/irq.c @@ -222,7 +222,7 @@ int hl_cq_init(struct hl_device *hdev, struct hl_cq *q, u32 hw_queue_id) BUILD_BUG_ON(HL_CQ_SIZE_IN_BYTES > HL_PAGE_SIZE); - p = hdev->asic_funcs->dma_alloc_coherent(hdev, HL_CQ_SIZE_IN_BYTES, + p = hdev->asic_funcs->asic_dma_alloc_coherent(hdev, HL_CQ_SIZE_IN_BYTES, &q->bus_address, GFP_KERNEL | __GFP_ZERO); if (!p) return -ENOMEM; @@ -248,7 +248,7 @@ int hl_cq_init(struct hl_device *hdev, struct hl_cq *q, u32 hw_queue_id) */ void hl_cq_fini(struct hl_device *hdev, struct hl_cq *q) { - hdev->asic_funcs->dma_free_coherent(hdev, HL_CQ_SIZE_IN_BYTES, + hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_CQ_SIZE_IN_BYTES, (void *) (uintptr_t) q->kernel_address, q->bus_address); } From 94cb669ceb0589f24ee91e3a8ae8ed3013fd6904 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Wed, 1 May 2019 11:28:15 +0300 Subject: [PATCH 193/255] habanalabs: Manipulate DMA addresses in ASIC functions Routing device accesses to the host memory requires the usage of a base offset, which is canceled by the iATU just before leaving the device. The value of the base offset might be distinctive between different ASIC types. The manipulation of the addresses is currently used throughout the driver code, and one should be aware to it whenever providing a host memory address to the device. This patch removes this manipulation from the driver common code, and moves it to the ASIC specific functions that are responsible for host memory allocation/mapping. Signed-off-by: Tomer Tayar Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/firmware_if.c | 7 +-- drivers/misc/habanalabs/goya/goya.c | 90 +++++++++++++++++---------- drivers/misc/habanalabs/habanalabs.h | 10 ++- drivers/misc/habanalabs/hw_queue.c | 6 +- drivers/misc/habanalabs/memory.c | 4 -- drivers/misc/habanalabs/pci.c | 11 ++-- 6 files changed, 72 insertions(+), 56 deletions(-) diff --git a/drivers/misc/habanalabs/firmware_if.c b/drivers/misc/habanalabs/firmware_if.c index 1acf82650b20..eda5d7fcb79f 100644 --- a/drivers/misc/habanalabs/firmware_if.c +++ b/drivers/misc/habanalabs/firmware_if.c @@ -249,8 +249,7 @@ int hl_fw_armcp_info_get(struct hl_device *hdev) pkt.ctl = cpu_to_le32(ARMCP_PACKET_INFO_GET << ARMCP_PKT_CTL_OPCODE_SHIFT); - pkt.addr = cpu_to_le64(armcp_info_dma_addr + - prop->host_phys_base_address); + pkt.addr = cpu_to_le64(armcp_info_dma_addr); pkt.data_max_size = cpu_to_le32(sizeof(struct armcp_info)); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), @@ -281,7 +280,6 @@ int hl_fw_armcp_info_get(struct hl_device *hdev) int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size) { - struct asic_fixed_properties *prop = &hdev->asic_prop; struct armcp_packet pkt = {}; void *eeprom_info_cpu_addr; dma_addr_t eeprom_info_dma_addr; @@ -301,8 +299,7 @@ int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size) pkt.ctl = cpu_to_le32(ARMCP_PACKET_EEPROM_DATA_GET << ARMCP_PKT_CTL_OPCODE_SHIFT); - pkt.addr = cpu_to_le64(eeprom_info_dma_addr + - prop->host_phys_base_address); + pkt.addr = cpu_to_le64(eeprom_info_dma_addr); pkt.data_max_size = cpu_to_le32(max_size); rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt), diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 8e18c80a22e7..31dc3b872f9e 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -345,7 +345,6 @@ void goya_get_fixed_properties(struct hl_device *hdev) prop->mmu_hop0_tables_total_size = HOP0_TABLES_TOTAL_SIZE; prop->dram_page_size = PAGE_SIZE_2MB; - prop->host_phys_base_address = HOST_PHYS_BASE; prop->va_space_host_start_address = VA_HOST_SPACE_START; prop->va_space_host_end_address = VA_HOST_SPACE_END; prop->va_space_dram_start_address = VA_DDR_SPACE_START; @@ -422,7 +421,7 @@ static u64 goya_set_ddr_bar_base(struct hl_device *hdev, u64 addr) static int goya_init_iatu(struct hl_device *hdev) { return hl_pci_init_iatu(hdev, SRAM_BASE_ADDR, DRAM_PHYS_BASE, - HOST_PHYS_SIZE); + HOST_PHYS_BASE, HOST_PHYS_SIZE); } /* @@ -804,7 +803,6 @@ void goya_init_dma_qmans(struct hl_device *hdev) { struct goya_device *goya = hdev->asic_specific; struct hl_hw_queue *q; - dma_addr_t bus_address; int i; if (goya->hw_cap_initialized & HW_CAP_DMA) @@ -813,10 +811,7 @@ void goya_init_dma_qmans(struct hl_device *hdev) q = &hdev->kernel_queues[0]; for (i = 0 ; i < NUMBER_OF_EXT_HW_QUEUES ; i++, q++) { - bus_address = q->bus_address + - hdev->asic_prop.host_phys_base_address; - - goya_init_dma_qman(hdev, i, bus_address); + goya_init_dma_qman(hdev, i, q->bus_address); goya_init_dma_ch(hdev, i); } @@ -957,7 +952,6 @@ int goya_init_cpu_queues(struct hl_device *hdev) { struct goya_device *goya = hdev->asic_specific; struct hl_eq *eq; - dma_addr_t bus_address; u32 status; struct hl_hw_queue *cpu_pq = &hdev->kernel_queues[GOYA_QUEUE_ID_CPU_PQ]; int err; @@ -970,19 +964,18 @@ int goya_init_cpu_queues(struct hl_device *hdev) eq = &hdev->event_queue; - bus_address = cpu_pq->bus_address + - hdev->asic_prop.host_phys_base_address; - WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_0, lower_32_bits(bus_address)); - WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_1, upper_32_bits(bus_address)); + WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_0, + lower_32_bits(cpu_pq->bus_address)); + WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_1, + upper_32_bits(cpu_pq->bus_address)); - bus_address = eq->bus_address + hdev->asic_prop.host_phys_base_address; - WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_2, lower_32_bits(bus_address)); - WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_3, upper_32_bits(bus_address)); + WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_2, lower_32_bits(eq->bus_address)); + WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_3, upper_32_bits(eq->bus_address)); - bus_address = hdev->cpu_accessible_dma_address + - hdev->asic_prop.host_phys_base_address; - WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_8, lower_32_bits(bus_address)); - WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_9, upper_32_bits(bus_address)); + WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_8, + lower_32_bits(hdev->cpu_accessible_dma_address)); + WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_9, + upper_32_bits(hdev->cpu_accessible_dma_address)); WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_5, HL_QUEUE_SIZE_IN_BYTES); WREG32(mmPSOC_GLOBAL_CONF_SCRATCHPAD_4, HL_EQ_SIZE_IN_BYTES); @@ -2731,13 +2724,23 @@ void goya_flush_pq_write(struct hl_device *hdev, u64 *pq, u64 exp_val) static void *goya_dma_alloc_coherent(struct hl_device *hdev, size_t size, dma_addr_t *dma_handle, gfp_t flags) { - return dma_alloc_coherent(&hdev->pdev->dev, size, dma_handle, flags); + void *kernel_addr = dma_alloc_coherent(&hdev->pdev->dev, size, + dma_handle, flags); + + /* Shift to the device's base physical address of host memory */ + if (kernel_addr) + *dma_handle += HOST_PHYS_BASE; + + return kernel_addr; } static void goya_dma_free_coherent(struct hl_device *hdev, size_t size, void *cpu_addr, dma_addr_t dma_handle) { - dma_free_coherent(&hdev->pdev->dev, size, cpu_addr, dma_handle); + /* Cancel the device's base physical address of host memory */ + dma_addr_t fixed_dma_handle = dma_handle - HOST_PHYS_BASE; + + dma_free_coherent(&hdev->pdev->dev, size, cpu_addr, fixed_dma_handle); } void *goya_get_int_queue_base(struct hl_device *hdev, u32 queue_id, @@ -2848,8 +2851,7 @@ static int goya_send_job_on_qman0(struct hl_device *hdev, struct hl_cs_job *job) (1 << GOYA_PKT_CTL_MB_SHIFT); fence_pkt->ctl = cpu_to_le32(tmp); fence_pkt->value = cpu_to_le32(GOYA_QMAN0_FENCE_VAL); - fence_pkt->addr = cpu_to_le64(fence_dma_addr + - hdev->asic_prop.host_phys_base_address); + fence_pkt->addr = cpu_to_le64(fence_dma_addr); rc = hl_hw_queue_send_cb_no_cmpl(hdev, GOYA_QUEUE_ID_DMA_0, job->job_cb_size, cb->bus_address); @@ -2928,8 +2930,7 @@ int goya_test_queue(struct hl_device *hdev, u32 hw_queue_id) (1 << GOYA_PKT_CTL_MB_SHIFT); fence_pkt->ctl = cpu_to_le32(tmp); fence_pkt->value = cpu_to_le32(fence_val); - fence_pkt->addr = cpu_to_le64(fence_dma_addr + - hdev->asic_prop.host_phys_base_address); + fence_pkt->addr = cpu_to_le64(fence_dma_addr); rc = hl_hw_queue_send_cb_no_cmpl(hdev, hw_queue_id, sizeof(struct packet_msg_prot), @@ -3001,16 +3002,27 @@ int goya_test_queues(struct hl_device *hdev) static void *goya_dma_pool_zalloc(struct hl_device *hdev, size_t size, gfp_t mem_flags, dma_addr_t *dma_handle) { + void *kernel_addr; + if (size > GOYA_DMA_POOL_BLK_SIZE) return NULL; - return dma_pool_zalloc(hdev->dma_pool, mem_flags, dma_handle); + kernel_addr = dma_pool_zalloc(hdev->dma_pool, mem_flags, dma_handle); + + /* Shift to the device's base physical address of host memory */ + if (kernel_addr) + *dma_handle += HOST_PHYS_BASE; + + return kernel_addr; } static void goya_dma_pool_free(struct hl_device *hdev, void *vaddr, dma_addr_t dma_addr) { - dma_pool_free(hdev->dma_pool, vaddr, dma_addr); + /* Cancel the device's base physical address of host memory */ + dma_addr_t fixed_dma_addr = dma_addr - HOST_PHYS_BASE; + + dma_pool_free(hdev->dma_pool, vaddr, fixed_dma_addr); } void *goya_cpu_accessible_dma_pool_alloc(struct hl_device *hdev, size_t size, @@ -3025,19 +3037,33 @@ void goya_cpu_accessible_dma_pool_free(struct hl_device *hdev, size_t size, hl_fw_cpu_accessible_dma_pool_free(hdev, size, vaddr); } -static int goya_dma_map_sg(struct hl_device *hdev, struct scatterlist *sg, +static int goya_dma_map_sg(struct hl_device *hdev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) { - if (!dma_map_sg(&hdev->pdev->dev, sg, nents, dir)) + struct scatterlist *sg; + int i; + + if (!dma_map_sg(&hdev->pdev->dev, sgl, nents, dir)) return -ENOMEM; + /* Shift to the device's base physical address of host memory */ + for_each_sg(sgl, sg, nents, i) + sg->dma_address += HOST_PHYS_BASE; + return 0; } -static void goya_dma_unmap_sg(struct hl_device *hdev, struct scatterlist *sg, +static void goya_dma_unmap_sg(struct hl_device *hdev, struct scatterlist *sgl, int nents, enum dma_data_direction dir) { - dma_unmap_sg(&hdev->pdev->dev, sg, nents, dir); + struct scatterlist *sg; + int i; + + /* Cancel the device's base physical address of host memory */ + for_each_sg(sgl, sg, nents, i) + sg->dma_address -= HOST_PHYS_BASE; + + dma_unmap_sg(&hdev->pdev->dev, sgl, nents, dir); } u32 goya_get_dma_desc_list_size(struct hl_device *hdev, struct sg_table *sgt) @@ -3589,8 +3615,6 @@ static int goya_patch_dma_packet(struct hl_device *hdev, new_dma_pkt->ctl = cpu_to_le32(ctl); new_dma_pkt->tsize = cpu_to_le32((u32) len); - dma_addr += hdev->asic_prop.host_phys_base_address; - if (dir == DMA_TO_DEVICE) { new_dma_pkt->src_addr = cpu_to_le64(dma_addr); new_dma_pkt->dst_addr = cpu_to_le64(device_memory_addr); diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index b64594be6dbd..f08f71982585 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -135,8 +135,6 @@ enum hl_device_hw_state { * @dram_user_base_address: DRAM physical start address for user access. * @dram_size: DRAM total size. * @dram_pci_bar_size: size of PCI bar towards DRAM. - * @host_phys_base_address: base physical address of host memory for - * transactions that the device generates. * @max_power_default: max power of the device after reset * @va_space_host_start_address: base address of virtual memory range for * mapping host memory. @@ -184,7 +182,6 @@ struct asic_fixed_properties { u64 dram_user_base_address; u64 dram_size; u64 dram_pci_bar_size; - u64 host_phys_base_address; u64 max_power_default; u64 va_space_host_start_address; u64 va_space_host_end_address; @@ -537,11 +534,11 @@ struct hl_asic_funcs { void (*cpu_accessible_dma_pool_free)(struct hl_device *hdev, size_t size, void *vaddr); void (*hl_dma_unmap_sg)(struct hl_device *hdev, - struct scatterlist *sg, int nents, + struct scatterlist *sgl, int nents, enum dma_data_direction dir); int (*cs_parser)(struct hl_device *hdev, struct hl_cs_parser *parser); int (*asic_dma_map_sg)(struct hl_device *hdev, - struct scatterlist *sg, int nents, + struct scatterlist *sgl, int nents, enum dma_data_direction dir); u32 (*get_dma_desc_list_size)(struct hl_device *hdev, struct sg_table *sgt); @@ -1450,7 +1447,8 @@ int hl_pci_iatu_write(struct hl_device *hdev, u32 addr, u32 data); int hl_pci_set_dram_bar_base(struct hl_device *hdev, u8 inbound_region, u8 bar, u64 addr); int hl_pci_init_iatu(struct hl_device *hdev, u64 sram_base_address, - u64 dram_base_address, u64 host_phys_size); + u64 dram_base_address, u64 host_phys_base_address, + u64 host_phys_size); int hl_pci_init(struct hl_device *hdev, u8 dma_mask); void hl_pci_fini(struct hl_device *hdev); int hl_pci_set_dma_mask(struct hl_device *hdev, u8 dma_mask); diff --git a/drivers/misc/habanalabs/hw_queue.c b/drivers/misc/habanalabs/hw_queue.c index 6cdaa117fc40..2894d8975933 100644 --- a/drivers/misc/habanalabs/hw_queue.c +++ b/drivers/misc/habanalabs/hw_queue.c @@ -82,7 +82,7 @@ static void ext_queue_submit_bd(struct hl_device *hdev, struct hl_hw_queue *q, bd += hl_pi_2_offset(q->pi); bd->ctl = __cpu_to_le32(ctl); bd->len = __cpu_to_le32(len); - bd->ptr = __cpu_to_le64(ptr + hdev->asic_prop.host_phys_base_address); + bd->ptr = __cpu_to_le64(ptr); q->pi = hl_queue_inc_ptr(q->pi); hdev->asic_funcs->ring_doorbell(hdev, q->hw_queue_id, q->pi); @@ -263,9 +263,7 @@ static void ext_hw_queue_schedule_job(struct hl_cs_job *job) * checked in hl_queue_sanity_checks */ cq = &hdev->completion_queue[q->hw_queue_id]; - cq_addr = cq->bus_address + - hdev->asic_prop.host_phys_base_address; - cq_addr += cq->pi * sizeof(struct hl_cq_entry); + cq_addr = cq->bus_address + cq->pi * sizeof(struct hl_cq_entry); hdev->asic_funcs->add_end_of_cb_packets(cb->kernel_address, len, cq_addr, diff --git a/drivers/misc/habanalabs/memory.c b/drivers/misc/habanalabs/memory.c index 43ef3ad8438a..d67d24c13efd 100644 --- a/drivers/misc/habanalabs/memory.c +++ b/drivers/misc/habanalabs/memory.c @@ -759,10 +759,6 @@ static int map_phys_page_pack(struct hl_ctx *ctx, u64 vaddr, for (i = 0 ; i < phys_pg_pack->npages ; i++) { paddr = phys_pg_pack->pages[i]; - /* For accessing the host we need to turn on bit 39 */ - if (phys_pg_pack->created_from_userptr) - paddr += hdev->asic_prop.host_phys_base_address; - rc = hl_mmu_map(ctx, next_vaddr, paddr, page_size); if (rc) { dev_err(hdev->dev, diff --git a/drivers/misc/habanalabs/pci.c b/drivers/misc/habanalabs/pci.c index 5278f086d65d..0e78a04d63f4 100644 --- a/drivers/misc/habanalabs/pci.c +++ b/drivers/misc/habanalabs/pci.c @@ -236,6 +236,8 @@ int hl_pci_set_dram_bar_base(struct hl_device *hdev, u8 inbound_region, u8 bar, * @hdev: Pointer to hl_device structure. * @sram_base_address: SRAM base address. * @dram_base_address: DRAM base address. + * @host_phys_base_address: Base physical address of host memory for device + * transactions. * @host_phys_size: Size of host memory for device transactions. * * This is needed in case the firmware doesn't initialize the iATU. @@ -243,7 +245,8 @@ int hl_pci_set_dram_bar_base(struct hl_device *hdev, u8 inbound_region, u8 bar, * Return: 0 on success, negative value for failure. */ int hl_pci_init_iatu(struct hl_device *hdev, u64 sram_base_address, - u64 dram_base_address, u64 host_phys_size) + u64 dram_base_address, u64 host_phys_base_address, + u64 host_phys_size) { struct asic_fixed_properties *prop = &hdev->asic_prop; u64 host_phys_end_addr; @@ -265,11 +268,11 @@ int hl_pci_init_iatu(struct hl_device *hdev, u64 sram_base_address, /* Outbound Region 0 - Point to Host */ - host_phys_end_addr = prop->host_phys_base_address + host_phys_size - 1; + host_phys_end_addr = host_phys_base_address + host_phys_size - 1; rc |= hl_pci_iatu_write(hdev, 0x008, - lower_32_bits(prop->host_phys_base_address)); + lower_32_bits(host_phys_base_address)); rc |= hl_pci_iatu_write(hdev, 0x00C, - upper_32_bits(prop->host_phys_base_address)); + upper_32_bits(host_phys_base_address)); rc |= hl_pci_iatu_write(hdev, 0x010, lower_32_bits(host_phys_end_addr)); rc |= hl_pci_iatu_write(hdev, 0x014, 0); rc |= hl_pci_iatu_write(hdev, 0x018, 0); From 5809e18e028218c006011dbbfe30429eaf4bb29b Mon Sep 17 00:00:00 2001 From: Dalit Ben Zoor Date: Wed, 1 May 2019 13:16:18 +0300 Subject: [PATCH 194/255] habanalabs: remove redundant member from parser struct use_virt_addr member was used for telling whether to treat the addresses in the CB as virtual during parsing. We disabled it only when calling the parser from the driver memset device function, and since this call had been removed, it should always be enabled. Signed-off-by: Dalit Ben Zoor Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/command_submission.c | 1 - drivers/misc/habanalabs/goya/goya.c | 2 +- drivers/misc/habanalabs/habanalabs.h | 3 --- 3 files changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index c4ab694b51b5..6fe785e26859 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -93,7 +93,6 @@ static int cs_parser(struct hl_fpriv *hpriv, struct hl_cs_job *job) parser.user_cb_size = job->user_cb_size; parser.ext_queue = job->ext_queue; job->patched_cb = NULL; - parser.use_virt_addr = hdev->mmu_enable; rc = hdev->asic_funcs->cs_parser(hdev, &parser); if (job->ext_queue) { diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 31dc3b872f9e..ba6790f9ec6b 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -3903,7 +3903,7 @@ int goya_cs_parser(struct hl_device *hdev, struct hl_cs_parser *parser) if (!parser->ext_queue) return goya_parse_cb_no_ext_queue(hdev, parser); - if ((goya->hw_cap_initialized & HW_CAP_MMU) && parser->use_virt_addr) + if (goya->hw_cap_initialized & HW_CAP_MMU) return goya_parse_cb_mmu(hdev, parser); else return goya_parse_cb_no_mmu(hdev, parser); diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index f08f71982585..0da80e8eab42 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -779,8 +779,6 @@ struct hl_cs_job { * @patched_cb_size: the size of the CB after parsing. * @ext_queue: whether the job is for external queue or internal queue. * @job_id: the id of the related job inside the related CS. - * @use_virt_addr: whether to treat the addresses in the CB as virtual during - * parsing. */ struct hl_cs_parser { struct hl_cb *user_cb; @@ -793,7 +791,6 @@ struct hl_cs_parser { u32 patched_cb_size; u8 ext_queue; u8 job_id; - u8 use_virt_addr; }; From f0539fb0fb5fcb595bbb46dfe88c97e825f29f1f Mon Sep 17 00:00:00 2001 From: Dalit Ben Zoor Date: Wed, 1 May 2019 13:24:58 +0300 Subject: [PATCH 195/255] habanalabs: remove condition that is always true After removing the parsing of the command submission when doing memset of the device memory, goya_validate_dma_pkt_host is never called by the kernel, so there is no need to check context id. Signed-off-by: Dalit Ben Zoor Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 44 ++++++++++++++--------------- 1 file changed, 21 insertions(+), 23 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index ba6790f9ec6b..9bf572a2d292 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -3213,31 +3213,29 @@ static int goya_validate_dma_pkt_host(struct hl_device *hdev, return -EFAULT; } - if (parser->ctx_id != HL_KERNEL_ASID_ID) { - if (sram_addr) { - if (!hl_mem_area_inside_range(device_memory_addr, - le32_to_cpu(user_dma_pkt->tsize), - hdev->asic_prop.sram_user_base_address, - hdev->asic_prop.sram_end_address)) { + if (sram_addr) { + if (!hl_mem_area_inside_range(device_memory_addr, + le32_to_cpu(user_dma_pkt->tsize), + hdev->asic_prop.sram_user_base_address, + hdev->asic_prop.sram_end_address)) { - dev_err(hdev->dev, - "SRAM address 0x%llx + 0x%x is invalid\n", - device_memory_addr, - user_dma_pkt->tsize); - return -EFAULT; - } - } else { - if (!hl_mem_area_inside_range(device_memory_addr, - le32_to_cpu(user_dma_pkt->tsize), - hdev->asic_prop.dram_user_base_address, - hdev->asic_prop.dram_end_address)) { + dev_err(hdev->dev, + "SRAM address 0x%llx + 0x%x is invalid\n", + device_memory_addr, + user_dma_pkt->tsize); + return -EFAULT; + } + } else { + if (!hl_mem_area_inside_range(device_memory_addr, + le32_to_cpu(user_dma_pkt->tsize), + hdev->asic_prop.dram_user_base_address, + hdev->asic_prop.dram_end_address)) { - dev_err(hdev->dev, - "DRAM address 0x%llx + 0x%x is invalid\n", - device_memory_addr, - user_dma_pkt->tsize); - return -EFAULT; - } + dev_err(hdev->dev, + "DRAM address 0x%llx + 0x%x is invalid\n", + device_memory_addr, + user_dma_pkt->tsize); + return -EFAULT; } } From b1b537713eb1a63a2ecc3547693b3eef7dfb9281 Mon Sep 17 00:00:00 2001 From: Dalit Ben Zoor Date: Tue, 30 Apr 2019 17:18:51 +0300 Subject: [PATCH 196/255] habanalabs: increase timeout if working with simulator Where there is a spike in the CPU consumption, it may cause random failures in the C/I since the KMD timeout for CPU and/or QMAN0 jobs expires and it stops communicating to the simulator. This commit fixes it by increasing timeout on polling functions if working with simulator. Signed-off-by: Dalit Ben Zoor Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/device.c | 8 +++++++- drivers/misc/habanalabs/habanalabs.h | 7 ++++++- 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c index 0e0b9ec71c80..91a9e47a3482 100644 --- a/drivers/misc/habanalabs/device.c +++ b/drivers/misc/habanalabs/device.c @@ -1147,7 +1147,13 @@ int hl_poll_timeout_memory(struct hl_device *hdev, u64 addr, * either by the direct access of the device or by another core */ u32 *paddr = (u32 *) (uintptr_t) addr; - ktime_t timeout = ktime_add_us(ktime_get(), timeout_us); + ktime_t timeout; + + /* timeout should be longer when working with simulator */ + if (!hdev->pdev) + timeout_us *= 10; + + timeout = ktime_add_us(ktime_get(), timeout_us); might_sleep(); diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 0da80e8eab42..71243b319920 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -1042,7 +1042,12 @@ void hl_wreg(struct hl_device *hdev, u32 reg, u32 val); #define hl_poll_timeout(hdev, addr, val, cond, sleep_us, timeout_us) \ ({ \ - ktime_t __timeout = ktime_add_us(ktime_get(), timeout_us); \ + ktime_t __timeout; \ + /* timeout should be longer when working with simulator */ \ + if (hdev->pdev) \ + __timeout = ktime_add_us(ktime_get(), timeout_us); \ + else \ + __timeout = ktime_add_us(ktime_get(), (timeout_us * 10)); \ might_sleep_if(sleep_us); \ for (;;) { \ (val) = RREG32(addr); \ From ba209e1587227f8f5a86bb4b040547cf9a79d4cc Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Thu, 2 May 2019 11:33:12 +0300 Subject: [PATCH 197/255] habanalabs: Update CPU DMA pool label name The CPU accessible DMA pool is general and not used only for PQ. Accordingly, this patch rename the "free_cpu_pq_pool" label with "free_cpu_accessible_dma_pool". Signed-off-by: Tomer Tayar Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 9bf572a2d292..0fa0bdd7c852 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -670,14 +670,14 @@ static int goya_sw_init(struct hl_device *hdev) dev_err(hdev->dev, "Failed to add memory to CPU accessible DMA pool\n"); rc = -EFAULT; - goto free_cpu_pq_pool; + goto free_cpu_accessible_dma_pool; } spin_lock_init(&goya->hw_queues_lock); return 0; -free_cpu_pq_pool: +free_cpu_accessible_dma_pool: gen_pool_destroy(hdev->cpu_accessible_dma_pool); free_cpu_pq_dma_mem: hdev->asic_funcs->asic_dma_free_coherent(hdev, From 9f832fda79eb6e4f8ebde8d77eb442b95bf6b08a Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Thu, 2 May 2019 15:37:19 +0300 Subject: [PATCH 198/255] habanalabs: Update CPU DMA memory label name The CPU accessible DMA memory is general and not used only for PQ. Accordingly, this patch renames the "free_cpu_pq_dma_mem" label with "free_cpu_dma_mem". Signed-off-by: Tomer Tayar Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/goya/goya.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 0fa0bdd7c852..a582e29c1ee4 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -660,7 +660,7 @@ static int goya_sw_init(struct hl_device *hdev) dev_err(hdev->dev, "Failed to create CPU accessible DMA pool\n"); rc = -ENOMEM; - goto free_cpu_pq_dma_mem; + goto free_cpu_dma_mem; } rc = gen_pool_add(hdev->cpu_accessible_dma_pool, @@ -679,7 +679,7 @@ static int goya_sw_init(struct hl_device *hdev) free_cpu_accessible_dma_pool: gen_pool_destroy(hdev->cpu_accessible_dma_pool); -free_cpu_pq_dma_mem: +free_cpu_dma_mem: hdev->asic_funcs->asic_dma_free_coherent(hdev, HL_CPU_ACCESSIBLE_MEM_SIZE, hdev->cpu_accessible_dma_mem, From 9d7cd9d500826a14fc68fb6994db375432866c6a Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:24 -0500 Subject: [PATCH 199/255] soundwire: Kconfig: fix help format Move to the regular help format, --help-- is no longer recommended. Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soundwire/Kconfig b/drivers/soundwire/Kconfig index 19c8efb9a5ee..84876a74874f 100644 --- a/drivers/soundwire/Kconfig +++ b/drivers/soundwire/Kconfig @@ -4,7 +4,7 @@ menuconfig SOUNDWIRE bool "SoundWire support" - ---help--- + help SoundWire is a 2-Pin interface with data and clock line ratified by the MIPI Alliance. SoundWire is used for transporting data typically related to audio functions. SoundWire interface is From 23859465529550fcf390f3a5a28cf767adb83232 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:25 -0500 Subject: [PATCH 200/255] soundwire: fix SPDX license for header files No C++ comments in .h files Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/bus.h | 4 ++-- drivers/soundwire/cadence_master.h | 4 ++-- drivers/soundwire/intel.h | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/soundwire/bus.h b/drivers/soundwire/bus.h index c77de05b8100..2f8436584e7f 100644 --- a/drivers/soundwire/bus.h +++ b/drivers/soundwire/bus.h @@ -1,5 +1,5 @@ -// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) -// Copyright(c) 2015-17 Intel Corporation. +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* Copyright(c) 2015-17 Intel Corporation. */ #ifndef __SDW_BUS_H #define __SDW_BUS_H diff --git a/drivers/soundwire/cadence_master.h b/drivers/soundwire/cadence_master.h index eb902b19c5a4..75f7412cfbbd 100644 --- a/drivers/soundwire/cadence_master.h +++ b/drivers/soundwire/cadence_master.h @@ -1,5 +1,5 @@ -// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) -// Copyright(c) 2015-17 Intel Corporation. +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* Copyright(c) 2015-17 Intel Corporation. */ #include #ifndef __SDW_CADENCE_H diff --git a/drivers/soundwire/intel.h b/drivers/soundwire/intel.h index c1a5bac6212e..71050e5f643d 100644 --- a/drivers/soundwire/intel.h +++ b/drivers/soundwire/intel.h @@ -1,5 +1,5 @@ -// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) -// Copyright(c) 2015-17 Intel Corporation. +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* Copyright(c) 2015-17 Intel Corporation. */ #ifndef __SDW_INTEL_LOCAL_H #define __SDW_INTEL_LOCAL_H From 392f10453dd2bfb86b10b7978020f0509a29b919 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:19 +0530 Subject: [PATCH 201/255] soundwire: intel: fix SPDX license for header file Some more headers had C++ style SDPX line, fix that and change copyright so that it is consistent with rest of the code in subsystem Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- include/linux/soundwire/sdw_intel.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 2b9573b8aedd..0848f9d38bcb 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -1,5 +1,5 @@ -// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) -// Copyright(c) 2015-17 Intel Corporation. +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* Copyright(c) 2015-17 Intel Corporation. */ #ifndef __SDW_INTEL_H #define __SDW_INTEL_H From 806a11f095e24f4fae12211ee86caa9bde3ae3c0 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:26 -0500 Subject: [PATCH 202/255] soundwire: fix alignment issues in header files use Linux style Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/bus.h | 12 ++++++------ drivers/soundwire/cadence_master.h | 18 +++++++++--------- 2 files changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/soundwire/bus.h b/drivers/soundwire/bus.h index 2f8436584e7f..3048ca153f22 100644 --- a/drivers/soundwire/bus.h +++ b/drivers/soundwire/bus.h @@ -16,7 +16,7 @@ static inline int sdw_acpi_find_slaves(struct sdw_bus *bus) #endif void sdw_extract_slave_id(struct sdw_bus *bus, - u64 addr, struct sdw_slave_id *id); + u64 addr, struct sdw_slave_id *id); enum { SDW_MSG_FLAG_READ = 0, @@ -116,19 +116,19 @@ struct sdw_master_runtime { }; struct sdw_dpn_prop *sdw_get_slave_dpn_prop(struct sdw_slave *slave, - enum sdw_data_direction direction, - unsigned int port_num); + enum sdw_data_direction direction, + unsigned int port_num); int sdw_configure_dpn_intr(struct sdw_slave *slave, int port, - bool enable, int mask); + bool enable, int mask); int sdw_transfer(struct sdw_bus *bus, struct sdw_msg *msg); int sdw_transfer_defer(struct sdw_bus *bus, struct sdw_msg *msg, - struct sdw_defer *defer); + struct sdw_defer *defer); #define SDW_READ_INTR_CLEAR_RETRY 10 int sdw_fill_msg(struct sdw_msg *msg, struct sdw_slave *slave, - u32 addr, size_t count, u16 dev_num, u8 flags, u8 *buf); + u32 addr, size_t count, u16 dev_num, u8 flags, u8 *buf); /* Read-Modify-Write Slave register */ static inline int diff --git a/drivers/soundwire/cadence_master.h b/drivers/soundwire/cadence_master.h index 75f7412cfbbd..fe2af62958b1 100644 --- a/drivers/soundwire/cadence_master.h +++ b/drivers/soundwire/cadence_master.h @@ -160,24 +160,24 @@ irqreturn_t sdw_cdns_thread(int irq, void *dev_id); int sdw_cdns_init(struct sdw_cdns *cdns); int sdw_cdns_pdi_init(struct sdw_cdns *cdns, - struct sdw_cdns_stream_config config); + struct sdw_cdns_stream_config config); int sdw_cdns_enable_interrupt(struct sdw_cdns *cdns); int sdw_cdns_get_stream(struct sdw_cdns *cdns, struct sdw_cdns_streams *stream, u32 ch, u32 dir); int sdw_cdns_alloc_stream(struct sdw_cdns *cdns, - struct sdw_cdns_streams *stream, - struct sdw_cdns_port *port, u32 ch, u32 dir); + struct sdw_cdns_streams *stream, + struct sdw_cdns_port *port, u32 ch, u32 dir); void sdw_cdns_config_stream(struct sdw_cdns *cdns, struct sdw_cdns_port *port, - u32 ch, u32 dir, struct sdw_cdns_pdi *pdi); + u32 ch, u32 dir, struct sdw_cdns_pdi *pdi); void sdw_cdns_shutdown(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai); + struct snd_soc_dai *dai); int sdw_cdns_pcm_set_stream(struct snd_soc_dai *dai, - void *stream, int direction); + void *stream, int direction); int sdw_cdns_pdm_set_stream(struct snd_soc_dai *dai, - void *stream, int direction); + void *stream, int direction); enum sdw_command_response cdns_reset_page_addr(struct sdw_bus *bus, unsigned int dev_num); @@ -187,7 +187,7 @@ cdns_xfer_msg(struct sdw_bus *bus, struct sdw_msg *msg); enum sdw_command_response cdns_xfer_msg_defer(struct sdw_bus *bus, - struct sdw_msg *msg, struct sdw_defer *defer); + struct sdw_msg *msg, struct sdw_defer *defer); enum sdw_command_response cdns_reset_page_addr(struct sdw_bus *bus, unsigned int dev_num); @@ -195,5 +195,5 @@ cdns_reset_page_addr(struct sdw_bus *bus, unsigned int dev_num); int cdns_bus_conf(struct sdw_bus *bus, struct sdw_bus_params *params); int cdns_set_sdw_stream(struct snd_soc_dai *dai, - void *stream, bool pcm, int direction); + void *stream, bool pcm, int direction); #endif /* __SDW_CADENCE_H */ From 73ede04682e18909d7f3f75c3ec6ab59f854661e Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:27 -0500 Subject: [PATCH 203/255] soundwire: bus: fix alignment issues Use Linux style Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/bus.c | 66 ++++++++++++++++++++--------------------- 1 file changed, 33 insertions(+), 33 deletions(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 688848637099..74e04caa811b 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -172,7 +172,8 @@ static inline int do_transfer(struct sdw_bus *bus, struct sdw_msg *msg) } static inline int do_transfer_defer(struct sdw_bus *bus, - struct sdw_msg *msg, struct sdw_defer *defer) + struct sdw_msg *msg, + struct sdw_defer *defer) { int retry = bus->prop.err_threshold; enum sdw_command_response resp; @@ -224,7 +225,7 @@ int sdw_transfer(struct sdw_bus *bus, struct sdw_msg *msg) ret = do_transfer(bus, msg); if (ret != 0 && ret != -ENODATA) dev_err(bus->dev, "trf on Slave %d failed:%d\n", - msg->dev_num, ret); + msg->dev_num, ret); if (msg->page) sdw_reset_page(bus, msg->dev_num); @@ -243,7 +244,7 @@ int sdw_transfer(struct sdw_bus *bus, struct sdw_msg *msg) * Caller needs to hold the msg_lock lock while calling this */ int sdw_transfer_defer(struct sdw_bus *bus, struct sdw_msg *msg, - struct sdw_defer *defer) + struct sdw_defer *defer) { int ret; @@ -253,7 +254,7 @@ int sdw_transfer_defer(struct sdw_bus *bus, struct sdw_msg *msg, ret = do_transfer_defer(bus, msg, defer); if (ret != 0 && ret != -ENODATA) dev_err(bus->dev, "Defer trf on Slave %d failed:%d\n", - msg->dev_num, ret); + msg->dev_num, ret); if (msg->page) sdw_reset_page(bus, msg->dev_num); @@ -261,9 +262,8 @@ int sdw_transfer_defer(struct sdw_bus *bus, struct sdw_msg *msg, return ret; } - int sdw_fill_msg(struct sdw_msg *msg, struct sdw_slave *slave, - u32 addr, size_t count, u16 dev_num, u8 flags, u8 *buf) + u32 addr, size_t count, u16 dev_num, u8 flags, u8 *buf) { memset(msg, 0, sizeof(*msg)); msg->addr = addr; /* addr is 16 bit and truncated here */ @@ -321,7 +321,7 @@ int sdw_nread(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) int ret; ret = sdw_fill_msg(&msg, slave, addr, count, - slave->dev_num, SDW_MSG_FLAG_READ, val); + slave->dev_num, SDW_MSG_FLAG_READ, val); if (ret < 0) return ret; @@ -349,7 +349,7 @@ int sdw_nwrite(struct sdw_slave *slave, u32 addr, size_t count, u8 *val) int ret; ret = sdw_fill_msg(&msg, slave, addr, count, - slave->dev_num, SDW_MSG_FLAG_WRITE, val); + slave->dev_num, SDW_MSG_FLAG_WRITE, val); if (ret < 0) return ret; @@ -456,13 +456,13 @@ static int sdw_assign_device_num(struct sdw_slave *slave) mutex_unlock(&slave->bus->bus_lock); if (dev_num < 0) { dev_err(slave->bus->dev, "Get dev_num failed: %d", - dev_num); + dev_num); return dev_num; } } else { dev_info(slave->bus->dev, - "Slave already registered dev_num:%d", - slave->dev_num); + "Slave already registered dev_num:%d", + slave->dev_num); /* Clear the slave->dev_num to transfer message on device 0 */ dev_num = slave->dev_num; @@ -483,7 +483,7 @@ static int sdw_assign_device_num(struct sdw_slave *slave) } void sdw_extract_slave_id(struct sdw_bus *bus, - u64 addr, struct sdw_slave_id *id) + u64 addr, struct sdw_slave_id *id) { dev_dbg(bus->dev, "SDW Slave Addr: %llx", addr); @@ -523,7 +523,7 @@ static int sdw_program_device_num(struct sdw_bus *bus) /* No Slave, so use raw xfer api */ ret = sdw_fill_msg(&msg, NULL, SDW_SCP_DEVID_0, - SDW_NUM_DEV_ID_REGISTERS, 0, SDW_MSG_FLAG_READ, buf); + SDW_NUM_DEV_ID_REGISTERS, 0, SDW_MSG_FLAG_READ, buf); if (ret < 0) return ret; @@ -590,7 +590,7 @@ static int sdw_program_device_num(struct sdw_bus *bus) } static void sdw_modify_slave_status(struct sdw_slave *slave, - enum sdw_slave_status status) + enum sdw_slave_status status) { mutex_lock(&slave->bus->bus_lock); slave->status = status; @@ -598,7 +598,7 @@ static void sdw_modify_slave_status(struct sdw_slave *slave, } int sdw_configure_dpn_intr(struct sdw_slave *slave, - int port, bool enable, int mask) + int port, bool enable, int mask) { u32 addr; int ret; @@ -618,7 +618,7 @@ int sdw_configure_dpn_intr(struct sdw_slave *slave, ret = sdw_update(slave, addr, (mask | SDW_DPN_INT_PORT_READY), val); if (ret < 0) dev_err(slave->bus->dev, - "SDW_DPN_INTMASK write failed:%d", val); + "SDW_DPN_INTMASK write failed:%d", val); return ret; } @@ -642,7 +642,7 @@ static int sdw_initialize_slave(struct sdw_slave *slave) ret = sdw_update(slave, SDW_SCP_INTMASK1, val, val); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_SCP_INTMASK1 write failed:%d", ret); + "SDW_SCP_INTMASK1 write failed:%d", ret); return ret; } @@ -657,7 +657,7 @@ static int sdw_initialize_slave(struct sdw_slave *slave) ret = sdw_update(slave, SDW_DP0_INTMASK, val, val); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_DP0_INTMASK read failed:%d", ret); + "SDW_DP0_INTMASK read failed:%d", ret); return val; } @@ -672,7 +672,7 @@ static int sdw_handle_dp0_interrupt(struct sdw_slave *slave, u8 *slave_status) status = sdw_read(slave, SDW_DP0_INT); if (status < 0) { dev_err(slave->bus->dev, - "SDW_DP0_INT read failed:%d", status); + "SDW_DP0_INT read failed:%d", status); return status; } @@ -735,7 +735,7 @@ static int sdw_handle_dp0_interrupt(struct sdw_slave *slave, u8 *slave_status) } static int sdw_handle_port_interrupt(struct sdw_slave *slave, - int port, u8 *slave_status) + int port, u8 *slave_status) { u8 clear = 0, impl_int_mask; int status, status2, ret, count = 0; @@ -748,7 +748,7 @@ static int sdw_handle_port_interrupt(struct sdw_slave *slave, status = sdw_read(slave, addr); if (status < 0) { dev_err(slave->bus->dev, - "SDW_DPN_INT read failed:%d", status); + "SDW_DPN_INT read failed:%d", status); return status; } @@ -782,7 +782,7 @@ static int sdw_handle_port_interrupt(struct sdw_slave *slave, ret = sdw_write(slave, addr, clear); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_DPN_INT write failed:%d", ret); + "SDW_DPN_INT write failed:%d", ret); return ret; } @@ -790,7 +790,7 @@ static int sdw_handle_port_interrupt(struct sdw_slave *slave, status2 = sdw_read(slave, addr); if (status2 < 0) { dev_err(slave->bus->dev, - "SDW_DPN_INT read failed:%d", status2); + "SDW_DPN_INT read failed:%d", status2); return status2; } status &= status2; @@ -821,14 +821,14 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) buf = ret = sdw_read(slave, SDW_SCP_INT1); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_SCP_INT1 read failed:%d", ret); + "SDW_SCP_INT1 read failed:%d", ret); return ret; } ret = sdw_nread(slave, SDW_SCP_INTSTAT2, 2, buf2); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_SCP_INT2/3 read failed:%d", ret); + "SDW_SCP_INT2/3 read failed:%d", ret); return ret; } @@ -867,7 +867,7 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) port = port >> SDW_REG_SHIFT(SDW_SCP_INT1_PORT0_3); for_each_set_bit(bit, &port, 8) { sdw_handle_port_interrupt(slave, bit, - &port_status[bit]); + &port_status[bit]); } @@ -900,7 +900,7 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) (slave->ops->interrupt_callback)) { slave_intr.control_port = clear; memcpy(slave_intr.port, &port_status, - sizeof(slave_intr.port)); + sizeof(slave_intr.port)); slave->ops->interrupt_callback(slave, &slave_intr); } @@ -909,7 +909,7 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) ret = sdw_write(slave, SDW_SCP_INT1, clear); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_SCP_INT1 write failed:%d", ret); + "SDW_SCP_INT1 write failed:%d", ret); return ret; } @@ -920,14 +920,14 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) _buf = ret = sdw_read(slave, SDW_SCP_INT1); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_SCP_INT1 read failed:%d", ret); + "SDW_SCP_INT1 read failed:%d", ret); return ret; } ret = sdw_nread(slave, SDW_SCP_INTSTAT2, 2, _buf2); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_SCP_INT2/3 read failed:%d", ret); + "SDW_SCP_INT2/3 read failed:%d", ret); return ret; } @@ -953,7 +953,7 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) } static int sdw_update_slave_status(struct sdw_slave *slave, - enum sdw_slave_status status) + enum sdw_slave_status status) { if ((slave->ops) && (slave->ops->update_status)) return slave->ops->update_status(slave, status); @@ -967,7 +967,7 @@ static int sdw_update_slave_status(struct sdw_slave *slave, * @status: Status for all Slave(s) */ int sdw_handle_slave_status(struct sdw_bus *bus, - enum sdw_slave_status status[]) + enum sdw_slave_status status[]) { enum sdw_slave_status prev_status; struct sdw_slave *slave; @@ -1028,7 +1028,7 @@ int sdw_handle_slave_status(struct sdw_bus *bus, default: dev_err(bus->dev, "Invalid slave %d status:%d", - i, status[i]); + i, status[i]); break; } From 21c2de29e85f084793c9beb016c8a5a23801b564 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:28 -0500 Subject: [PATCH 204/255] soundwire: bus: fix typos in comments spelling mistakes Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/bus.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 74e04caa811b..efdcefc62e1a 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -49,7 +49,7 @@ int sdw_add_bus_master(struct sdw_bus *bus) } /* - * Device numbers in SoundWire are 0 thru 15. Enumeration device + * Device numbers in SoundWire are 0 through 15. Enumeration device * number (0), Broadcast device number (15), Group numbers (12 and * 13) and Master device number (14) are not used for assignment so * mask these and other higher bits. @@ -282,7 +282,7 @@ int sdw_fill_msg(struct sdw_msg *msg, struct sdw_slave *slave, if (addr < SDW_REG_OPTIONAL_PAGE) { /* 32k but no page */ if (slave && !slave->prop.paging_support) return 0; - /* no need for else as that will fall thru to paging */ + /* no need for else as that will fall-through to paging */ } /* paging mandatory */ From 09830d5e34586ca66b22fa745ee18fe826b36065 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:29 -0500 Subject: [PATCH 205/255] soundwire: bus: remove useless parentheses and make the code more readable Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/bus.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index efdcefc62e1a..423dc6d17999 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -415,10 +415,10 @@ static struct sdw_slave *sdw_get_slave(struct sdw_bus *bus, int i) static int sdw_compare_devid(struct sdw_slave *slave, struct sdw_slave_id id) { - if ((slave->id.unique_id != id.unique_id) || - (slave->id.mfg_id != id.mfg_id) || - (slave->id.part_id != id.part_id) || - (slave->id.class_id != id.class_id)) + if (slave->id.unique_id != id.unique_id || + slave->id.mfg_id != id.mfg_id || + slave->id.part_id != id.part_id || + slave->id.class_id != id.class_id) return -ENODEV; return 0; @@ -896,8 +896,8 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) } /* Update the Slave driver */ - if (slave_notify && (slave->ops) && - (slave->ops->interrupt_callback)) { + if (slave_notify && slave->ops && + slave->ops->interrupt_callback) { slave_intr.control_port = clear; memcpy(slave_intr.port, &port_status, sizeof(slave_intr.port)); @@ -955,7 +955,7 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) static int sdw_update_slave_status(struct sdw_slave *slave, enum sdw_slave_status status) { - if ((slave->ops) && (slave->ops->update_status)) + if (slave->ops && slave->ops->update_status) return slave->ops->update_status(slave, status); return 0; From d7b956b6257b20e3c65ed5877e3ac493a88350fd Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:30 -0500 Subject: [PATCH 206/255] soundwire: bus: fix boolean comparisons no need for an explicit test against false reported by Coccinelle Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/bus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 423dc6d17999..863bf418e342 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -571,7 +571,7 @@ static int sdw_program_device_num(struct sdw_bus *bus) } } - if (found == false) { + if (!found) { /* TODO: Park this device in Group 13 */ dev_err(bus->dev, "Slave Entry not found"); } From 816d9bf4788bae059d19f84ad9375485e0e63ef8 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:31 -0500 Subject: [PATCH 207/255] soundwire: bus: remove spurious newline tools complain here and the location of the newline does not improve readability. Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/bus.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 863bf418e342..bb697fd68580 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -772,7 +772,6 @@ static int sdw_handle_port_interrupt(struct sdw_slave *slave, impl_int_mask = SDW_DPN_INT_IMPDEF1 | SDW_DPN_INT_IMPDEF2 | SDW_DPN_INT_IMPDEF3; - if (status & impl_int_mask) { clear |= impl_int_mask; *slave_status = clear; From 74a8d8022fd9d91a56d02d10e6c0d53481172f51 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:32 -0500 Subject: [PATCH 208/255] soundwire: bus_type: fix alignment issues Use Linux style Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/bus_type.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c index 283b2832728e..2655602f0cfb 100644 --- a/drivers/soundwire/bus_type.c +++ b/drivers/soundwire/bus_type.c @@ -107,7 +107,7 @@ static int sdw_drv_probe(struct device *dev) slave->prop.clk_stop_timeout = 300; slave->bus->clk_stop_timeout = max_t(u32, slave->bus->clk_stop_timeout, - slave->prop.clk_stop_timeout); + slave->prop.clk_stop_timeout); return 0; } @@ -148,7 +148,7 @@ int __sdw_register_driver(struct sdw_driver *drv, struct module *owner) if (!drv->probe) { pr_err("driver %s didn't provide SDW probe routine\n", - drv->name); + drv->name); return -EINVAL; } From 31dba31297fd9e79798b85c58043641f3fdac825 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:33 -0500 Subject: [PATCH 209/255] soundwire: mipi_disco: fix alignment issues Use Linux style. In some cases parenthesis alignment is modified to keep the code readable. Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/mipi_disco.c | 112 ++++++++++++++++++--------------- 1 file changed, 62 insertions(+), 50 deletions(-) diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c index fdeba0c3b589..95efa82dc73b 100644 --- a/drivers/soundwire/mipi_disco.c +++ b/drivers/soundwire/mipi_disco.c @@ -35,11 +35,12 @@ int sdw_master_read_prop(struct sdw_bus *bus) int nval, i; device_property_read_u32(bus->dev, - "mipi-sdw-sw-interface-revision", &prop->revision); + "mipi-sdw-sw-interface-revision", + &prop->revision); /* Find master handle */ snprintf(name, sizeof(name), - "mipi-sdw-master-%d-subproperties", bus->link_id); + "mipi-sdw-master-%d-subproperties", bus->link_id); link = device_get_named_child_node(bus->dev, name); if (!link) { @@ -56,7 +57,8 @@ int sdw_master_read_prop(struct sdw_bus *bus) prop->clk_stop_mode |= SDW_CLK_STOP_MODE1; fwnode_property_read_u32(link, - "mipi-sdw-max-clock-frequency", &prop->max_freq); + "mipi-sdw-max-clock-frequency", + &prop->max_freq); nval = fwnode_property_read_u32_array(link, "mipi-sdw-clock-frequencies-supported", NULL, 0); @@ -64,7 +66,7 @@ int sdw_master_read_prop(struct sdw_bus *bus) prop->num_freq = nval; prop->freq = devm_kcalloc(bus->dev, prop->num_freq, - sizeof(*prop->freq), GFP_KERNEL); + sizeof(*prop->freq), GFP_KERNEL); if (!prop->freq) return -ENOMEM; @@ -91,44 +93,47 @@ int sdw_master_read_prop(struct sdw_bus *bus) prop->num_clk_gears = nval; prop->clk_gears = devm_kcalloc(bus->dev, prop->num_clk_gears, - sizeof(*prop->clk_gears), GFP_KERNEL); + sizeof(*prop->clk_gears), + GFP_KERNEL); if (!prop->clk_gears) return -ENOMEM; fwnode_property_read_u32_array(link, - "mipi-sdw-supported-clock-gears", - prop->clk_gears, prop->num_clk_gears); + "mipi-sdw-supported-clock-gears", + prop->clk_gears, + prop->num_clk_gears); } fwnode_property_read_u32(link, "mipi-sdw-default-frame-rate", - &prop->default_frame_rate); + &prop->default_frame_rate); fwnode_property_read_u32(link, "mipi-sdw-default-frame-row-size", - &prop->default_row); + &prop->default_row); fwnode_property_read_u32(link, "mipi-sdw-default-frame-col-size", - &prop->default_col); + &prop->default_col); prop->dynamic_frame = fwnode_property_read_bool(link, "mipi-sdw-dynamic-frame-shape"); fwnode_property_read_u32(link, "mipi-sdw-command-error-threshold", - &prop->err_threshold); + &prop->err_threshold); return 0; } EXPORT_SYMBOL(sdw_master_read_prop); static int sdw_slave_read_dp0(struct sdw_slave *slave, - struct fwnode_handle *port, struct sdw_dp0_prop *dp0) + struct fwnode_handle *port, + struct sdw_dp0_prop *dp0) { int nval; fwnode_property_read_u32(port, "mipi-sdw-port-max-wordlength", - &dp0->max_word); + &dp0->max_word); fwnode_property_read_u32(port, "mipi-sdw-port-min-wordlength", - &dp0->min_word); + &dp0->min_word); nval = fwnode_property_read_u32_array(port, "mipi-sdw-port-wordlength-configs", NULL, 0); @@ -136,8 +141,8 @@ static int sdw_slave_read_dp0(struct sdw_slave *slave, dp0->num_words = nval; dp0->words = devm_kcalloc(&slave->dev, - dp0->num_words, sizeof(*dp0->words), - GFP_KERNEL); + dp0->num_words, sizeof(*dp0->words), + GFP_KERNEL); if (!dp0->words) return -ENOMEM; @@ -146,20 +151,21 @@ static int sdw_slave_read_dp0(struct sdw_slave *slave, dp0->words, dp0->num_words); } - dp0->flow_controlled = fwnode_property_read_bool( - port, "mipi-sdw-bra-flow-controlled"); + dp0->flow_controlled = fwnode_property_read_bool(port, + "mipi-sdw-bra-flow-controlled"); - dp0->simple_ch_prep_sm = fwnode_property_read_bool( - port, "mipi-sdw-simplified-channel-prepare-sm"); + dp0->simple_ch_prep_sm = fwnode_property_read_bool(port, + "mipi-sdw-simplified-channel-prepare-sm"); - dp0->device_interrupts = fwnode_property_read_bool( - port, "mipi-sdw-imp-def-dp0-interrupts-supported"); + dp0->device_interrupts = fwnode_property_read_bool(port, + "mipi-sdw-imp-def-dp0-interrupts-supported"); return 0; } static int sdw_slave_read_dpn(struct sdw_slave *slave, - struct sdw_dpn_prop *dpn, int count, int ports, char *type) + struct sdw_dpn_prop *dpn, int count, int ports, + char *type) { struct fwnode_handle *node; u32 bit, i = 0; @@ -173,7 +179,7 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, for_each_set_bit(bit, &addr, 32) { snprintf(name, sizeof(name), - "mipi-sdw-dp-%d-%s-subproperties", bit, type); + "mipi-sdw-dp-%d-%s-subproperties", bit, type); dpn[i].num = bit; @@ -184,9 +190,9 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, } fwnode_property_read_u32(node, "mipi-sdw-port-max-wordlength", - &dpn[i].max_word); + &dpn[i].max_word); fwnode_property_read_u32(node, "mipi-sdw-port-min-wordlength", - &dpn[i].min_word); + &dpn[i].min_word); nval = fwnode_property_read_u32_array(node, "mipi-sdw-port-wordlength-configs", NULL, 0); @@ -194,8 +200,9 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, dpn[i].num_words = nval; dpn[i].words = devm_kcalloc(&slave->dev, - dpn[i].num_words, - sizeof(*dpn[i].words), GFP_KERNEL); + dpn[i].num_words, + sizeof(*dpn[i].words), + GFP_KERNEL); if (!dpn[i].words) return -ENOMEM; @@ -205,28 +212,28 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, } fwnode_property_read_u32(node, "mipi-sdw-data-port-type", - &dpn[i].type); + &dpn[i].type); fwnode_property_read_u32(node, - "mipi-sdw-max-grouping-supported", - &dpn[i].max_grouping); + "mipi-sdw-max-grouping-supported", + &dpn[i].max_grouping); dpn[i].simple_ch_prep_sm = fwnode_property_read_bool(node, "mipi-sdw-simplified-channelprepare-sm"); fwnode_property_read_u32(node, - "mipi-sdw-port-channelprepare-timeout", - &dpn[i].ch_prep_timeout); + "mipi-sdw-port-channelprepare-timeout", + &dpn[i].ch_prep_timeout); fwnode_property_read_u32(node, "mipi-sdw-imp-def-dpn-interrupts-supported", &dpn[i].device_interrupts); fwnode_property_read_u32(node, "mipi-sdw-min-channel-number", - &dpn[i].min_ch); + &dpn[i].min_ch); fwnode_property_read_u32(node, "mipi-sdw-max-channel-number", - &dpn[i].max_ch); + &dpn[i].max_ch); nval = fwnode_property_read_u32_array(node, "mipi-sdw-channel-number-list", NULL, 0); @@ -234,7 +241,8 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, dpn[i].num_ch = nval; dpn[i].ch = devm_kcalloc(&slave->dev, dpn[i].num_ch, - sizeof(*dpn[i].ch), GFP_KERNEL); + sizeof(*dpn[i].ch), + GFP_KERNEL); if (!dpn[i].ch) return -ENOMEM; @@ -265,13 +273,13 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, "mipi-sdw-modes-supported", &dpn[i].modes); fwnode_property_read_u32(node, "mipi-sdw-max-async-buffer", - &dpn[i].max_async_buffer); + &dpn[i].max_async_buffer); dpn[i].block_pack_mode = fwnode_property_read_bool(node, "mipi-sdw-block-packing-mode"); fwnode_property_read_u32(node, "mipi-sdw-port-encoding-type", - &dpn[i].port_encoding); + &dpn[i].port_encoding); /* TODO: Read audio mode */ @@ -293,7 +301,7 @@ int sdw_slave_read_prop(struct sdw_slave *slave) int num_of_ports, nval, i, dp0 = 0; device_property_read_u32(dev, "mipi-sdw-sw-interface-revision", - &prop->mipi_revision); + &prop->mipi_revision); prop->wake_capable = device_property_read_bool(dev, "mipi-sdw-wake-up-unavailable"); @@ -311,10 +319,10 @@ int sdw_slave_read_prop(struct sdw_slave *slave) "mipi-sdw-simplified-clockstopprepare-sm-supported"); device_property_read_u32(dev, "mipi-sdw-clockstopprepare-timeout", - &prop->clk_stop_timeout); + &prop->clk_stop_timeout); device_property_read_u32(dev, "mipi-sdw-slave-channelprepare-timeout", - &prop->ch_prep_timeout); + &prop->ch_prep_timeout); device_property_read_u32(dev, "mipi-sdw-clockstopprepare-hard-reset-behavior", @@ -333,13 +341,13 @@ int sdw_slave_read_prop(struct sdw_slave *slave) "mipi-sdw-port15-read-behavior", &prop->p15_behave); device_property_read_u32(dev, "mipi-sdw-master-count", - &prop->master_count); + &prop->master_count); device_property_read_u32(dev, "mipi-sdw-source-port-list", - &prop->source_ports); + &prop->source_ports); device_property_read_u32(dev, "mipi-sdw-sink-port-list", - &prop->sink_ports); + &prop->sink_ports); /* Read dp0 properties */ port = device_get_named_child_node(dev, "mipi-sdw-dp-0-subproperties"); @@ -348,7 +356,8 @@ int sdw_slave_read_prop(struct sdw_slave *slave) } else { prop->dp0_prop = devm_kzalloc(&slave->dev, - sizeof(*prop->dp0_prop), GFP_KERNEL); + sizeof(*prop->dp0_prop), + GFP_KERNEL); if (!prop->dp0_prop) return -ENOMEM; @@ -364,23 +373,25 @@ int sdw_slave_read_prop(struct sdw_slave *slave) /* Allocate memory for set bits in port lists */ nval = hweight32(prop->source_ports); prop->src_dpn_prop = devm_kcalloc(&slave->dev, nval, - sizeof(*prop->src_dpn_prop), GFP_KERNEL); + sizeof(*prop->src_dpn_prop), + GFP_KERNEL); if (!prop->src_dpn_prop) return -ENOMEM; /* Read dpn properties for source port(s) */ sdw_slave_read_dpn(slave, prop->src_dpn_prop, nval, - prop->source_ports, "source"); + prop->source_ports, "source"); nval = hweight32(prop->sink_ports); prop->sink_dpn_prop = devm_kcalloc(&slave->dev, nval, - sizeof(*prop->sink_dpn_prop), GFP_KERNEL); + sizeof(*prop->sink_dpn_prop), + GFP_KERNEL); if (!prop->sink_dpn_prop) return -ENOMEM; /* Read dpn properties for sink port(s) */ sdw_slave_read_dpn(slave, prop->sink_dpn_prop, nval, - prop->sink_ports, "sink"); + prop->sink_ports, "sink"); /* some ports are bidirectional so check total ports by ORing */ nval = prop->source_ports | prop->sink_ports; @@ -388,7 +399,8 @@ int sdw_slave_read_prop(struct sdw_slave *slave) /* Allocate port_ready based on num_of_ports */ slave->port_ready = devm_kcalloc(&slave->dev, num_of_ports, - sizeof(*slave->port_ready), GFP_KERNEL); + sizeof(*slave->port_ready), + GFP_KERNEL); if (!slave->port_ready) return -ENOMEM; From 00910f3cb0c59f0d9c5acf2f85395b2af7955526 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:34 -0500 Subject: [PATCH 210/255] soundwire: mipi_disco: fix boolean comparisons No need for explicit test against true Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/mipi_disco.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c index 95efa82dc73b..2bf4046e68b6 100644 --- a/drivers/soundwire/mipi_disco.c +++ b/drivers/soundwire/mipi_disco.c @@ -49,11 +49,11 @@ int sdw_master_read_prop(struct sdw_bus *bus) } if (fwnode_property_read_bool(link, - "mipi-sdw-clock-stop-mode0-supported") == true) + "mipi-sdw-clock-stop-mode0-supported")) prop->clk_stop_mode = SDW_CLK_STOP_MODE0; if (fwnode_property_read_bool(link, - "mipi-sdw-clock-stop-mode1-supported") == true) + "mipi-sdw-clock-stop-mode1-supported")) prop->clk_stop_mode |= SDW_CLK_STOP_MODE1; fwnode_property_read_u32(link, From 1fe74a5e41d6e57d8078de79fe0379e7701b1492 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:35 -0500 Subject: [PATCH 211/255] soundwire: stream: fix alignment issues Use Linux style Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/stream.c | 161 +++++++++++++++++++------------------ 1 file changed, 84 insertions(+), 77 deletions(-) diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index 63b162feecfc..ab64c2c4c33f 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -53,9 +53,9 @@ static int sdw_find_row_index(int row) return 0; } static int _sdw_program_slave_port_params(struct sdw_bus *bus, - struct sdw_slave *slave, - struct sdw_transport_params *t_params, - enum sdw_dpn_type type) + struct sdw_slave *slave, + struct sdw_transport_params *t_params, + enum sdw_dpn_type type) { u32 addr1, addr2, addr3, addr4; int ret; @@ -119,8 +119,8 @@ static int _sdw_program_slave_port_params(struct sdw_bus *bus, } static int sdw_program_slave_port_params(struct sdw_bus *bus, - struct sdw_slave_runtime *s_rt, - struct sdw_port_runtime *p_rt) + struct sdw_slave_runtime *s_rt, + struct sdw_port_runtime *p_rt) { struct sdw_transport_params *t_params = &p_rt->transport_params; struct sdw_port_params *p_params = &p_rt->port_params; @@ -131,8 +131,8 @@ static int sdw_program_slave_port_params(struct sdw_bus *bus, u8 wbuf; dpn_prop = sdw_get_slave_dpn_prop(s_rt->slave, - s_rt->direction, - t_params->port_num); + s_rt->direction, + t_params->port_num); if (!dpn_prop) return -EINVAL; @@ -216,7 +216,7 @@ static int sdw_program_slave_port_params(struct sdw_bus *bus, if (dpn_prop->type != SDW_DPN_SIMPLE) { ret = _sdw_program_slave_port_params(bus, s_rt->slave, - t_params, dpn_prop->type); + t_params, dpn_prop->type); if (ret < 0) dev_err(&s_rt->slave->dev, "Transport reg write failed for port: %d", @@ -227,7 +227,7 @@ static int sdw_program_slave_port_params(struct sdw_bus *bus, } static int sdw_program_master_port_params(struct sdw_bus *bus, - struct sdw_port_runtime *p_rt) + struct sdw_port_runtime *p_rt) { int ret; @@ -244,8 +244,8 @@ static int sdw_program_master_port_params(struct sdw_bus *bus, return ret; return bus->port_ops->dpn_set_port_params(bus, - &p_rt->port_params, - bus->params.next_bank); + &p_rt->port_params, + bus->params.next_bank); } /** @@ -292,8 +292,9 @@ static int sdw_program_port_params(struct sdw_master_runtime *m_rt) * actual enable/disable is done with a bank switch */ static int sdw_enable_disable_slave_ports(struct sdw_bus *bus, - struct sdw_slave_runtime *s_rt, - struct sdw_port_runtime *p_rt, bool en) + struct sdw_slave_runtime *s_rt, + struct sdw_port_runtime *p_rt, + bool en) { struct sdw_transport_params *t_params = &p_rt->transport_params; u32 addr; @@ -322,7 +323,8 @@ static int sdw_enable_disable_slave_ports(struct sdw_bus *bus, } static int sdw_enable_disable_master_ports(struct sdw_master_runtime *m_rt, - struct sdw_port_runtime *p_rt, bool en) + struct sdw_port_runtime *p_rt, + bool en) { struct sdw_transport_params *t_params = &p_rt->transport_params; struct sdw_bus *bus = m_rt->bus; @@ -336,7 +338,8 @@ static int sdw_enable_disable_master_ports(struct sdw_master_runtime *m_rt, /* Perform Master port channel(s) enable/disable */ if (bus->port_ops->dpn_port_enable_ch) { ret = bus->port_ops->dpn_port_enable_ch(bus, - &enable_ch, bus->params.next_bank); + &enable_ch, + bus->params.next_bank); if (ret < 0) { dev_err(bus->dev, "Master chn_en write failed:%d port:%d", @@ -370,7 +373,7 @@ static int sdw_enable_disable_ports(struct sdw_master_runtime *m_rt, bool en) list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) { list_for_each_entry(s_port, &s_rt->port_list, port_node) { ret = sdw_enable_disable_slave_ports(m_rt->bus, s_rt, - s_port, en); + s_port, en); if (ret < 0) return ret; } @@ -387,7 +390,8 @@ static int sdw_enable_disable_ports(struct sdw_master_runtime *m_rt, bool en) } static int sdw_do_port_prep(struct sdw_slave_runtime *s_rt, - struct sdw_prepare_ch prep_ch, enum sdw_port_prep_ops cmd) + struct sdw_prepare_ch prep_ch, + enum sdw_port_prep_ops cmd) { const struct sdw_slave_ops *ops = s_rt->slave->ops; int ret; @@ -405,8 +409,9 @@ static int sdw_do_port_prep(struct sdw_slave_runtime *s_rt, } static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus, - struct sdw_slave_runtime *s_rt, - struct sdw_port_runtime *p_rt, bool prep) + struct sdw_slave_runtime *s_rt, + struct sdw_port_runtime *p_rt, + bool prep) { struct completion *port_ready = NULL; struct sdw_dpn_prop *dpn_prop; @@ -420,8 +425,8 @@ static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus, prep_ch.ch_mask = p_rt->ch_mask; dpn_prop = sdw_get_slave_dpn_prop(s_rt->slave, - s_rt->direction, - prep_ch.num); + s_rt->direction, + prep_ch.num); if (!dpn_prop) { dev_err(bus->dev, "Slave Port:%d properties not found", prep_ch.num); @@ -442,7 +447,7 @@ static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus, */ if (prep && intr) { ret = sdw_configure_dpn_intr(s_rt->slave, p_rt->num, prep, - dpn_prop->device_interrupts); + dpn_prop->device_interrupts); if (ret < 0) return ret; } @@ -456,7 +461,7 @@ static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus, if (prep) ret = sdw_update(s_rt->slave, addr, - 0xFF, p_rt->ch_mask); + 0xFF, p_rt->ch_mask); else ret = sdw_update(s_rt->slave, addr, 0xFF, 0x0); @@ -486,13 +491,14 @@ static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus, /* Disable interrupt after Port de-prepare */ if (!prep && intr) ret = sdw_configure_dpn_intr(s_rt->slave, p_rt->num, prep, - dpn_prop->device_interrupts); + dpn_prop->device_interrupts); return ret; } static int sdw_prep_deprep_master_ports(struct sdw_master_runtime *m_rt, - struct sdw_port_runtime *p_rt, bool prep) + struct sdw_port_runtime *p_rt, + bool prep) { struct sdw_transport_params *t_params = &p_rt->transport_params; struct sdw_bus *bus = m_rt->bus; @@ -510,7 +516,7 @@ static int sdw_prep_deprep_master_ports(struct sdw_master_runtime *m_rt, ret = ops->dpn_port_prep(bus, &prep_ch); if (ret < 0) { dev_err(bus->dev, "Port prepare failed for port:%d", - t_params->port_num); + t_params->port_num); return ret; } } @@ -535,7 +541,7 @@ static int sdw_prep_deprep_ports(struct sdw_master_runtime *m_rt, bool prep) list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) { list_for_each_entry(p_rt, &s_rt->port_list, port_node) { ret = sdw_prep_deprep_slave_ports(m_rt->bus, s_rt, - p_rt, prep); + p_rt, prep); if (ret < 0) return ret; } @@ -579,7 +585,7 @@ static int sdw_notify_config(struct sdw_master_runtime *m_rt) ret = slave->ops->bus_config(slave, &bus->params); if (ret < 0) dev_err(bus->dev, "Notify Slave: %d failed", - slave->dev_num); + slave->dev_num); return ret; } } @@ -658,7 +664,7 @@ static int sdw_bank_switch(struct sdw_bus *bus, int m_rt_count) addr = SDW_SCP_FRAMECTRL_B0; sdw_fill_msg(wr_msg, NULL, addr, 1, SDW_BROADCAST_DEV_NUM, - SDW_MSG_FLAG_WRITE, wbuf); + SDW_MSG_FLAG_WRITE, wbuf); wr_msg->ssp_sync = true; /* @@ -873,7 +879,7 @@ EXPORT_SYMBOL(sdw_alloc_stream); static struct sdw_master_runtime *sdw_find_master_rt(struct sdw_bus *bus, - struct sdw_stream_runtime *stream) + struct sdw_stream_runtime *stream) { struct sdw_master_runtime *m_rt = NULL; @@ -897,8 +903,8 @@ static struct sdw_master_runtime */ static struct sdw_master_runtime *sdw_alloc_master_rt(struct sdw_bus *bus, - struct sdw_stream_config *stream_config, - struct sdw_stream_runtime *stream) + struct sdw_stream_config *stream_config, + struct sdw_stream_runtime *stream) { struct sdw_master_runtime *m_rt; @@ -941,8 +947,8 @@ static struct sdw_master_runtime */ static struct sdw_slave_runtime *sdw_alloc_slave_rt(struct sdw_slave *slave, - struct sdw_stream_config *stream_config, - struct sdw_stream_runtime *stream) + struct sdw_stream_config *stream_config, + struct sdw_stream_runtime *stream) { struct sdw_slave_runtime *s_rt = NULL; @@ -959,20 +965,19 @@ static struct sdw_slave_runtime } static void sdw_master_port_release(struct sdw_bus *bus, - struct sdw_master_runtime *m_rt) + struct sdw_master_runtime *m_rt) { struct sdw_port_runtime *p_rt, *_p_rt; - list_for_each_entry_safe(p_rt, _p_rt, - &m_rt->port_list, port_node) { + list_for_each_entry_safe(p_rt, _p_rt, &m_rt->port_list, port_node) { list_del(&p_rt->port_node); kfree(p_rt); } } static void sdw_slave_port_release(struct sdw_bus *bus, - struct sdw_slave *slave, - struct sdw_stream_runtime *stream) + struct sdw_slave *slave, + struct sdw_stream_runtime *stream) { struct sdw_port_runtime *p_rt, *_p_rt; struct sdw_master_runtime *m_rt; @@ -985,7 +990,7 @@ static void sdw_slave_port_release(struct sdw_bus *bus, continue; list_for_each_entry_safe(p_rt, _p_rt, - &s_rt->port_list, port_node) { + &s_rt->port_list, port_node) { list_del(&p_rt->port_node); kfree(p_rt); @@ -1003,7 +1008,7 @@ static void sdw_slave_port_release(struct sdw_bus *bus, * This function is to be called with bus_lock held. */ static void sdw_release_slave_stream(struct sdw_slave *slave, - struct sdw_stream_runtime *stream) + struct sdw_stream_runtime *stream) { struct sdw_slave_runtime *s_rt, *_s_rt; struct sdw_master_runtime *m_rt; @@ -1011,7 +1016,7 @@ static void sdw_release_slave_stream(struct sdw_slave *slave, list_for_each_entry(m_rt, &stream->master_list, stream_node) { /* Retrieve Slave runtime handle */ list_for_each_entry_safe(s_rt, _s_rt, - &m_rt->slave_rt_list, m_rt_node) { + &m_rt->slave_rt_list, m_rt_node) { if (s_rt->slave == slave) { list_del(&s_rt->m_rt_node); @@ -1034,7 +1039,7 @@ static void sdw_release_slave_stream(struct sdw_slave *slave, * no effect as Slave(s) runtime handle would already be freed up. */ static void sdw_release_master_stream(struct sdw_master_runtime *m_rt, - struct sdw_stream_runtime *stream) + struct sdw_stream_runtime *stream) { struct sdw_slave_runtime *s_rt, *_s_rt; @@ -1057,14 +1062,14 @@ static void sdw_release_master_stream(struct sdw_master_runtime *m_rt, * This removes and frees port_rt and master_rt from a stream */ int sdw_stream_remove_master(struct sdw_bus *bus, - struct sdw_stream_runtime *stream) + struct sdw_stream_runtime *stream) { struct sdw_master_runtime *m_rt, *_m_rt; mutex_lock(&bus->bus_lock); list_for_each_entry_safe(m_rt, _m_rt, - &stream->master_list, stream_node) { + &stream->master_list, stream_node) { if (m_rt->bus != bus) continue; @@ -1092,7 +1097,7 @@ EXPORT_SYMBOL(sdw_stream_remove_master); * This removes and frees port_rt and slave_rt from a stream */ int sdw_stream_remove_slave(struct sdw_slave *slave, - struct sdw_stream_runtime *stream) + struct sdw_stream_runtime *stream) { mutex_lock(&slave->bus->bus_lock); @@ -1116,8 +1121,9 @@ EXPORT_SYMBOL(sdw_stream_remove_slave); * This function is to be called with bus_lock held. */ static int sdw_config_stream(struct device *dev, - struct sdw_stream_runtime *stream, - struct sdw_stream_config *stream_config, bool is_slave) + struct sdw_stream_runtime *stream, + struct sdw_stream_config *stream_config, + bool is_slave) { /* * Update the stream rate, channel and bps based on data @@ -1128,13 +1134,13 @@ static int sdw_config_stream(struct device *dev, * comparison and allow the value to be set and stored in stream */ if (stream->params.rate && - stream->params.rate != stream_config->frame_rate) { + stream->params.rate != stream_config->frame_rate) { dev_err(dev, "rate not matching, stream:%s", stream->name); return -EINVAL; } if (stream->params.bps && - stream->params.bps != stream_config->bps) { + stream->params.bps != stream_config->bps) { dev_err(dev, "bps not matching, stream:%s", stream->name); return -EINVAL; } @@ -1151,7 +1157,7 @@ static int sdw_config_stream(struct device *dev, } static int sdw_is_valid_port_range(struct device *dev, - struct sdw_port_runtime *p_rt) + struct sdw_port_runtime *p_rt) { if (!SDW_VALID_PORT_RANGE(p_rt->num)) { dev_err(dev, @@ -1162,9 +1168,10 @@ static int sdw_is_valid_port_range(struct device *dev, return 0; } -static struct sdw_port_runtime *sdw_port_alloc(struct device *dev, - struct sdw_port_config *port_config, - int port_index) +static struct sdw_port_runtime +*sdw_port_alloc(struct device *dev, + struct sdw_port_config *port_config, + int port_index) { struct sdw_port_runtime *p_rt; @@ -1179,9 +1186,9 @@ static struct sdw_port_runtime *sdw_port_alloc(struct device *dev, } static int sdw_master_port_config(struct sdw_bus *bus, - struct sdw_master_runtime *m_rt, - struct sdw_port_config *port_config, - unsigned int num_ports) + struct sdw_master_runtime *m_rt, + struct sdw_port_config *port_config, + unsigned int num_ports) { struct sdw_port_runtime *p_rt; int i; @@ -1204,9 +1211,9 @@ static int sdw_master_port_config(struct sdw_bus *bus, } static int sdw_slave_port_config(struct sdw_slave *slave, - struct sdw_slave_runtime *s_rt, - struct sdw_port_config *port_config, - unsigned int num_config) + struct sdw_slave_runtime *s_rt, + struct sdw_port_config *port_config, + unsigned int num_config) { struct sdw_port_runtime *p_rt; int i, ret; @@ -1248,10 +1255,10 @@ static int sdw_slave_port_config(struct sdw_slave *slave, * @stream: SoundWire stream */ int sdw_stream_add_master(struct sdw_bus *bus, - struct sdw_stream_config *stream_config, - struct sdw_port_config *port_config, - unsigned int num_ports, - struct sdw_stream_runtime *stream) + struct sdw_stream_config *stream_config, + struct sdw_port_config *port_config, + unsigned int num_ports, + struct sdw_stream_runtime *stream) { struct sdw_master_runtime *m_rt = NULL; int ret; @@ -1273,8 +1280,8 @@ int sdw_stream_add_master(struct sdw_bus *bus, m_rt = sdw_alloc_master_rt(bus, stream_config, stream); if (!m_rt) { dev_err(bus->dev, - "Master runtime config failed for stream:%s", - stream->name); + "Master runtime config failed for stream:%s", + stream->name); ret = -ENOMEM; goto unlock; } @@ -1313,10 +1320,10 @@ EXPORT_SYMBOL(sdw_stream_add_master); * */ int sdw_stream_add_slave(struct sdw_slave *slave, - struct sdw_stream_config *stream_config, - struct sdw_port_config *port_config, - unsigned int num_ports, - struct sdw_stream_runtime *stream) + struct sdw_stream_config *stream_config, + struct sdw_port_config *port_config, + unsigned int num_ports, + struct sdw_stream_runtime *stream) { struct sdw_slave_runtime *s_rt; struct sdw_master_runtime *m_rt; @@ -1331,8 +1338,8 @@ int sdw_stream_add_slave(struct sdw_slave *slave, m_rt = sdw_alloc_master_rt(slave->bus, stream_config, stream); if (!m_rt) { dev_err(&slave->dev, - "alloc master runtime failed for stream:%s", - stream->name); + "alloc master runtime failed for stream:%s", + stream->name); ret = -ENOMEM; goto error; } @@ -1340,8 +1347,8 @@ int sdw_stream_add_slave(struct sdw_slave *slave, s_rt = sdw_alloc_slave_rt(slave, stream_config, stream); if (!s_rt) { dev_err(&slave->dev, - "Slave runtime config failed for stream:%s", - stream->name); + "Slave runtime config failed for stream:%s", + stream->name); ret = -ENOMEM; goto stream_error; } @@ -1385,8 +1392,8 @@ EXPORT_SYMBOL(sdw_stream_add_slave); * @port_num: Port number */ struct sdw_dpn_prop *sdw_get_slave_dpn_prop(struct sdw_slave *slave, - enum sdw_data_direction direction, - unsigned int port_num) + enum sdw_data_direction direction, + unsigned int port_num) { struct sdw_dpn_prop *dpn_prop; u8 num_ports; @@ -1501,7 +1508,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream) ret = sdw_prep_deprep_ports(m_rt, true); if (ret < 0) { dev_err(bus->dev, "Prepare port(s) failed ret = %d", - ret); + ret); return ret; } } From c0cbfb0310452a6a6120485938a42151d0bacd37 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:36 -0500 Subject: [PATCH 212/255] soundwire: slave: fix alignment issues Use Linux style Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/slave.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/soundwire/slave.c b/drivers/soundwire/slave.c index ac103bd0c176..f39a5815e25d 100644 --- a/drivers/soundwire/slave.c +++ b/drivers/soundwire/slave.c @@ -14,7 +14,7 @@ static void sdw_slave_release(struct device *dev) } static int sdw_slave_add(struct sdw_bus *bus, - struct sdw_slave_id *id, struct fwnode_handle *fwnode) + struct sdw_slave_id *id, struct fwnode_handle *fwnode) { struct sdw_slave *slave; int ret; @@ -30,8 +30,8 @@ static int sdw_slave_add(struct sdw_bus *bus, /* name shall be sdw:link:mfg:part:class:unique */ dev_set_name(&slave->dev, "sdw:%x:%x:%x:%x:%x", - bus->link_id, id->mfg_id, id->part_id, - id->class_id, id->unique_id); + bus->link_id, id->mfg_id, id->part_id, + id->class_id, id->unique_id); slave->dev.release = sdw_slave_release; slave->dev.bus = &sdw_bus_type; @@ -84,11 +84,11 @@ int sdw_acpi_find_slaves(struct sdw_bus *bus) acpi_status status; status = acpi_evaluate_integer(adev->handle, - METHOD_NAME__ADR, NULL, &addr); + METHOD_NAME__ADR, NULL, &addr); if (ACPI_FAILURE(status)) { dev_err(bus->dev, "_ADR resolution failed: %x\n", - status); + status); return status; } From 505ccb0065208214a9b582dea6984532c1c241c6 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:37 -0500 Subject: [PATCH 213/255] soundwire: intel_init: fix alignment issues Use Linux style Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/intel_init.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/soundwire/intel_init.c b/drivers/soundwire/intel_init.c index e0f2903101c7..9ad6045720c4 100644 --- a/drivers/soundwire/intel_init.c +++ b/drivers/soundwire/intel_init.c @@ -69,7 +69,7 @@ static struct sdw_intel_ctx /* Found controller, find links supported */ count = 0; ret = fwnode_property_read_u8_array(acpi_fwnode_handle(adev), - "mipi-sdw-master-count", &count, 1); + "mipi-sdw-master-count", &count, 1); /* Don't fail on error, continue and use hw value */ if (ret) { @@ -87,7 +87,7 @@ static struct sdw_intel_ctx /* Check count is within bounds */ if (count > SDW_MAX_LINKS) { dev_err(&adev->dev, "Link count %d exceeds max %d\n", - count, SDW_MAX_LINKS); + count, SDW_MAX_LINKS); return NULL; } @@ -147,7 +147,7 @@ static struct sdw_intel_ctx } static acpi_status sdw_intel_acpi_cb(acpi_handle handle, u32 level, - void *cdata, void **return_value) + void *cdata, void **return_value) { struct sdw_intel_res *res = cdata; struct acpi_device *adev; @@ -174,9 +174,9 @@ void *sdw_intel_init(acpi_handle *parent_handle, struct sdw_intel_res *res) acpi_status status; status = acpi_walk_namespace(ACPI_TYPE_DEVICE, - parent_handle, 1, - sdw_intel_acpi_cb, - NULL, res, NULL); + parent_handle, 1, + sdw_intel_acpi_cb, + NULL, res, NULL); if (ACPI_FAILURE(status)) return NULL; From d542bc9e22342d29de9ef0a7f31b8f158711753a Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:38 -0500 Subject: [PATCH 214/255] soundwire: intel: fix alignment issues Use Linux style Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/intel.c | 59 +++++++++++++++++++-------------------- 1 file changed, 29 insertions(+), 30 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 70ca27ccad85..56d6c1dda0ff 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -236,7 +236,7 @@ static int intel_shim_init(struct sdw_intel *sdw) /* Set SyncCPU bit */ sync_reg |= SDW_SHIM_SYNC_SYNCCPU; ret = intel_clear_bit(shim, SDW_SHIM_SYNC, sync_reg, - SDW_SHIM_SYNC_SYNCCPU); + SDW_SHIM_SYNC_SYNCCPU); if (ret < 0) dev_err(sdw->cdns.dev, "Failed to set sync period: %d", ret); @@ -247,7 +247,7 @@ static int intel_shim_init(struct sdw_intel *sdw) * PDI routines */ static void intel_pdi_init(struct sdw_intel *sdw, - struct sdw_cdns_stream_config *config) + struct sdw_cdns_stream_config *config) { void __iomem *shim = sdw->res->shim; unsigned int link_id = sdw->instance; @@ -296,9 +296,9 @@ intel_pdi_get_ch_cap(struct sdw_intel *sdw, unsigned int pdi_num, bool pcm) } static int intel_pdi_get_ch_update(struct sdw_intel *sdw, - struct sdw_cdns_pdi *pdi, - unsigned int num_pdi, - unsigned int *num_ch, bool pcm) + struct sdw_cdns_pdi *pdi, + unsigned int num_pdi, + unsigned int *num_ch, bool pcm) { int i, ch_count = 0; @@ -313,16 +313,16 @@ static int intel_pdi_get_ch_update(struct sdw_intel *sdw, } static int intel_pdi_stream_ch_update(struct sdw_intel *sdw, - struct sdw_cdns_streams *stream, bool pcm) + struct sdw_cdns_streams *stream, bool pcm) { intel_pdi_get_ch_update(sdw, stream->bd, stream->num_bd, - &stream->num_ch_bd, pcm); + &stream->num_ch_bd, pcm); intel_pdi_get_ch_update(sdw, stream->in, stream->num_in, - &stream->num_ch_in, pcm); + &stream->num_ch_in, pcm); intel_pdi_get_ch_update(sdw, stream->out, stream->num_out, - &stream->num_ch_out, pcm); + &stream->num_ch_out, pcm); return 0; } @@ -387,9 +387,9 @@ intel_pdi_alh_configure(struct sdw_intel *sdw, struct sdw_cdns_pdi *pdi) } static int intel_config_stream(struct sdw_intel *sdw, - struct snd_pcm_substream *substream, - struct snd_soc_dai *dai, - struct snd_pcm_hw_params *hw_params, int link_id) + struct snd_pcm_substream *substream, + struct snd_soc_dai *dai, + struct snd_pcm_hw_params *hw_params, int link_id) { if (sdw->res->ops && sdw->res->ops->config_stream) return sdw->res->ops->config_stream(sdw->res->arg, @@ -454,7 +454,7 @@ static int intel_post_bank_switch(struct sdw_bus *bus) sync_reg |= SDW_SHIM_SYNC_SYNCGO; ret = intel_clear_bit(shim, SDW_SHIM_SYNC, sync_reg, - SDW_SHIM_SYNC_SYNCGO); + SDW_SHIM_SYNC_SYNCGO); if (ret < 0) dev_err(sdw->cdns.dev, "Post bank switch failed: %d", ret); @@ -466,7 +466,7 @@ static int intel_post_bank_switch(struct sdw_bus *bus) */ static struct sdw_cdns_port *intel_alloc_port(struct sdw_intel *sdw, - u32 ch, u32 dir, bool pcm) + u32 ch, u32 dir, bool pcm) { struct sdw_cdns *cdns = &sdw->cdns; struct sdw_cdns_port *port = NULL; @@ -526,8 +526,8 @@ static void intel_port_cleanup(struct sdw_cdns_dma_data *dma) } static int intel_hw_params(struct snd_pcm_substream *substream, - struct snd_pcm_hw_params *params, - struct snd_soc_dai *dai) + struct snd_pcm_hw_params *params, + struct snd_soc_dai *dai) { struct sdw_cdns *cdns = snd_soc_dai_get_drvdata(dai); struct sdw_intel *sdw = cdns_to_intel(cdns); @@ -575,7 +575,7 @@ static int intel_hw_params(struct snd_pcm_substream *substream, /* Inform DSP about PDI stream number */ for (i = 0; i < dma->nr_ports; i++) { ret = intel_config_stream(sdw, substream, dai, params, - dma->port[i]->pdi->intel_alh_id); + dma->port[i]->pdi->intel_alh_id); if (ret) goto port_error; } @@ -605,7 +605,7 @@ static int intel_hw_params(struct snd_pcm_substream *substream, } ret = sdw_stream_add_master(&cdns->bus, &sconfig, - pconfig, dma->nr_ports, dma->stream); + pconfig, dma->nr_ports, dma->stream); if (ret) { dev_err(cdns->dev, "add master to stream failed:%d", ret); goto stream_error; @@ -636,7 +636,7 @@ intel_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) ret = sdw_stream_remove_master(&cdns->bus, dma->stream); if (ret < 0) dev_err(dai->dev, "remove master from stream %s failed: %d", - dma->stream->name, ret); + dma->stream->name, ret); intel_port_cleanup(dma); kfree(dma->port); @@ -644,13 +644,13 @@ intel_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) } static int intel_pcm_set_sdw_stream(struct snd_soc_dai *dai, - void *stream, int direction) + void *stream, int direction) { return cdns_set_sdw_stream(dai, stream, true, direction); } static int intel_pdm_set_sdw_stream(struct snd_soc_dai *dai, - void *stream, int direction) + void *stream, int direction) { return cdns_set_sdw_stream(dai, stream, false, direction); } @@ -674,9 +674,9 @@ static const struct snd_soc_component_driver dai_component = { }; static int intel_create_dai(struct sdw_cdns *cdns, - struct snd_soc_dai_driver *dais, - enum intel_pdi_type type, - u32 num, u32 off, u32 max_ch, bool pcm) + struct snd_soc_dai_driver *dais, + enum intel_pdi_type type, + u32 num, u32 off, u32 max_ch, bool pcm) { int i; @@ -686,7 +686,7 @@ static int intel_create_dai(struct sdw_cdns *cdns, /* TODO: Read supported rates/formats from hardware */ for (i = off; i < (off + num); i++) { dais[i].name = kasprintf(GFP_KERNEL, "SDW%d Pin%d", - cdns->instance, i); + cdns->instance, i); if (!dais[i].name) return -ENOMEM; @@ -787,7 +787,7 @@ static int intel_register_dai(struct sdw_intel *sdw) return ret; return snd_soc_register_component(cdns->dev, &dai_component, - dais, num_dai); + dais, num_dai); } static int intel_prop_read(struct sdw_bus *bus) @@ -873,12 +873,11 @@ static int intel_probe(struct platform_device *pdev) intel_pdi_ch_update(sdw); /* Acquire IRQ */ - ret = request_threaded_irq(sdw->res->irq, sdw_cdns_irq, - sdw_cdns_thread, IRQF_SHARED, KBUILD_MODNAME, - &sdw->cdns); + ret = request_threaded_irq(sdw->res->irq, sdw_cdns_irq, sdw_cdns_thread, + IRQF_SHARED, KBUILD_MODNAME, &sdw->cdns); if (ret < 0) { dev_err(sdw->cdns.dev, "unable to grab IRQ %d, disabling device\n", - sdw->res->irq); + sdw->res->irq); goto err_init; } From 7cc6e315317fe3a077fa474941a3ebf93fc15e78 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:39 -0500 Subject: [PATCH 215/255] soundwire: intel: protect macro parameters Extra parentheses required here Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/intel.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 56d6c1dda0ff..8c653a563534 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -24,18 +24,18 @@ #define SDW_SHIM_IPPTR 0x8 #define SDW_SHIM_SYNC 0xC -#define SDW_SHIM_CTLSCAP(x) (0x010 + 0x60 * x) -#define SDW_SHIM_CTLS0CM(x) (0x012 + 0x60 * x) -#define SDW_SHIM_CTLS1CM(x) (0x014 + 0x60 * x) -#define SDW_SHIM_CTLS2CM(x) (0x016 + 0x60 * x) -#define SDW_SHIM_CTLS3CM(x) (0x018 + 0x60 * x) -#define SDW_SHIM_PCMSCAP(x) (0x020 + 0x60 * x) +#define SDW_SHIM_CTLSCAP(x) (0x010 + 0x60 * (x)) +#define SDW_SHIM_CTLS0CM(x) (0x012 + 0x60 * (x)) +#define SDW_SHIM_CTLS1CM(x) (0x014 + 0x60 * (x)) +#define SDW_SHIM_CTLS2CM(x) (0x016 + 0x60 * (x)) +#define SDW_SHIM_CTLS3CM(x) (0x018 + 0x60 * (x)) +#define SDW_SHIM_PCMSCAP(x) (0x020 + 0x60 * (x)) -#define SDW_SHIM_PCMSYCHM(x, y) (0x022 + (0x60 * x) + (0x2 * y)) -#define SDW_SHIM_PCMSYCHC(x, y) (0x042 + (0x60 * x) + (0x2 * y)) -#define SDW_SHIM_PDMSCAP(x) (0x062 + 0x60 * x) -#define SDW_SHIM_IOCTL(x) (0x06C + 0x60 * x) -#define SDW_SHIM_CTMCTL(x) (0x06E + 0x60 * x) +#define SDW_SHIM_PCMSYCHM(x, y) (0x022 + (0x60 * (x)) + (0x2 * (y))) +#define SDW_SHIM_PCMSYCHC(x, y) (0x042 + (0x60 * (x)) + (0x2 * (y))) +#define SDW_SHIM_PDMSCAP(x) (0x062 + 0x60 * (x)) +#define SDW_SHIM_IOCTL(x) (0x06C + 0x60 * (x)) +#define SDW_SHIM_CTMCTL(x) (0x06E + 0x60 * (x)) #define SDW_SHIM_WAKEEN 0x190 #define SDW_SHIM_WAKESTS 0x192 @@ -82,7 +82,7 @@ #define SDW_SHIM_WAKESTS_STATUS BIT(0) /* Intel ALH Register definitions */ -#define SDW_ALH_STRMZCFG(x) (0x000 + (0x4 * x)) +#define SDW_ALH_STRMZCFG(x) (0x000 + (0x4 * (x))) #define SDW_ALH_STRMZCFG_DMAT_VAL 0x3 #define SDW_ALH_STRMZCFG_DMAT GENMASK(7, 0) From 2890a6363a8d42f6a24f0bbe6a48fae53d8bd875 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:40 -0500 Subject: [PATCH 216/255] soundwire: intel: fix boolean comparison No need for explicit test against true Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/intel.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 8c653a563534..2852ce293fd4 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -473,7 +473,7 @@ static struct sdw_cdns_port *intel_alloc_port(struct sdw_intel *sdw, int i, ret = 0; for (i = 0; i < cdns->num_ports; i++) { - if (cdns->ports[i].assigned == true) + if (cdns->ports[i].assigned) continue; port = &cdns->ports[i]; From bbb6381727b3f47f94bc19cec55149358dc3dc12 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:41 -0500 Subject: [PATCH 217/255] soundwire: cadence_master: fix alignment issues Use Linux style Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/cadence_master.c | 79 +++++++++++++++--------------- 1 file changed, 40 insertions(+), 39 deletions(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index cb6a331f448a..e45076be1e09 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -226,9 +226,9 @@ static int cdns_clear_bit(struct sdw_cdns *cdns, int offset, u32 value) /* * IO Calls */ -static enum sdw_command_response cdns_fill_msg_resp( - struct sdw_cdns *cdns, - struct sdw_msg *msg, int count, int offset) +static enum sdw_command_response +cdns_fill_msg_resp(struct sdw_cdns *cdns, + struct sdw_msg *msg, int count, int offset) { int nack = 0, no_ack = 0; int i; @@ -263,7 +263,7 @@ static enum sdw_command_response cdns_fill_msg_resp( static enum sdw_command_response _cdns_xfer_msg(struct sdw_cdns *cdns, struct sdw_msg *msg, int cmd, - int offset, int count, bool defer) + int offset, int count, bool defer) { unsigned long time; u32 base, i, data; @@ -296,7 +296,7 @@ _cdns_xfer_msg(struct sdw_cdns *cdns, struct sdw_msg *msg, int cmd, /* wait for timeout or response */ time = wait_for_completion_timeout(&cdns->tx_complete, - msecs_to_jiffies(CDNS_TX_TIMEOUT)); + msecs_to_jiffies(CDNS_TX_TIMEOUT)); if (!time) { dev_err(cdns->dev, "IO transfer timed out\n"); msg->len = 0; @@ -306,8 +306,8 @@ _cdns_xfer_msg(struct sdw_cdns *cdns, struct sdw_msg *msg, int cmd, return cdns_fill_msg_resp(cdns, msg, count, offset); } -static enum sdw_command_response cdns_program_scp_addr( - struct sdw_cdns *cdns, struct sdw_msg *msg) +static enum sdw_command_response +cdns_program_scp_addr(struct sdw_cdns *cdns, struct sdw_msg *msg) { int nack = 0, no_ack = 0; unsigned long time; @@ -336,7 +336,7 @@ static enum sdw_command_response cdns_program_scp_addr( cdns_writel(cdns, base, data[1]); time = wait_for_completion_timeout(&cdns->tx_complete, - msecs_to_jiffies(CDNS_TX_TIMEOUT)); + msecs_to_jiffies(CDNS_TX_TIMEOUT)); if (!time) { dev_err(cdns->dev, "SCP Msg trf timed out\n"); msg->len = 0; @@ -410,7 +410,7 @@ cdns_xfer_msg(struct sdw_bus *bus, struct sdw_msg *msg) for (i = 0; i < msg->len / CDNS_MCP_CMD_LEN; i++) { ret = _cdns_xfer_msg(cdns, msg, cmd, i * CDNS_MCP_CMD_LEN, - CDNS_MCP_CMD_LEN, false); + CDNS_MCP_CMD_LEN, false); if (ret < 0) goto exit; } @@ -419,7 +419,7 @@ cdns_xfer_msg(struct sdw_bus *bus, struct sdw_msg *msg) goto exit; ret = _cdns_xfer_msg(cdns, msg, cmd, i * CDNS_MCP_CMD_LEN, - msg->len % CDNS_MCP_CMD_LEN, false); + msg->len % CDNS_MCP_CMD_LEN, false); exit: return ret; @@ -428,7 +428,7 @@ EXPORT_SYMBOL(cdns_xfer_msg); enum sdw_command_response cdns_xfer_msg_defer(struct sdw_bus *bus, - struct sdw_msg *msg, struct sdw_defer *defer) + struct sdw_msg *msg, struct sdw_defer *defer) { struct sdw_cdns *cdns = bus_to_cdns(bus); int cmd = 0, ret; @@ -483,7 +483,7 @@ static void cdns_read_response(struct sdw_cdns *cdns) } static int cdns_update_slave_status(struct sdw_cdns *cdns, - u32 slave0, u32 slave1) + u32 slave0, u32 slave1) { enum sdw_slave_status status[SDW_MAX_DEVICES + 1]; bool is_slave = false; @@ -526,8 +526,8 @@ static int cdns_update_slave_status(struct sdw_cdns *cdns, /* first check if Slave reported multiple status */ if (set_status > 1) { dev_warn(cdns->dev, - "Slave reported multiple Status: %d\n", - status[i]); + "Slave reported multiple Status: %d\n", + status[i]); /* * TODO: we need to reread the status here by * issuing a PING cmd @@ -566,7 +566,7 @@ irqreturn_t sdw_cdns_irq(int irq, void *dev_id) if (cdns->defer) { cdns_fill_msg_resp(cdns, cdns->defer->msg, - cdns->defer->length, 0); + cdns->defer->length, 0); complete(&cdns->defer->complete); cdns->defer = NULL; } else @@ -592,7 +592,7 @@ irqreturn_t sdw_cdns_irq(int irq, void *dev_id) if (int_status & CDNS_MCP_INT_SLAVE_MASK) { /* Mask the Slave interrupt and wake thread */ cdns_updatel(cdns, CDNS_MCP_INTMASK, - CDNS_MCP_INT_SLAVE_MASK, 0); + CDNS_MCP_INT_SLAVE_MASK, 0); int_status &= ~CDNS_MCP_INT_SLAVE_MASK; ret = IRQ_WAKE_THREAD; @@ -625,7 +625,7 @@ irqreturn_t sdw_cdns_thread(int irq, void *dev_id) /* clear and unmask Slave interrupt now */ cdns_writel(cdns, CDNS_MCP_INTSTAT, CDNS_MCP_INT_SLAVE_MASK); cdns_updatel(cdns, CDNS_MCP_INTMASK, - CDNS_MCP_INT_SLAVE_MASK, CDNS_MCP_INT_SLAVE_MASK); + CDNS_MCP_INT_SLAVE_MASK, CDNS_MCP_INT_SLAVE_MASK); return IRQ_HANDLED; } @@ -639,9 +639,9 @@ static int _cdns_enable_interrupt(struct sdw_cdns *cdns) u32 mask; cdns_writel(cdns, CDNS_MCP_SLAVE_INTMASK0, - CDNS_MCP_SLAVE_INTMASK0_MASK); + CDNS_MCP_SLAVE_INTMASK0_MASK); cdns_writel(cdns, CDNS_MCP_SLAVE_INTMASK1, - CDNS_MCP_SLAVE_INTMASK1_MASK); + CDNS_MCP_SLAVE_INTMASK1_MASK); mask = CDNS_MCP_INT_SLAVE_RSVD | CDNS_MCP_INT_SLAVE_ALERT | CDNS_MCP_INT_SLAVE_ATTACH | CDNS_MCP_INT_SLAVE_NATTACH | @@ -663,7 +663,7 @@ int sdw_cdns_enable_interrupt(struct sdw_cdns *cdns) _cdns_enable_interrupt(cdns); ret = cdns_clear_bit(cdns, CDNS_MCP_CONFIG_UPDATE, - CDNS_MCP_CONFIG_UPDATE_BIT); + CDNS_MCP_CONFIG_UPDATE_BIT); if (ret < 0) dev_err(cdns->dev, "Config update timedout"); @@ -672,8 +672,8 @@ int sdw_cdns_enable_interrupt(struct sdw_cdns *cdns) EXPORT_SYMBOL(sdw_cdns_enable_interrupt); static int cdns_allocate_pdi(struct sdw_cdns *cdns, - struct sdw_cdns_pdi **stream, - u32 num, u32 pdi_offset) + struct sdw_cdns_pdi **stream, + u32 num, u32 pdi_offset) { struct sdw_cdns_pdi *pdi; int i; @@ -701,7 +701,7 @@ static int cdns_allocate_pdi(struct sdw_cdns *cdns, * @config: Stream configurations */ int sdw_cdns_pdi_init(struct sdw_cdns *cdns, - struct sdw_cdns_stream_config config) + struct sdw_cdns_stream_config config) { struct sdw_cdns_streams *stream; int offset, i, ret; @@ -770,7 +770,7 @@ int sdw_cdns_pdi_init(struct sdw_cdns *cdns, cdns->num_ports += stream->num_pdi; cdns->ports = devm_kcalloc(cdns->dev, cdns->num_ports, - sizeof(*cdns->ports), GFP_KERNEL); + sizeof(*cdns->ports), GFP_KERNEL); if (!cdns->ports) { ret = -ENOMEM; return ret; @@ -796,7 +796,7 @@ int sdw_cdns_init(struct sdw_cdns *cdns) /* Exit clock stop */ ret = cdns_clear_bit(cdns, CDNS_MCP_CONTROL, - CDNS_MCP_CONTROL_CLK_STOP_CLR); + CDNS_MCP_CONTROL_CLK_STOP_CLR); if (ret < 0) { dev_err(cdns->dev, "Couldn't exit from clock stop\n"); return ret; @@ -816,7 +816,7 @@ int sdw_cdns_init(struct sdw_cdns *cdns) /* Set cmd accept mode */ cdns_updatel(cdns, CDNS_MCP_CONTROL, CDNS_MCP_CONTROL_CMD_ACCEPT, - CDNS_MCP_CONTROL_CMD_ACCEPT); + CDNS_MCP_CONTROL_CMD_ACCEPT); /* Configure mcp config */ val = cdns_readl(cdns, CDNS_MCP_CONFIG); @@ -873,7 +873,7 @@ int cdns_bus_conf(struct sdw_bus *bus, struct sdw_bus_params *params) EXPORT_SYMBOL(cdns_bus_conf); static int cdns_port_params(struct sdw_bus *bus, - struct sdw_port_params *p_params, unsigned int bank) + struct sdw_port_params *p_params, unsigned int bank) { struct sdw_cdns *cdns = bus_to_cdns(bus); int dpn_config = 0, dpn_config_off; @@ -898,8 +898,8 @@ static int cdns_port_params(struct sdw_bus *bus, } static int cdns_transport_params(struct sdw_bus *bus, - struct sdw_transport_params *t_params, - enum sdw_reg_bank bank) + struct sdw_transport_params *t_params, + enum sdw_reg_bank bank) { struct sdw_cdns *cdns = bus_to_cdns(bus); int dpn_offsetctrl = 0, dpn_offsetctrl_off; @@ -952,7 +952,7 @@ static int cdns_transport_params(struct sdw_bus *bus, } static int cdns_port_enable(struct sdw_bus *bus, - struct sdw_enable_ch *enable_ch, unsigned int bank) + struct sdw_enable_ch *enable_ch, unsigned int bank) { struct sdw_cdns *cdns = bus_to_cdns(bus); int dpn_chnen_off, ch_mask; @@ -988,7 +988,7 @@ int sdw_cdns_probe(struct sdw_cdns *cdns) EXPORT_SYMBOL(sdw_cdns_probe); int cdns_set_sdw_stream(struct snd_soc_dai *dai, - void *stream, bool pcm, int direction) + void *stream, bool pcm, int direction) { struct sdw_cdns *cdns = snd_soc_dai_get_drvdata(dai); struct sdw_cdns_dma_data *dma; @@ -1026,7 +1026,8 @@ EXPORT_SYMBOL(cdns_set_sdw_stream); * Find and return a free PDI for a given PDI array */ static struct sdw_cdns_pdi *cdns_find_pdi(struct sdw_cdns *cdns, - unsigned int num, struct sdw_cdns_pdi *pdi) + unsigned int num, + struct sdw_cdns_pdi *pdi) { int i; @@ -1050,8 +1051,8 @@ static struct sdw_cdns_pdi *cdns_find_pdi(struct sdw_cdns *cdns, * @pdi: PDI to be used */ void sdw_cdns_config_stream(struct sdw_cdns *cdns, - struct sdw_cdns_port *port, - u32 ch, u32 dir, struct sdw_cdns_pdi *pdi) + struct sdw_cdns_port *port, + u32 ch, u32 dir, struct sdw_cdns_pdi *pdi) { u32 offset, val = 0; @@ -1076,8 +1077,8 @@ EXPORT_SYMBOL(sdw_cdns_config_stream); * @ch_count: Channel count */ static int cdns_get_num_pdi(struct sdw_cdns *cdns, - struct sdw_cdns_pdi *pdi, - unsigned int num, u32 ch_count) + struct sdw_cdns_pdi *pdi, + unsigned int num, u32 ch_count) { int i, pdis = 0; @@ -1139,8 +1140,8 @@ EXPORT_SYMBOL(sdw_cdns_get_stream); * @dir: Data direction */ int sdw_cdns_alloc_stream(struct sdw_cdns *cdns, - struct sdw_cdns_streams *stream, - struct sdw_cdns_port *port, u32 ch, u32 dir) + struct sdw_cdns_streams *stream, + struct sdw_cdns_port *port, u32 ch, u32 dir) { struct sdw_cdns_pdi *pdi = NULL; @@ -1167,7 +1168,7 @@ int sdw_cdns_alloc_stream(struct sdw_cdns *cdns, EXPORT_SYMBOL(sdw_cdns_alloc_stream); void sdw_cdns_shutdown(struct snd_pcm_substream *substream, - struct snd_soc_dai *dai) + struct snd_soc_dai *dai) { struct sdw_cdns_dma_data *dma; From f6e20967d86db68fbd795fcfcabe6cb7348ea306 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:42 -0500 Subject: [PATCH 218/255] soundwire: cadence_master: balance parentheses While not strictly necessary, balanced parentheses help with code readability. Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/cadence_master.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index e45076be1e09..04632a97721e 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -569,8 +569,9 @@ irqreturn_t sdw_cdns_irq(int irq, void *dev_id) cdns->defer->length, 0); complete(&cdns->defer->complete); cdns->defer = NULL; - } else + } else { complete(&cdns->tx_complete); + } } if (int_status & CDNS_MCP_INT_CTRL_CLASH) { From 4c56860280b85061f266c2e38c3f42a5f3085de9 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:43 -0500 Subject: [PATCH 219/255] soundwire: cadence_master: fix boolean comparisons No need for explicit test against true Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/cadence_master.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 04632a97721e..50181752c2a4 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -1033,7 +1033,7 @@ static struct sdw_cdns_pdi *cdns_find_pdi(struct sdw_cdns *cdns, int i; for (i = 0; i < num; i++) { - if (pdi[i].assigned == true) + if (pdi[i].assigned) continue; pdi[i].assigned = true; return &pdi[i]; @@ -1084,7 +1084,7 @@ static int cdns_get_num_pdi(struct sdw_cdns *cdns, int i, pdis = 0; for (i = 0; i < num; i++) { - if (pdi[i].assigned == true) + if (pdi[i].assigned) continue; if (pdi[i].ch_count < ch_count) From 5d2ab7e97ae888e68ada96e1216840e8e521e432 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:44 -0500 Subject: [PATCH 220/255] soundwire: cadence_master: remove spurious newline Extra newline does not improve readability. Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/cadence_master.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 50181752c2a4..5786a2e0be84 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -42,7 +42,6 @@ #define CDNS_MCP_CONTROL_CMD_ACCEPT BIT(1) #define CDNS_MCP_CONTROL_BLOCK_WAKEUP BIT(0) - #define CDNS_MCP_CMDCTRL 0x8 #define CDNS_MCP_SSPSTAT 0xC #define CDNS_MCP_FRAME_SHAPE 0x10 From 17ed5bef49f42ec04beb2ce2aebd24a5296c2a80 Mon Sep 17 00:00:00 2001 From: Pierre-Louis Bossart Date: Wed, 1 May 2019 10:57:45 -0500 Subject: [PATCH 221/255] soundwire: add missing newlines in dynamic debug logs For some reason the newlines are not used everywhere. Fix as needed. Reported-by: Joe Perches Reviewed-by: Takashi Iwai Signed-off-by: Pierre-Louis Bossart Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/bus.c | 74 +++++++++---------- drivers/soundwire/cadence_master.c | 12 ++-- drivers/soundwire/intel.c | 12 ++-- drivers/soundwire/stream.c | 110 ++++++++++++++--------------- 4 files changed, 104 insertions(+), 104 deletions(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index bb697fd68580..fa86957cb615 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -21,12 +21,12 @@ int sdw_add_bus_master(struct sdw_bus *bus) int ret; if (!bus->dev) { - pr_err("SoundWire bus has no device"); + pr_err("SoundWire bus has no device\n"); return -ENODEV; } if (!bus->ops) { - dev_err(bus->dev, "SoundWire Bus ops are not set"); + dev_err(bus->dev, "SoundWire Bus ops are not set\n"); return -EINVAL; } @@ -43,7 +43,7 @@ int sdw_add_bus_master(struct sdw_bus *bus) if (bus->ops->read_prop) { ret = bus->ops->read_prop(bus); if (ret < 0) { - dev_err(bus->dev, "Bus read properties failed:%d", ret); + dev_err(bus->dev, "Bus read properties failed:%d\n", ret); return ret; } } @@ -296,7 +296,7 @@ int sdw_fill_msg(struct sdw_msg *msg, struct sdw_slave *slave, return -EINVAL; } else if (!slave->prop.paging_support) { dev_err(&slave->dev, - "address %x needs paging but no support", addr); + "address %x needs paging but no support\n", addr); return -EINVAL; } @@ -455,13 +455,13 @@ static int sdw_assign_device_num(struct sdw_slave *slave) dev_num = sdw_get_device_num(slave); mutex_unlock(&slave->bus->bus_lock); if (dev_num < 0) { - dev_err(slave->bus->dev, "Get dev_num failed: %d", + dev_err(slave->bus->dev, "Get dev_num failed: %d\n", dev_num); return dev_num; } } else { dev_info(slave->bus->dev, - "Slave already registered dev_num:%d", + "Slave already registered dev_num:%d\n", slave->dev_num); /* Clear the slave->dev_num to transfer message on device 0 */ @@ -472,7 +472,7 @@ static int sdw_assign_device_num(struct sdw_slave *slave) ret = sdw_write(slave, SDW_SCP_DEVNUMBER, dev_num); if (ret < 0) { - dev_err(&slave->dev, "Program device_num failed: %d", ret); + dev_err(&slave->dev, "Program device_num failed: %d\n", ret); return ret; } @@ -485,7 +485,7 @@ static int sdw_assign_device_num(struct sdw_slave *slave) void sdw_extract_slave_id(struct sdw_bus *bus, u64 addr, struct sdw_slave_id *id) { - dev_dbg(bus->dev, "SDW Slave Addr: %llx", addr); + dev_dbg(bus->dev, "SDW Slave Addr: %llx\n", addr); /* * Spec definition @@ -505,7 +505,7 @@ void sdw_extract_slave_id(struct sdw_bus *bus, id->class_id = addr & GENMASK(7, 0); dev_dbg(bus->dev, - "SDW Slave class_id %x, part_id %x, mfg_id %x, unique_id %x, version %x", + "SDW Slave class_id %x, part_id %x, mfg_id %x, unique_id %x, version %x\n", id->class_id, id->part_id, id->mfg_id, id->unique_id, id->sdw_version); @@ -562,7 +562,7 @@ static int sdw_program_device_num(struct sdw_bus *bus) ret = sdw_assign_device_num(slave); if (ret) { dev_err(slave->bus->dev, - "Assign dev_num failed:%d", + "Assign dev_num failed:%d\n", ret); return ret; } @@ -573,7 +573,7 @@ static int sdw_program_device_num(struct sdw_bus *bus) if (!found) { /* TODO: Park this device in Group 13 */ - dev_err(bus->dev, "Slave Entry not found"); + dev_err(bus->dev, "Slave Entry not found\n"); } count++; @@ -618,7 +618,7 @@ int sdw_configure_dpn_intr(struct sdw_slave *slave, ret = sdw_update(slave, addr, (mask | SDW_DPN_INT_PORT_READY), val); if (ret < 0) dev_err(slave->bus->dev, - "SDW_DPN_INTMASK write failed:%d", val); + "SDW_DPN_INTMASK write failed:%d\n", val); return ret; } @@ -642,7 +642,7 @@ static int sdw_initialize_slave(struct sdw_slave *slave) ret = sdw_update(slave, SDW_SCP_INTMASK1, val, val); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_SCP_INTMASK1 write failed:%d", ret); + "SDW_SCP_INTMASK1 write failed:%d\n", ret); return ret; } @@ -657,7 +657,7 @@ static int sdw_initialize_slave(struct sdw_slave *slave) ret = sdw_update(slave, SDW_DP0_INTMASK, val, val); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_DP0_INTMASK read failed:%d", ret); + "SDW_DP0_INTMASK read failed:%d\n", ret); return val; } @@ -672,14 +672,14 @@ static int sdw_handle_dp0_interrupt(struct sdw_slave *slave, u8 *slave_status) status = sdw_read(slave, SDW_DP0_INT); if (status < 0) { dev_err(slave->bus->dev, - "SDW_DP0_INT read failed:%d", status); + "SDW_DP0_INT read failed:%d\n", status); return status; } do { if (status & SDW_DP0_INT_TEST_FAIL) { - dev_err(&slave->dev, "Test fail for port 0"); + dev_err(&slave->dev, "Test fail for port 0\n"); clear |= SDW_DP0_INT_TEST_FAIL; } @@ -694,7 +694,7 @@ static int sdw_handle_dp0_interrupt(struct sdw_slave *slave, u8 *slave_status) } if (status & SDW_DP0_INT_BRA_FAILURE) { - dev_err(&slave->dev, "BRA failed"); + dev_err(&slave->dev, "BRA failed\n"); clear |= SDW_DP0_INT_BRA_FAILURE; } @@ -710,7 +710,7 @@ static int sdw_handle_dp0_interrupt(struct sdw_slave *slave, u8 *slave_status) ret = sdw_write(slave, SDW_DP0_INT, clear); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_DP0_INT write failed:%d", ret); + "SDW_DP0_INT write failed:%d\n", ret); return ret; } @@ -718,7 +718,7 @@ static int sdw_handle_dp0_interrupt(struct sdw_slave *slave, u8 *slave_status) status2 = sdw_read(slave, SDW_DP0_INT); if (status2 < 0) { dev_err(slave->bus->dev, - "SDW_DP0_INT read failed:%d", status2); + "SDW_DP0_INT read failed:%d\n", status2); return status2; } status &= status2; @@ -729,7 +729,7 @@ static int sdw_handle_dp0_interrupt(struct sdw_slave *slave, u8 *slave_status) } while (status != 0 && count < SDW_READ_INTR_CLEAR_RETRY); if (count == SDW_READ_INTR_CLEAR_RETRY) - dev_warn(slave->bus->dev, "Reached MAX_RETRY on DP0 read"); + dev_warn(slave->bus->dev, "Reached MAX_RETRY on DP0 read\n"); return ret; } @@ -748,7 +748,7 @@ static int sdw_handle_port_interrupt(struct sdw_slave *slave, status = sdw_read(slave, addr); if (status < 0) { dev_err(slave->bus->dev, - "SDW_DPN_INT read failed:%d", status); + "SDW_DPN_INT read failed:%d\n", status); return status; } @@ -756,7 +756,7 @@ static int sdw_handle_port_interrupt(struct sdw_slave *slave, do { if (status & SDW_DPN_INT_TEST_FAIL) { - dev_err(&slave->dev, "Test fail for port:%d", port); + dev_err(&slave->dev, "Test fail for port:%d\n", port); clear |= SDW_DPN_INT_TEST_FAIL; } @@ -781,7 +781,7 @@ static int sdw_handle_port_interrupt(struct sdw_slave *slave, ret = sdw_write(slave, addr, clear); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_DPN_INT write failed:%d", ret); + "SDW_DPN_INT write failed:%d\n", ret); return ret; } @@ -789,7 +789,7 @@ static int sdw_handle_port_interrupt(struct sdw_slave *slave, status2 = sdw_read(slave, addr); if (status2 < 0) { dev_err(slave->bus->dev, - "SDW_DPN_INT read failed:%d", status2); + "SDW_DPN_INT read failed:%d\n", status2); return status2; } status &= status2; @@ -820,14 +820,14 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) buf = ret = sdw_read(slave, SDW_SCP_INT1); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_SCP_INT1 read failed:%d", ret); + "SDW_SCP_INT1 read failed:%d\n", ret); return ret; } ret = sdw_nread(slave, SDW_SCP_INTSTAT2, 2, buf2); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_SCP_INT2/3 read failed:%d", ret); + "SDW_SCP_INT2/3 read failed:%d\n", ret); return ret; } @@ -837,12 +837,12 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) * interrupt */ if (buf & SDW_SCP_INT1_PARITY) { - dev_err(&slave->dev, "Parity error detected"); + dev_err(&slave->dev, "Parity error detected\n"); clear |= SDW_SCP_INT1_PARITY; } if (buf & SDW_SCP_INT1_BUS_CLASH) { - dev_err(&slave->dev, "Bus clash error detected"); + dev_err(&slave->dev, "Bus clash error detected\n"); clear |= SDW_SCP_INT1_BUS_CLASH; } @@ -908,7 +908,7 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) ret = sdw_write(slave, SDW_SCP_INT1, clear); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_SCP_INT1 write failed:%d", ret); + "SDW_SCP_INT1 write failed:%d\n", ret); return ret; } @@ -919,14 +919,14 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) _buf = ret = sdw_read(slave, SDW_SCP_INT1); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_SCP_INT1 read failed:%d", ret); + "SDW_SCP_INT1 read failed:%d\n", ret); return ret; } ret = sdw_nread(slave, SDW_SCP_INTSTAT2, 2, _buf2); if (ret < 0) { dev_err(slave->bus->dev, - "SDW_SCP_INT2/3 read failed:%d", ret); + "SDW_SCP_INT2/3 read failed:%d\n", ret); return ret; } @@ -946,7 +946,7 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) } while (stat != 0 && count < SDW_READ_INTR_CLEAR_RETRY); if (count == SDW_READ_INTR_CLEAR_RETRY) - dev_warn(slave->bus->dev, "Reached MAX_RETRY on alert read"); + dev_warn(slave->bus->dev, "Reached MAX_RETRY on alert read\n"); return ret; } @@ -975,7 +975,7 @@ int sdw_handle_slave_status(struct sdw_bus *bus, if (status[0] == SDW_SLAVE_ATTACHED) { ret = sdw_program_device_num(bus); if (ret) - dev_err(bus->dev, "Slave attach failed: %d", ret); + dev_err(bus->dev, "Slave attach failed: %d\n", ret); } /* Continue to check other slave statuses */ @@ -1003,7 +1003,7 @@ int sdw_handle_slave_status(struct sdw_bus *bus, ret = sdw_handle_slave_alerts(slave); if (ret) dev_err(bus->dev, - "Slave %d alert handling failed: %d", + "Slave %d alert handling failed: %d\n", i, ret); break; @@ -1020,13 +1020,13 @@ int sdw_handle_slave_status(struct sdw_bus *bus, ret = sdw_initialize_slave(slave); if (ret) dev_err(bus->dev, - "Slave %d initialization failed: %d", + "Slave %d initialization failed: %d\n", i, ret); break; default: - dev_err(bus->dev, "Invalid slave %d status:%d", + dev_err(bus->dev, "Invalid slave %d status:%d\n", i, status[i]); break; } @@ -1034,7 +1034,7 @@ int sdw_handle_slave_status(struct sdw_bus *bus, ret = sdw_update_slave_status(slave, status[i]); if (ret) dev_err(slave->bus->dev, - "Update Slave status failed:%d", ret); + "Update Slave status failed:%d\n", ret); } diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 5786a2e0be84..0fdc17b995fc 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -346,10 +346,10 @@ cdns_program_scp_addr(struct sdw_cdns *cdns, struct sdw_msg *msg) for (i = 0; i < 2; i++) { if (!(cdns->response_buf[i] & CDNS_MCP_RESP_ACK)) { no_ack = 1; - dev_err(cdns->dev, "Program SCP Ack not received"); + dev_err(cdns->dev, "Program SCP Ack not received\n"); if (cdns->response_buf[i] & CDNS_MCP_RESP_NACK) { nack = 1; - dev_err(cdns->dev, "Program SCP NACK received"); + dev_err(cdns->dev, "Program SCP NACK received\n"); } } } @@ -357,11 +357,11 @@ cdns_program_scp_addr(struct sdw_cdns *cdns, struct sdw_msg *msg) /* For NACK, NO ack, don't return err if we are in Broadcast mode */ if (nack) { dev_err(cdns->dev, - "SCP_addrpage NACKed for Slave %d", msg->dev_num); + "SCP_addrpage NACKed for Slave %d\n", msg->dev_num); return SDW_CMD_FAIL; } else if (no_ack) { dev_dbg(cdns->dev, - "SCP_addrpage ignored for Slave %d", msg->dev_num); + "SCP_addrpage ignored for Slave %d\n", msg->dev_num); return SDW_CMD_IGNORED; } @@ -665,7 +665,7 @@ int sdw_cdns_enable_interrupt(struct sdw_cdns *cdns) ret = cdns_clear_bit(cdns, CDNS_MCP_CONFIG_UPDATE, CDNS_MCP_CONFIG_UPDATE_BIT); if (ret < 0) - dev_err(cdns->dev, "Config update timedout"); + dev_err(cdns->dev, "Config update timedout\n"); return ret; } @@ -853,7 +853,7 @@ int cdns_bus_conf(struct sdw_bus *bus, struct sdw_bus_params *params) int divider; if (!params->curr_dr_freq) { - dev_err(cdns->dev, "NULL curr_dr_freq"); + dev_err(cdns->dev, "NULL curr_dr_freq\n"); return -EINVAL; } diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 2852ce293fd4..9774dc1e4029 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -238,7 +238,7 @@ static int intel_shim_init(struct sdw_intel *sdw) ret = intel_clear_bit(shim, SDW_SHIM_SYNC, sync_reg, SDW_SHIM_SYNC_SYNCCPU); if (ret < 0) - dev_err(sdw->cdns.dev, "Failed to set sync period: %d", ret); + dev_err(sdw->cdns.dev, "Failed to set sync period: %d\n", ret); return ret; } @@ -456,7 +456,7 @@ static int intel_post_bank_switch(struct sdw_bus *bus) ret = intel_clear_bit(shim, SDW_SHIM_SYNC, sync_reg, SDW_SHIM_SYNC_SYNCGO); if (ret < 0) - dev_err(sdw->cdns.dev, "Post bank switch failed: %d", ret); + dev_err(sdw->cdns.dev, "Post bank switch failed: %d\n", ret); return ret; } @@ -556,7 +556,7 @@ static int intel_hw_params(struct snd_pcm_substream *substream, } if (!dma->nr_ports) { - dev_err(dai->dev, "ports/resources not available"); + dev_err(dai->dev, "ports/resources not available\n"); return -EINVAL; } @@ -607,7 +607,7 @@ static int intel_hw_params(struct snd_pcm_substream *substream, ret = sdw_stream_add_master(&cdns->bus, &sconfig, pconfig, dma->nr_ports, dma->stream); if (ret) { - dev_err(cdns->dev, "add master to stream failed:%d", ret); + dev_err(cdns->dev, "add master to stream failed:%d\n", ret); goto stream_error; } @@ -635,7 +635,7 @@ intel_hw_free(struct snd_pcm_substream *substream, struct snd_soc_dai *dai) ret = sdw_stream_remove_master(&cdns->bus, dma->stream); if (ret < 0) - dev_err(dai->dev, "remove master from stream %s failed: %d", + dev_err(dai->dev, "remove master from stream %s failed: %d\n", dma->stream->name, ret); intel_port_cleanup(dma); @@ -884,7 +884,7 @@ static int intel_probe(struct platform_device *pdev) /* Register DAIs */ ret = intel_register_dai(sdw); if (ret) { - dev_err(sdw->cdns.dev, "DAI registration failed: %d", ret); + dev_err(sdw->cdns.dev, "DAI registration failed: %d\n", ret); snd_soc_unregister_component(sdw->cdns.dev); goto err_dai; } diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index ab64c2c4c33f..166b0c16003f 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -76,14 +76,14 @@ static int _sdw_program_slave_port_params(struct sdw_bus *bus, /* Program DPN_OffsetCtrl2 registers */ ret = sdw_write(slave, addr1, t_params->offset2); if (ret < 0) { - dev_err(bus->dev, "DPN_OffsetCtrl2 register write failed"); + dev_err(bus->dev, "DPN_OffsetCtrl2 register write failed\n"); return ret; } /* Program DPN_BlockCtrl3 register */ ret = sdw_write(slave, addr2, t_params->blk_pkg_mode); if (ret < 0) { - dev_err(bus->dev, "DPN_BlockCtrl3 register write failed"); + dev_err(bus->dev, "DPN_BlockCtrl3 register write failed\n"); return ret; } @@ -102,7 +102,7 @@ static int _sdw_program_slave_port_params(struct sdw_bus *bus, ret = sdw_write(slave, addr3, wbuf); if (ret < 0) { - dev_err(bus->dev, "DPN_SampleCtrl2 register write failed"); + dev_err(bus->dev, "DPN_SampleCtrl2 register write failed\n"); return ret; } @@ -113,7 +113,7 @@ static int _sdw_program_slave_port_params(struct sdw_bus *bus, ret = sdw_write(slave, addr4, wbuf); if (ret < 0) - dev_err(bus->dev, "DPN_HCtrl register write failed"); + dev_err(bus->dev, "DPN_HCtrl register write failed\n"); return ret; } @@ -159,7 +159,7 @@ static int sdw_program_slave_port_params(struct sdw_bus *bus, ret = sdw_update(s_rt->slave, addr1, 0xF, wbuf); if (ret < 0) { dev_err(&s_rt->slave->dev, - "DPN_PortCtrl register write failed for port %d", + "DPN_PortCtrl register write failed for port %d\n", t_params->port_num); return ret; } @@ -168,7 +168,7 @@ static int sdw_program_slave_port_params(struct sdw_bus *bus, ret = sdw_write(s_rt->slave, addr2, (p_params->bps - 1)); if (ret < 0) { dev_err(&s_rt->slave->dev, - "DPN_BlockCtrl1 register write failed for port %d", + "DPN_BlockCtrl1 register write failed for port %d\n", t_params->port_num); return ret; } @@ -178,7 +178,7 @@ static int sdw_program_slave_port_params(struct sdw_bus *bus, ret = sdw_write(s_rt->slave, addr3, wbuf); if (ret < 0) { dev_err(&s_rt->slave->dev, - "DPN_SampleCtrl1 register write failed for port %d", + "DPN_SampleCtrl1 register write failed for port %d\n", t_params->port_num); return ret; } @@ -187,7 +187,7 @@ static int sdw_program_slave_port_params(struct sdw_bus *bus, ret = sdw_write(s_rt->slave, addr4, t_params->offset1); if (ret < 0) { dev_err(&s_rt->slave->dev, - "DPN_OffsetCtrl1 register write failed for port %d", + "DPN_OffsetCtrl1 register write failed for port %d\n", t_params->port_num); return ret; } @@ -197,7 +197,7 @@ static int sdw_program_slave_port_params(struct sdw_bus *bus, ret = sdw_write(s_rt->slave, addr5, t_params->blk_grp_ctrl); if (ret < 0) { dev_err(&s_rt->slave->dev, - "DPN_BlockCtrl2 reg write failed for port %d", + "DPN_BlockCtrl2 reg write failed for port %d\n", t_params->port_num); return ret; } @@ -208,7 +208,7 @@ static int sdw_program_slave_port_params(struct sdw_bus *bus, ret = sdw_write(s_rt->slave, addr6, t_params->lane_ctrl); if (ret < 0) { dev_err(&s_rt->slave->dev, - "DPN_LaneCtrl register write failed for port %d", + "DPN_LaneCtrl register write failed for port %d\n", t_params->port_num); return ret; } @@ -219,7 +219,7 @@ static int sdw_program_slave_port_params(struct sdw_bus *bus, t_params, dpn_prop->type); if (ret < 0) dev_err(&s_rt->slave->dev, - "Transport reg write failed for port: %d", + "Transport reg write failed for port: %d\n", t_params->port_num); } @@ -316,7 +316,7 @@ static int sdw_enable_disable_slave_ports(struct sdw_bus *bus, if (ret < 0) dev_err(&s_rt->slave->dev, - "Slave chn_en reg write failed:%d port:%d", + "Slave chn_en reg write failed:%d port:%d\n", ret, t_params->port_num); return ret; @@ -342,7 +342,7 @@ static int sdw_enable_disable_master_ports(struct sdw_master_runtime *m_rt, bus->params.next_bank); if (ret < 0) { dev_err(bus->dev, - "Master chn_en write failed:%d port:%d", + "Master chn_en write failed:%d port:%d\n", ret, t_params->port_num); return ret; } @@ -400,7 +400,7 @@ static int sdw_do_port_prep(struct sdw_slave_runtime *s_rt, ret = ops->port_prep(s_rt->slave, &prep_ch, cmd); if (ret < 0) { dev_err(&s_rt->slave->dev, - "Slave Port Prep cmd %d failed: %d", cmd, ret); + "Slave Port Prep cmd %d failed: %d\n", cmd, ret); return ret; } } @@ -429,7 +429,7 @@ static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus, prep_ch.num); if (!dpn_prop) { dev_err(bus->dev, - "Slave Port:%d properties not found", prep_ch.num); + "Slave Port:%d properties not found\n", prep_ch.num); return -EINVAL; } @@ -467,7 +467,7 @@ static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus, if (ret < 0) { dev_err(&s_rt->slave->dev, - "Slave prep_ctrl reg write failed"); + "Slave prep_ctrl reg write failed\n"); return ret; } @@ -480,7 +480,7 @@ static int sdw_prep_deprep_slave_ports(struct sdw_bus *bus, val &= p_rt->ch_mask; if (!time_left || val) { dev_err(&s_rt->slave->dev, - "Chn prep failed for port:%d", prep_ch.num); + "Chn prep failed for port:%d\n", prep_ch.num); return -ETIMEDOUT; } } @@ -515,7 +515,7 @@ static int sdw_prep_deprep_master_ports(struct sdw_master_runtime *m_rt, if (ops->dpn_port_prep) { ret = ops->dpn_port_prep(bus, &prep_ch); if (ret < 0) { - dev_err(bus->dev, "Port prepare failed for port:%d", + dev_err(bus->dev, "Port prepare failed for port:%d\n", t_params->port_num); return ret; } @@ -584,7 +584,7 @@ static int sdw_notify_config(struct sdw_master_runtime *m_rt) if (slave->ops->bus_config) { ret = slave->ops->bus_config(slave, &bus->params); if (ret < 0) - dev_err(bus->dev, "Notify Slave: %d failed", + dev_err(bus->dev, "Notify Slave: %d failed\n", slave->dev_num); return ret; } @@ -608,13 +608,13 @@ static int sdw_program_params(struct sdw_bus *bus) ret = sdw_program_port_params(m_rt); if (ret < 0) { dev_err(bus->dev, - "Program transport params failed: %d", ret); + "Program transport params failed: %d\n", ret); return ret; } ret = sdw_notify_config(m_rt); if (ret < 0) { - dev_err(bus->dev, "Notify bus config failed: %d", ret); + dev_err(bus->dev, "Notify bus config failed: %d\n", ret); return ret; } @@ -624,7 +624,7 @@ static int sdw_program_params(struct sdw_bus *bus) ret = sdw_enable_disable_ports(m_rt, true); if (ret < 0) { - dev_err(bus->dev, "Enable channel failed: %d", ret); + dev_err(bus->dev, "Enable channel failed: %d\n", ret); return ret; } } @@ -679,7 +679,7 @@ static int sdw_bank_switch(struct sdw_bus *bus, int m_rt_count) ret = sdw_transfer(bus, wr_msg); if (ret < 0) { - dev_err(bus->dev, "Slave frame_ctrl reg write failed"); + dev_err(bus->dev, "Slave frame_ctrl reg write failed\n"); goto error; } @@ -719,7 +719,7 @@ static int sdw_ml_sync_bank_switch(struct sdw_bus *bus) bus->bank_switch_timeout); if (!time_left) { - dev_err(bus->dev, "Controller Timed out on bank switch"); + dev_err(bus->dev, "Controller Timed out on bank switch\n"); return -ETIMEDOUT; } @@ -756,7 +756,7 @@ static int do_bank_switch(struct sdw_stream_runtime *stream) ret = ops->pre_bank_switch(bus); if (ret < 0) { dev_err(bus->dev, - "Pre bank switch op failed: %d", ret); + "Pre bank switch op failed: %d\n", ret); goto msg_unlock; } } @@ -769,7 +769,7 @@ static int do_bank_switch(struct sdw_stream_runtime *stream) */ ret = sdw_bank_switch(bus, stream->m_rt_count); if (ret < 0) { - dev_err(bus->dev, "Bank switch failed: %d", ret); + dev_err(bus->dev, "Bank switch failed: %d\n", ret); goto error; } @@ -790,12 +790,12 @@ static int do_bank_switch(struct sdw_stream_runtime *stream) ret = ops->post_bank_switch(bus); if (ret < 0) { dev_err(bus->dev, - "Post bank switch op failed: %d", ret); + "Post bank switch op failed: %d\n", ret); goto error; } } else if (bus->multi_link && stream->m_rt_count > 1) { dev_err(bus->dev, - "Post bank switch ops not implemented"); + "Post bank switch ops not implemented\n"); goto error; } @@ -807,7 +807,7 @@ static int do_bank_switch(struct sdw_stream_runtime *stream) ret = sdw_ml_sync_bank_switch(bus); if (ret < 0) { dev_err(bus->dev, - "multi link bank switch failed: %d", ret); + "multi link bank switch failed: %d\n", ret); goto error; } @@ -1135,13 +1135,13 @@ static int sdw_config_stream(struct device *dev, */ if (stream->params.rate && stream->params.rate != stream_config->frame_rate) { - dev_err(dev, "rate not matching, stream:%s", stream->name); + dev_err(dev, "rate not matching, stream:%s\n", stream->name); return -EINVAL; } if (stream->params.bps && stream->params.bps != stream_config->bps) { - dev_err(dev, "bps not matching, stream:%s", stream->name); + dev_err(dev, "bps not matching, stream:%s\n", stream->name); return -EINVAL; } @@ -1161,7 +1161,7 @@ static int sdw_is_valid_port_range(struct device *dev, { if (!SDW_VALID_PORT_RANGE(p_rt->num)) { dev_err(dev, - "SoundWire: Invalid port number :%d", p_rt->num); + "SoundWire: Invalid port number :%d\n", p_rt->num); return -EINVAL; } @@ -1272,7 +1272,7 @@ int sdw_stream_add_master(struct sdw_bus *bus, */ if (!bus->multi_link && stream->m_rt_count > 0) { dev_err(bus->dev, - "Multilink not supported, link %d", bus->link_id); + "Multilink not supported, link %d\n", bus->link_id); ret = -EINVAL; goto unlock; } @@ -1280,7 +1280,7 @@ int sdw_stream_add_master(struct sdw_bus *bus, m_rt = sdw_alloc_master_rt(bus, stream_config, stream); if (!m_rt) { dev_err(bus->dev, - "Master runtime config failed for stream:%s", + "Master runtime config failed for stream:%s\n", stream->name); ret = -ENOMEM; goto unlock; @@ -1338,7 +1338,7 @@ int sdw_stream_add_slave(struct sdw_slave *slave, m_rt = sdw_alloc_master_rt(slave->bus, stream_config, stream); if (!m_rt) { dev_err(&slave->dev, - "alloc master runtime failed for stream:%s", + "alloc master runtime failed for stream:%s\n", stream->name); ret = -ENOMEM; goto error; @@ -1347,7 +1347,7 @@ int sdw_stream_add_slave(struct sdw_slave *slave, s_rt = sdw_alloc_slave_rt(slave, stream_config, stream); if (!s_rt) { dev_err(&slave->dev, - "Slave runtime config failed for stream:%s", + "Slave runtime config failed for stream:%s\n", stream->name); ret = -ENOMEM; goto stream_error; @@ -1477,7 +1477,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream) /* TODO: Support Asynchronous mode */ if ((prop->max_freq % stream->params.rate) != 0) { - dev_err(bus->dev, "Async mode not supported"); + dev_err(bus->dev, "Async mode not supported\n"); return -EINVAL; } @@ -1489,7 +1489,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream) /* Program params */ ret = sdw_program_params(bus); if (ret < 0) { - dev_err(bus->dev, "Program params failed: %d", ret); + dev_err(bus->dev, "Program params failed: %d\n", ret); goto restore_params; } @@ -1497,7 +1497,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream) ret = do_bank_switch(stream); if (ret < 0) { - dev_err(bus->dev, "Bank switch failed: %d", ret); + dev_err(bus->dev, "Bank switch failed: %d\n", ret); goto restore_params; } @@ -1507,7 +1507,7 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream) /* Prepare port(s) on the new clock configuration */ ret = sdw_prep_deprep_ports(m_rt, true); if (ret < 0) { - dev_err(bus->dev, "Prepare port(s) failed ret = %d", + dev_err(bus->dev, "Prepare port(s) failed ret = %d\n", ret); return ret; } @@ -1534,7 +1534,7 @@ int sdw_prepare_stream(struct sdw_stream_runtime *stream) int ret = 0; if (!stream) { - pr_err("SoundWire: Handle not found for stream"); + pr_err("SoundWire: Handle not found for stream\n"); return -EINVAL; } @@ -1542,7 +1542,7 @@ int sdw_prepare_stream(struct sdw_stream_runtime *stream) ret = _sdw_prepare_stream(stream); if (ret < 0) - pr_err("Prepare for stream:%s failed: %d", stream->name, ret); + pr_err("Prepare for stream:%s failed: %d\n", stream->name, ret); sdw_release_bus_lock(stream); return ret; @@ -1562,21 +1562,21 @@ static int _sdw_enable_stream(struct sdw_stream_runtime *stream) /* Program params */ ret = sdw_program_params(bus); if (ret < 0) { - dev_err(bus->dev, "Program params failed: %d", ret); + dev_err(bus->dev, "Program params failed: %d\n", ret); return ret; } /* Enable port(s) */ ret = sdw_enable_disable_ports(m_rt, true); if (ret < 0) { - dev_err(bus->dev, "Enable port(s) failed ret: %d", ret); + dev_err(bus->dev, "Enable port(s) failed ret: %d\n", ret); return ret; } } ret = do_bank_switch(stream); if (ret < 0) { - dev_err(bus->dev, "Bank switch failed: %d", ret); + dev_err(bus->dev, "Bank switch failed: %d\n", ret); return ret; } @@ -1596,7 +1596,7 @@ int sdw_enable_stream(struct sdw_stream_runtime *stream) int ret = 0; if (!stream) { - pr_err("SoundWire: Handle not found for stream"); + pr_err("SoundWire: Handle not found for stream\n"); return -EINVAL; } @@ -1604,7 +1604,7 @@ int sdw_enable_stream(struct sdw_stream_runtime *stream) ret = _sdw_enable_stream(stream); if (ret < 0) - pr_err("Enable for stream:%s failed: %d", stream->name, ret); + pr_err("Enable for stream:%s failed: %d\n", stream->name, ret); sdw_release_bus_lock(stream); return ret; @@ -1622,7 +1622,7 @@ static int _sdw_disable_stream(struct sdw_stream_runtime *stream) /* Disable port(s) */ ret = sdw_enable_disable_ports(m_rt, false); if (ret < 0) { - dev_err(bus->dev, "Disable port(s) failed: %d", ret); + dev_err(bus->dev, "Disable port(s) failed: %d\n", ret); return ret; } } @@ -1633,7 +1633,7 @@ static int _sdw_disable_stream(struct sdw_stream_runtime *stream) /* Program params */ ret = sdw_program_params(bus); if (ret < 0) { - dev_err(bus->dev, "Program params failed: %d", ret); + dev_err(bus->dev, "Program params failed: %d\n", ret); return ret; } } @@ -1653,7 +1653,7 @@ int sdw_disable_stream(struct sdw_stream_runtime *stream) int ret = 0; if (!stream) { - pr_err("SoundWire: Handle not found for stream"); + pr_err("SoundWire: Handle not found for stream\n"); return -EINVAL; } @@ -1661,7 +1661,7 @@ int sdw_disable_stream(struct sdw_stream_runtime *stream) ret = _sdw_disable_stream(stream); if (ret < 0) - pr_err("Disable for stream:%s failed: %d", stream->name, ret); + pr_err("Disable for stream:%s failed: %d\n", stream->name, ret); sdw_release_bus_lock(stream); return ret; @@ -1679,7 +1679,7 @@ static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream) /* De-prepare port(s) */ ret = sdw_prep_deprep_ports(m_rt, false); if (ret < 0) { - dev_err(bus->dev, "De-prepare port(s) failed: %d", ret); + dev_err(bus->dev, "De-prepare port(s) failed: %d\n", ret); return ret; } @@ -1690,7 +1690,7 @@ static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream) /* Program params */ ret = sdw_program_params(bus); if (ret < 0) { - dev_err(bus->dev, "Program params failed: %d", ret); + dev_err(bus->dev, "Program params failed: %d\n", ret); return ret; } @@ -1712,14 +1712,14 @@ int sdw_deprepare_stream(struct sdw_stream_runtime *stream) int ret = 0; if (!stream) { - pr_err("SoundWire: Handle not found for stream"); + pr_err("SoundWire: Handle not found for stream\n"); return -EINVAL; } sdw_acquire_bus_lock(stream); ret = _sdw_deprepare_stream(stream); if (ret < 0) - pr_err("De-prepare for stream:%d failed: %d", ret, ret); + pr_err("De-prepare for stream:%d failed: %d\n", ret, ret); sdw_release_bus_lock(stream); return ret; From 92fd75f103248f9dff32ad8ca8cc6d1c05756712 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:17 +0530 Subject: [PATCH 222/255] soundwire: fix kconfig help format Move to help format instead of --help-- as that is not recommended and this makes file consistent with other instance Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/soundwire/Kconfig b/drivers/soundwire/Kconfig index 84876a74874f..53b55b79c4af 100644 --- a/drivers/soundwire/Kconfig +++ b/drivers/soundwire/Kconfig @@ -28,7 +28,7 @@ config SOUNDWIRE_INTEL select SOUNDWIRE_CADENCE select SOUNDWIRE_BUS depends on X86 && ACPI && SND_SOC - ---help--- + help SoundWire Intel Master driver. If you have an Intel platform which has a SoundWire Master then enable this config option to get the SoundWire support for that From 171580f69ebc88370204482464804d94f78f077a Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:18 +0530 Subject: [PATCH 223/255] soundwire: fix SPDX license for header files Some more headers had C++ style SDPX line, fix that and change copyright so that it is consistent with rest of the code in subsystem Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- include/linux/soundwire/sdw.h | 4 ++-- include/linux/soundwire/sdw_registers.h | 4 ++-- include/linux/soundwire/sdw_type.h | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index df313913e856..d9102af5e26c 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -1,5 +1,5 @@ -// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) -// Copyright(c) 2015-17 Intel Corporation. +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* Copyright(c) 2015-17 Intel Corporation. */ #ifndef __SOUNDWIRE_H #define __SOUNDWIRE_H diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h index df472b1ab410..e75b2e3cf93d 100644 --- a/include/linux/soundwire/sdw_registers.h +++ b/include/linux/soundwire/sdw_registers.h @@ -1,5 +1,5 @@ -// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) -// Copyright(c) 2015-17 Intel Corporation. +/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */ +/* Copyright(c) 2015-17 Intel Corporation. */ #ifndef __SDW_REGISTERS_H #define __SDW_REGISTERS_H diff --git a/include/linux/soundwire/sdw_type.h b/include/linux/soundwire/sdw_type.h index 9fd553e553e9..b7e198a035c9 100644 --- a/include/linux/soundwire/sdw_type.h +++ b/include/linux/soundwire/sdw_type.h @@ -1,5 +1,5 @@ -// SPDX-License-Identifier: GPL-2.0 -// Copyright(c) 2015-17 Intel Corporation. +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2015-17 Intel Corporation. */ #ifndef __SOUNDWIRE_TYPES_H #define __SOUNDWIRE_TYPES_H From fa358bb536b96a9c920bc4156664587412c57b2c Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:20 +0530 Subject: [PATCH 224/255] soundwire: remove empty line before/after braces Linux code style doesn't expect empty lines before or after braces and gives warning: CHECK: Blank lines aren't necessary after an open brace '{' CHECK: Blank lines aren't necessary before a close brace '}' Fix these instances in soundwire core Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/bus.c | 8 -------- drivers/soundwire/mipi_disco.c | 6 ------ drivers/soundwire/stream.c | 8 -------- 3 files changed, 22 deletions(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index fa86957cb615..e2ee305905a6 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -391,7 +391,6 @@ EXPORT_SYMBOL(sdw_read); int sdw_write(struct sdw_slave *slave, u32 addr, u8 value) { return sdw_nwrite(slave, addr, 1, &value); - } EXPORT_SYMBOL(sdw_write); @@ -414,7 +413,6 @@ static struct sdw_slave *sdw_get_slave(struct sdw_bus *bus, int i) static int sdw_compare_devid(struct sdw_slave *slave, struct sdw_slave_id id) { - if (slave->id.unique_id != id.unique_id || slave->id.mfg_id != id.mfg_id || slave->id.part_id != id.part_id || @@ -467,7 +465,6 @@ static int sdw_assign_device_num(struct sdw_slave *slave) /* Clear the slave->dev_num to transfer message on device 0 */ dev_num = slave->dev_num; slave->dev_num = 0; - } ret = sdw_write(slave, SDW_SCP_DEVNUMBER, dev_num); @@ -508,7 +505,6 @@ void sdw_extract_slave_id(struct sdw_bus *bus, "SDW Slave class_id %x, part_id %x, mfg_id %x, unique_id %x, version %x\n", id->class_id, id->part_id, id->mfg_id, id->unique_id, id->sdw_version); - } static int sdw_program_device_num(struct sdw_bus *bus) @@ -677,7 +673,6 @@ static int sdw_handle_dp0_interrupt(struct sdw_slave *slave, u8 *slave_status) } do { - if (status & SDW_DP0_INT_TEST_FAIL) { dev_err(&slave->dev, "Test fail for port 0\n"); clear |= SDW_DP0_INT_TEST_FAIL; @@ -754,7 +749,6 @@ static int sdw_handle_port_interrupt(struct sdw_slave *slave, } do { - if (status & SDW_DPN_INT_TEST_FAIL) { dev_err(&slave->dev, "Test fail for port:%d\n", port); clear |= SDW_DPN_INT_TEST_FAIL; @@ -867,7 +861,6 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) for_each_set_bit(bit, &port, 8) { sdw_handle_port_interrupt(slave, bit, &port_status[bit]); - } /* Check if cascade 2 interrupt is present */ @@ -1035,7 +1028,6 @@ int sdw_handle_slave_status(struct sdw_bus *bus, if (ret) dev_err(slave->bus->dev, "Update Slave status failed:%d\n", ret); - } return ret; diff --git a/drivers/soundwire/mipi_disco.c b/drivers/soundwire/mipi_disco.c index 2bf4046e68b6..c1f51d6a23d2 100644 --- a/drivers/soundwire/mipi_disco.c +++ b/drivers/soundwire/mipi_disco.c @@ -63,7 +63,6 @@ int sdw_master_read_prop(struct sdw_bus *bus) nval = fwnode_property_read_u32_array(link, "mipi-sdw-clock-frequencies-supported", NULL, 0); if (nval > 0) { - prop->num_freq = nval; prop->freq = devm_kcalloc(bus->dev, prop->num_freq, sizeof(*prop->freq), GFP_KERNEL); @@ -90,7 +89,6 @@ int sdw_master_read_prop(struct sdw_bus *bus) nval = fwnode_property_read_u32_array(link, "mipi-sdw-supported-clock-gears", NULL, 0); if (nval > 0) { - prop->num_clk_gears = nval; prop->clk_gears = devm_kcalloc(bus->dev, prop->num_clk_gears, sizeof(*prop->clk_gears), @@ -197,7 +195,6 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, nval = fwnode_property_read_u32_array(node, "mipi-sdw-port-wordlength-configs", NULL, 0); if (nval > 0) { - dpn[i].num_words = nval; dpn[i].words = devm_kcalloc(&slave->dev, dpn[i].num_words, @@ -238,7 +235,6 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, nval = fwnode_property_read_u32_array(node, "mipi-sdw-channel-number-list", NULL, 0); if (nval > 0) { - dpn[i].num_ch = nval; dpn[i].ch = devm_kcalloc(&slave->dev, dpn[i].num_ch, sizeof(*dpn[i].ch), @@ -254,7 +250,6 @@ static int sdw_slave_read_dpn(struct sdw_slave *slave, nval = fwnode_property_read_u32_array(node, "mipi-sdw-channel-combination-list", NULL, 0); if (nval > 0) { - dpn[i].num_ch_combinations = nval; dpn[i].ch_combinations = devm_kcalloc(&slave->dev, dpn[i].num_ch_combinations, @@ -354,7 +349,6 @@ int sdw_slave_read_prop(struct sdw_slave *slave) if (!port) { dev_dbg(dev, "DP0 node not found!!\n"); } else { - prop->dp0_prop = devm_kzalloc(&slave->dev, sizeof(*prop->dp0_prop), GFP_KERNEL); diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index 166b0c16003f..032a326a96d7 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -771,7 +771,6 @@ static int do_bank_switch(struct sdw_stream_runtime *stream) if (ret < 0) { dev_err(bus->dev, "Bank switch failed: %d\n", ret); goto error; - } } @@ -818,7 +817,6 @@ static int do_bank_switch(struct sdw_stream_runtime *stream) error: list_for_each_entry(m_rt, &stream->master_list, stream_node) { - bus = m_rt->bus; kfree(bus->defer_msg.msg->buf); @@ -985,13 +983,11 @@ static void sdw_slave_port_release(struct sdw_bus *bus, list_for_each_entry(m_rt, &stream->master_list, stream_node) { list_for_each_entry(s_rt, &m_rt->slave_rt_list, m_rt_node) { - if (s_rt->slave != slave) continue; list_for_each_entry_safe(p_rt, _p_rt, &s_rt->port_list, port_node) { - list_del(&p_rt->port_node); kfree(p_rt); } @@ -1017,7 +1013,6 @@ static void sdw_release_slave_stream(struct sdw_slave *slave, /* Retrieve Slave runtime handle */ list_for_each_entry_safe(s_rt, _s_rt, &m_rt->slave_rt_list, m_rt_node) { - if (s_rt->slave == slave) { list_del(&s_rt->m_rt_node); kfree(s_rt); @@ -1070,7 +1065,6 @@ int sdw_stream_remove_master(struct sdw_bus *bus, list_for_each_entry_safe(m_rt, _m_rt, &stream->master_list, stream_node) { - if (m_rt->bus != bus) continue; @@ -1492,7 +1486,6 @@ static int _sdw_prepare_stream(struct sdw_stream_runtime *stream) dev_err(bus->dev, "Program params failed: %d\n", ret); goto restore_params; } - } ret = do_bank_switch(stream); @@ -1693,7 +1686,6 @@ static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream) dev_err(bus->dev, "Program params failed: %d\n", ret); return ret; } - } stream->state = SDW_STREAM_DEPREPARED; From 4415b443ca08e1e230c818361235cd10527cbb82 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:21 +0530 Subject: [PATCH 225/255] soundwire: cadence: remove empty line after braces Linux code style doesn't expect empty lines after braces and gives warning: CHECK: Blank lines aren't necessary after an open brace '{' Remove the empty line in cadence lib Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/cadence_master.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/soundwire/cadence_master.c b/drivers/soundwire/cadence_master.c index 0fdc17b995fc..682789bb8ab3 100644 --- a/drivers/soundwire/cadence_master.c +++ b/drivers/soundwire/cadence_master.c @@ -574,7 +574,6 @@ irqreturn_t sdw_cdns_irq(int irq, void *dev_id) } if (int_status & CDNS_MCP_INT_CTRL_CLASH) { - /* Slave is driving bit slot during control word */ dev_err_ratelimited(cdns->dev, "Bus clash for control word\n"); int_status |= CDNS_MCP_INT_CTRL_CLASH; From d6badd1c15352ebd80c3eb2132f8bcc9fe3cb1d8 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:22 +0530 Subject: [PATCH 226/255] soundwire: intel: remove empty line after braces Linux code style doesn't expect empty lines after braces and gives warning: CHECK: Blank lines aren't necessary after an open brace '{' Remove the empty line in intel module Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/intel_init.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/soundwire/intel_init.c b/drivers/soundwire/intel_init.c index 9ad6045720c4..d3d6b54c5791 100644 --- a/drivers/soundwire/intel_init.c +++ b/drivers/soundwire/intel_init.c @@ -106,7 +106,6 @@ static struct sdw_intel_ctx /* Create SDW Master devices */ for (i = 0; i < count; i++) { - link->res.irq = res->irq; link->res.registers = res->mmio_base + SDW_LINK_BASE + (SDW_LINK_SIZE * i); From 51ed743734fa90c215310854d502371adfa63575 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:23 +0530 Subject: [PATCH 227/255] soundwire: add argument to function definition Checkpatch warns that function definition of __sdw_register_driver misses argument, so add it WARNING: function definition argument 'struct module *' should also have an identifier name Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- include/linux/soundwire/sdw_type.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/soundwire/sdw_type.h b/include/linux/soundwire/sdw_type.h index b7e198a035c9..9c756b5a0dfe 100644 --- a/include/linux/soundwire/sdw_type.h +++ b/include/linux/soundwire/sdw_type.h @@ -11,7 +11,7 @@ extern struct bus_type sdw_bus_type; #define sdw_register_driver(drv) \ __sdw_register_driver(drv, THIS_MODULE) -int __sdw_register_driver(struct sdw_driver *drv, struct module *); +int __sdw_register_driver(struct sdw_driver *drv, struct module *owner); void sdw_unregister_driver(struct sdw_driver *drv); int sdw_slave_modalias(const struct sdw_slave *slave, char *buf, size_t size); From 62f0cec3b0da067ec689edbefea5de61f025f6d6 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:24 +0530 Subject: [PATCH 228/255] soundwire: more alignment fixes Found few more issues reported checkpatch on code alignment so fix those as well in the soundwire core. Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/bus.c | 3 ++- drivers/soundwire/stream.c | 15 ++++++++++----- include/linux/soundwire/sdw.h | 10 +++++----- 3 files changed, 17 insertions(+), 11 deletions(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index e2ee305905a6..16b2a3b2662d 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -43,7 +43,8 @@ int sdw_add_bus_master(struct sdw_bus *bus) if (bus->ops->read_prop) { ret = bus->ops->read_prop(bus); if (ret < 0) { - dev_err(bus->dev, "Bus read properties failed:%d\n", ret); + dev_err(bus->dev, + "Bus read properties failed:%d\n", ret); return ret; } } diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index 032a326a96d7..bffa535294ed 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -400,7 +400,8 @@ static int sdw_do_port_prep(struct sdw_slave_runtime *s_rt, ret = ops->port_prep(s_rt->slave, &prep_ch, cmd); if (ret < 0) { dev_err(&s_rt->slave->dev, - "Slave Port Prep cmd %d failed: %d\n", cmd, ret); + "Slave Port Prep cmd %d failed: %d\n", + cmd, ret); return ret; } } @@ -614,7 +615,8 @@ static int sdw_program_params(struct sdw_bus *bus) ret = sdw_notify_config(m_rt); if (ret < 0) { - dev_err(bus->dev, "Notify bus config failed: %d\n", ret); + dev_err(bus->dev, + "Notify bus config failed: %d\n", ret); return ret; } @@ -789,7 +791,8 @@ static int do_bank_switch(struct sdw_stream_runtime *stream) ret = ops->post_bank_switch(bus); if (ret < 0) { dev_err(bus->dev, - "Post bank switch op failed: %d\n", ret); + "Post bank switch op failed: %d\n", + ret); goto error; } } else if (bus->multi_link && stream->m_rt_count > 1) { @@ -1562,7 +1565,8 @@ static int _sdw_enable_stream(struct sdw_stream_runtime *stream) /* Enable port(s) */ ret = sdw_enable_disable_ports(m_rt, true); if (ret < 0) { - dev_err(bus->dev, "Enable port(s) failed ret: %d\n", ret); + dev_err(bus->dev, + "Enable port(s) failed ret: %d\n", ret); return ret; } } @@ -1672,7 +1676,8 @@ static int _sdw_deprepare_stream(struct sdw_stream_runtime *stream) /* De-prepare port(s) */ ret = sdw_prep_deprep_ports(m_rt, false); if (ret < 0) { - dev_err(bus->dev, "De-prepare port(s) failed: %d\n", ret); + dev_err(bus->dev, + "De-prepare port(s) failed: %d\n", ret); return ret; } diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index d9102af5e26c..41c49631288a 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -470,14 +470,14 @@ struct sdw_bus_params { struct sdw_slave_ops { int (*read_prop)(struct sdw_slave *sdw); int (*interrupt_callback)(struct sdw_slave *slave, - struct sdw_slave_intr_status *status); + struct sdw_slave_intr_status *status); int (*update_status)(struct sdw_slave *slave, - enum sdw_slave_status status); + enum sdw_slave_status status); int (*bus_config)(struct sdw_slave *slave, - struct sdw_bus_params *params); + struct sdw_bus_params *params); int (*port_prep)(struct sdw_slave *slave, - struct sdw_prepare_ch *prepare_ch, - enum sdw_port_prep_ops pre_ops); + struct sdw_prepare_ch *prepare_ch, + enum sdw_port_prep_ops pre_ops); }; /** From 1215daee56edc1640997b439506b2006e47574c0 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:25 +0530 Subject: [PATCH 229/255] soundwire: intel: more alignment fixes Found few more issues reported checkpatch on code alignment so fix those as well in the intel module. Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/intel.c | 36 ++++++++++++++--------------- include/linux/soundwire/sdw_intel.h | 2 +- 2 files changed, 19 insertions(+), 19 deletions(-) diff --git a/drivers/soundwire/intel.c b/drivers/soundwire/intel.c index 9774dc1e4029..31336b0271b0 100644 --- a/drivers/soundwire/intel.c +++ b/drivers/soundwire/intel.c @@ -691,9 +691,9 @@ static int intel_create_dai(struct sdw_cdns *cdns, return -ENOMEM; if (type == INTEL_PDI_BD || type == INTEL_PDI_OUT) { - dais[i].playback.stream_name = kasprintf(GFP_KERNEL, - "SDW%d Tx%d", - cdns->instance, i); + dais[i].playback.stream_name = + kasprintf(GFP_KERNEL, "SDW%d Tx%d", + cdns->instance, i); if (!dais[i].playback.stream_name) { kfree(dais[i].name); return -ENOMEM; @@ -706,9 +706,9 @@ static int intel_create_dai(struct sdw_cdns *cdns, } if (type == INTEL_PDI_BD || type == INTEL_PDI_IN) { - dais[i].capture.stream_name = kasprintf(GFP_KERNEL, - "SDW%d Rx%d", - cdns->instance, i); + dais[i].capture.stream_name = + kasprintf(GFP_KERNEL, "SDW%d Rx%d", + cdns->instance, i); if (!dais[i].capture.stream_name) { kfree(dais[i].name); kfree(dais[i].playback.stream_name); @@ -749,40 +749,40 @@ static int intel_register_dai(struct sdw_intel *sdw) /* Create PCM DAIs */ stream = &cdns->pcm; - ret = intel_create_dai(cdns, dais, INTEL_PDI_IN, - stream->num_in, off, stream->num_ch_in, true); + ret = intel_create_dai(cdns, dais, INTEL_PDI_IN, stream->num_in, + off, stream->num_ch_in, true); if (ret) return ret; off += cdns->pcm.num_in; - ret = intel_create_dai(cdns, dais, INTEL_PDI_OUT, - cdns->pcm.num_out, off, stream->num_ch_out, true); + ret = intel_create_dai(cdns, dais, INTEL_PDI_OUT, cdns->pcm.num_out, + off, stream->num_ch_out, true); if (ret) return ret; off += cdns->pcm.num_out; - ret = intel_create_dai(cdns, dais, INTEL_PDI_BD, - cdns->pcm.num_bd, off, stream->num_ch_bd, true); + ret = intel_create_dai(cdns, dais, INTEL_PDI_BD, cdns->pcm.num_bd, + off, stream->num_ch_bd, true); if (ret) return ret; /* Create PDM DAIs */ stream = &cdns->pdm; off += cdns->pcm.num_bd; - ret = intel_create_dai(cdns, dais, INTEL_PDI_IN, - cdns->pdm.num_in, off, stream->num_ch_in, false); + ret = intel_create_dai(cdns, dais, INTEL_PDI_IN, cdns->pdm.num_in, + off, stream->num_ch_in, false); if (ret) return ret; off += cdns->pdm.num_in; - ret = intel_create_dai(cdns, dais, INTEL_PDI_OUT, - cdns->pdm.num_out, off, stream->num_ch_out, false); + ret = intel_create_dai(cdns, dais, INTEL_PDI_OUT, cdns->pdm.num_out, + off, stream->num_ch_out, false); if (ret) return ret; off += cdns->pdm.num_bd; - ret = intel_create_dai(cdns, dais, INTEL_PDI_BD, - cdns->pdm.num_bd, off, stream->num_ch_bd, false); + ret = intel_create_dai(cdns, dais, INTEL_PDI_BD, cdns->pdm.num_bd, + off, stream->num_ch_bd, false); if (ret) return ret; diff --git a/include/linux/soundwire/sdw_intel.h b/include/linux/soundwire/sdw_intel.h index 0848f9d38bcb..4d70da45363d 100644 --- a/include/linux/soundwire/sdw_intel.h +++ b/include/linux/soundwire/sdw_intel.h @@ -11,7 +11,7 @@ */ struct sdw_intel_ops { int (*config_stream)(void *arg, void *substream, - void *dai, void *hw_params, int stream_num); + void *dai, void *hw_params, int stream_num); }; /** From 72b16d4a91d44c6b09e599fd49379440afa419c2 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:26 +0530 Subject: [PATCH 230/255] soundwire: avoid multiple assignments Modify the code to avoid multiple assignments by assigning to variable after error checks in soundwire bus. CHECK: multiple assignments should be avoided Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/bus.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 16b2a3b2662d..aac35fc3cf22 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -812,12 +812,13 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) sdw_modify_slave_status(slave, SDW_SLAVE_ALERT); /* Read Instat 1, Instat 2 and Instat 3 registers */ - buf = ret = sdw_read(slave, SDW_SCP_INT1); + ret = sdw_read(slave, SDW_SCP_INT1); if (ret < 0) { dev_err(slave->bus->dev, "SDW_SCP_INT1 read failed:%d\n", ret); return ret; } + buf = ret; ret = sdw_nread(slave, SDW_SCP_INTSTAT2, 2, buf2); if (ret < 0) { @@ -910,12 +911,13 @@ static int sdw_handle_slave_alerts(struct sdw_slave *slave) * Read status again to ensure no new interrupts arrived * while servicing interrupts. */ - _buf = ret = sdw_read(slave, SDW_SCP_INT1); + ret = sdw_read(slave, SDW_SCP_INT1); if (ret < 0) { dev_err(slave->bus->dev, "SDW_SCP_INT1 read failed:%d\n", ret); return ret; } + _buf = ret; ret = sdw_nread(slave, SDW_SCP_INTSTAT2, 2, _buf2); if (ret < 0) { From 7d3b3cdfd16536642f7eebcdb33daaf1ce9469c5 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:27 +0530 Subject: [PATCH 231/255] soundwire: fix more typos Found few more typos in the code, fix them CHECK: 'and and' may be misspelled - perhaps 'and'? CHECK: 'smaple' may be misspelled - perhaps 'sample'? Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/stream.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index bffa535294ed..debb67882df4 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -89,7 +89,7 @@ static int _sdw_program_slave_port_params(struct sdw_bus *bus, /* * Data ports are FULL, SIMPLE and REDUCED. This function handles - * FULL and REDUCED only and and beyond this point only FULL is + * FULL and REDUCED only and beyond this point only FULL is * handled, so bail out if we are not FULL data port type */ if (type != SDW_DPN_FULL) @@ -233,7 +233,7 @@ static int sdw_program_master_port_params(struct sdw_bus *bus, /* * we need to set transport and port parameters for the port. - * Transport parameters refers to the smaple interval, offsets and + * Transport parameters refers to the sample interval, offsets and * hstart/stop etc of the data. Port parameters refers to word * length, flow mode etc of the port */ From 1824dd8035fceb337801bed76515eceda8d7af6b Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:28 +0530 Subject: [PATCH 232/255] soundwire: wrap macro argument in parenthesis macro argument should be inside a parenthesis to avoid precedence issues checkpatch complains: CHECK: Macro argument 'n' may be better as '(n)' to avoid precedence issues Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- include/linux/soundwire/sdw.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/soundwire/sdw.h b/include/linux/soundwire/sdw.h index 41c49631288a..35662d9c2c62 100644 --- a/include/linux/soundwire/sdw.h +++ b/include/linux/soundwire/sdw.h @@ -36,7 +36,7 @@ struct sdw_slave; #define SDW_FRAME_CTRL_BITS 48 #define SDW_MAX_DEVICES 11 -#define SDW_VALID_PORT_RANGE(n) (n <= 14 && n >= 1) +#define SDW_VALID_PORT_RANGE(n) ((n) <= 14 && (n) >= 1) #define SDW_DAI_ID_RANGE_START 100 #define SDW_DAI_ID_RANGE_END 200 From 897fe40e5227bc11365980a772dac4a16d56f8ca Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:29 +0530 Subject: [PATCH 233/255] soundwire: add a blank line between functions For improving code readability it helps to have a blank line between function so add when missing. Checkpatch complains: CHECK: Please use a blank line after function/struct/union/enum declarations Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- drivers/soundwire/stream.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c index debb67882df4..d01060dbee96 100644 --- a/drivers/soundwire/stream.c +++ b/drivers/soundwire/stream.c @@ -52,6 +52,7 @@ static int sdw_find_row_index(int row) pr_warn("Requested row not found, selecting lowest row no: 48\n"); return 0; } + static int _sdw_program_slave_port_params(struct sdw_bus *bus, struct sdw_slave *slave, struct sdw_transport_params *t_params, From b57969db81a258a25dd59e306584ba671a037350 Mon Sep 17 00:00:00 2001 From: Vinod Koul Date: Thu, 2 May 2019 16:29:30 +0530 Subject: [PATCH 234/255] soundwire: remove multiple blank lines Multi-blank lines do not help readability so remove them Checkpatch complains: CHECK: Please don't use multiple blank lines Signed-off-by: Vinod Koul Signed-off-by: Greg Kroah-Hartman --- include/linux/soundwire/sdw_registers.h | 1 - 1 file changed, 1 deletion(-) diff --git a/include/linux/soundwire/sdw_registers.h b/include/linux/soundwire/sdw_registers.h index e75b2e3cf93d..a686f7988156 100644 --- a/include/linux/soundwire/sdw_registers.h +++ b/include/linux/soundwire/sdw_registers.h @@ -73,7 +73,6 @@ #define SDW_SCP_INTSTAT2_SCP3_CASCADE BIT(7) #define SDW_SCP_INTSTAT2_PORT4_10 GENMASK(6, 0) - #define SDW_SCP_INTSTAT3 0x43 #define SDW_SCP_INTSTAT3_PORT11_14 GENMASK(3, 0) From 635b90f47d7f8a3777c229a2ac0d5f0fee006795 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Thu, 2 May 2019 10:54:02 -0600 Subject: [PATCH 235/255] dt-bindings: arm: coresight: Add new compatible for static replicator CoreSight uses below bindings for replicator: Dynamic replicator, aka. configurable replicator: "arm,coresight-dynamic-replicator", "arm,primecell"; Static replicator, aka. non-configurable replicator: "arm,coresight-replicator"; The compatible string "arm,coresight-replicator" is not an explicit naming to express the replicator is 'static'. To unify the naming convention, this patch introduces a new compatible string "arm,coresight-static-replicator" for the static replicator; the compatible string "arm,coresight-replicator" is kept for backward compatibility, but tag it as obsolete and suggest to use the new compatible string. As result CoreSight replicator have below bindings: Dynamic replicator: "arm,coresight-dynamic-replicator", "arm,primecell"; Static replicator: "arm,coresight-static-replicator"; "arm,coresight-replicator"; (obsolete) Signed-off-by: Leo Yan Reviewed-by: Suzuki K Poulose Reviewed-by: Rob Herring Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/arm/coresight.txt | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/arm/coresight.txt b/Documentation/devicetree/bindings/arm/coresight.txt index f8aff65ab921..d02d160fa8ac 100644 --- a/Documentation/devicetree/bindings/arm/coresight.txt +++ b/Documentation/devicetree/bindings/arm/coresight.txt @@ -69,7 +69,10 @@ its hardware characteristcs. * compatible: Currently supported value is (note the absence of the AMBA markee): - - "arm,coresight-replicator" + - Coresight Non-configurable Replicator: + "arm,coresight-static-replicator"; + "arm,coresight-replicator"; (OBSOLETE. For backward + compatibility and will be removed) * port or ports: see "Graph bindings for Coresight" below. @@ -169,7 +172,7 @@ Example: /* non-configurable replicators don't show up on the * AMBA bus. As such no need to add "arm,primecell". */ - compatible = "arm,coresight-replicator"; + compatible = "arm,coresight-static-replicator"; out-ports { #address-cells = <1>; From 5c84b87bb1ee7ce8e0849ce2c1b3fecf4faa4c82 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Thu, 2 May 2019 10:54:03 -0600 Subject: [PATCH 236/255] coresight: replicator: Add new device id for static replicator This patch adds a device id for the new static replicator compatible string; it changes the driver name from "coresight-replicator" to "coresight-static-replicator" as well. This patch also gives warning when use the replicator obsolete DT binding. Signed-off-by: Leo Yan Reviewed-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/coresight/coresight-replicator.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/hwtracing/coresight/coresight-replicator.c b/drivers/hwtracing/coresight/coresight-replicator.c index 4e0da85efd2d..8c9ce74498e1 100644 --- a/drivers/hwtracing/coresight/coresight-replicator.c +++ b/drivers/hwtracing/coresight/coresight-replicator.c @@ -189,6 +189,9 @@ static int replicator_probe(struct device *dev, struct resource *res) dev->platform_data = pdata; } + if (of_device_is_compatible(np, "arm,coresight-replicator")) + pr_warn_once("Uses OBSOLETE CoreSight replicator binding\n"); + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); if (!drvdata) return -ENOMEM; @@ -285,13 +288,14 @@ static const struct dev_pm_ops replicator_dev_pm_ops = { static const struct of_device_id static_replicator_match[] = { {.compatible = "arm,coresight-replicator"}, + {.compatible = "arm,coresight-static-replicator"}, {} }; static struct platform_driver static_replicator_driver = { .probe = static_replicator_probe, .driver = { - .name = "coresight-replicator", + .name = "coresight-static-replicator", .of_match_table = static_replicator_match, .pm = &replicator_dev_pm_ops, .suppress_bind_attrs = true, From d3b18ad63dca3ff3b5a169cbbe629b1d039a4483 Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Thu, 2 May 2019 10:54:04 -0600 Subject: [PATCH 237/255] dt-bindings: arm: coresight: Unify funnel DT binding Following the same fashion with replicator DT binding, this patch is to unify the DT binding for funnel to support static and dynamic modes; finally we get the funnel DT binding as below: Before patch: Static funnel, aka. non-configurable funnel: Not supported; Dynamic funnel, aka. configurable funnel: "arm,coresight-funnel", "arm,primecell"; After patch: Static funnel: "arm,coresight-static-funnel"; Dynamic funnel: "arm,coresight-dynamic-funnel", "arm,primecell"; "arm,coresight-funnel", "arm,primecell"; (obsolete) At the end of this patch, it gives an example for static funnel DT binding, and updates the dynamic funnel example. Cc: Mathieu Poirier Cc: Suzuki K Poulose Cc: Wanglai Shi Signed-off-by: Leo Yan Reviewed-by: Suzuki K Poulose Reviewed-by: Rob Herring Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- .../devicetree/bindings/arm/coresight.txt | 53 +++++++++++++++++-- 1 file changed, 48 insertions(+), 5 deletions(-) diff --git a/Documentation/devicetree/bindings/arm/coresight.txt b/Documentation/devicetree/bindings/arm/coresight.txt index d02d160fa8ac..8a88ddebc1a2 100644 --- a/Documentation/devicetree/bindings/arm/coresight.txt +++ b/Documentation/devicetree/bindings/arm/coresight.txt @@ -8,7 +8,8 @@ through the intermediate links connecting the source to the currently selected sink. Each CoreSight component device should use these properties to describe its hardware characteristcs. -* Required properties for all components *except* non-configurable replicators: +* Required properties for all components *except* non-configurable replicators + and non-configurable funnels: * compatible: These have to be supplemented with "arm,primecell" as drivers are using the AMBA bus interface. Possible values include: @@ -24,8 +25,10 @@ its hardware characteristcs. discovered at boot time when the device is probed. "arm,coresight-tmc", "arm,primecell"; - - Trace Funnel: - "arm,coresight-funnel", "arm,primecell"; + - Trace Programmable Funnel: + "arm,coresight-dynamic-funnel", "arm,primecell"; + "arm,coresight-funnel", "arm,primecell"; (OBSOLETE. For + backward compatibility and will be removed) - Embedded Trace Macrocell (version 3.x) and Program Flow Trace Macrocell: @@ -65,7 +68,7 @@ its hardware characteristcs. "stm-stimulus-base", each corresponding to the areas defined in "reg". * Required properties for devices that don't show up on the AMBA bus, such as - non-configurable replicators: + non-configurable replicators and non-configurable funnels: * compatible: Currently supported value is (note the absence of the AMBA markee): @@ -74,6 +77,9 @@ its hardware characteristcs. "arm,coresight-replicator"; (OBSOLETE. For backward compatibility and will be removed) + - Coresight Non-configurable Funnel: + "arm,coresight-static-funnel"; + * port or ports: see "Graph bindings for Coresight" below. * Optional properties for ETM/PTMs: @@ -203,8 +209,45 @@ Example: }; }; + funnel { + /* + * non-configurable funnel don't show up on the AMBA + * bus. As such no need to add "arm,primecell". + */ + compatible = "arm,coresight-static-funnel"; + clocks = <&crg_ctrl HI3660_PCLK>; + clock-names = "apb_pclk"; + + out-ports { + port { + combo_funnel_out: endpoint { + remote-endpoint = <&top_funnel_in>; + }; + }; + }; + + in-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + combo_funnel_in0: endpoint { + remote-endpoint = <&cluster0_etf_out>; + }; + }; + + port@1 { + reg = <1>; + combo_funnel_in1: endpoint { + remote-endpoint = <&cluster1_etf_out>; + }; + }; + }; + }; + funnel@20040000 { - compatible = "arm,coresight-funnel", "arm,primecell"; + compatible = "arm,coresight-dynamic-funnel", "arm,primecell"; reg = <0 0x20040000 0 0x1000>; clocks = <&oscclk6a>; From 78e6427b4e7b017951785982f7f97cf64e2d624b Mon Sep 17 00:00:00 2001 From: Leo Yan Date: Thu, 2 May 2019 10:54:05 -0600 Subject: [PATCH 238/255] coresight: funnel: Support static funnel Since CoreSight hardware topology can use a 'hidden' funnel in the trace data path, this kind funnel doesn't have register for accessing and is used by default from hardware design perspective. Below is an example for related hardware topology: +------+ +------+ | cpu0 |->| ETM |-\ +------+ +------+ \-> +--------+ +-----+ ...... | Funnel |->| ETF |-\ Hidden funnel +------+ +------+ /-> +--------+ +-----+ \ | | cpu3 |->| ETM |-/ \ V +------+ +------+ \-> +--------+ | Funnel |-> ... +------+ +------+ /-> +--------+ | cpu4 |->| ETM |-\ / +------+ +------+ \-> +--------+ +-----+ / ...... | Funnel |->| ETF |-/ +------+ +------+ /-> +--------+ +-----+ | cpu7 |->| ETM |-/ +------+ +------+ The CoreSight funnel driver only supports dynamic funnel with registration register resource, thus it cannot support for the static funnel case and it's impossible to create trace data path for this case. This patch is to extend CoreSight funnel driver to support both for static funnel and dynamic funnel. For the dynamic funnel it reuses the code existed in the driver, for static funnel the driver will support device probe if without providing register resource and the driver skips registers accessing when detect the register base is NULL. Cc: Mathieu Poirier Cc: Suzuki K Poulose Cc: Wanglai Shi Suggested-by: Suzuki K Poulose Signed-off-by: Leo Yan Reviewed-by: Suzuki K Poulose Signed-off-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- .../hwtracing/coresight/coresight-funnel.c | 118 +++++++++++++----- 1 file changed, 90 insertions(+), 28 deletions(-) diff --git a/drivers/hwtracing/coresight/coresight-funnel.c b/drivers/hwtracing/coresight/coresight-funnel.c index 927925151509..16b0c0e1e43a 100644 --- a/drivers/hwtracing/coresight/coresight-funnel.c +++ b/drivers/hwtracing/coresight/coresight-funnel.c @@ -12,6 +12,8 @@ #include #include #include +#include +#include #include #include #include @@ -43,7 +45,7 @@ struct funnel_drvdata { unsigned long priority; }; -static int funnel_enable_hw(struct funnel_drvdata *drvdata, int port) +static int dynamic_funnel_enable_hw(struct funnel_drvdata *drvdata, int port) { u32 functl; int rc = 0; @@ -71,17 +73,19 @@ static int funnel_enable_hw(struct funnel_drvdata *drvdata, int port) static int funnel_enable(struct coresight_device *csdev, int inport, int outport) { - int rc; + int rc = 0; struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - rc = funnel_enable_hw(drvdata, inport); + if (drvdata->base) + rc = dynamic_funnel_enable_hw(drvdata, inport); if (!rc) dev_dbg(drvdata->dev, "FUNNEL inport %d enabled\n", inport); return rc; } -static void funnel_disable_hw(struct funnel_drvdata *drvdata, int inport) +static void dynamic_funnel_disable_hw(struct funnel_drvdata *drvdata, + int inport) { u32 functl; @@ -103,7 +107,8 @@ static void funnel_disable(struct coresight_device *csdev, int inport, { struct funnel_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); - funnel_disable_hw(drvdata, inport); + if (drvdata->base) + dynamic_funnel_disable_hw(drvdata, inport); dev_dbg(drvdata->dev, "FUNNEL inport %d disabled\n", inport); } @@ -177,54 +182,70 @@ static struct attribute *coresight_funnel_attrs[] = { }; ATTRIBUTE_GROUPS(coresight_funnel); -static int funnel_probe(struct amba_device *adev, const struct amba_id *id) +static int funnel_probe(struct device *dev, struct resource *res) { int ret; void __iomem *base; - struct device *dev = &adev->dev; struct coresight_platform_data *pdata = NULL; struct funnel_drvdata *drvdata; - struct resource *res = &adev->res; struct coresight_desc desc = { 0 }; - struct device_node *np = adev->dev.of_node; + struct device_node *np = dev->of_node; if (np) { pdata = of_get_coresight_platform_data(dev, np); if (IS_ERR(pdata)) return PTR_ERR(pdata); - adev->dev.platform_data = pdata; + dev->platform_data = pdata; } + if (of_device_is_compatible(np, "arm,coresight-funnel")) + pr_warn_once("Uses OBSOLETE CoreSight funnel binding\n"); + drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL); if (!drvdata) return -ENOMEM; - drvdata->dev = &adev->dev; - drvdata->atclk = devm_clk_get(&adev->dev, "atclk"); /* optional */ + drvdata->dev = dev; + drvdata->atclk = devm_clk_get(dev, "atclk"); /* optional */ if (!IS_ERR(drvdata->atclk)) { ret = clk_prepare_enable(drvdata->atclk); if (ret) return ret; } + + /* + * Map the device base for dynamic-funnel, which has been + * validated by AMBA core. + */ + if (res) { + base = devm_ioremap_resource(dev, res); + if (IS_ERR(base)) { + ret = PTR_ERR(base); + goto out_disable_clk; + } + drvdata->base = base; + desc.groups = coresight_funnel_groups; + } + dev_set_drvdata(dev, drvdata); - /* Validity for the resource is already checked by the AMBA core */ - base = devm_ioremap_resource(dev, res); - if (IS_ERR(base)) - return PTR_ERR(base); - - drvdata->base = base; - pm_runtime_put(&adev->dev); - desc.type = CORESIGHT_DEV_TYPE_LINK; desc.subtype.link_subtype = CORESIGHT_DEV_SUBTYPE_LINK_MERG; desc.ops = &funnel_cs_ops; desc.pdata = pdata; desc.dev = dev; - desc.groups = coresight_funnel_groups; drvdata->csdev = coresight_register(&desc); + if (IS_ERR(drvdata->csdev)) { + ret = PTR_ERR(drvdata->csdev); + goto out_disable_clk; + } - return PTR_ERR_OR_ZERO(drvdata->csdev); + pm_runtime_put(dev); + +out_disable_clk: + if (ret && !IS_ERR_OR_NULL(drvdata->atclk)) + clk_disable_unprepare(drvdata->atclk); + return ret; } #ifdef CONFIG_PM @@ -253,7 +274,48 @@ static const struct dev_pm_ops funnel_dev_pm_ops = { SET_RUNTIME_PM_OPS(funnel_runtime_suspend, funnel_runtime_resume, NULL) }; -static const struct amba_id funnel_ids[] = { +static int static_funnel_probe(struct platform_device *pdev) +{ + int ret; + + pm_runtime_get_noresume(&pdev->dev); + pm_runtime_set_active(&pdev->dev); + pm_runtime_enable(&pdev->dev); + + /* Static funnel do not have programming base */ + ret = funnel_probe(&pdev->dev, NULL); + + if (ret) { + pm_runtime_put_noidle(&pdev->dev); + pm_runtime_disable(&pdev->dev); + } + + return ret; +} + +static const struct of_device_id static_funnel_match[] = { + {.compatible = "arm,coresight-static-funnel"}, + {} +}; + +static struct platform_driver static_funnel_driver = { + .probe = static_funnel_probe, + .driver = { + .name = "coresight-static-funnel", + .of_match_table = static_funnel_match, + .pm = &funnel_dev_pm_ops, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver(static_funnel_driver); + +static int dynamic_funnel_probe(struct amba_device *adev, + const struct amba_id *id) +{ + return funnel_probe(&adev->dev, &adev->res); +} + +static const struct amba_id dynamic_funnel_ids[] = { { .id = 0x000bb908, .mask = 0x000fffff, @@ -266,14 +328,14 @@ static const struct amba_id funnel_ids[] = { { 0, 0}, }; -static struct amba_driver funnel_driver = { +static struct amba_driver dynamic_funnel_driver = { .drv = { - .name = "coresight-funnel", + .name = "coresight-dynamic-funnel", .owner = THIS_MODULE, .pm = &funnel_dev_pm_ops, .suppress_bind_attrs = true, }, - .probe = funnel_probe, - .id_table = funnel_ids, + .probe = dynamic_funnel_probe, + .id_table = dynamic_funnel_ids, }; -builtin_amba_driver(funnel_driver); +builtin_amba_driver(dynamic_funnel_driver); From 4e0eaf239fb33ebc671303e2b736fa043462e2f4 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:34 +0300 Subject: [PATCH 239/255] intel_th: msu: Fix single mode with IOMMU Currently, the pages that are allocated for the single mode of MSC are not mapped into the device's dma space and the code is incorrectly using *_to_phys() in place of a dma address. This fails with IOMMU enabled and is otherwise bad practice. Fix the single mode buffer allocation to map the pages into the device's DMA space. Signed-off-by: Alexander Shishkin Fixes: ba82664c134e ("intel_th: Add Memory Storage Unit driver") Cc: stable@vger.kernel.org # v4.4+ Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/msu.c | 35 +++++++++++++++++++++++++++++--- 1 file changed, 32 insertions(+), 3 deletions(-) diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index ba7aaf421f36..8ff326c0c406 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -84,6 +84,7 @@ struct msc_iter { * @reg_base: register window base address * @thdev: intel_th_device pointer * @win_list: list of windows in multiblock mode + * @single_sgt: single mode buffer * @nr_pages: total number of pages allocated for this buffer * @single_sz: amount of data in single mode * @single_wrap: single mode wrap occurred @@ -104,6 +105,7 @@ struct msc { struct intel_th_device *thdev; struct list_head win_list; + struct sg_table single_sgt; unsigned long nr_pages; unsigned long single_sz; unsigned int single_wrap : 1; @@ -617,22 +619,45 @@ static void intel_th_msc_deactivate(struct intel_th_device *thdev) */ static int msc_buffer_contig_alloc(struct msc *msc, unsigned long size) { + unsigned long nr_pages = size >> PAGE_SHIFT; unsigned int order = get_order(size); struct page *page; + int ret; if (!size) return 0; + ret = sg_alloc_table(&msc->single_sgt, 1, GFP_KERNEL); + if (ret) + goto err_out; + + ret = -ENOMEM; page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order); if (!page) - return -ENOMEM; + goto err_free_sgt; split_page(page, order); - msc->nr_pages = size >> PAGE_SHIFT; + sg_set_buf(msc->single_sgt.sgl, page_address(page), size); + + ret = dma_map_sg(msc_dev(msc)->parent->parent, msc->single_sgt.sgl, 1, + DMA_FROM_DEVICE); + if (ret < 0) + goto err_free_pages; + + msc->nr_pages = nr_pages; msc->base = page_address(page); - msc->base_addr = page_to_phys(page); + msc->base_addr = sg_dma_address(msc->single_sgt.sgl); return 0; + +err_free_pages: + __free_pages(page, order); + +err_free_sgt: + sg_free_table(&msc->single_sgt); + +err_out: + return ret; } /** @@ -643,6 +668,10 @@ static void msc_buffer_contig_free(struct msc *msc) { unsigned long off; + dma_unmap_sg(msc_dev(msc)->parent->parent, msc->single_sgt.sgl, + 1, DMA_FROM_DEVICE); + sg_free_table(&msc->single_sgt); + for (off = 0; off < msc->nr_pages << PAGE_SHIFT; off += PAGE_SIZE) { struct page *page = virt_to_page(msc->base + off); From 85d49eb130ad747abebb9b0ff151f8afa7733115 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:35 +0300 Subject: [PATCH 240/255] intel_th: SPDX-ify the documentation Add the SPDX header to the Intel TH documentation. Signed-off-by: Alexander Shishkin Tested-by: Mathieu Poirier Signed-off-by: Greg Kroah-Hartman --- Documentation/trace/intel_th.rst | 2 ++ 1 file changed, 2 insertions(+) diff --git a/Documentation/trace/intel_th.rst b/Documentation/trace/intel_th.rst index 19e2d633f3c7..baa12eb09ef4 100644 --- a/Documentation/trace/intel_th.rst +++ b/Documentation/trace/intel_th.rst @@ -1,3 +1,5 @@ +.. SPDX-License-Identifier: GPL-2.0 + ======================= Intel(R) Trace Hub (TH) ======================= From db73a059de00eed721f13051c0d6ff3e7de90fe8 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:36 +0300 Subject: [PATCH 241/255] intel_th: Rework resource passing between glue layers and core Currently, MMIO resource numbers in the TH driver core correspond to PCI BAR numbers, because in the beginning there was only the PCI glue layer. This created some confusion when the ACPI glue layer was added. To avoid confusion and remove glue-specific code from the driver core, split the resource indices between core and glue layers and change the API so that the driver core receives the MMIO resources in the same fixed order. At the same time, make the IRQ always be a parameter to intel_th_alloc() instead of sometimes passing it as a resource. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/acpi.c | 12 ++++++++++-- drivers/hwtracing/intel_th/core.c | 27 +++++++-------------------- drivers/hwtracing/intel_th/intel_th.h | 8 ++++---- drivers/hwtracing/intel_th/pci.c | 15 ++++++++++++--- 4 files changed, 33 insertions(+), 29 deletions(-) diff --git a/drivers/hwtracing/intel_th/acpi.c b/drivers/hwtracing/intel_th/acpi.c index 87bc3744755f..b528e5b113ff 100644 --- a/drivers/hwtracing/intel_th/acpi.c +++ b/drivers/hwtracing/intel_th/acpi.c @@ -37,15 +37,23 @@ MODULE_DEVICE_TABLE(acpi, intel_th_acpi_ids); static int intel_th_acpi_probe(struct platform_device *pdev) { struct acpi_device *adev = ACPI_COMPANION(&pdev->dev); + struct resource resource[TH_MMIO_END]; const struct acpi_device_id *id; struct intel_th *th; + int i, r, irq = -1; id = acpi_match_device(intel_th_acpi_ids, &pdev->dev); if (!id) return -ENODEV; - th = intel_th_alloc(&pdev->dev, (void *)id->driver_data, - pdev->resource, pdev->num_resources, -1); + for (i = 0, r = 0; i < pdev->num_resources && r < TH_MMIO_END; i++) + if (pdev->resource[i].flags & IORESOURCE_IRQ) + irq = pdev->resource[i].start; + else if (pdev->resource[i].flags & IORESOURCE_MEM) + resource[r++] = pdev->resource[i]; + + th = intel_th_alloc(&pdev->dev, (void *)id->driver_data, resource, r, + irq); if (IS_ERR(th)) return PTR_ERR(th); diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 7c1acc2f801c..c577b94ee606 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -491,7 +491,7 @@ static const struct intel_th_subdevice { .flags = IORESOURCE_MEM, }, { - .start = 1, /* use resource[1] */ + .start = TH_MMIO_SW, .end = 0, .flags = IORESOURCE_MEM, }, @@ -584,7 +584,6 @@ intel_th_subdevice_alloc(struct intel_th *th, struct intel_th_device *thdev; struct resource res[3]; unsigned int req = 0; - bool is64bit = false; int r, err; thdev = intel_th_device_alloc(th, subdev->type, subdev->name, @@ -594,18 +593,12 @@ intel_th_subdevice_alloc(struct intel_th *th, thdev->drvdata = th->drvdata; - for (r = 0; r < th->num_resources; r++) - if (th->resource[r].flags & IORESOURCE_MEM_64) { - is64bit = true; - break; - } - memcpy(res, subdev->res, sizeof(struct resource) * subdev->nres); for (r = 0; r < subdev->nres; r++) { struct resource *devres = th->resource; - int bar = 0; /* cut subdevices' MMIO from resource[0] */ + int bar = TH_MMIO_CONFIG; /* * Take .end == 0 to mean 'take the whole bar', @@ -614,8 +607,6 @@ intel_th_subdevice_alloc(struct intel_th *th, */ if (!res[r].end && res[r].flags == IORESOURCE_MEM) { bar = res[r].start; - if (is64bit) - bar *= 2; res[r].start = 0; res[r].end = resource_size(&devres[bar]) - 1; } @@ -812,8 +803,7 @@ static const struct file_operations intel_th_output_fops = { /** * intel_th_alloc() - allocate a new Intel TH device and its subdevices * @dev: parent device - * @devres: parent's resources - * @ndevres: number of resources + * @devres: resources indexed by th_mmio_idx * @irq: irq number */ struct intel_th * @@ -823,12 +813,8 @@ intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, struct intel_th *th; int err, r; - if (irq == -1) - for (r = 0; r < ndevres; r++) - if (devres[r].flags & IORESOURCE_IRQ) { - irq = devres[r].start; - break; - } + if (ndevres < TH_MMIO_END) + return ERR_PTR(-EINVAL); th = kzalloc(sizeof(*th), GFP_KERNEL); if (!th) @@ -849,7 +835,8 @@ intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, th->dev = dev; th->drvdata = drvdata; - th->resource = devres; + for (r = 0; r < ndevres; r++) + th->resource[r] = devres[r]; th->num_resources = ndevres; th->irq = irq; diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 780206dc9012..8c90c8d01867 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -225,9 +225,9 @@ int intel_th_set_output(struct intel_th_device *thdev, unsigned int master); int intel_th_output_enable(struct intel_th *th, unsigned int otype); -enum { +enum th_mmio_idx { TH_MMIO_CONFIG = 0, - TH_MMIO_SW = 2, + TH_MMIO_SW = 1, TH_MMIO_END, }; @@ -244,7 +244,7 @@ enum { * @hub: "switch" subdevice (GTH) * @resource: resources of the entire controller * @num_thdevs: number of devices in the @thdev array - * @num_resources: number or resources in the @resource array + * @num_resources: number of resources in the @resource array * @irq: irq number * @id: this Intel TH controller's device ID in the system * @major: device node major for output devices @@ -256,7 +256,7 @@ struct intel_th { struct intel_th_device *hub; struct intel_th_drvdata *drvdata; - struct resource *resource; + struct resource resource[TH_MMIO_END]; int (*activate)(struct intel_th *); void (*deactivate)(struct intel_th *); unsigned int num_thdevs; diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 1cf6290d6435..9dd2d75bd539 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -17,7 +17,12 @@ #define DRIVER_NAME "intel_th_pci" -#define BAR_MASK (BIT(TH_MMIO_CONFIG) | BIT(TH_MMIO_SW)) +enum { + TH_PCI_CONFIG_BAR = 0, + TH_PCI_STH_SW_BAR = 2, +}; + +#define BAR_MASK (BIT(TH_PCI_CONFIG_BAR) | BIT(TH_PCI_STH_SW_BAR)) #define PCI_REG_NPKDSC 0x80 #define NPKDSC_TSACT BIT(5) @@ -66,6 +71,10 @@ static int intel_th_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct intel_th_drvdata *drvdata = (void *)id->driver_data; + struct resource resource[TH_MMIO_END] = { + [TH_MMIO_CONFIG] = pdev->resource[TH_PCI_CONFIG_BAR], + [TH_MMIO_SW] = pdev->resource[TH_PCI_STH_SW_BAR], + }; struct intel_th *th; int err; @@ -77,8 +86,8 @@ static int intel_th_pci_probe(struct pci_dev *pdev, if (err) return err; - th = intel_th_alloc(&pdev->dev, drvdata, pdev->resource, - DEVICE_COUNT_RESOURCE, pdev->irq); + th = intel_th_alloc(&pdev->dev, drvdata, resource, TH_MMIO_END, + pdev->irq); if (IS_ERR(th)) return PTR_ERR(th); From 23f667494b4d65d230cf61ad0d0b96c72f3a163c Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:37 +0300 Subject: [PATCH 242/255] intel_th: Skip subdevices if their MMIO is missing If a subdevice requires an MMIO region that wasn't in the resources passed down from the glue layer, don't instantiate it, but don't error out. This means that that particular subdevice doesn't exist for this instance of Intel TH, which is a perfectly normal situation. This applies, for example, to the "rtit" source device. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/core.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index c577b94ee606..8c221e1ed12d 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -607,6 +607,9 @@ intel_th_subdevice_alloc(struct intel_th *th, */ if (!res[r].end && res[r].flags == IORESOURCE_MEM) { bar = res[r].start; + err = -ENODEV; + if (bar >= th->num_resources) + goto fail_put_device; res[r].start = 0; res[r].end = resource_size(&devres[bar]) - 1; } @@ -749,8 +752,13 @@ static int intel_th_populate(struct intel_th *th) thdev = intel_th_subdevice_alloc(th, subdev); /* note: caller should free subdevices from th::thdev[] */ - if (IS_ERR(thdev)) + if (IS_ERR(thdev)) { + /* ENODEV for individual subdevices is allowed */ + if (PTR_ERR(thdev) == -ENODEV) + continue; + return PTR_ERR(thdev); + } th->thdev[th->num_thdevs++] = thdev; } @@ -813,9 +821,6 @@ intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, struct intel_th *th; int err, r; - if (ndevres < TH_MMIO_END) - return ERR_PTR(-EINVAL); - th = kzalloc(sizeof(*th), GFP_KERNEL); if (!th) return ERR_PTR(-ENOMEM); From fc027f4ce7c718660e046c3269b303bdbe692fda Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:38 +0300 Subject: [PATCH 243/255] intel_th: Add "rtit" source device In some versions of Intel TH, the Software Trace Hub (STH) has a second MMIO BAR dedicated to the input from Intel PT. This calls for a new subdevice that will be enumerated if the corresponding BAR is present. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/core.c | 18 ++++++++++++++++++ drivers/hwtracing/intel_th/intel_th.h | 1 + drivers/hwtracing/intel_th/pci.c | 11 ++++++++--- 3 files changed, 27 insertions(+), 3 deletions(-) diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 8c221e1ed12d..a0b8b0182daa 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -500,6 +500,24 @@ static const struct intel_th_subdevice { .name = "sth", .type = INTEL_TH_SOURCE, }, + { + .nres = 2, + .res = { + { + .start = REG_STH_OFFSET, + .end = REG_STH_OFFSET + REG_STH_LENGTH - 1, + .flags = IORESOURCE_MEM, + }, + { + .start = TH_MMIO_RTIT, + .end = 0, + .flags = IORESOURCE_MEM, + }, + }, + .id = -1, + .name = "rtit", + .type = INTEL_TH_SOURCE, + }, { .nres = 1, .res = { diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 8c90c8d01867..3fca86d78fdd 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -228,6 +228,7 @@ int intel_th_output_enable(struct intel_th *th, unsigned int otype); enum th_mmio_idx { TH_MMIO_CONFIG = 0, TH_MMIO_SW = 1, + TH_MMIO_RTIT = 2, TH_MMIO_END, }; diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 9dd2d75bd539..fd8267bbaf2c 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -20,6 +20,7 @@ enum { TH_PCI_CONFIG_BAR = 0, TH_PCI_STH_SW_BAR = 2, + TH_PCI_RTIT_BAR = 4, }; #define BAR_MASK (BIT(TH_PCI_CONFIG_BAR) | BIT(TH_PCI_STH_SW_BAR)) @@ -75,8 +76,8 @@ static int intel_th_pci_probe(struct pci_dev *pdev, [TH_MMIO_CONFIG] = pdev->resource[TH_PCI_CONFIG_BAR], [TH_MMIO_SW] = pdev->resource[TH_PCI_STH_SW_BAR], }; + int err, r = TH_MMIO_SW + 1; struct intel_th *th; - int err; err = pcim_enable_device(pdev); if (err) @@ -86,8 +87,12 @@ static int intel_th_pci_probe(struct pci_dev *pdev, if (err) return err; - th = intel_th_alloc(&pdev->dev, drvdata, resource, TH_MMIO_END, - pdev->irq); + if (pdev->resource[TH_PCI_RTIT_BAR].start) { + resource[TH_MMIO_RTIT] = pdev->resource[TH_PCI_RTIT_BAR]; + r++; + } + + th = intel_th_alloc(&pdev->dev, drvdata, resource, r, pdev->irq); if (IS_ERR(th)) return PTR_ERR(th); From 62a593022c32380d040303a5e3d6b67fd9c415bc Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:39 +0300 Subject: [PATCH 244/255] intel_th: Communicate IRQ via resource Currently, the IRQ is passed between the glue layers and the core as a separate argument, while the MMIO resources are passed as resources. This also limits the number of IRQs thus used to one, while the current versions of Intel TH use a different MSI vector for each interrupt triggering event, of which there are 7. Change this to pass IRQ in the resources array. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/acpi.c | 10 ++++------ drivers/hwtracing/intel_th/core.c | 23 ++++++++++++++++++----- drivers/hwtracing/intel_th/intel_th.h | 2 +- drivers/hwtracing/intel_th/pci.c | 9 +++++++-- 4 files changed, 30 insertions(+), 14 deletions(-) diff --git a/drivers/hwtracing/intel_th/acpi.c b/drivers/hwtracing/intel_th/acpi.c index b528e5b113ff..87f9024e4bbb 100644 --- a/drivers/hwtracing/intel_th/acpi.c +++ b/drivers/hwtracing/intel_th/acpi.c @@ -40,20 +40,18 @@ static int intel_th_acpi_probe(struct platform_device *pdev) struct resource resource[TH_MMIO_END]; const struct acpi_device_id *id; struct intel_th *th; - int i, r, irq = -1; + int i, r; id = acpi_match_device(intel_th_acpi_ids, &pdev->dev); if (!id) return -ENODEV; for (i = 0, r = 0; i < pdev->num_resources && r < TH_MMIO_END; i++) - if (pdev->resource[i].flags & IORESOURCE_IRQ) - irq = pdev->resource[i].start; - else if (pdev->resource[i].flags & IORESOURCE_MEM) + if (pdev->resource[i].flags & + (IORESOURCE_IRQ | IORESOURCE_MEM)) resource[r++] = pdev->resource[i]; - th = intel_th_alloc(&pdev->dev, (void *)id->driver_data, resource, r, - irq); + th = intel_th_alloc(&pdev->dev, (void *)id->driver_data, resource, r); if (IS_ERR(th)) return PTR_ERR(th); diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index a0b8b0182daa..0205fca4c606 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -834,10 +834,10 @@ static const struct file_operations intel_th_output_fops = { */ struct intel_th * intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, - struct resource *devres, unsigned int ndevres, int irq) + struct resource *devres, unsigned int ndevres) { + int err, r, nr_mmios = 0; struct intel_th *th; - int err, r; th = kzalloc(sizeof(*th), GFP_KERNEL); if (!th) @@ -855,13 +855,26 @@ intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, err = th->major; goto err_ida; } + th->irq = -1; th->dev = dev; th->drvdata = drvdata; for (r = 0; r < ndevres; r++) - th->resource[r] = devres[r]; - th->num_resources = ndevres; - th->irq = irq; + switch (devres[r].flags & IORESOURCE_TYPE_BITS) { + case IORESOURCE_MEM: + th->resource[nr_mmios++] = devres[r]; + break; + case IORESOURCE_IRQ: + if (th->irq == -1) + th->irq = devres[r].start; + break; + default: + dev_warn(dev, "Unknown resource type %lx\n", + devres[r].flags); + break; + } + + th->num_resources = nr_mmios; dev_set_drvdata(dev, th); diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 3fca86d78fdd..6c6eb87e48a0 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -213,7 +213,7 @@ static inline struct intel_th *to_intel_th(struct intel_th_device *thdev) struct intel_th * intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, - struct resource *devres, unsigned int ndevres, int irq); + struct resource *devres, unsigned int ndevres); void intel_th_free(struct intel_th *th); int intel_th_driver_register(struct intel_th_driver *thdrv); diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index fd8267bbaf2c..03d6894cd9c9 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -72,7 +72,7 @@ static int intel_th_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct intel_th_drvdata *drvdata = (void *)id->driver_data; - struct resource resource[TH_MMIO_END] = { + struct resource resource[TH_MMIO_END + 1] = { [TH_MMIO_CONFIG] = pdev->resource[TH_PCI_CONFIG_BAR], [TH_MMIO_SW] = pdev->resource[TH_PCI_STH_SW_BAR], }; @@ -92,7 +92,12 @@ static int intel_th_pci_probe(struct pci_dev *pdev, r++; } - th = intel_th_alloc(&pdev->dev, drvdata, resource, r, pdev->irq); + if (pdev->irq > 0) { + resource[r].flags = IORESOURCE_IRQ; + resource[r++].start = pdev->irq; + } + + th = intel_th_alloc(&pdev->dev, drvdata, resource, r); if (IS_ERR(th)) return PTR_ERR(th); From 7b7036d47c356a40818e516a69ac81a5dcc1613f Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:40 +0300 Subject: [PATCH 245/255] intel_th: pci: Use MSI interrupt signalling Since Intel TH is capable of MSI interrupt signalling, make use of it. The way it works is, each of the 7 interrupt triggering events has its own vector in this mode, as opposed to interrupt line delivery, where all events are signalled via the same line. Failing to enable MSI, the driver falls back to using an interrupt line. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/intel_th.h | 3 +++ drivers/hwtracing/intel_th/pci.c | 16 ++++++++++------ 2 files changed, 13 insertions(+), 6 deletions(-) diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 6c6eb87e48a0..db3ad8ca1c48 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -238,6 +238,9 @@ enum th_mmio_idx { #define TH_CONFIGURABLE_MASTERS 256 #define TH_MSC_MAX 2 +/* Maximum IRQ vectors */ +#define TH_NVEC_MAX 8 + /** * struct intel_th - Intel TH controller * @dev: driver core's device diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index 03d6894cd9c9..f5643444481b 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -72,11 +72,11 @@ static int intel_th_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct intel_th_drvdata *drvdata = (void *)id->driver_data; - struct resource resource[TH_MMIO_END + 1] = { + struct resource resource[TH_MMIO_END + TH_NVEC_MAX] = { [TH_MMIO_CONFIG] = pdev->resource[TH_PCI_CONFIG_BAR], [TH_MMIO_SW] = pdev->resource[TH_PCI_STH_SW_BAR], }; - int err, r = TH_MMIO_SW + 1; + int err, r = TH_MMIO_SW + 1, i; struct intel_th *th; err = pcim_enable_device(pdev); @@ -92,10 +92,12 @@ static int intel_th_pci_probe(struct pci_dev *pdev, r++; } - if (pdev->irq > 0) { - resource[r].flags = IORESOURCE_IRQ; - resource[r++].start = pdev->irq; - } + err = pci_alloc_irq_vectors(pdev, 1, 8, PCI_IRQ_ALL_TYPES); + if (err > 0) + for (i = 0; i < err; i++, r++) { + resource[r].flags = IORESOURCE_IRQ; + resource[r].start = pci_irq_vector(pdev, i); + } th = intel_th_alloc(&pdev->dev, drvdata, resource, r); if (IS_ERR(th)) @@ -114,6 +116,8 @@ static void intel_th_pci_remove(struct pci_dev *pdev) struct intel_th *th = pci_get_drvdata(pdev); intel_th_free(th); + + pci_free_irq_vectors(pdev); } static const struct intel_th_drvdata intel_th_2x = { From aac8da65174a35749fcf21dbca4c1be314b562b5 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:41 +0300 Subject: [PATCH 246/255] intel_th: msu: Start handling IRQs We intend to use the interrupt to detect Last Block condition in the MSU driver, which we can use for double-buffering software-managed data transfers. Add an interrupt handler to the MSU driver. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/core.c | 32 ++++++++++++++ drivers/hwtracing/intel_th/intel_th.h | 4 +- drivers/hwtracing/intel_th/msu.c | 64 ++++++++++++++++++++++++++- drivers/hwtracing/intel_th/msu.h | 8 ++++ 4 files changed, 106 insertions(+), 2 deletions(-) diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 0205fca4c606..750aa9d6f849 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -826,6 +826,28 @@ static const struct file_operations intel_th_output_fops = { .llseek = noop_llseek, }; +static irqreturn_t intel_th_irq(int irq, void *data) +{ + struct intel_th *th = data; + irqreturn_t ret = IRQ_NONE; + struct intel_th_driver *d; + int i; + + for (i = 0; i < th->num_thdevs; i++) { + if (th->thdev[i]->type != INTEL_TH_OUTPUT) + continue; + + d = to_intel_th_driver(th->thdev[i]->dev.driver); + if (d && d->irq) + ret |= d->irq(th->thdev[i]); + } + + if (ret == IRQ_NONE) + pr_warn_ratelimited("nobody cared for irq\n"); + + return ret; +} + /** * intel_th_alloc() - allocate a new Intel TH device and its subdevices * @dev: parent device @@ -865,6 +887,12 @@ intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, th->resource[nr_mmios++] = devres[r]; break; case IORESOURCE_IRQ: + err = devm_request_irq(dev, devres[r].start, + intel_th_irq, IRQF_SHARED, + dev_name(dev), th); + if (err) + goto err_chrdev; + if (th->irq == -1) th->irq = devres[r].start; break; @@ -891,6 +919,10 @@ intel_th_alloc(struct device *dev, struct intel_th_drvdata *drvdata, return th; +err_chrdev: + __unregister_chrdev(th->major, 0, TH_POSSIBLE_OUTPUTS, + "intel_th/output"); + err_ida: ida_simple_remove(&intel_th_ida, th->id); diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index db3ad8ca1c48..59038215489a 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -8,6 +8,8 @@ #ifndef __INTEL_TH_H__ #define __INTEL_TH_H__ +#include + /* intel_th_device device types */ enum { /* Devices that generate trace data */ @@ -160,7 +162,7 @@ struct intel_th_driver { void (*disable)(struct intel_th_device *thdev, struct intel_th_output *output); /* output ops */ - void (*irq)(struct intel_th_device *thdev); + irqreturn_t (*irq)(struct intel_th_device *thdev); int (*activate)(struct intel_th_device *thdev); void (*deactivate)(struct intel_th_device *thdev); /* file_operations for those who want a device node */ diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index 8ff326c0c406..3716d312a4ee 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -102,6 +102,7 @@ struct msc_iter { */ struct msc { void __iomem *reg_base; + void __iomem *msu_base; struct intel_th_device *thdev; struct list_head win_list; @@ -122,7 +123,8 @@ struct msc { /* config */ unsigned int enabled : 1, - wrap : 1; + wrap : 1, + do_irq : 1; unsigned int mode; unsigned int burst_len; unsigned int index; @@ -476,6 +478,40 @@ static void msc_buffer_clear_hw_header(struct msc *msc) } } +static int intel_th_msu_init(struct msc *msc) +{ + u32 mintctl, msusts; + + if (!msc->do_irq) + return 0; + + mintctl = ioread32(msc->msu_base + REG_MSU_MINTCTL); + mintctl |= msc->index ? M1BLIE : M0BLIE; + iowrite32(mintctl, msc->msu_base + REG_MSU_MINTCTL); + if (mintctl != ioread32(msc->msu_base + REG_MSU_MINTCTL)) { + dev_info(msc_dev(msc), "MINTCTL ignores writes: no usable interrupts\n"); + msc->do_irq = 0; + return 0; + } + + msusts = ioread32(msc->msu_base + REG_MSU_MSUSTS); + iowrite32(msusts, msc->msu_base + REG_MSU_MSUSTS); + + return 0; +} + +static void intel_th_msu_deinit(struct msc *msc) +{ + u32 mintctl; + + if (!msc->do_irq) + return; + + mintctl = ioread32(msc->msu_base + REG_MSU_MINTCTL); + mintctl &= msc->index ? ~M1BLIE : ~M0BLIE; + iowrite32(mintctl, msc->msu_base + REG_MSU_MINTCTL); +} + /** * msc_configure() - set up MSC hardware * @msc: the MSC device to configure @@ -1295,6 +1331,21 @@ static int intel_th_msc_init(struct msc *msc) return 0; } +static irqreturn_t intel_th_msc_interrupt(struct intel_th_device *thdev) +{ + struct msc *msc = dev_get_drvdata(&thdev->dev); + u32 msusts = ioread32(msc->msu_base + REG_MSU_MSUSTS); + u32 mask = msc->index ? MSUSTS_MSC1BLAST : MSUSTS_MSC0BLAST; + + if (!(msusts & mask)) { + if (msc->enabled) + return IRQ_HANDLED; + return IRQ_NONE; + } + + return IRQ_HANDLED; +} + static const char * const msc_mode[] = { [MSC_MODE_SINGLE] = "single", [MSC_MODE_MULTI] = "multi", @@ -1500,10 +1551,19 @@ static int intel_th_msc_probe(struct intel_th_device *thdev) if (!msc) return -ENOMEM; + res = intel_th_device_get_resource(thdev, IORESOURCE_IRQ, 1); + if (!res) + msc->do_irq = 1; + msc->index = thdev->id; msc->thdev = thdev; msc->reg_base = base + msc->index * 0x100; + msc->msu_base = base; + + err = intel_th_msu_init(msc); + if (err) + return err; err = intel_th_msc_init(msc); if (err) @@ -1520,6 +1580,7 @@ static void intel_th_msc_remove(struct intel_th_device *thdev) int ret; intel_th_msc_deactivate(thdev); + intel_th_msu_deinit(msc); /* * Buffers should not be used at this point except if the @@ -1533,6 +1594,7 @@ static void intel_th_msc_remove(struct intel_th_device *thdev) static struct intel_th_driver intel_th_msc_driver = { .probe = intel_th_msc_probe, .remove = intel_th_msc_remove, + .irq = intel_th_msc_interrupt, .activate = intel_th_msc_activate, .deactivate = intel_th_msc_deactivate, .fops = &intel_th_msc_fops, diff --git a/drivers/hwtracing/intel_th/msu.h b/drivers/hwtracing/intel_th/msu.h index 9cc8aced6116..e8cb819a3804 100644 --- a/drivers/hwtracing/intel_th/msu.h +++ b/drivers/hwtracing/intel_th/msu.h @@ -11,6 +11,7 @@ enum { REG_MSU_MSUPARAMS = 0x0000, REG_MSU_MSUSTS = 0x0008, + REG_MSU_MINTCTL = 0x0004, /* MSU-global interrupt control */ REG_MSU_MSC0CTL = 0x0100, /* MSC0 control */ REG_MSU_MSC0STS = 0x0104, /* MSC0 status */ REG_MSU_MSC0BAR = 0x0108, /* MSC0 output base address */ @@ -28,6 +29,8 @@ enum { /* MSUSTS bits */ #define MSUSTS_MSU_INT BIT(0) +#define MSUSTS_MSC0BLAST BIT(16) +#define MSUSTS_MSC1BLAST BIT(24) /* MSCnCTL bits */ #define MSC_EN BIT(0) @@ -36,6 +39,11 @@ enum { #define MSC_MODE (BIT(4) | BIT(5)) #define MSC_LEN (BIT(8) | BIT(9) | BIT(10)) +/* MINTCTL bits */ +#define MICDE BIT(0) +#define M0BLIE BIT(16) +#define M1BLIE BIT(24) + /* MSC operating modes (MSC_MODE) */ enum { MSC_MODE_SINGLE = 0, From 4c5bb6eb4055adcefaeb5da56dfbecf7df3695d7 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:42 +0300 Subject: [PATCH 247/255] intel_th: Only report useful IRQs to subdevices The only type of IRQ triggering event that is useful to us at the moment is the "last block" interrupt of the MSU. This interrupt can only be enabled via "MINTCTL" register that doesn't exist in earlier version of the Intel TH. Enumerate the presence of MINTCTL via per-device driver data structure and only instantiate the IRQ resource for subdevices if this capability is present. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/core.c | 7 ++++++- drivers/hwtracing/intel_th/intel_th.h | 2 ++ drivers/hwtracing/intel_th/pci.c | 1 + 3 files changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 750aa9d6f849..390031df3edf 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -639,7 +639,12 @@ intel_th_subdevice_alloc(struct intel_th *th, dev_dbg(th->dev, "%s:%d @ %pR\n", subdev->name, r, &res[r]); } else if (res[r].flags & IORESOURCE_IRQ) { - res[r].start = th->irq; + /* + * Only pass on the IRQ if we have useful interrupts: + * the ones that can be configured via MINTCTL. + */ + if (INTEL_TH_CAP(th, has_mintctl) && th->irq != -1) + res[r].start = th->irq; } } diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 59038215489a..8b986ba160e4 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -44,10 +44,12 @@ struct intel_th_output { /** * struct intel_th_drvdata - describes hardware capabilities and quirks * @tscu_enable: device needs SW to enable time stamping unit + * @has_mintctl: device has interrupt control (MINTCTL) register * @host_mode_only: device can only operate in 'host debugger' mode */ struct intel_th_drvdata { unsigned int tscu_enable : 1, + has_mintctl : 1, host_mode_only : 1; }; diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c index f5643444481b..5808dd4c104c 100644 --- a/drivers/hwtracing/intel_th/pci.c +++ b/drivers/hwtracing/intel_th/pci.c @@ -122,6 +122,7 @@ static void intel_th_pci_remove(struct pci_dev *pdev) static const struct intel_th_drvdata intel_th_2x = { .tscu_enable = 1, + .has_mintctl = 1, }; static const struct pci_device_id intel_th_pci_id_table[] = { From 0de9e0351d4d4266b3e3f4ecf405c21af61a1f9e Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:43 +0300 Subject: [PATCH 248/255] intel_th: msu: Replace open-coded list_{first,last,next}_entry variants There are a few places in the code where open-coded versions of list entry accessors list_first_entry()/list_last_entry()/list_next_entry() are used. Replace those with the standard macros. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/msu.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index 3716d312a4ee..f5d5cb862a81 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -179,7 +179,7 @@ static struct msc_window *msc_oldest_window(struct msc *msc) return win; } - return list_entry(msc->win_list.next, struct msc_window, entry); + return list_first_entry(&msc->win_list, struct msc_window, entry); } /** @@ -230,10 +230,10 @@ static inline bool msc_is_last_win(struct msc_window *win) static struct msc_window *msc_next_window(struct msc_window *win) { if (msc_is_last_win(win)) - return list_entry(win->msc->win_list.next, struct msc_window, - entry); + return list_first_entry(&win->msc->win_list, struct msc_window, + entry); - return list_entry(win->entry.next, struct msc_window, entry); + return list_next_entry(win, entry); } static struct msc_block_desc *msc_iter_bdesc(struct msc_iter *iter) @@ -759,8 +759,9 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks) return -ENOMEM; if (!list_empty(&msc->win_list)) { - struct msc_window *prev = list_entry(msc->win_list.prev, - struct msc_window, entry); + struct msc_window *prev = list_last_entry(&msc->win_list, + struct msc_window, + entry); win->pgoff = prev->pgoff + prev->nr_blocks; } @@ -863,11 +864,10 @@ static void msc_buffer_relink(struct msc *msc) */ if (msc_is_last_win(win)) { sw_tag |= MSC_SW_TAG_LASTWIN; - next_win = list_entry(msc->win_list.next, - struct msc_window, entry); + next_win = list_first_entry(&msc->win_list, + struct msc_window, entry); } else { - next_win = list_entry(win->entry.next, - struct msc_window, entry); + next_win = list_next_entry(win, entry); } for (blk = 0; blk < win->nr_blocks; blk++) { From ba39bd8306057fb343dfb75d93a76d824b625236 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:44 +0300 Subject: [PATCH 249/255] intel_th: msu: Switch over to scatterlist Instead of using a home-grown array of pointers to the DMA pages, switch over to scatterlist data types and accessors, which has all the convenient accessors, can be used to batch-map DMA memory and is convenient for passing around between different layers, which will be useful when MSU buffer management has to cross the boundaries of the MSU driver. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/msu.c | 163 ++++++++++++++++++++----------- 1 file changed, 104 insertions(+), 59 deletions(-) diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index f5d5cb862a81..0e7fbef8dee0 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -28,29 +28,19 @@ #define msc_dev(x) (&(x)->thdev->dev) -/** - * struct msc_block - multiblock mode block descriptor - * @bdesc: pointer to hardware descriptor (beginning of the block) - * @addr: physical address of the block - */ -struct msc_block { - struct msc_block_desc *bdesc; - dma_addr_t addr; -}; - /** * struct msc_window - multiblock mode window descriptor * @entry: window list linkage (msc::win_list) * @pgoff: page offset into the buffer that this window starts at * @nr_blocks: number of blocks (pages) in this window - * @block: array of block descriptors + * @sgt: array of block descriptors */ struct msc_window { struct list_head entry; unsigned long pgoff; unsigned int nr_blocks; struct msc *msc; - struct msc_block block[0]; + struct sg_table sgt; }; /** @@ -143,6 +133,24 @@ static inline bool msc_block_is_empty(struct msc_block_desc *bdesc) return false; } +static inline struct msc_block_desc * +msc_win_block(struct msc_window *win, unsigned int block) +{ + return sg_virt(&win->sgt.sgl[block]); +} + +static inline dma_addr_t +msc_win_baddr(struct msc_window *win, unsigned int block) +{ + return sg_dma_address(&win->sgt.sgl[block]); +} + +static inline unsigned long +msc_win_bpfn(struct msc_window *win, unsigned int block) +{ + return msc_win_baddr(win, block) >> PAGE_SHIFT; +} + /** * msc_oldest_window() - locate the window with oldest data * @msc: MSC device @@ -168,11 +176,11 @@ static struct msc_window *msc_oldest_window(struct msc *msc) * something like 2, in which case we're good */ list_for_each_entry(win, &msc->win_list, entry) { - if (win->block[0].addr == win_addr) + if (sg_dma_address(win->sgt.sgl) == win_addr) found++; /* skip the empty ones */ - if (msc_block_is_empty(win->block[0].bdesc)) + if (msc_block_is_empty(msc_win_block(win, 0))) continue; if (found) @@ -191,7 +199,7 @@ static struct msc_window *msc_oldest_window(struct msc *msc) static unsigned int msc_win_oldest_block(struct msc_window *win) { unsigned int blk; - struct msc_block_desc *bdesc = win->block[0].bdesc; + struct msc_block_desc *bdesc = msc_win_block(win, 0); /* without wrapping, first block is the oldest */ if (!msc_block_wrapped(bdesc)) @@ -202,7 +210,7 @@ static unsigned int msc_win_oldest_block(struct msc_window *win) * oldest data for this window. */ for (blk = 0; blk < win->nr_blocks; blk++) { - bdesc = win->block[blk].bdesc; + bdesc = msc_win_block(win, blk); if (msc_block_last_written(bdesc)) return blk; @@ -238,7 +246,7 @@ static struct msc_window *msc_next_window(struct msc_window *win) static struct msc_block_desc *msc_iter_bdesc(struct msc_iter *iter) { - return iter->win->block[iter->block].bdesc; + return msc_win_block(iter->win, iter->block); } static void msc_iter_init(struct msc_iter *iter) @@ -471,7 +479,7 @@ static void msc_buffer_clear_hw_header(struct msc *msc) offsetof(struct msc_block_desc, hw_tag); for (blk = 0; blk < win->nr_blocks; blk++) { - struct msc_block_desc *bdesc = win->block[blk].bdesc; + struct msc_block_desc *bdesc = msc_win_block(win, blk); memset(&bdesc->hw_tag, 0, hw_sz); } @@ -734,6 +742,40 @@ static struct page *msc_buffer_contig_get_page(struct msc *msc, return virt_to_page(msc->base + (pgoff << PAGE_SHIFT)); } +static int __msc_buffer_win_alloc(struct msc_window *win, + unsigned int nr_blocks) +{ + struct scatterlist *sg_ptr; + void *block; + int i, ret; + + ret = sg_alloc_table(&win->sgt, nr_blocks, GFP_KERNEL); + if (ret) + return -ENOMEM; + + for_each_sg(win->sgt.sgl, sg_ptr, nr_blocks, i) { + block = dma_alloc_coherent(msc_dev(win->msc)->parent->parent, + PAGE_SIZE, &sg_dma_address(sg_ptr), + GFP_KERNEL); + if (!block) + goto err_nomem; + + sg_set_buf(sg_ptr, block, PAGE_SIZE); + } + + return nr_blocks; + +err_nomem: + for (i--; i >= 0; i--) + dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE, + msc_win_block(win, i), + msc_win_baddr(win, i)); + + sg_free_table(&win->sgt); + + return -ENOMEM; +} + /** * msc_buffer_win_alloc() - alloc a window for a multiblock mode * @msc: MSC device @@ -747,45 +789,48 @@ static struct page *msc_buffer_contig_get_page(struct msc *msc, static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks) { struct msc_window *win; - unsigned long size = PAGE_SIZE; - int i, ret = -ENOMEM; + int ret = -ENOMEM, i; if (!nr_blocks) return 0; - win = kzalloc(offsetof(struct msc_window, block[nr_blocks]), - GFP_KERNEL); + /* + * This limitation hold as long as we need random access to the + * block. When that changes, this can go away. + */ + if (nr_blocks > SG_MAX_SINGLE_ALLOC) + return -EINVAL; + + win = kzalloc(sizeof(*win), GFP_KERNEL); if (!win) return -ENOMEM; + win->msc = msc; + if (!list_empty(&msc->win_list)) { struct msc_window *prev = list_last_entry(&msc->win_list, struct msc_window, entry); + /* This works as long as blocks are page-sized */ win->pgoff = prev->pgoff + prev->nr_blocks; } - for (i = 0; i < nr_blocks; i++) { - win->block[i].bdesc = - dma_alloc_coherent(msc_dev(msc)->parent->parent, size, - &win->block[i].addr, GFP_KERNEL); - - if (!win->block[i].bdesc) - goto err_nomem; + ret = __msc_buffer_win_alloc(win, nr_blocks); + if (ret < 0) + goto err_nomem; #ifdef CONFIG_X86 + for (i = 0; i < ret; i++) /* Set the page as uncached */ - set_memory_uc((unsigned long)win->block[i].bdesc, 1); + set_memory_uc((unsigned long)msc_win_block(win, i), 1); #endif - } - win->msc = msc; - win->nr_blocks = nr_blocks; + win->nr_blocks = ret; if (list_empty(&msc->win_list)) { - msc->base = win->block[0].bdesc; - msc->base_addr = win->block[0].addr; + msc->base = msc_win_block(win, 0); + msc->base_addr = msc_win_baddr(win, 0); } list_add_tail(&win->entry, &msc->win_list); @@ -794,19 +839,25 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks) return 0; err_nomem: - for (i--; i >= 0; i--) { -#ifdef CONFIG_X86 - /* Reset the page to write-back before releasing */ - set_memory_wb((unsigned long)win->block[i].bdesc, 1); -#endif - dma_free_coherent(msc_dev(msc)->parent->parent, size, - win->block[i].bdesc, win->block[i].addr); - } kfree(win); return ret; } +static void __msc_buffer_win_free(struct msc *msc, struct msc_window *win) +{ + int i; + + for (i = 0; i < win->nr_blocks; i++) { + struct page *page = sg_page(&win->sgt.sgl[i]); + + page->mapping = NULL; + dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE, + msc_win_block(win, i), msc_win_baddr(win, i)); + } + sg_free_table(&win->sgt); +} + /** * msc_buffer_win_free() - free a window from MSC's window list * @msc: MSC device @@ -827,17 +878,13 @@ static void msc_buffer_win_free(struct msc *msc, struct msc_window *win) msc->base_addr = 0; } - for (i = 0; i < win->nr_blocks; i++) { - struct page *page = virt_to_page(win->block[i].bdesc); - - page->mapping = NULL; #ifdef CONFIG_X86 - /* Reset the page to write-back before releasing */ - set_memory_wb((unsigned long)win->block[i].bdesc, 1); + for (i = 0; i < win->nr_blocks; i++) + /* Reset the page to write-back */ + set_memory_wb((unsigned long)msc_win_block(win, i), 1); #endif - dma_free_coherent(msc_dev(win->msc)->parent->parent, PAGE_SIZE, - win->block[i].bdesc, win->block[i].addr); - } + + __msc_buffer_win_free(msc, win); kfree(win); } @@ -871,11 +918,11 @@ static void msc_buffer_relink(struct msc *msc) } for (blk = 0; blk < win->nr_blocks; blk++) { - struct msc_block_desc *bdesc = win->block[blk].bdesc; + struct msc_block_desc *bdesc = msc_win_block(win, blk); memset(bdesc, 0, sizeof(*bdesc)); - bdesc->next_win = next_win->block[0].addr >> PAGE_SHIFT; + bdesc->next_win = msc_win_bpfn(next_win, 0); /* * Similarly to last window, last block should point @@ -883,11 +930,9 @@ static void msc_buffer_relink(struct msc *msc) */ if (blk == win->nr_blocks - 1) { sw_tag |= MSC_SW_TAG_LASTBLK; - bdesc->next_blk = - win->block[0].addr >> PAGE_SHIFT; + bdesc->next_blk = msc_win_bpfn(win, 0); } else { - bdesc->next_blk = - win->block[blk + 1].addr >> PAGE_SHIFT; + bdesc->next_blk = msc_win_bpfn(win, blk + 1); } bdesc->sw_tag = sw_tag; @@ -1062,7 +1107,7 @@ static struct page *msc_buffer_get_page(struct msc *msc, unsigned long pgoff) found: pgoff -= win->pgoff; - return virt_to_page(win->block[pgoff].bdesc); + return sg_page(&win->sgt.sgl[pgoff]); } /** From 8d4155126e32fdceda7e1520e77a7beac2217f4a Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:46 +0300 Subject: [PATCH 250/255] intel_th: msu: Factor out pipeline draining The code that waits for the pipeline empty condition of the MSU is currently called in the path that disables the trace. We will also need this in the window switch trigger sequence. Therefore, factor out this code and make it accessible to the GTH device. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/gth.c | 7 +++++++ drivers/hwtracing/intel_th/intel_th.h | 4 ++++ drivers/hwtracing/intel_th/msu.c | 28 +++++++++++++++++---------- 3 files changed, 29 insertions(+), 10 deletions(-) diff --git a/drivers/hwtracing/intel_th/gth.c b/drivers/hwtracing/intel_th/gth.c index edc52d75e6bd..7e6b70047125 100644 --- a/drivers/hwtracing/intel_th/gth.c +++ b/drivers/hwtracing/intel_th/gth.c @@ -469,6 +469,10 @@ static void intel_th_gth_disable(struct intel_th_device *thdev, struct intel_th_output *output) { struct gth_device *gth = dev_get_drvdata(&thdev->dev); + struct intel_th_device *outdev = + container_of(output, struct intel_th_device, output); + struct intel_th_driver *outdrv = + to_intel_th_driver(outdev->dev.driver); unsigned long count; int master; u32 reg; @@ -492,6 +496,9 @@ static void intel_th_gth_disable(struct intel_th_device *thdev, cpu_relax(); } + if (outdrv->wait_empty) + outdrv->wait_empty(outdev); + /* clear force capture done for next captures */ iowrite32(0xfc, gth->base + REG_GTH_SCR2); diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 8b986ba160e4..74a6a4071e7f 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -20,6 +20,8 @@ enum { INTEL_TH_SWITCH, }; +struct intel_th_device; + /** * struct intel_th_output - descriptor INTEL_TH_OUTPUT type devices * @port: output port number, assigned by the switch @@ -27,6 +29,7 @@ enum { * @scratchpad: scratchpad bits to flag when this output is enabled * @multiblock: true for multiblock output configuration * @active: true when this output is enabled + * @wait_empty: wait for device pipeline to be empty * * Output port descriptor, used by switch driver to tell which output * port this output device corresponds to. Filled in at output device's @@ -165,6 +168,7 @@ struct intel_th_driver { struct intel_th_output *output); /* output ops */ irqreturn_t (*irq)(struct intel_th_device *thdev); + void (*wait_empty)(struct intel_th_device *thdev); int (*activate)(struct intel_th_device *thdev); void (*deactivate)(struct intel_th_device *thdev); /* file_operations for those who want a device node */ diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index 0e7fbef8dee0..b0bb69942328 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -577,23 +577,14 @@ static int msc_configure(struct msc *msc) */ static void msc_disable(struct msc *msc) { - unsigned long count; u32 reg; lockdep_assert_held(&msc->buf_mutex); intel_th_trace_disable(msc->thdev); - for (reg = 0, count = MSC_PLE_WAITLOOP_DEPTH; - count && !(reg & MSCSTS_PLE); count--) { - reg = ioread32(msc->reg_base + REG_MSU_MSC0STS); - cpu_relax(); - } - - if (!count) - dev_dbg(msc_dev(msc), "timeout waiting for MSC0 PLE\n"); - if (msc->mode == MSC_MODE_SINGLE) { + reg = ioread32(msc->reg_base + REG_MSU_MSC0STS); msc->single_wrap = !!(reg & MSCSTS_WRAPSTAT); reg = ioread32(msc->reg_base + REG_MSU_MSC0MWP); @@ -1360,6 +1351,22 @@ static const struct file_operations intel_th_msc_fops = { .owner = THIS_MODULE, }; +static void intel_th_msc_wait_empty(struct intel_th_device *thdev) +{ + struct msc *msc = dev_get_drvdata(&thdev->dev); + unsigned long count; + u32 reg; + + for (reg = 0, count = MSC_PLE_WAITLOOP_DEPTH; + count && !(reg & MSCSTS_PLE); count--) { + reg = __raw_readl(msc->reg_base + REG_MSU_MSC0STS); + cpu_relax(); + } + + if (!count) + dev_dbg(msc_dev(msc), "timeout waiting for MSC0 PLE\n"); +} + static int intel_th_msc_init(struct msc *msc) { atomic_set(&msc->user_count, -1); @@ -1640,6 +1647,7 @@ static struct intel_th_driver intel_th_msc_driver = { .probe = intel_th_msc_probe, .remove = intel_th_msc_remove, .irq = intel_th_msc_interrupt, + .wait_empty = intel_th_msc_wait_empty, .activate = intel_th_msc_activate, .deactivate = intel_th_msc_deactivate, .fops = &intel_th_msc_fops, From 9958e02523eea424d4848ef426c5aa7e07e4e207 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:47 +0300 Subject: [PATCH 251/255] intel_th: gth: Factor out trace start/stop The trace enable/disable functions of the GTH include the code that starts and stops trace flom from the sources. This start/stop functionality will also be used in the window switch trigger sequence. Factor out start/stop code from the larger trace enable/disable code in preparation for the window switch sequence. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/gth.c | 95 ++++++++++++++++++++++---------- 1 file changed, 65 insertions(+), 30 deletions(-) diff --git a/drivers/hwtracing/intel_th/gth.c b/drivers/hwtracing/intel_th/gth.c index 7e6b70047125..a879445ef451 100644 --- a/drivers/hwtracing/intel_th/gth.c +++ b/drivers/hwtracing/intel_th/gth.c @@ -456,6 +456,68 @@ static int intel_th_output_attributes(struct gth_device *gth) return sysfs_create_group(>h->dev->kobj, >h->output_group); } +/** + * intel_th_gth_stop() - stop tracing to an output device + * @gth: GTH device + * @output: output device's descriptor + * @capture_done: set when no more traces will be captured + * + * This will stop tracing using force storeEn off signal and wait for the + * pipelines to be empty for the corresponding output port. + */ +static void intel_th_gth_stop(struct gth_device *gth, + struct intel_th_output *output, + bool capture_done) +{ + struct intel_th_device *outdev = + container_of(output, struct intel_th_device, output); + struct intel_th_driver *outdrv = + to_intel_th_driver(outdev->dev.driver); + unsigned long count; + u32 reg; + u32 scr2 = 0xfc | (capture_done ? 1 : 0); + + iowrite32(0, gth->base + REG_GTH_SCR); + iowrite32(scr2, gth->base + REG_GTH_SCR2); + + /* wait on pipeline empty for the given port */ + for (reg = 0, count = GTH_PLE_WAITLOOP_DEPTH; + count && !(reg & BIT(output->port)); count--) { + reg = ioread32(gth->base + REG_GTH_STAT); + cpu_relax(); + } + + if (!count) + dev_dbg(gth->dev, "timeout waiting for GTH[%d] PLE\n", + output->port); + + /* wait on output piepline empty */ + if (outdrv->wait_empty) + outdrv->wait_empty(outdev); + + /* clear force capture done for next captures */ + iowrite32(0xfc, gth->base + REG_GTH_SCR2); +} + +/** + * intel_th_gth_start() - start tracing to an output device + * @gth: GTH device + * @output: output device's descriptor + * + * This will start tracing using force storeEn signal. + */ +static void intel_th_gth_start(struct gth_device *gth, + struct intel_th_output *output) +{ + u32 scr = 0xfc0000; + + if (output->multiblock) + scr |= 0xff; + + iowrite32(scr, gth->base + REG_GTH_SCR); + iowrite32(0, gth->base + REG_GTH_SCR2); +} + /** * intel_th_gth_disable() - disable tracing to an output device * @thdev: GTH device @@ -469,11 +531,6 @@ static void intel_th_gth_disable(struct intel_th_device *thdev, struct intel_th_output *output) { struct gth_device *gth = dev_get_drvdata(&thdev->dev); - struct intel_th_device *outdev = - container_of(output, struct intel_th_device, output); - struct intel_th_driver *outdrv = - to_intel_th_driver(outdev->dev.driver); - unsigned long count; int master; u32 reg; @@ -486,25 +543,7 @@ static void intel_th_gth_disable(struct intel_th_device *thdev, } spin_unlock(>h->gth_lock); - iowrite32(0, gth->base + REG_GTH_SCR); - iowrite32(0xfd, gth->base + REG_GTH_SCR2); - - /* wait on pipeline empty for the given port */ - for (reg = 0, count = GTH_PLE_WAITLOOP_DEPTH; - count && !(reg & BIT(output->port)); count--) { - reg = ioread32(gth->base + REG_GTH_STAT); - cpu_relax(); - } - - if (outdrv->wait_empty) - outdrv->wait_empty(outdev); - - /* clear force capture done for next captures */ - iowrite32(0xfc, gth->base + REG_GTH_SCR2); - - if (!count) - dev_dbg(&thdev->dev, "timeout waiting for GTH[%d] PLE\n", - output->port); + intel_th_gth_stop(gth, output, true); reg = ioread32(gth->base + REG_GTH_SCRPD0); reg &= ~output->scratchpad; @@ -533,8 +572,8 @@ static void intel_th_gth_enable(struct intel_th_device *thdev, { struct gth_device *gth = dev_get_drvdata(&thdev->dev); struct intel_th *th = to_intel_th(thdev); - u32 scr = 0xfc0000, scrpd; int master; + u32 scrpd; spin_lock(>h->gth_lock); for_each_set_bit(master, gth->output[output->port].master, @@ -542,9 +581,6 @@ static void intel_th_gth_enable(struct intel_th_device *thdev, gth_master_set(gth, master, output->port); } - if (output->multiblock) - scr |= 0xff; - output->active = true; spin_unlock(>h->gth_lock); @@ -555,8 +591,7 @@ static void intel_th_gth_enable(struct intel_th_device *thdev, scrpd |= output->scratchpad; iowrite32(scrpd, gth->base + REG_GTH_SCRPD0); - iowrite32(scr, gth->base + REG_GTH_SCR); - iowrite32(0, gth->base + REG_GTH_SCR2); + intel_th_gth_start(gth, output); } /** From 8116db57cf1618cb21dab957952e7bd1395430da Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:48 +0300 Subject: [PATCH 252/255] intel_th: Add switch triggering support Add support for asserting window switch trigger when tracing to MSU output ports. This allows for software controlled switching between windows of the MSU buffer, which can be used for double buffering while exporting the trace data further from the MSU. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/core.c | 25 ++++++++++++++++-- drivers/hwtracing/intel_th/gth.c | 37 +++++++++++++++++++++++++++ drivers/hwtracing/intel_th/gth.h | 19 ++++++++++++++ drivers/hwtracing/intel_th/intel_th.h | 6 +++++ 4 files changed, 85 insertions(+), 2 deletions(-) diff --git a/drivers/hwtracing/intel_th/core.c b/drivers/hwtracing/intel_th/core.c index 390031df3edf..033dce563c99 100644 --- a/drivers/hwtracing/intel_th/core.c +++ b/drivers/hwtracing/intel_th/core.c @@ -430,9 +430,9 @@ static const struct intel_th_subdevice { .nres = 1, .res = { { - /* Handle TSCU from GTH driver */ + /* Handle TSCU and CTS from GTH driver */ .start = REG_GTH_OFFSET, - .end = REG_TSCU_OFFSET + REG_TSCU_LENGTH - 1, + .end = REG_CTS_OFFSET + REG_CTS_LENGTH - 1, .flags = IORESOURCE_MEM, }, }, @@ -987,6 +987,27 @@ int intel_th_trace_enable(struct intel_th_device *thdev) } EXPORT_SYMBOL_GPL(intel_th_trace_enable); +/** + * intel_th_trace_switch() - execute a switch sequence + * @thdev: output device that requests tracing switch + */ +int intel_th_trace_switch(struct intel_th_device *thdev) +{ + struct intel_th_device *hub = to_intel_th_device(thdev->dev.parent); + struct intel_th_driver *hubdrv = to_intel_th_driver(hub->dev.driver); + + if (WARN_ON_ONCE(hub->type != INTEL_TH_SWITCH)) + return -EINVAL; + + if (WARN_ON_ONCE(thdev->type != INTEL_TH_OUTPUT)) + return -EINVAL; + + hubdrv->trig_switch(hub, &thdev->output); + + return 0; +} +EXPORT_SYMBOL_GPL(intel_th_trace_switch); + /** * intel_th_trace_disable() - disable tracing for an output device * @thdev: output device that requests tracing be disabled diff --git a/drivers/hwtracing/intel_th/gth.c b/drivers/hwtracing/intel_th/gth.c index a879445ef451..fa9d34af87ac 100644 --- a/drivers/hwtracing/intel_th/gth.c +++ b/drivers/hwtracing/intel_th/gth.c @@ -308,6 +308,11 @@ static int intel_th_gth_reset(struct gth_device *gth) iowrite32(0, gth->base + REG_GTH_SCR); iowrite32(0xfc, gth->base + REG_GTH_SCR2); + /* setup CTS for single trigger */ + iowrite32(CTS_EVENT_ENABLE_IF_ANYTHING, gth->base + REG_CTS_C0S0_EN); + iowrite32(CTS_ACTION_CONTROL_SET_STATE(CTS_STATE_IDLE) | + CTS_ACTION_CONTROL_TRIGGER, gth->base + REG_CTS_C0S0_ACT); + return 0; } @@ -594,6 +599,37 @@ static void intel_th_gth_enable(struct intel_th_device *thdev, intel_th_gth_start(gth, output); } +/** + * intel_th_gth_switch() - execute a switch sequence + * @thdev: GTH device + * @output: output device's descriptor + * + * This will execute a switch sequence that will trigger a switch window + * when tracing to MSC in multi-block mode. + */ +static void intel_th_gth_switch(struct intel_th_device *thdev, + struct intel_th_output *output) +{ + struct gth_device *gth = dev_get_drvdata(&thdev->dev); + unsigned long count; + u32 reg; + + /* trigger */ + iowrite32(0, gth->base + REG_CTS_CTL); + iowrite32(CTS_CTL_SEQUENCER_ENABLE, gth->base + REG_CTS_CTL); + /* wait on trigger status */ + for (reg = 0, count = CTS_TRIG_WAITLOOP_DEPTH; + count && !(reg & BIT(4)); count--) { + reg = ioread32(gth->base + REG_CTS_STAT); + cpu_relax(); + } + if (!count) + dev_dbg(&thdev->dev, "timeout waiting for CTS Trigger\n"); + + intel_th_gth_stop(gth, output, false); + intel_th_gth_start(gth, output); +} + /** * intel_th_gth_assign() - assign output device to a GTH output port * @thdev: GTH device @@ -777,6 +813,7 @@ static struct intel_th_driver intel_th_gth_driver = { .unassign = intel_th_gth_unassign, .set_output = intel_th_gth_set_output, .enable = intel_th_gth_enable, + .trig_switch = intel_th_gth_switch, .disable = intel_th_gth_disable, .driver = { .name = "gth", diff --git a/drivers/hwtracing/intel_th/gth.h b/drivers/hwtracing/intel_th/gth.h index 6f2b0b930875..bfcc0fd01177 100644 --- a/drivers/hwtracing/intel_th/gth.h +++ b/drivers/hwtracing/intel_th/gth.h @@ -49,6 +49,12 @@ enum { REG_GTH_SCRPD3 = 0xec, /* ScratchPad[3] */ REG_TSCU_TSUCTRL = 0x2000, /* TSCU control register */ REG_TSCU_TSCUSTAT = 0x2004, /* TSCU status register */ + + /* Common Capture Sequencer (CTS) registers */ + REG_CTS_C0S0_EN = 0x30c0, /* clause_event_enable_c0s0 */ + REG_CTS_C0S0_ACT = 0x3180, /* clause_action_control_c0s0 */ + REG_CTS_STAT = 0x32a0, /* cts_status */ + REG_CTS_CTL = 0x32a4, /* cts_control */ }; /* waiting for Pipeline Empty bit(s) to assert for GTH */ @@ -57,4 +63,17 @@ enum { #define TSUCTRL_CTCRESYNC BIT(0) #define TSCUSTAT_CTCSYNCING BIT(1) +/* waiting for Trigger status to assert for CTS */ +#define CTS_TRIG_WAITLOOP_DEPTH 10000 + +#define CTS_EVENT_ENABLE_IF_ANYTHING BIT(31) +#define CTS_ACTION_CONTROL_STATE_OFF 27 +#define CTS_ACTION_CONTROL_SET_STATE(x) \ + (((x) & 0x1f) << CTS_ACTION_CONTROL_STATE_OFF) +#define CTS_ACTION_CONTROL_TRIGGER BIT(4) + +#define CTS_STATE_IDLE 0x10u + +#define CTS_CTL_SEQUENCER_ENABLE BIT(0) + #endif /* __INTEL_TH_GTH_H__ */ diff --git a/drivers/hwtracing/intel_th/intel_th.h b/drivers/hwtracing/intel_th/intel_th.h index 74a6a4071e7f..0df480072b6c 100644 --- a/drivers/hwtracing/intel_th/intel_th.h +++ b/drivers/hwtracing/intel_th/intel_th.h @@ -164,6 +164,8 @@ struct intel_th_driver { struct intel_th_device *othdev); void (*enable)(struct intel_th_device *thdev, struct intel_th_output *output); + void (*trig_switch)(struct intel_th_device *thdev, + struct intel_th_output *output); void (*disable)(struct intel_th_device *thdev, struct intel_th_output *output); /* output ops */ @@ -228,6 +230,7 @@ int intel_th_driver_register(struct intel_th_driver *thdrv); void intel_th_driver_unregister(struct intel_th_driver *thdrv); int intel_th_trace_enable(struct intel_th_device *thdev); +int intel_th_trace_switch(struct intel_th_device *thdev); int intel_th_trace_disable(struct intel_th_device *thdev); int intel_th_set_output(struct intel_th_device *thdev, unsigned int master); @@ -308,6 +311,9 @@ enum { REG_TSCU_OFFSET = 0x2000, REG_TSCU_LENGTH = 0x1000, + REG_CTS_OFFSET = 0x3000, + REG_CTS_LENGTH = 0x1000, + /* Software Trace Hub (STH) [0x4000..0x4fff] */ REG_STH_OFFSET = 0x4000, REG_STH_LENGTH = 0x2000, From 4840572d3d7e66d7b55d3fc3b0f52711fd172eb8 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:49 +0300 Subject: [PATCH 253/255] intel_th: msu: Correct the block wrap detection In multi window mode the MSU will set "window wrap" bit to indicate block wrapping as well. Take this into account when checking data blocks. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/msu.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwtracing/intel_th/msu.h b/drivers/hwtracing/intel_th/msu.h index e8cb819a3804..574c16004cb2 100644 --- a/drivers/hwtracing/intel_th/msu.h +++ b/drivers/hwtracing/intel_th/msu.h @@ -95,7 +95,7 @@ static inline unsigned long msc_data_sz(struct msc_block_desc *bdesc) static inline bool msc_block_wrapped(struct msc_block_desc *bdesc) { - if (bdesc->hw_tag & MSC_HW_TAG_BLOCKWRAP) + if (bdesc->hw_tag & (MSC_HW_TAG_BLOCKWRAP | MSC_HW_TAG_WINWRAP)) return true; return false; From 6cac7866c27418cd784fbb8041c2dddd6d966bc7 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:50 +0300 Subject: [PATCH 254/255] intel_th: msu: Add a sysfs attribute to trigger window switch Now that we have the means to trigger a window switch for the MSU trace store, add a sysfs file to allow triggering it from userspace. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- .../testing/sysfs-bus-intel_th-devices-msc | 8 ++++++ drivers/hwtracing/intel_th/msu.c | 28 +++++++++++++++++++ 2 files changed, 36 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc b/Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc index b940c5d91cf7..f54ae244f3f1 100644 --- a/Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc +++ b/Documentation/ABI/testing/sysfs-bus-intel_th-devices-msc @@ -30,4 +30,12 @@ Description: (RW) Configure MSC buffer size for "single" or "multi" modes. there are no active users and tracing is not enabled) and then allocates a new one. +What: /sys/bus/intel_th/devices/-msc/win_switch +Date: May 2019 +KernelVersion: 5.2 +Contact: Alexander Shishkin +Description: (RW) Trigger window switch for the MSC's buffer, in + multi-window mode. In "multi" mode, accepts writes of "1", thereby + triggering a window switch for the buffer. Returns an error in any + other operating mode or attempts to write something other than "1". diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index b0bb69942328..aed72b33675d 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -1572,10 +1572,38 @@ nr_pages_store(struct device *dev, struct device_attribute *attr, static DEVICE_ATTR_RW(nr_pages); +static ssize_t +win_switch_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t size) +{ + struct msc *msc = dev_get_drvdata(dev); + unsigned long val; + int ret; + + ret = kstrtoul(buf, 10, &val); + if (ret) + return ret; + + if (val != 1) + return -EINVAL; + + mutex_lock(&msc->buf_mutex); + if (msc->mode != MSC_MODE_MULTI) + ret = -ENOTSUPP; + else + ret = intel_th_trace_switch(msc->thdev); + mutex_unlock(&msc->buf_mutex); + + return ret ? ret : size; +} + +static DEVICE_ATTR_WO(win_switch); + static struct attribute *msc_output_attrs[] = { &dev_attr_wrap.attr, &dev_attr_mode.attr, &dev_attr_nr_pages.attr, + &dev_attr_win_switch.attr, NULL, }; From aad14ad3cf3a63bd258b65e18d49c3eb8472d344 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:44:51 +0300 Subject: [PATCH 255/255] intel_th: msu: Add current window tracking Now that we have a way to switch between MSC buffer windows, add code to track the current window. The hardware register NWSA that contains the address of the next window is unfortunately not always usable, and since the driver has full control of the window switching, there is no reason not to keep this on the software side. Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- drivers/hwtracing/intel_th/msu.c | 79 ++++++++++++++++++++------------ 1 file changed, 49 insertions(+), 30 deletions(-) diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c index aed72b33675d..81bb54fa3ce8 100644 --- a/drivers/hwtracing/intel_th/msu.c +++ b/drivers/hwtracing/intel_th/msu.c @@ -75,6 +75,7 @@ struct msc_iter { * @thdev: intel_th_device pointer * @win_list: list of windows in multiblock mode * @single_sgt: single mode buffer + * @cur_win: current window * @nr_pages: total number of pages allocated for this buffer * @single_sz: amount of data in single mode * @single_wrap: single mode wrap occurred @@ -97,6 +98,7 @@ struct msc { struct list_head win_list; struct sg_table single_sgt; + struct msc_window *cur_win; unsigned long nr_pages; unsigned long single_sz; unsigned int single_wrap : 1; @@ -151,6 +153,31 @@ msc_win_bpfn(struct msc_window *win, unsigned int block) return msc_win_baddr(win, block) >> PAGE_SHIFT; } +/** + * msc_is_last_win() - check if a window is the last one for a given MSC + * @win: window + * Return: true if @win is the last window in MSC's multiblock buffer + */ +static inline bool msc_is_last_win(struct msc_window *win) +{ + return win->entry.next == &win->msc->win_list; +} + +/** + * msc_next_window() - return next window in the multiblock buffer + * @win: current window + * + * Return: window following the current one + */ +static struct msc_window *msc_next_window(struct msc_window *win) +{ + if (msc_is_last_win(win)) + return list_first_entry(&win->msc->win_list, struct msc_window, + entry); + + return list_next_entry(win, entry); +} + /** * msc_oldest_window() - locate the window with oldest data * @msc: MSC device @@ -162,9 +189,7 @@ msc_win_bpfn(struct msc_window *win, unsigned int block) */ static struct msc_window *msc_oldest_window(struct msc *msc) { - struct msc_window *win; - u32 reg = ioread32(msc->reg_base + REG_MSU_MSC0NWSA); - unsigned long win_addr = (unsigned long)reg << PAGE_SHIFT; + struct msc_window *win, *next = msc_next_window(msc->cur_win); unsigned int found = 0; if (list_empty(&msc->win_list)) @@ -176,7 +201,7 @@ static struct msc_window *msc_oldest_window(struct msc *msc) * something like 2, in which case we're good */ list_for_each_entry(win, &msc->win_list, entry) { - if (sg_dma_address(win->sgt.sgl) == win_addr) + if (win == next) found++; /* skip the empty ones */ @@ -219,31 +244,6 @@ static unsigned int msc_win_oldest_block(struct msc_window *win) return 0; } -/** - * msc_is_last_win() - check if a window is the last one for a given MSC - * @win: window - * Return: true if @win is the last window in MSC's multiblock buffer - */ -static inline bool msc_is_last_win(struct msc_window *win) -{ - return win->entry.next == &win->msc->win_list; -} - -/** - * msc_next_window() - return next window in the multiblock buffer - * @win: current window - * - * Return: window following the current one - */ -static struct msc_window *msc_next_window(struct msc_window *win) -{ - if (msc_is_last_win(win)) - return list_first_entry(&win->msc->win_list, struct msc_window, - entry); - - return list_next_entry(win, entry); -} - static struct msc_block_desc *msc_iter_bdesc(struct msc_iter *iter) { return msc_win_block(iter->win, iter->block); @@ -822,6 +822,7 @@ static int msc_buffer_win_alloc(struct msc *msc, unsigned int nr_blocks) if (list_empty(&msc->win_list)) { msc->base = msc_win_block(win, 0); msc->base_addr = msc_win_baddr(win, 0); + msc->cur_win = win; } list_add_tail(&win->entry, &msc->win_list); @@ -1383,6 +1384,24 @@ static int intel_th_msc_init(struct msc *msc) return 0; } +static void msc_win_switch(struct msc *msc) +{ + struct msc_window *last, *first; + + first = list_first_entry(&msc->win_list, struct msc_window, entry); + last = list_last_entry(&msc->win_list, struct msc_window, entry); + + if (msc_is_last_win(msc->cur_win)) + msc->cur_win = first; + else + msc->cur_win = list_next_entry(msc->cur_win, entry); + + msc->base = msc_win_block(msc->cur_win, 0); + msc->base_addr = msc_win_baddr(msc->cur_win, 0); + + intel_th_trace_switch(msc->thdev); +} + static irqreturn_t intel_th_msc_interrupt(struct intel_th_device *thdev) { struct msc *msc = dev_get_drvdata(&thdev->dev); @@ -1591,7 +1610,7 @@ win_switch_store(struct device *dev, struct device_attribute *attr, if (msc->mode != MSC_MODE_MULTI) ret = -ENOTSUPP; else - ret = intel_th_trace_switch(msc->thdev); + msc_win_switch(msc); mutex_unlock(&msc->buf_mutex); return ret ? ret : size;