* [PATCH 2/4] habanalabs/gaudi: Update async events header
2021-03-14 12:59 [PATCH 1/4] habanalabs/gaudi: unsecure TPC cfg status registers Oded Gabbay
@ 2021-03-14 12:59 ` Oded Gabbay
2021-03-14 12:59 ` [PATCH 3/4] habanalabs: avoid soft lockup bug upon mapping error Oded Gabbay
2021-03-14 12:59 ` [PATCH 4/4] habanalabs: support dynamic PLL numbering Oded Gabbay
2 siblings, 0 replies; 4+ messages in thread
From: Oded Gabbay @ 2021-03-14 12:59 UTC (permalink / raw)
To: linux-kernel; +Cc: Ofir Bitton
From: Ofir Bitton <obitton@habana.ai>
Update with latest version from the Firmware team.
Signed-off-by: Ofir Bitton <obitton@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
drivers/misc/habanalabs/gaudi/gaudi.c | 2 +-
.../include/gaudi/gaudi_async_events.h | 2 +-
.../gaudi/gaudi_async_ids_map_extended.h | 35 ++++++++++++-------
3 files changed, 25 insertions(+), 14 deletions(-)
diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c
index 0bcee675e1db..a65ae0dbdb92 100644
--- a/drivers/misc/habanalabs/gaudi/gaudi.c
+++ b/drivers/misc/habanalabs/gaudi/gaudi.c
@@ -7574,7 +7574,7 @@ static void gaudi_handle_eqe(struct hl_device *hdev,
event_type, cause);
break;
- case GAUDI_EVENT_BMC_RESET_CMD:
+ case GAUDI_EVENT_DEV_RESET_REQ:
gaudi_print_irq_info(hdev, event_type, false);
goto reset_device;
diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h b/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h
index 25f835ba2cd6..e8651abf84f2 100644
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_async_events.h
@@ -303,7 +303,7 @@ enum gaudi_async_event_id {
GAUDI_EVENT_NIC3_QP1 = 619,
GAUDI_EVENT_NIC4_QP0 = 620,
GAUDI_EVENT_NIC4_QP1 = 621,
- GAUDI_EVENT_BMC_RESET_CMD = 646,
+ GAUDI_EVENT_DEV_RESET_REQ = 646,
GAUDI_EVENT_PKT_QUEUE_OUT_SYNC = 647,
GAUDI_EVENT_FIX_POWER_ENV_S = 658,
GAUDI_EVENT_FIX_POWER_ENV_E = 659,
diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_async_ids_map_extended.h b/drivers/misc/habanalabs/include/gaudi/gaudi_async_ids_map_extended.h
index 079be1fb8f70..3dc79c131805 100644
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_async_ids_map_extended.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_async_ids_map_extended.h
@@ -670,18 +670,29 @@ static struct gaudi_async_events_ids_map gaudi_irq_map_table[] = {
{ .fc_id = 643, .cpu_id = 492, .valid = 0, .name = "" },
{ .fc_id = 644, .cpu_id = 493, .valid = 0, .name = "" },
{ .fc_id = 645, .cpu_id = 494, .valid = 0, .name = "" },
- { .fc_id = 646, .cpu_id = 495, .valid = 1, .name = "BMC_RST_CMD" },
- { .fc_id = 647, .cpu_id = 496, .valid = 0, .name = "" },
- { .fc_id = 648, .cpu_id = 497, .valid = 0, .name = "" },
- { .fc_id = 649, .cpu_id = 498, .valid = 0, .name = "" },
- { .fc_id = 650, .cpu_id = 499, .valid = 0, .name = "" },
- { .fc_id = 651, .cpu_id = 500, .valid = 0, .name = "" },
- { .fc_id = 652, .cpu_id = 501, .valid = 0, .name = "" },
- { .fc_id = 653, .cpu_id = 502, .valid = 0, .name = "" },
- { .fc_id = 654, .cpu_id = 503, .valid = 0, .name = "" },
- { .fc_id = 655, .cpu_id = 504, .valid = 0, .name = "" },
- { .fc_id = 656, .cpu_id = 505, .valid = 0, .name = "" },
- { .fc_id = 657, .cpu_id = 506, .valid = 1, .name = "PKT_QUEUE_ASYNC" },
+ { .fc_id = 646, .cpu_id = 495, .valid = 1, .name = "DEV_RESET_REQ" },
+ { .fc_id = 647, .cpu_id = 496, .valid = 1,
+ .name = "PKT_QUEUE_OUT_SYNC" },
+ { .fc_id = 648, .cpu_id = 497, .valid = 1,
+ .name = "STATUS_NIC0_ENG0" },
+ { .fc_id = 649, .cpu_id = 498, .valid = 1,
+ .name = "STATUS_NIC0_ENG1" },
+ { .fc_id = 650, .cpu_id = 499, .valid = 1,
+ .name = "STATUS_NIC1_ENG0" },
+ { .fc_id = 651, .cpu_id = 500, .valid = 1,
+ .name = "STATUS_NIC1_ENG1" },
+ { .fc_id = 652, .cpu_id = 501, .valid = 1,
+ .name = "STATUS_NIC2_ENG0" },
+ { .fc_id = 653, .cpu_id = 502, .valid = 1,
+ .name = "STATUS_NIC2_ENG1" },
+ { .fc_id = 654, .cpu_id = 503, .valid = 1,
+ .name = "STATUS_NIC3_ENG0" },
+ { .fc_id = 655, .cpu_id = 504, .valid = 1,
+ .name = "STATUS_NIC3_ENG1" },
+ { .fc_id = 656, .cpu_id = 505, .valid = 1,
+ .name = "STATUS_NIC4_ENG0" },
+ { .fc_id = 657, .cpu_id = 506, .valid = 1,
+ .name = "STATUS_NIC4_ENG1" },
{ .fc_id = 658, .cpu_id = 507, .valid = 1, .name = "FIX_POWER_ENV_S" },
{ .fc_id = 659, .cpu_id = 508, .valid = 1, .name = "FIX_POWER_ENV_E" },
{ .fc_id = 660, .cpu_id = 509, .valid = 1,
--
2.25.1
^ permalink raw reply related [flat|nested] 4+ messages in thread* [PATCH 3/4] habanalabs: avoid soft lockup bug upon mapping error
2021-03-14 12:59 [PATCH 1/4] habanalabs/gaudi: unsecure TPC cfg status registers Oded Gabbay
2021-03-14 12:59 ` [PATCH 2/4] habanalabs/gaudi: Update async events header Oded Gabbay
@ 2021-03-14 12:59 ` Oded Gabbay
2021-03-14 12:59 ` [PATCH 4/4] habanalabs: support dynamic PLL numbering Oded Gabbay
2 siblings, 0 replies; 4+ messages in thread
From: Oded Gabbay @ 2021-03-14 12:59 UTC (permalink / raw)
To: linux-kernel; +Cc: farah kassabri
From: farah kassabri <fkassabri@habana.ai>
Add a little sleep between page unmappings in case mapping of
large number of host pages failed, in order to
avoid soft lockup bug during the rollback.
Signed-off-by: farah kassabri <fkassabri@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
drivers/misc/habanalabs/common/memory.c | 20 +++++++++++++++++---
1 file changed, 17 insertions(+), 3 deletions(-)
diff --git a/drivers/misc/habanalabs/common/memory.c b/drivers/misc/habanalabs/common/memory.c
index 1b69573369cf..6530fddbbc21 100644
--- a/drivers/misc/habanalabs/common/memory.c
+++ b/drivers/misc/habanalabs/common/memory.c
@@ -857,6 +857,7 @@ static int map_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
u64 next_vaddr = vaddr, paddr, mapped_pg_cnt = 0, i;
u32 page_size = phys_pg_pack->page_size;
int rc = 0;
+ bool is_host_addr;
for (i = 0 ; i < phys_pg_pack->npages ; i++) {
paddr = phys_pg_pack->pages[i];
@@ -878,6 +879,8 @@ static int map_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
return 0;
err:
+ is_host_addr = !hl_is_dram_va(hdev, vaddr);
+
next_vaddr = vaddr;
for (i = 0 ; i < mapped_pg_cnt ; i++) {
if (hl_mmu_unmap_page(ctx, next_vaddr, page_size,
@@ -888,6 +891,17 @@ static int map_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
phys_pg_pack->pages[i], page_size);
next_vaddr += page_size;
+
+ /*
+ * unmapping on Palladium can be really long, so avoid a CPU
+ * soft lockup bug by sleeping a little between unmapping pages
+ *
+ * In addition, on host num of pages could be huge,
+ * because page size could be 4KB, so when unmapping host
+ * pages sleep every 32K pages to avoid soft lockup
+ */
+ if (hdev->pldm || (is_host_addr && (i & 0x7FFF) == 0))
+ usleep_range(50, 200);
}
return rc;
@@ -921,9 +935,9 @@ static void unmap_phys_pg_pack(struct hl_ctx *ctx, u64 vaddr,
* unmapping on Palladium can be really long, so avoid a CPU
* soft lockup bug by sleeping a little between unmapping pages
*
- * In addition, when unmapping host memory we pass through
- * the Linux kernel to unpin the pages and that takes a long
- * time. Therefore, sleep every 32K pages to avoid soft lockup
+ * In addition, on host num of pages could be huge,
+ * because page size could be 4KB, so when unmapping host
+ * pages sleep every 32K pages to avoid soft lockup
*/
if (hdev->pldm || (is_host_addr && (i & 0x7FFF) == 0))
usleep_range(50, 200);
--
2.25.1
^ permalink raw reply related [flat|nested] 4+ messages in thread* [PATCH 4/4] habanalabs: support dynamic PLL numbering
2021-03-14 12:59 [PATCH 1/4] habanalabs/gaudi: unsecure TPC cfg status registers Oded Gabbay
2021-03-14 12:59 ` [PATCH 2/4] habanalabs/gaudi: Update async events header Oded Gabbay
2021-03-14 12:59 ` [PATCH 3/4] habanalabs: avoid soft lockup bug upon mapping error Oded Gabbay
@ 2021-03-14 12:59 ` Oded Gabbay
2 siblings, 0 replies; 4+ messages in thread
From: Oded Gabbay @ 2021-03-14 12:59 UTC (permalink / raw)
To: linux-kernel; +Cc: Ohad Sharabi
From: Ohad Sharabi <osharabi@habana.ai>
As part of the effort remove hard-coded assumptions from the F/W-driver
communication, introduce support for dynamic pll numbering.
Signed-off-by: Ohad Sharabi <osharabi@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
---
drivers/misc/habanalabs/common/firmware_if.c | 22 +++++++++-
drivers/misc/habanalabs/common/habanalabs.h | 2 +-
.../misc/habanalabs/include/common/cpucp_if.h | 41 +++++++++++++++++++
.../habanalabs/include/gaudi/gaudi_fw_if.h | 14 -------
.../misc/habanalabs/include/goya/goya_fw_if.h | 11 -----
5 files changed, 62 insertions(+), 28 deletions(-)
diff --git a/drivers/misc/habanalabs/common/firmware_if.c b/drivers/misc/habanalabs/common/firmware_if.c
index 2a58edaf984a..8843e040c660 100644
--- a/drivers/misc/habanalabs/common/firmware_if.c
+++ b/drivers/misc/habanalabs/common/firmware_if.c
@@ -539,18 +539,36 @@ int hl_fw_cpucp_total_energy_get(struct hl_device *hdev, u64 *total_energy)
return rc;
}
-int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, u16 pll_index,
+int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, enum pll_index pll_index,
u16 *pll_freq_arr)
{
+ struct asic_fixed_properties *prop = &hdev->asic_prop;
+ u8 pll_byte, pll_bit_off;
struct cpucp_packet pkt;
u64 result;
int rc;
+ if (pll_index >= PLL_MAX) {
+ dev_err(hdev->dev, "PLL index %d is out of range\n",
+ pll_index);
+ return -EINVAL;
+ }
+
+ /* PLL map is a u8 array */
+ pll_byte = prop->cpucp_info.pll_map[pll_index >> 3];
+ pll_bit_off = pll_index & 0x7;
+
+ if (!(pll_byte & BIT(pll_bit_off))) {
+ dev_err(hdev->dev, "PLL index %d is not supported\n",
+ pll_index);
+ return -EINVAL;
+ }
+
memset(&pkt, 0, sizeof(pkt));
pkt.ctl = cpu_to_le32(CPUCP_PACKET_PLL_INFO_GET <<
CPUCP_PKT_CTL_OPCODE_SHIFT);
- pkt.pll_type = __cpu_to_le16(pll_index);
+ pkt.pll_type = __cpu_to_le16((u16)pll_index);
rc = hdev->asic_funcs->send_cpu_message(hdev, (u32 *) &pkt, sizeof(pkt),
HL_CPUCP_INFO_TIMEOUT_USEC, &result);
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 2dcefd6485e5..5f930cb5e33d 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -2379,7 +2379,7 @@ int hl_fw_cpucp_pci_counters_get(struct hl_device *hdev,
struct hl_info_pci_counters *counters);
int hl_fw_cpucp_total_energy_get(struct hl_device *hdev,
u64 *total_energy);
-int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, u16 pll_index,
+int hl_fw_cpucp_pll_info_get(struct hl_device *hdev, enum pll_index pll_index,
u16 *pll_freq_arr);
int hl_fw_cpucp_power_get(struct hl_device *hdev, u64 *power);
int hl_fw_init_cpu(struct hl_device *hdev, u32 cpu_boot_status_reg,
diff --git a/drivers/misc/habanalabs/include/common/cpucp_if.h b/drivers/misc/habanalabs/include/common/cpucp_if.h
index 6ba480a316ce..e745c78dd8fd 100644
--- a/drivers/misc/habanalabs/include/common/cpucp_if.h
+++ b/drivers/misc/habanalabs/include/common/cpucp_if.h
@@ -28,6 +28,9 @@
#define CPUCP_PKT_HBM_ECC_INFO_HBM_CH_SHIFT 6
#define CPUCP_PKT_HBM_ECC_INFO_HBM_CH_MASK 0x000007C0
+#define PLL_MAP_MAX_BITS 128
+#define PLL_MAP_LEN (PLL_MAP_MAX_BITS / 8)
+
/*
* info of the pkt queue pointers in the first async occurrence
*/
@@ -473,6 +476,42 @@ enum cpucp_pll_type_attributes {
cpucp_pll_pci,
};
+/*
+ * PLL enumeration table used for all ASICs and future SW versions.
+ * For future ASIC-LKD compatibility, we can only add new enumerations.
+ * at the end of the table.
+ * Changing the order of entries or removing entries is not allowed.
+ */
+enum pll_index {
+ CPU_PLL = 0,
+ PCI_PLL = 1,
+ NIC_PLL = 2,
+ DMA_PLL = 3,
+ MESH_PLL = 4,
+ MME_PLL = 5,
+ TPC_PLL = 6,
+ IF_PLL = 7,
+ SRAM_PLL = 8,
+ NS_DCORE_PLL = 9,
+ MESH_DCORE_PLL = 10,
+ HBM_PLL = 11,
+ TPC_DCORE_PLL = 12,
+ VIDEO_DCORE_PLL = 13,
+ SRAM_DCORE_PLL = 14,
+ NIC_PHY_DCORE_PLL = 15,
+ MSS_DCORE_PLL = 16,
+ DMA_DCORE_PLL = 17,
+ SIF_PLL = 18,
+ DDR_PLL = 19,
+ VID_PLL = 20,
+ BANK_PLL = 21,
+ MMU_PLL = 22,
+ IC_PLL = 23,
+ MC_PLL = 24,
+ EMMC_PLL = 25,
+ PLL_MAX
+};
+
/* Event Queue Packets */
struct eq_generic_event {
@@ -547,6 +586,7 @@ struct cpucp_security_info {
* @dram_size: available DRAM size.
* @card_name: card name that will be displayed in HWMON subsystem on the host
* @sec_info: security information
+ * @pll_map: Bit map of supported PLLs for current ASIC version.
*/
struct cpucp_info {
struct cpucp_sensor sensors[CPUCP_MAX_SENSORS];
@@ -568,6 +608,7 @@ struct cpucp_info {
__u8 pad[7];
struct cpucp_security_info sec_info;
__le32 reserved6;
+ uint8_t pll_map[PLL_MAP_LEN];
};
struct cpucp_mac_addr {
diff --git a/drivers/misc/habanalabs/include/gaudi/gaudi_fw_if.h b/drivers/misc/habanalabs/include/gaudi/gaudi_fw_if.h
index 25acd9e87e20..a9f51f9f9e92 100644
--- a/drivers/misc/habanalabs/include/gaudi/gaudi_fw_if.h
+++ b/drivers/misc/habanalabs/include/gaudi/gaudi_fw_if.h
@@ -20,20 +20,6 @@
#define UBOOT_FW_OFFSET 0x100000 /* 1MB in SRAM */
#define LINUX_FW_OFFSET 0x800000 /* 8MB in HBM */
-enum gaudi_pll_index {
- CPU_PLL = 0,
- PCI_PLL,
- SRAM_PLL,
- HBM_PLL,
- NIC_PLL,
- DMA_PLL,
- MESH_PLL,
- MME_PLL,
- TPC_PLL,
- IF_PLL,
- PLL_MAX
-};
-
enum gaudi_nic_axi_error {
RXB,
RXE,
diff --git a/drivers/misc/habanalabs/include/goya/goya_fw_if.h b/drivers/misc/habanalabs/include/goya/goya_fw_if.h
index daf8d8cd14be..bc05f86c73ac 100644
--- a/drivers/misc/habanalabs/include/goya/goya_fw_if.h
+++ b/drivers/misc/habanalabs/include/goya/goya_fw_if.h
@@ -15,17 +15,6 @@
#define UBOOT_FW_OFFSET 0x100000 /* 1MB in SRAM */
#define LINUX_FW_OFFSET 0x800000 /* 8MB in DDR */
-enum goya_pll_index {
- CPU_PLL = 0,
- IC_PLL,
- MC_PLL,
- MME_PLL,
- PCI_PLL,
- EMMC_PLL,
- TPC_PLL,
- PLL_MAX
-};
-
#define GOYA_PLL_FREQ_LOW 50000000 /* 50 MHz */
#endif /* GOYA_FW_IF_H */
--
2.25.1
^ permalink raw reply related [flat|nested] 4+ messages in thread