From d2ccde1c8e90d38cee87a1b0309ad2827f3fd30d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 11 Dec 2023 02:45:28 +0000
Subject: [PATCH] add boot partition size
---
kernel/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c | 217 ++++++++++++++++++++++++++---------------------------
1 files changed, 107 insertions(+), 110 deletions(-)
diff --git a/kernel/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/kernel/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 358004a..873bc33 100644
--- a/kernel/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/kernel/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -20,13 +20,17 @@
* OTHER DEALINGS IN THE SOFTWARE.
*
*/
+
#include <linux/firmware.h>
-#include <drm/drmP.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
#include <drm/drm_cache.h>
#include "amdgpu.h"
#include "gmc_v8_0.h"
#include "amdgpu_ucode.h"
#include "amdgpu_amdkfd.h"
+#include "amdgpu_gem.h"
#include "gmc/gmc_8_1_d.h"
#include "gmc/gmc_8_1_sh_mask.h"
@@ -288,7 +292,7 @@
*
* @adev: amdgpu_device pointer
*
- * Load the GDDR MC ucode into the hw (CIK).
+ * Load the GDDR MC ucode into the hw (VI).
* Returns 0 on success, error on failure.
*/
static int gmc_v8_0_tonga_mc_load_microcode(struct amdgpu_device *adev)
@@ -432,8 +436,8 @@
base = RREG32(mmMC_VM_FB_LOCATION) & 0xFFFF;
base <<= 24;
- amdgpu_device_vram_location(adev, &adev->gmc, base);
- amdgpu_device_gart_location(adev, mc);
+ amdgpu_gmc_vram_location(adev, mc, base);
+ amdgpu_gmc_gart_location(adev, mc);
}
/**
@@ -442,7 +446,7 @@
* @adev: amdgpu_device pointer
*
* Set the location of vram, gart, and AGP in the GPU's
- * physical address space (CIK).
+ * physical address space (VI).
*/
static void gmc_v8_0_mc_program(struct amdgpu_device *adev)
{
@@ -514,7 +518,7 @@
* @adev: amdgpu_device pointer
*
* Look up the amount of vram, vram width, and decide how to place
- * vram and gart within the GPU's physical address space (CIK).
+ * vram and gart within the GPU's physical address space (VI).
* Returns 0 for success.
*/
static int gmc_v8_0_mc_init(struct amdgpu_device *adev)
@@ -623,6 +627,39 @@
return 0;
}
+/**
+ * gmc_v8_0_flush_gpu_tlb_pasid - tlb flush via pasid
+ *
+ * @adev: amdgpu_device pointer
+ * @pasid: pasid to be flush
+ *
+ * Flush the TLB for the requested pasid.
+ */
+static int gmc_v8_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
+ uint16_t pasid, uint32_t flush_type,
+ bool all_hub)
+{
+ int vmid;
+ unsigned int tmp;
+
+ if (amdgpu_in_reset(adev))
+ return -EIO;
+
+ for (vmid = 1; vmid < 16; vmid++) {
+
+ tmp = RREG32(mmATC_VMID0_PASID_MAPPING + vmid);
+ if ((tmp & ATC_VMID0_PASID_MAPPING__VALID_MASK) &&
+ (tmp & ATC_VMID0_PASID_MAPPING__PASID_MASK) == pasid) {
+ WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
+ RREG32(mmVM_INVALIDATE_RESPONSE);
+ break;
+ }
+ }
+
+ return 0;
+
+}
+
/*
* GART
* VMID 0 is the physical GPU addresses as used by the kernel.
@@ -636,10 +673,10 @@
* @adev: amdgpu_device pointer
* @vmid: vm instance to flush
*
- * Flush the TLB for the requested page table (CIK).
+ * Flush the TLB for the requested page table (VI).
*/
-static void gmc_v8_0_flush_gpu_tlb(struct amdgpu_device *adev,
- uint32_t vmid)
+static void gmc_v8_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
+ uint32_t vmhub, uint32_t flush_type)
{
/* bits 0-15 are the VM contexts0-15 */
WREG32(mmVM_INVALIDATE_REQUEST, 1 << vmid);
@@ -668,72 +705,40 @@
amdgpu_ring_emit_wreg(ring, mmIH_VMID_0_LUT + vmid, pasid);
}
-/**
- * gmc_v8_0_set_pte_pde - update the page tables using MMIO
+/*
+ * PTE format on VI:
+ * 63:40 reserved
+ * 39:12 4k physical page base address
+ * 11:7 fragment
+ * 6 write
+ * 5 read
+ * 4 exe
+ * 3 reserved
+ * 2 snooped
+ * 1 system
+ * 0 valid
*
- * @adev: amdgpu_device pointer
- * @cpu_pt_addr: cpu address of the page table
- * @gpu_page_idx: entry in the page table to update
- * @addr: dst addr to write into pte/pde
- * @flags: access flags
- *
- * Update the page tables using the CPU.
+ * PDE format on VI:
+ * 63:59 block fragment size
+ * 58:40 reserved
+ * 39:1 physical base address of PTE
+ * bits 5:1 must be 0.
+ * 0 valid
*/
-static int gmc_v8_0_set_pte_pde(struct amdgpu_device *adev, void *cpu_pt_addr,
- uint32_t gpu_page_idx, uint64_t addr,
- uint64_t flags)
-{
- void __iomem *ptr = (void *)cpu_pt_addr;
- uint64_t value;
-
- /*
- * PTE format on VI:
- * 63:40 reserved
- * 39:12 4k physical page base address
- * 11:7 fragment
- * 6 write
- * 5 read
- * 4 exe
- * 3 reserved
- * 2 snooped
- * 1 system
- * 0 valid
- *
- * PDE format on VI:
- * 63:59 block fragment size
- * 58:40 reserved
- * 39:1 physical base address of PTE
- * bits 5:1 must be 0.
- * 0 valid
- */
- value = addr & 0x000000FFFFFFF000ULL;
- value |= flags;
- writeq(value, ptr + (gpu_page_idx * 8));
-
- return 0;
-}
-
-static uint64_t gmc_v8_0_get_vm_pte_flags(struct amdgpu_device *adev,
- uint32_t flags)
-{
- uint64_t pte_flag = 0;
-
- if (flags & AMDGPU_VM_PAGE_EXECUTABLE)
- pte_flag |= AMDGPU_PTE_EXECUTABLE;
- if (flags & AMDGPU_VM_PAGE_READABLE)
- pte_flag |= AMDGPU_PTE_READABLE;
- if (flags & AMDGPU_VM_PAGE_WRITEABLE)
- pte_flag |= AMDGPU_PTE_WRITEABLE;
- if (flags & AMDGPU_VM_PAGE_PRT)
- pte_flag |= AMDGPU_PTE_PRT;
-
- return pte_flag;
-}
static void gmc_v8_0_get_vm_pde(struct amdgpu_device *adev, int level,
uint64_t *addr, uint64_t *flags)
{
BUG_ON(*addr & 0xFFFFFF0000000FFFULL);
+}
+
+static void gmc_v8_0_get_vm_pte(struct amdgpu_device *adev,
+ struct amdgpu_bo_va_mapping *mapping,
+ uint64_t *flags)
+{
+ *flags &= ~AMDGPU_PTE_EXECUTABLE;
+ *flags |= mapping->flags & AMDGPU_PTE_EXECUTABLE;
+ *flags &= ~AMDGPU_PTE_PRT;
}
/**
@@ -830,21 +835,25 @@
* This sets up the TLBs, programs the page tables for VMID0,
* sets up the hw for VMIDs 1-15 which are allocated on
* demand, and sets up the global locations for the LDS, GDS,
- * and GPUVM for FSA64 clients (CIK).
+ * and GPUVM for FSA64 clients (VI).
* Returns 0 for success, errors for failure.
*/
static int gmc_v8_0_gart_enable(struct amdgpu_device *adev)
{
+ uint64_t table_addr;
int r, i;
u32 tmp, field;
- if (adev->gart.robj == NULL) {
+ if (adev->gart.bo == NULL) {
dev_err(adev->dev, "No VRAM object for PCIE GART.\n");
return -EINVAL;
}
r = amdgpu_gart_table_vram_pin(adev);
if (r)
return r;
+
+ table_addr = amdgpu_bo_gpu_offset(adev->gart.bo);
+
/* Setup TLB control */
tmp = RREG32(mmMC_VM_MX_L1_TLB_CNTL);
tmp = REG_SET_FIELD(tmp, MC_VM_MX_L1_TLB_CNTL, ENABLE_L1_TLB, 1);
@@ -892,7 +901,7 @@
/* setup context0 */
WREG32(mmVM_CONTEXT0_PAGE_TABLE_START_ADDR, adev->gmc.gart_start >> 12);
WREG32(mmVM_CONTEXT0_PAGE_TABLE_END_ADDR, adev->gmc.gart_end >> 12);
- WREG32(mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR, adev->gart.table_addr >> 12);
+ WREG32(mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR, table_addr >> 12);
WREG32(mmVM_CONTEXT0_PROTECTION_FAULT_DEFAULT_ADDR,
(u32)(adev->dummy_page_addr >> 12));
WREG32(mmVM_CONTEXT0_CNTL2, 0);
@@ -916,10 +925,10 @@
for (i = 1; i < 16; i++) {
if (i < 8)
WREG32(mmVM_CONTEXT0_PAGE_TABLE_BASE_ADDR + i,
- adev->gart.table_addr >> 12);
+ table_addr >> 12);
else
WREG32(mmVM_CONTEXT8_PAGE_TABLE_BASE_ADDR + i - 8,
- adev->gart.table_addr >> 12);
+ table_addr >> 12);
}
/* enable context1-15 */
@@ -944,10 +953,10 @@
else
gmc_v8_0_set_fault_enable_default(adev, true);
- gmc_v8_0_flush_gpu_tlb(adev, 0);
+ gmc_v8_0_flush_gpu_tlb(adev, 0, 0, 0);
DRM_INFO("PCIE GART of %uM enabled (table at 0x%016llX).\n",
(unsigned)(adev->gmc.gart_size >> 20),
- (unsigned long long)adev->gart.table_addr);
+ (unsigned long long)table_addr);
adev->gart.ready = true;
return 0;
}
@@ -956,7 +965,7 @@
{
int r;
- if (adev->gart.robj) {
+ if (adev->gart.bo) {
WARN(1, "R600 PCIE GART already initialized\n");
return 0;
}
@@ -974,7 +983,7 @@
*
* @adev: amdgpu_device pointer
*
- * This disables all VM page table (CIK).
+ * This disables all VM page table (VI).
*/
static void gmc_v8_0_gart_disable(struct amdgpu_device *adev)
{
@@ -1003,8 +1012,9 @@
* @adev: amdgpu_device pointer
* @status: VM_CONTEXT1_PROTECTION_FAULT_STATUS register value
* @addr: VM_CONTEXT1_PROTECTION_FAULT_ADDR register value
+ * @mc_client: VM_CONTEXT1_PROTECTION_FAULT_MCCLIENT register value
*
- * Print human readable fault information (CIK).
+ * Print human readable fault information (VI).
*/
static void gmc_v8_0_vm_decode_fault(struct amdgpu_device *adev, u32 status,
u32 addr, u32 mc_client, unsigned pasid)
@@ -1084,16 +1094,14 @@
unsigned size;
if (REG_GET_FIELD(d1vga_control, D1VGA_CONTROL, D1VGA_MODE_ENABLE)) {
- size = 9 * 1024 * 1024; /* reserve 8MB for vga emulator and 1 MB for FB */
+ size = AMDGPU_VBIOS_VGA_ALLOCATION;
} else {
u32 viewport = RREG32(mmVIEWPORT_SIZE);
size = (REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_HEIGHT) *
REG_GET_FIELD(viewport, VIEWPORT_SIZE, VIEWPORT_WIDTH) *
4);
}
- /* return 0 if the pre-OS buffer uses up most of vram */
- if ((adev->gmc.real_vram_size - size) < (8 * 1024 * 1024))
- return 0;
+
return size;
}
@@ -1102,8 +1110,9 @@
static int gmc_v8_0_sw_init(void *handle)
{
int r;
- int dma_bits;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+ adev->num_vmhubs = 1;
if (adev->flags & AMD_IS_APU) {
adev->gmc.vram_type = AMDGPU_VRAM_TYPE_UNKNOWN;
@@ -1119,11 +1128,11 @@
adev->gmc.vram_type = gmc_v8_0_convert_vram_type(tmp);
}
- r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_PAGE_INV_FAULT, &adev->gmc.vm_fault);
+ r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_PAGE_INV_FAULT, &adev->gmc.vm_fault);
if (r)
return r;
- r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_MEM_PROT_FAULT, &adev->gmc.vm_fault);
+ r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_MEM_PROT_FAULT, &adev->gmc.vm_fault);
if (r)
return r;
@@ -1139,25 +1148,12 @@
*/
adev->gmc.mc_mask = 0xffffffffffULL; /* 40 bit MC */
- /* set DMA mask + need_dma32 flags.
- * PCIE - can handle 40-bits.
- * IGP - can handle 40-bits
- * PCI - dma32 for legacy pci gart, 40 bits on newer asics
- */
- adev->need_dma32 = false;
- dma_bits = adev->need_dma32 ? 32 : 40;
- r = pci_set_dma_mask(adev->pdev, DMA_BIT_MASK(dma_bits));
+ r = dma_set_mask_and_coherent(adev->dev, DMA_BIT_MASK(40));
if (r) {
- adev->need_dma32 = true;
- dma_bits = 32;
- pr_warn("amdgpu: No suitable DMA available\n");
+ pr_warn("No suitable DMA available\n");
+ return r;
}
- r = pci_set_consistent_dma_mask(adev->pdev, DMA_BIT_MASK(dma_bits));
- if (r) {
- pci_set_consistent_dma_mask(adev->pdev, DMA_BIT_MASK(32));
- pr_warn("amdgpu: No coherent DMA available\n");
- }
- adev->need_swiotlb = drm_get_max_iomem() > ((u64)1 << dma_bits);
+ adev->need_swiotlb = drm_need_swiotlb(40);
r = gmc_v8_0_init_microcode(adev);
if (r) {
@@ -1169,7 +1165,7 @@
if (r)
return r;
- adev->gmc.stolen_size = gmc_v8_0_get_vbios_fb_size(adev);
+ amdgpu_gmc_get_vbios_allocations(adev);
/* Memory manager */
r = amdgpu_bo_init(adev);
@@ -1186,7 +1182,7 @@
* amdgpu graphics/compute will use VMIDs 1-7
* amdkfd will use VMIDs 8-15
*/
- adev->vm_manager.id_mgr[0].num_ids = AMDGPU_NUM_OF_VMIDS;
+ adev->vm_manager.first_kfd_vmid = 8;
amdgpu_vm_manager_init(adev);
/* base offset of vram pages */
@@ -1473,8 +1469,9 @@
gmc_v8_0_set_fault_enable_default(adev, false);
if (printk_ratelimit()) {
- struct amdgpu_task_info task_info = { 0 };
+ struct amdgpu_task_info task_info;
+ memset(&task_info, 0, sizeof(struct amdgpu_task_info));
amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
dev_err(adev->dev, "GPU fault detected: %d 0x%08x for process %s pid %d thread %s pid %d\n",
@@ -1742,12 +1739,13 @@
static const struct amdgpu_gmc_funcs gmc_v8_0_gmc_funcs = {
.flush_gpu_tlb = gmc_v8_0_flush_gpu_tlb,
+ .flush_gpu_tlb_pasid = gmc_v8_0_flush_gpu_tlb_pasid,
.emit_flush_gpu_tlb = gmc_v8_0_emit_flush_gpu_tlb,
.emit_pasid_mapping = gmc_v8_0_emit_pasid_mapping,
- .set_pte_pde = gmc_v8_0_set_pte_pde,
.set_prt = gmc_v8_0_set_prt,
- .get_vm_pte_flags = gmc_v8_0_get_vm_pte_flags,
- .get_vm_pde = gmc_v8_0_get_vm_pde
+ .get_vm_pde = gmc_v8_0_get_vm_pde,
+ .get_vm_pte = gmc_v8_0_get_vm_pte,
+ .get_vbios_fb_size = gmc_v8_0_get_vbios_fb_size,
};
static const struct amdgpu_irq_src_funcs gmc_v8_0_irq_funcs = {
@@ -1757,8 +1755,7 @@
static void gmc_v8_0_set_gmc_funcs(struct amdgpu_device *adev)
{
- if (adev->gmc.gmc_funcs == NULL)
- adev->gmc.gmc_funcs = &gmc_v8_0_gmc_funcs;
+ adev->gmc.gmc_funcs = &gmc_v8_0_gmc_funcs;
}
static void gmc_v8_0_set_irq_funcs(struct amdgpu_device *adev)
--
Gitblit v1.6.2