From a5778d10a12da26de55f88a9d03cbea78f73f8c4 Mon Sep 17 00:00:00 2001 From: Ofir Bitton Date: Wed, 24 Feb 2021 11:51:40 +0200 Subject: [PATCH] habanalabs: debugfs access to user mapped host addresses In order to have a better debuggability we allow debugfs access to user mmu mapped host memory. Non-user host memory access will be rejected. Signed-off-by: Ofir Bitton Reviewed-by: Oded Gabbay Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/common/debugfs.c | 87 ++++++++++++++++++++++------- drivers/misc/habanalabs/common/habanalabs.h | 12 ++-- drivers/misc/habanalabs/common/mmu/mmu.c | 2 + drivers/misc/habanalabs/gaudi/gaudi.c | 40 ++++++++++--- drivers/misc/habanalabs/goya/goya.c | 44 ++++++++++++--- 5 files changed, 144 insertions(+), 41 deletions(-) diff --git a/drivers/misc/habanalabs/common/debugfs.c b/drivers/misc/habanalabs/common/debugfs.c index fd3135c..33de540 100644 --- a/drivers/misc/habanalabs/common/debugfs.c +++ b/drivers/misc/habanalabs/common/debugfs.c @@ -457,21 +457,58 @@ out: return false; } -static int device_va_to_pa(struct hl_device *hdev, u64 virt_addr, - u64 *phys_addr) +static int device_va_to_pa(struct hl_device *hdev, u64 virt_addr, u32 size, + u64 *phys_addr) { + struct hl_vm_phys_pg_pack *phys_pg_pack; struct hl_ctx *ctx = hdev->compute_ctx; - int rc = 0; + struct hl_vm_hash_node *hnode; + struct hl_userptr *userptr; + enum vm_type_t *vm_type; + bool valid = false; + u64 end_address; + u32 range_size; + int i, rc = 0; if (!ctx) { dev_err(hdev->dev, "no ctx available\n"); return -EINVAL; } + /* Verify address is mapped */ + mutex_lock(&ctx->mem_hash_lock); + hash_for_each(ctx->mem_hash, i, hnode, node) { + vm_type = hnode->ptr; + + if (*vm_type == VM_TYPE_USERPTR) { + userptr = hnode->ptr; + range_size = userptr->size; + } else { + phys_pg_pack = hnode->ptr; + range_size = phys_pg_pack->total_size; + } + + end_address = virt_addr + size; + if ((virt_addr >= hnode->vaddr) && + (end_address <= hnode->vaddr + range_size)) { + valid = true; + break; + } + } + mutex_unlock(&ctx->mem_hash_lock); + + if (!valid) { + dev_err(hdev->dev, + "virt addr 0x%llx is not mapped\n", + virt_addr); + return -EINVAL; + } + rc = hl_mmu_va_to_pa(ctx, virt_addr, phys_addr); if (rc) { - dev_err(hdev->dev, "virt addr 0x%llx is not mapped to phys addr\n", - virt_addr); + dev_err(hdev->dev, + "virt addr 0x%llx is not mapped to phys addr\n", + virt_addr); rc = -EINVAL; } @@ -483,10 +520,11 @@ static ssize_t hl_data_read32(struct file *f, char __user *buf, { struct hl_dbg_device_entry *entry = file_inode(f)->i_private; struct hl_device *hdev = entry->hdev; - char tmp_buf[32]; u64 addr = entry->addr; - u32 val; + bool user_address; + char tmp_buf[32]; ssize_t rc; + u32 val; if (atomic_read(&hdev->in_reset)) { dev_warn_ratelimited(hdev->dev, "Can't read during reset\n"); @@ -496,13 +534,14 @@ static ssize_t hl_data_read32(struct file *f, char __user *buf, if (*ppos) return 0; - if (hl_is_device_va(hdev, addr)) { - rc = device_va_to_pa(hdev, addr, &addr); + user_address = hl_is_device_va(hdev, addr); + if (user_address) { + rc = device_va_to_pa(hdev, addr, sizeof(val), &addr); if (rc) return rc; } - rc = hdev->asic_funcs->debugfs_read32(hdev, addr, &val); + rc = hdev->asic_funcs->debugfs_read32(hdev, addr, user_address, &val); if (rc) { dev_err(hdev->dev, "Failed to read from 0x%010llx\n", addr); return rc; @@ -519,6 +558,7 @@ 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; u64 addr = entry->addr; + bool user_address; u32 value; ssize_t rc; @@ -531,13 +571,14 @@ static ssize_t hl_data_write32(struct file *f, const char __user *buf, if (rc) return rc; - if (hl_is_device_va(hdev, addr)) { - rc = device_va_to_pa(hdev, addr, &addr); + user_address = hl_is_device_va(hdev, addr); + if (user_address) { + rc = device_va_to_pa(hdev, addr, sizeof(value), &addr); if (rc) return rc; } - rc = hdev->asic_funcs->debugfs_write32(hdev, addr, value); + rc = hdev->asic_funcs->debugfs_write32(hdev, addr, user_address, value); if (rc) { dev_err(hdev->dev, "Failed to write 0x%08x to 0x%010llx\n", value, addr); @@ -552,21 +593,23 @@ static ssize_t hl_data_read64(struct file *f, char __user *buf, { struct hl_dbg_device_entry *entry = file_inode(f)->i_private; struct hl_device *hdev = entry->hdev; - char tmp_buf[32]; u64 addr = entry->addr; - u64 val; + bool user_address; + char tmp_buf[32]; ssize_t rc; + u64 val; if (*ppos) return 0; - if (hl_is_device_va(hdev, addr)) { - rc = device_va_to_pa(hdev, addr, &addr); + user_address = hl_is_device_va(hdev, addr); + if (user_address) { + rc = device_va_to_pa(hdev, addr, sizeof(val), &addr); if (rc) return rc; } - rc = hdev->asic_funcs->debugfs_read64(hdev, addr, &val); + rc = hdev->asic_funcs->debugfs_read64(hdev, addr, user_address, &val); if (rc) { dev_err(hdev->dev, "Failed to read from 0x%010llx\n", addr); return rc; @@ -583,6 +626,7 @@ static ssize_t hl_data_write64(struct file *f, const char __user *buf, struct hl_dbg_device_entry *entry = file_inode(f)->i_private; struct hl_device *hdev = entry->hdev; u64 addr = entry->addr; + bool user_address; u64 value; ssize_t rc; @@ -590,13 +634,14 @@ static ssize_t hl_data_write64(struct file *f, const char __user *buf, if (rc) return rc; - if (hl_is_device_va(hdev, addr)) { - rc = device_va_to_pa(hdev, addr, &addr); + user_address = hl_is_device_va(hdev, addr); + if (user_address) { + rc = device_va_to_pa(hdev, addr, sizeof(value), &addr); if (rc) return rc; } - rc = hdev->asic_funcs->debugfs_write64(hdev, addr, value); + rc = hdev->asic_funcs->debugfs_write64(hdev, addr, user_address, value); if (rc) { dev_err(hdev->dev, "Failed to write 0x%016llx to 0x%010llx\n", value, addr); diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h index 780adde..2dcefd6 100644 --- a/drivers/misc/habanalabs/common/habanalabs.h +++ b/drivers/misc/habanalabs/common/habanalabs.h @@ -969,10 +969,14 @@ struct hl_asic_funcs { void (*update_eq_ci)(struct hl_device *hdev, u32 val); int (*context_switch)(struct hl_device *hdev, u32 asid); void (*restore_phase_topology)(struct hl_device *hdev); - int (*debugfs_read32)(struct hl_device *hdev, u64 addr, u32 *val); - int (*debugfs_write32)(struct hl_device *hdev, u64 addr, u32 val); - int (*debugfs_read64)(struct hl_device *hdev, u64 addr, u64 *val); - int (*debugfs_write64)(struct hl_device *hdev, u64 addr, u64 val); + int (*debugfs_read32)(struct hl_device *hdev, u64 addr, + bool user_address, u32 *val); + int (*debugfs_write32)(struct hl_device *hdev, u64 addr, + bool user_address, u32 val); + int (*debugfs_read64)(struct hl_device *hdev, u64 addr, + bool user_address, u64 *val); + int (*debugfs_write64)(struct hl_device *hdev, u64 addr, + bool user_address, u64 val); void (*add_device_attr)(struct hl_device *hdev, struct attribute_group *dev_attr_grp); void (*handle_eqe)(struct hl_device *hdev, diff --git a/drivers/misc/habanalabs/common/mmu/mmu.c b/drivers/misc/habanalabs/common/mmu/mmu.c index 93c9e5f..ae17781 100644 --- a/drivers/misc/habanalabs/common/mmu/mmu.c +++ b/drivers/misc/habanalabs/common/mmu/mmu.c @@ -532,6 +532,8 @@ int hl_mmu_va_to_pa(struct hl_ctx *ctx, u64 virt_addr, u64 *phys_addr) struct hl_mmu_hop_info hops; int rc; + memset(&hops, 0, sizeof(hops)); + rc = hl_mmu_get_tlb_info(ctx, virt_addr, &hops); if (rc) return rc; diff --git a/drivers/misc/habanalabs/gaudi/gaudi.c b/drivers/misc/habanalabs/gaudi/gaudi.c index 37e3f4c..8be75f7 100644 --- a/drivers/misc/habanalabs/gaudi/gaudi.c +++ b/drivers/misc/habanalabs/gaudi/gaudi.c @@ -5911,13 +5911,16 @@ static void gaudi_restore_phase_topology(struct hl_device *hdev) } -static int gaudi_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val) +static int gaudi_debugfs_read32(struct hl_device *hdev, u64 addr, + bool user_address, u32 *val) { struct asic_fixed_properties *prop = &hdev->asic_prop; struct gaudi_device *gaudi = hdev->asic_specific; - u64 hbm_bar_addr; + u64 hbm_bar_addr, host_phys_end; int rc = 0; + host_phys_end = HOST_PHYS_BASE + HOST_PHYS_SIZE; + if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) { if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && @@ -5949,6 +5952,9 @@ static int gaudi_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val) } if (hbm_bar_addr == U64_MAX) rc = -EIO; + } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end && + user_address && !iommu_present(&pci_bus_type)) { + *val = *(u32 *) phys_to_virt(addr - HOST_PHYS_BASE); } else { rc = -EFAULT; } @@ -5956,13 +5962,16 @@ static int gaudi_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val) return rc; } -static int gaudi_debugfs_write32(struct hl_device *hdev, u64 addr, u32 val) +static int gaudi_debugfs_write32(struct hl_device *hdev, u64 addr, + bool user_address, u32 val) { struct asic_fixed_properties *prop = &hdev->asic_prop; struct gaudi_device *gaudi = hdev->asic_specific; - u64 hbm_bar_addr; + u64 hbm_bar_addr, host_phys_end; int rc = 0; + host_phys_end = HOST_PHYS_BASE + HOST_PHYS_SIZE; + if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) { if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && @@ -5994,6 +6003,9 @@ static int gaudi_debugfs_write32(struct hl_device *hdev, u64 addr, u32 val) } if (hbm_bar_addr == U64_MAX) rc = -EIO; + } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end && + user_address && !iommu_present(&pci_bus_type)) { + *(u32 *) phys_to_virt(addr - HOST_PHYS_BASE) = val; } else { rc = -EFAULT; } @@ -6001,13 +6013,16 @@ static int gaudi_debugfs_write32(struct hl_device *hdev, u64 addr, u32 val) return rc; } -static int gaudi_debugfs_read64(struct hl_device *hdev, u64 addr, u64 *val) +static int gaudi_debugfs_read64(struct hl_device *hdev, u64 addr, + bool user_address, u64 *val) { struct asic_fixed_properties *prop = &hdev->asic_prop; struct gaudi_device *gaudi = hdev->asic_specific; - u64 hbm_bar_addr; + u64 hbm_bar_addr, host_phys_end; int rc = 0; + host_phys_end = HOST_PHYS_BASE + HOST_PHYS_SIZE; + if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) { if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && @@ -6043,6 +6058,9 @@ static int gaudi_debugfs_read64(struct hl_device *hdev, u64 addr, u64 *val) } if (hbm_bar_addr == U64_MAX) rc = -EIO; + } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end && + user_address && !iommu_present(&pci_bus_type)) { + *val = *(u64 *) phys_to_virt(addr - HOST_PHYS_BASE); } else { rc = -EFAULT; } @@ -6050,13 +6068,16 @@ static int gaudi_debugfs_read64(struct hl_device *hdev, u64 addr, u64 *val) return rc; } -static int gaudi_debugfs_write64(struct hl_device *hdev, u64 addr, u64 val) +static int gaudi_debugfs_write64(struct hl_device *hdev, u64 addr, + bool user_address, u64 val) { struct asic_fixed_properties *prop = &hdev->asic_prop; struct gaudi_device *gaudi = hdev->asic_specific; - u64 hbm_bar_addr; + u64 hbm_bar_addr, host_phys_end; int rc = 0; + host_phys_end = HOST_PHYS_BASE + HOST_PHYS_SIZE; + if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) { if ((gaudi->hw_cap_initialized & HW_CAP_CLK_GATE) && @@ -6091,6 +6112,9 @@ static int gaudi_debugfs_write64(struct hl_device *hdev, u64 addr, u64 val) } if (hbm_bar_addr == U64_MAX) rc = -EIO; + } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end && + user_address && !iommu_present(&pci_bus_type)) { + *(u64 *) phys_to_virt(addr - HOST_PHYS_BASE) = val; } else { rc = -EFAULT; } diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 452bef4..9e75311 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -4101,12 +4101,15 @@ static void goya_clear_sm_regs(struct hl_device *hdev) * lead to undefined behavior and therefore, should be done with extreme care * */ -static int goya_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val) +static int goya_debugfs_read32(struct hl_device *hdev, u64 addr, + bool user_address, u32 *val) { struct asic_fixed_properties *prop = &hdev->asic_prop; - u64 ddr_bar_addr; + u64 ddr_bar_addr, host_phys_end; int rc = 0; + host_phys_end = HOST_PHYS_BASE + HOST_PHYS_SIZE; + if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) { *val = RREG32(addr - CFG_BASE); @@ -4132,6 +4135,10 @@ static int goya_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val) if (ddr_bar_addr == U64_MAX) rc = -EIO; + } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end && + user_address && !iommu_present(&pci_bus_type)) { + *val = *(u32 *) phys_to_virt(addr - HOST_PHYS_BASE); + } else { rc = -EFAULT; } @@ -4154,12 +4161,15 @@ static int goya_debugfs_read32(struct hl_device *hdev, u64 addr, u32 *val) * lead to undefined behavior and therefore, should be done with extreme care * */ -static int goya_debugfs_write32(struct hl_device *hdev, u64 addr, u32 val) +static int goya_debugfs_write32(struct hl_device *hdev, u64 addr, + bool user_address, u32 val) { struct asic_fixed_properties *prop = &hdev->asic_prop; - u64 ddr_bar_addr; + u64 ddr_bar_addr, host_phys_end; int rc = 0; + host_phys_end = HOST_PHYS_BASE + HOST_PHYS_SIZE; + if ((addr >= CFG_BASE) && (addr < CFG_BASE + CFG_SIZE)) { WREG32(addr - CFG_BASE, val); @@ -4185,6 +4195,10 @@ static int goya_debugfs_write32(struct hl_device *hdev, u64 addr, u32 val) if (ddr_bar_addr == U64_MAX) rc = -EIO; + } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end && + user_address && !iommu_present(&pci_bus_type)) { + *(u32 *) phys_to_virt(addr - HOST_PHYS_BASE) = val; + } else { rc = -EFAULT; } @@ -4192,12 +4206,15 @@ static int goya_debugfs_write32(struct hl_device *hdev, u64 addr, u32 val) return rc; } -static int goya_debugfs_read64(struct hl_device *hdev, u64 addr, u64 *val) +static int goya_debugfs_read64(struct hl_device *hdev, u64 addr, + bool user_address, u64 *val) { struct asic_fixed_properties *prop = &hdev->asic_prop; - u64 ddr_bar_addr; + u64 ddr_bar_addr, host_phys_end; int rc = 0; + host_phys_end = HOST_PHYS_BASE + HOST_PHYS_SIZE; + if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) { u32 val_l = RREG32(addr - CFG_BASE); u32 val_h = RREG32(addr + sizeof(u32) - CFG_BASE); @@ -4227,6 +4244,10 @@ static int goya_debugfs_read64(struct hl_device *hdev, u64 addr, u64 *val) if (ddr_bar_addr == U64_MAX) rc = -EIO; + } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end && + user_address && !iommu_present(&pci_bus_type)) { + *val = *(u64 *) phys_to_virt(addr - HOST_PHYS_BASE); + } else { rc = -EFAULT; } @@ -4234,12 +4255,15 @@ static int goya_debugfs_read64(struct hl_device *hdev, u64 addr, u64 *val) return rc; } -static int goya_debugfs_write64(struct hl_device *hdev, u64 addr, u64 val) +static int goya_debugfs_write64(struct hl_device *hdev, u64 addr, + bool user_address, u64 val) { struct asic_fixed_properties *prop = &hdev->asic_prop; - u64 ddr_bar_addr; + u64 ddr_bar_addr, host_phys_end; int rc = 0; + host_phys_end = HOST_PHYS_BASE + HOST_PHYS_SIZE; + if ((addr >= CFG_BASE) && (addr <= CFG_BASE + CFG_SIZE - sizeof(u64))) { WREG32(addr - CFG_BASE, lower_32_bits(val)); WREG32(addr + sizeof(u32) - CFG_BASE, upper_32_bits(val)); @@ -4267,6 +4291,10 @@ static int goya_debugfs_write64(struct hl_device *hdev, u64 addr, u64 val) if (ddr_bar_addr == U64_MAX) rc = -EIO; + } else if (addr >= HOST_PHYS_BASE && addr < host_phys_end && + user_address && !iommu_present(&pci_bus_type)) { + *(u64 *) phys_to_virt(addr - HOST_PHYS_BASE) = val; + } else { rc = -EFAULT; } -- 2.7.4