diff options
Diffstat (limited to 'drivers/crypto/ccp/sev-dev.c')
| -rw-r--r-- | drivers/crypto/ccp/sev-dev.c | 1825 |
1 files changed, 1696 insertions, 129 deletions
diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index f97166fba9d9..956ea609d0cc 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -21,14 +21,20 @@ #include <linux/hw_random.h> #include <linux/ccp.h> #include <linux/firmware.h> +#include <linux/panic_notifier.h> #include <linux/gfp.h> #include <linux/cpufeature.h> #include <linux/fs.h> #include <linux/fs_struct.h> #include <linux/psp.h> +#include <linux/amd-iommu.h> +#include <linux/crash_dump.h> #include <asm/smp.h> #include <asm/cacheflush.h> +#include <asm/e820/types.h> +#include <asm/sev.h> +#include <asm/msr.h> #include "psp-dev.h" #include "sev-dev.h" @@ -37,6 +43,19 @@ #define SEV_FW_FILE "amd/sev.fw" #define SEV_FW_NAME_SIZE 64 +/* Minimum firmware version required for the SEV-SNP support */ +#define SNP_MIN_API_MAJOR 1 +#define SNP_MIN_API_MINOR 51 + +/* + * Maximum number of firmware-writable buffers that might be specified + * in the parameters of a legacy SEV command buffer. + */ +#define CMD_BUF_FW_WRITABLE_MAX 2 + +/* Leave room in the descriptor array for an end-of-list indicator. */ +#define CMD_BUF_DESC_MAX (CMD_BUF_FW_WRITABLE_MAX + 1) + static DEFINE_MUTEX(sev_cmd_mutex); static struct sev_misc_dev *misc_dev; @@ -56,6 +75,14 @@ static bool psp_init_on_probe = true; module_param(psp_init_on_probe, bool, 0444); MODULE_PARM_DESC(psp_init_on_probe, " if true, the PSP will be initialized on module init. Else the PSP will be initialized on the first command requiring it"); +#if IS_ENABLED(CONFIG_PCI_TSM) +static bool sev_tio_enabled = true; +module_param_named(tio, sev_tio_enabled, bool, 0444); +MODULE_PARM_DESC(tio, "Enables TIO in SNP_INIT_EX"); +#else +static const bool sev_tio_enabled = false; +#endif + MODULE_FIRMWARE("amd/amd_sev_fam17h_model0xh.sbin"); /* 1st gen EPYC */ MODULE_FIRMWARE("amd/amd_sev_fam17h_model3xh.sbin"); /* 2nd gen EPYC */ MODULE_FIRMWARE("amd/amd_sev_fam19h_model0xh.sbin"); /* 3rd gen EPYC */ @@ -64,13 +91,33 @@ MODULE_FIRMWARE("amd/amd_sev_fam19h_model1xh.sbin"); /* 4th gen EPYC */ static bool psp_dead; static int psp_timeout; +enum snp_hv_fixed_pages_state { + ALLOCATED, + HV_FIXED, +}; + +struct snp_hv_fixed_pages_entry { + struct list_head list; + struct page *page; + unsigned int order; + bool free; + enum snp_hv_fixed_pages_state page_state; +}; + +static LIST_HEAD(snp_hv_fixed_pages); + /* Trusted Memory Region (TMR): * The TMR is a 1MB area that must be 1MB aligned. Use the page allocator * to allocate the memory, which will return aligned memory for the specified * allocation order. + * + * When SEV-SNP is enabled the TMR needs to be 2MB aligned and 2MB sized. */ -#define SEV_ES_TMR_SIZE (1024 * 1024) +#define SEV_TMR_SIZE (1024 * 1024) +#define SNP_TMR_SIZE (2 * 1024 * 1024) + static void *sev_es_tmr; +static size_t sev_es_tmr_size = SEV_TMR_SIZE; /* INIT_EX NV Storage: * The NV Storage is a 32Kb area and must be 4Kb page aligned. Use the page @@ -80,6 +127,22 @@ static void *sev_es_tmr; #define NV_LENGTH (32 * 1024) static void *sev_init_ex_buffer; +/* + * SEV_DATA_RANGE_LIST: + * Array containing range of pages that firmware transitions to HV-fixed + * page state. + */ +static struct sev_data_range_list *snp_range_list; + +static void __sev_firmware_shutdown(struct sev_device *sev, bool panic); + +static int snp_shutdown_on_panic(struct notifier_block *nb, + unsigned long reason, void *arg); + +static struct notifier_block snp_panic_notifier = { + .notifier_call = snp_shutdown_on_panic, +}; + static inline bool sev_version_greater_or_equal(u8 maj, u8 min) { struct sev_device *sev = psp_master->sev_data; @@ -115,6 +178,25 @@ static int sev_wait_cmd_ioc(struct sev_device *sev, { int ret; + /* + * If invoked during panic handling, local interrupts are disabled, + * so the PSP command completion interrupt can't be used. Poll for + * PSP command completion instead. + */ + if (irqs_disabled()) { + unsigned long timeout_usecs = (timeout * USEC_PER_SEC) / 10; + + /* Poll for SEV command completion: */ + while (timeout_usecs--) { + *reg = ioread32(sev->io_regs + sev->vdata->cmdresp_reg); + if (*reg & PSP_CMDRESP_RESP) + return 0; + + udelay(10); + } + return -ETIMEDOUT; + } + ret = wait_event_timeout(sev->int_queue, sev->int_rcvd, timeout * HZ); if (!ret) @@ -130,6 +212,8 @@ static int sev_cmd_buffer_len(int cmd) switch (cmd) { case SEV_CMD_INIT: return sizeof(struct sev_data_init); case SEV_CMD_INIT_EX: return sizeof(struct sev_data_init_ex); + case SEV_CMD_SNP_SHUTDOWN_EX: return sizeof(struct sev_data_snp_shutdown_ex); + case SEV_CMD_SNP_INIT_EX: return sizeof(struct sev_data_snp_init_ex); case SEV_CMD_PLATFORM_STATUS: return sizeof(struct sev_user_data_status); case SEV_CMD_PEK_CSR: return sizeof(struct sev_data_pek_csr); case SEV_CMD_PEK_CERT_IMPORT: return sizeof(struct sev_data_pek_cert_import); @@ -158,46 +242,45 @@ static int sev_cmd_buffer_len(int cmd) case SEV_CMD_GET_ID: return sizeof(struct sev_data_get_id); case SEV_CMD_ATTESTATION_REPORT: return sizeof(struct sev_data_attestation_report); case SEV_CMD_SEND_CANCEL: return sizeof(struct sev_data_send_cancel); - default: return 0; + case SEV_CMD_SNP_GCTX_CREATE: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_LAUNCH_START: return sizeof(struct sev_data_snp_launch_start); + case SEV_CMD_SNP_LAUNCH_UPDATE: return sizeof(struct sev_data_snp_launch_update); + case SEV_CMD_SNP_ACTIVATE: return sizeof(struct sev_data_snp_activate); + case SEV_CMD_SNP_DECOMMISSION: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_PAGE_RECLAIM: return sizeof(struct sev_data_snp_page_reclaim); + case SEV_CMD_SNP_GUEST_STATUS: return sizeof(struct sev_data_snp_guest_status); + case SEV_CMD_SNP_LAUNCH_FINISH: return sizeof(struct sev_data_snp_launch_finish); + case SEV_CMD_SNP_DBG_DECRYPT: return sizeof(struct sev_data_snp_dbg); + case SEV_CMD_SNP_DBG_ENCRYPT: return sizeof(struct sev_data_snp_dbg); + case SEV_CMD_SNP_PAGE_UNSMASH: return sizeof(struct sev_data_snp_page_unsmash); + case SEV_CMD_SNP_PLATFORM_STATUS: return sizeof(struct sev_data_snp_addr); + case SEV_CMD_SNP_GUEST_REQUEST: return sizeof(struct sev_data_snp_guest_request); + case SEV_CMD_SNP_CONFIG: return sizeof(struct sev_user_data_snp_config); + case SEV_CMD_SNP_COMMIT: return sizeof(struct sev_data_snp_commit); + case SEV_CMD_SNP_FEATURE_INFO: return sizeof(struct sev_data_snp_feature_info); + case SEV_CMD_SNP_VLEK_LOAD: return sizeof(struct sev_user_data_snp_vlek_load); + default: return sev_tio_cmd_buffer_len(cmd); } return 0; } -static void *sev_fw_alloc(unsigned long len) -{ - struct page *page; - - page = alloc_pages(GFP_KERNEL, get_order(len)); - if (!page) - return NULL; - - return page_address(page); -} - static struct file *open_file_as_root(const char *filename, int flags, umode_t mode) { - struct file *fp; - struct path root; - struct cred *cred; - const struct cred *old_cred; + struct path root __free(path_put) = {}; task_lock(&init_task); get_fs_root(init_task.fs, &root); task_unlock(&init_task); - cred = prepare_creds(); + CLASS(prepare_creds, cred)(); if (!cred) return ERR_PTR(-ENOMEM); - cred->fsuid = GLOBAL_ROOT_UID; - old_cred = override_creds(cred); - - fp = file_open_root(&root, filename, flags, mode); - path_put(&root); - revert_creds(old_cred); + cred->fsuid = GLOBAL_ROOT_UID; - return fp; + scoped_with_creds(cred) + return file_open_root(&root, filename, flags, mode); } static int sev_read_init_ex_file(void) @@ -305,13 +388,482 @@ static int sev_write_init_ex_file_if_required(int cmd_id) return sev_write_init_ex_file(); } -static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) +int snp_reclaim_pages(unsigned long paddr, unsigned int npages, bool locked) +{ + int ret, err, i; + + paddr = __sme_clr(ALIGN_DOWN(paddr, PAGE_SIZE)); + + for (i = 0; i < npages; i++, paddr += PAGE_SIZE) { + struct sev_data_snp_page_reclaim data = {0}; + + data.paddr = paddr; + + if (locked) + ret = __sev_do_cmd_locked(SEV_CMD_SNP_PAGE_RECLAIM, &data, &err); + else + ret = sev_do_cmd(SEV_CMD_SNP_PAGE_RECLAIM, &data, &err); + + if (ret) + goto cleanup; + + ret = rmp_make_shared(__phys_to_pfn(paddr), PG_LEVEL_4K); + if (ret) + goto cleanup; + } + + return 0; + +cleanup: + /* + * If there was a failure reclaiming the page then it is no longer safe + * to release it back to the system; leak it instead. + */ + snp_leak_pages(__phys_to_pfn(paddr), npages - i); + return ret; +} +EXPORT_SYMBOL_GPL(snp_reclaim_pages); + +static int rmp_mark_pages_firmware(unsigned long paddr, unsigned int npages, bool locked) +{ + unsigned long pfn = __sme_clr(paddr) >> PAGE_SHIFT; + int rc, i; + + for (i = 0; i < npages; i++, pfn++) { + rc = rmp_make_private(pfn, 0, PG_LEVEL_4K, 0, true); + if (rc) + goto cleanup; + } + + return 0; + +cleanup: + /* + * Try unrolling the firmware state changes by + * reclaiming the pages which were already changed to the + * firmware state. + */ + snp_reclaim_pages(paddr, i, locked); + + return rc; +} + +static struct page *__snp_alloc_firmware_pages(gfp_t gfp_mask, int order, bool locked) +{ + unsigned long npages = 1ul << order, paddr; + struct sev_device *sev; + struct page *page; + + if (!psp_master || !psp_master->sev_data) + return NULL; + + page = alloc_pages(gfp_mask, order); + if (!page) + return NULL; + + /* If SEV-SNP is initialized then add the page in RMP table. */ + sev = psp_master->sev_data; + if (!sev->snp_initialized) + return page; + + paddr = __pa((unsigned long)page_address(page)); + if (rmp_mark_pages_firmware(paddr, npages, locked)) + return NULL; + + return page; +} + +void *snp_alloc_firmware_page(gfp_t gfp_mask) +{ + struct page *page; + + page = __snp_alloc_firmware_pages(gfp_mask, 0, false); + + return page ? page_address(page) : NULL; +} +EXPORT_SYMBOL_GPL(snp_alloc_firmware_page); + +static void __snp_free_firmware_pages(struct page *page, int order, bool locked) +{ + struct sev_device *sev = psp_master->sev_data; + unsigned long paddr, npages = 1ul << order; + + if (!page) + return; + + paddr = __pa((unsigned long)page_address(page)); + if (sev->snp_initialized && + snp_reclaim_pages(paddr, npages, locked)) + return; + + __free_pages(page, order); +} + +void snp_free_firmware_page(void *addr) +{ + if (!addr) + return; + + __snp_free_firmware_pages(virt_to_page(addr), 0, false); +} +EXPORT_SYMBOL_GPL(snp_free_firmware_page); + +static void *sev_fw_alloc(unsigned long len) +{ + struct page *page; + + page = __snp_alloc_firmware_pages(GFP_KERNEL, get_order(len), true); + if (!page) + return NULL; + + return page_address(page); +} + +/** + * struct cmd_buf_desc - descriptors for managing legacy SEV command address + * parameters corresponding to buffers that may be written to by firmware. + * + * @paddr_ptr: pointer to the address parameter in the command buffer which may + * need to be saved/restored depending on whether a bounce buffer + * is used. In the case of a bounce buffer, the command buffer + * needs to be updated with the address of the new bounce buffer + * snp_map_cmd_buf_desc() has allocated specifically for it. Must + * be NULL if this descriptor is only an end-of-list indicator. + * + * @paddr_orig: storage for the original address parameter, which can be used to + * restore the original value in @paddr_ptr in cases where it is + * replaced with the address of a bounce buffer. + * + * @len: length of buffer located at the address originally stored at @paddr_ptr + * + * @guest_owned: true if the address corresponds to guest-owned pages, in which + * case bounce buffers are not needed. + */ +struct cmd_buf_desc { + u64 *paddr_ptr; + u64 paddr_orig; + u32 len; + bool guest_owned; +}; + +/* + * If a legacy SEV command parameter is a memory address, those pages in + * turn need to be transitioned to/from firmware-owned before/after + * executing the firmware command. + * + * Additionally, in cases where those pages are not guest-owned, a bounce + * buffer is needed in place of the original memory address parameter. + * + * A set of descriptors are used to keep track of this handling, and + * initialized here based on the specific commands being executed. + */ +static void snp_populate_cmd_buf_desc_list(int cmd, void *cmd_buf, + struct cmd_buf_desc *desc_list) +{ + switch (cmd) { + case SEV_CMD_PDH_CERT_EXPORT: { + struct sev_data_pdh_cert_export *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->pdh_cert_address; + desc_list[0].len = data->pdh_cert_len; + desc_list[1].paddr_ptr = &data->cert_chain_address; + desc_list[1].len = data->cert_chain_len; + break; + } + case SEV_CMD_GET_ID: { + struct sev_data_get_id *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_PEK_CSR: { + struct sev_data_pek_csr *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_LAUNCH_UPDATE_DATA: { + struct sev_data_launch_update_data *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_LAUNCH_UPDATE_VMSA: { + struct sev_data_launch_update_vmsa *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_LAUNCH_MEASURE: { + struct sev_data_launch_measure *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_LAUNCH_UPDATE_SECRET: { + struct sev_data_launch_secret *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->guest_address; + desc_list[0].len = data->guest_len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_DBG_DECRYPT: { + struct sev_data_dbg *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->dst_addr; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_DBG_ENCRYPT: { + struct sev_data_dbg *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->dst_addr; + desc_list[0].len = data->len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_ATTESTATION_REPORT: { + struct sev_data_attestation_report *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->address; + desc_list[0].len = data->len; + break; + } + case SEV_CMD_SEND_START: { + struct sev_data_send_start *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->session_address; + desc_list[0].len = data->session_len; + break; + } + case SEV_CMD_SEND_UPDATE_DATA: { + struct sev_data_send_update_data *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->hdr_address; + desc_list[0].len = data->hdr_len; + desc_list[1].paddr_ptr = &data->trans_address; + desc_list[1].len = data->trans_len; + break; + } + case SEV_CMD_SEND_UPDATE_VMSA: { + struct sev_data_send_update_vmsa *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->hdr_address; + desc_list[0].len = data->hdr_len; + desc_list[1].paddr_ptr = &data->trans_address; + desc_list[1].len = data->trans_len; + break; + } + case SEV_CMD_RECEIVE_UPDATE_DATA: { + struct sev_data_receive_update_data *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->guest_address; + desc_list[0].len = data->guest_len; + desc_list[0].guest_owned = true; + break; + } + case SEV_CMD_RECEIVE_UPDATE_VMSA: { + struct sev_data_receive_update_vmsa *data = cmd_buf; + + desc_list[0].paddr_ptr = &data->guest_address; + desc_list[0].len = data->guest_len; + desc_list[0].guest_owned = true; + break; + } + default: + break; + } +} + +static int snp_map_cmd_buf_desc(struct cmd_buf_desc *desc) { + unsigned int npages; + + if (!desc->len) + return 0; + + /* Allocate a bounce buffer if this isn't a guest owned page. */ + if (!desc->guest_owned) { + struct page *page; + + page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(desc->len)); + if (!page) { + pr_warn("Failed to allocate bounce buffer for SEV legacy command.\n"); + return -ENOMEM; + } + + desc->paddr_orig = *desc->paddr_ptr; + *desc->paddr_ptr = __psp_pa(page_to_virt(page)); + } + + npages = PAGE_ALIGN(desc->len) >> PAGE_SHIFT; + + /* Transition the buffer to firmware-owned. */ + if (rmp_mark_pages_firmware(*desc->paddr_ptr, npages, true)) { + pr_warn("Error moving pages to firmware-owned state for SEV legacy command.\n"); + return -EFAULT; + } + + return 0; +} + +static int snp_unmap_cmd_buf_desc(struct cmd_buf_desc *desc) +{ + unsigned int npages; + + if (!desc->len) + return 0; + + npages = PAGE_ALIGN(desc->len) >> PAGE_SHIFT; + + /* Transition the buffers back to hypervisor-owned. */ + if (snp_reclaim_pages(*desc->paddr_ptr, npages, true)) { + pr_warn("Failed to reclaim firmware-owned pages while issuing SEV legacy command.\n"); + return -EFAULT; + } + + /* Copy data from bounce buffer and then free it. */ + if (!desc->guest_owned) { + void *bounce_buf = __va(__sme_clr(*desc->paddr_ptr)); + void *dst_buf = __va(__sme_clr(desc->paddr_orig)); + + memcpy(dst_buf, bounce_buf, desc->len); + __free_pages(virt_to_page(bounce_buf), get_order(desc->len)); + + /* Restore the original address in the command buffer. */ + *desc->paddr_ptr = desc->paddr_orig; + } + + return 0; +} + +static int snp_map_cmd_buf_desc_list(int cmd, void *cmd_buf, struct cmd_buf_desc *desc_list) +{ + int i; + + snp_populate_cmd_buf_desc_list(cmd, cmd_buf, desc_list); + + for (i = 0; i < CMD_BUF_DESC_MAX; i++) { + struct cmd_buf_desc *desc = &desc_list[i]; + + if (!desc->paddr_ptr) + break; + + if (snp_map_cmd_buf_desc(desc)) + goto err_unmap; + } + + return 0; + +err_unmap: + for (i--; i >= 0; i--) + snp_unmap_cmd_buf_desc(&desc_list[i]); + + return -EFAULT; +} + +static int snp_unmap_cmd_buf_desc_list(struct cmd_buf_desc *desc_list) +{ + int i, ret = 0; + + for (i = 0; i < CMD_BUF_DESC_MAX; i++) { + struct cmd_buf_desc *desc = &desc_list[i]; + + if (!desc->paddr_ptr) + break; + + if (snp_unmap_cmd_buf_desc(&desc_list[i])) + ret = -EFAULT; + } + + return ret; +} + +static bool sev_cmd_buf_writable(int cmd) +{ + switch (cmd) { + case SEV_CMD_PLATFORM_STATUS: + case SEV_CMD_GUEST_STATUS: + case SEV_CMD_LAUNCH_START: + case SEV_CMD_RECEIVE_START: + case SEV_CMD_LAUNCH_MEASURE: + case SEV_CMD_SEND_START: + case SEV_CMD_SEND_UPDATE_DATA: + case SEV_CMD_SEND_UPDATE_VMSA: + case SEV_CMD_PEK_CSR: + case SEV_CMD_PDH_CERT_EXPORT: + case SEV_CMD_GET_ID: + case SEV_CMD_ATTESTATION_REPORT: + return true; + default: + return false; + } +} + +/* After SNP is INIT'ed, the behavior of legacy SEV commands is changed. */ +static bool snp_legacy_handling_needed(int cmd) +{ + struct sev_device *sev = psp_master->sev_data; + + return cmd < SEV_CMD_SNP_INIT && sev->snp_initialized; +} + +static int snp_prep_cmd_buf(int cmd, void *cmd_buf, struct cmd_buf_desc *desc_list) +{ + if (!snp_legacy_handling_needed(cmd)) + return 0; + + if (snp_map_cmd_buf_desc_list(cmd, cmd_buf, desc_list)) + return -EFAULT; + + /* + * Before command execution, the command buffer needs to be put into + * the firmware-owned state. + */ + if (sev_cmd_buf_writable(cmd)) { + if (rmp_mark_pages_firmware(__pa(cmd_buf), 1, true)) + return -EFAULT; + } + + return 0; +} + +static int snp_reclaim_cmd_buf(int cmd, void *cmd_buf) +{ + if (!snp_legacy_handling_needed(cmd)) + return 0; + + /* + * After command completion, the command buffer needs to be put back + * into the hypervisor-owned state. + */ + if (sev_cmd_buf_writable(cmd)) + if (snp_reclaim_pages(__pa(cmd_buf), 1, true)) + return -EFAULT; + + return 0; +} + +int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) +{ + struct cmd_buf_desc desc_list[CMD_BUF_DESC_MAX] = {0}; struct psp_device *psp = psp_master; struct sev_device *sev; + unsigned int cmdbuff_hi, cmdbuff_lo; unsigned int phys_lsb, phys_msb; - unsigned int reg, ret = 0; + unsigned int reg; + void *cmd_buf; int buf_len; + int ret = 0; if (!psp || !psp->sev_data) return -ENODEV; @@ -330,12 +882,47 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) * work for some memory, e.g. vmalloc'd addresses, and @data may not be * physically contiguous. */ - if (data) - memcpy(sev->cmd_buf, data, buf_len); + if (data) { + /* + * Commands are generally issued one at a time and require the + * sev_cmd_mutex, but there could be recursive firmware requests + * due to SEV_CMD_SNP_PAGE_RECLAIM needing to be issued while + * preparing buffers for another command. This is the only known + * case of nesting in the current code, so exactly one + * additional command buffer is available for that purpose. + */ + if (!sev->cmd_buf_active) { + cmd_buf = sev->cmd_buf; + sev->cmd_buf_active = true; + } else if (!sev->cmd_buf_backup_active) { + cmd_buf = sev->cmd_buf_backup; + sev->cmd_buf_backup_active = true; + } else { + dev_err(sev->dev, + "SEV: too many firmware commands in progress, no command buffers available.\n"); + return -EBUSY; + } + + memcpy(cmd_buf, data, buf_len); + + /* + * The behavior of the SEV-legacy commands is altered when the + * SNP firmware is in the INIT state. + */ + ret = snp_prep_cmd_buf(cmd, cmd_buf, desc_list); + if (ret) { + dev_err(sev->dev, + "SEV: failed to prepare buffer for legacy command 0x%x. Error: %d\n", + cmd, ret); + return ret; + } + } else { + cmd_buf = sev->cmd_buf; + } /* Get the physical address of the command buffer */ - phys_lsb = data ? lower_32_bits(__psp_pa(sev->cmd_buf)) : 0; - phys_msb = data ? upper_32_bits(__psp_pa(sev->cmd_buf)) : 0; + phys_lsb = data ? lower_32_bits(__psp_pa(cmd_buf)) : 0; + phys_msb = data ? upper_32_bits(__psp_pa(cmd_buf)) : 0; dev_dbg(sev->dev, "sev command id %#x buffer 0x%08x%08x timeout %us\n", cmd, phys_msb, phys_lsb, psp_timeout); @@ -348,7 +935,18 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) sev->int_rcvd = 0; - reg = FIELD_PREP(SEV_CMDRESP_CMD, cmd) | SEV_CMDRESP_IOC; + reg = FIELD_PREP(SEV_CMDRESP_CMD, cmd); + + /* + * If invoked during panic handling, local interrupts are disabled so + * the PSP command completion interrupt can't be used. + * sev_wait_cmd_ioc() already checks for interrupts disabled and + * polls for PSP command completion. Ensure we do not request an + * interrupt from the PSP if irqs disabled. + */ + if (!irqs_disabled()) + reg |= SEV_CMDRESP_IOC; + iowrite32(reg, sev->io_regs + sev->vdata->cmdresp_reg); /* wait for command completion */ @@ -371,25 +969,59 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret) if (FIELD_GET(PSP_CMDRESP_STS, reg)) { dev_dbg(sev->dev, "sev command %#x failed (%#010lx)\n", cmd, FIELD_GET(PSP_CMDRESP_STS, reg)); + + /* + * PSP firmware may report additional error information in the + * command buffer registers on error. Print contents of command + * buffer registers if they changed. + */ + cmdbuff_hi = ioread32(sev->io_regs + sev->vdata->cmdbuff_addr_hi_reg); + cmdbuff_lo = ioread32(sev->io_regs + sev->vdata->cmdbuff_addr_lo_reg); + if (cmdbuff_hi != phys_msb || cmdbuff_lo != phys_lsb) { + dev_dbg(sev->dev, "Additional error information reported in cmdbuff:"); + dev_dbg(sev->dev, " cmdbuff hi: %#010x\n", cmdbuff_hi); + dev_dbg(sev->dev, " cmdbuff lo: %#010x\n", cmdbuff_lo); + } ret = -EIO; } else { ret = sev_write_init_ex_file_if_required(cmd); } - print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data, - buf_len, false); - /* * Copy potential output from the PSP back to data. Do this even on * failure in case the caller wants to glean something from the error. */ - if (data) - memcpy(data, sev->cmd_buf, buf_len); + if (data) { + int ret_reclaim; + /* + * Restore the page state after the command completes. + */ + ret_reclaim = snp_reclaim_cmd_buf(cmd, cmd_buf); + if (ret_reclaim) { + dev_err(sev->dev, + "SEV: failed to reclaim buffer for legacy command %#x. Error: %d\n", + cmd, ret_reclaim); + return ret_reclaim; + } + + memcpy(data, cmd_buf, buf_len); + + if (sev->cmd_buf_backup_active) + sev->cmd_buf_backup_active = false; + else + sev->cmd_buf_active = false; + + if (snp_unmap_cmd_buf_desc_list(desc_list)) + return -EFAULT; + } + + print_hex_dump_debug("(out): ", DUMP_PREFIX_OFFSET, 16, 2, data, + buf_len, false); return ret; } -static int sev_do_cmd(int cmd, void *data, int *psp_ret) +int sev_do_cmd(int cmd, void *data, int *psp_ret) { int rc; @@ -399,6 +1031,7 @@ static int sev_do_cmd(int cmd, void *data, int *psp_ret) return rc; } +EXPORT_SYMBOL_GPL(sev_do_cmd); static int __sev_init_locked(int *error) { @@ -413,7 +1046,7 @@ static int __sev_init_locked(int *error) data.tmr_address = __pa(sev_es_tmr); data.flags |= SEV_INIT_FLAGS_SEV_ES; - data.tmr_len = SEV_ES_TMR_SIZE; + data.tmr_len = sev_es_tmr_size; } return __sev_do_cmd_locked(SEV_CMD_INIT, &data, error); @@ -436,7 +1069,7 @@ static int __sev_init_ex_locked(int *error) data.tmr_address = __pa(sev_es_tmr); data.flags |= SEV_INIT_FLAGS_SEV_ES; - data.tmr_len = SEV_ES_TMR_SIZE; + data.tmr_len = sev_es_tmr_size; } return __sev_do_cmd_locked(SEV_CMD_INIT_EX, &data, error); @@ -450,26 +1083,518 @@ static inline int __sev_do_init_locked(int *psp_ret) return __sev_init_locked(psp_ret); } -static int __sev_platform_init_locked(int *error) +static void snp_set_hsave_pa(void *arg) +{ + wrmsrq(MSR_VM_HSAVE_PA, 0); +} + +/* Hypervisor Fixed pages API interface */ +static void snp_hv_fixed_pages_state_update(struct sev_device *sev, + enum snp_hv_fixed_pages_state page_state) +{ + struct snp_hv_fixed_pages_entry *entry; + + /* List is protected by sev_cmd_mutex */ + lockdep_assert_held(&sev_cmd_mutex); + + if (list_empty(&snp_hv_fixed_pages)) + return; + + list_for_each_entry(entry, &snp_hv_fixed_pages, list) + entry->page_state = page_state; +} + +/* + * Allocate HV_FIXED pages in 2MB aligned sizes to ensure the whole + * 2MB pages are marked as HV_FIXED. + */ +struct page *snp_alloc_hv_fixed_pages(unsigned int num_2mb_pages) +{ + struct psp_device *psp_master = psp_get_master_device(); + struct snp_hv_fixed_pages_entry *entry; + struct sev_device *sev; + unsigned int order; + struct page *page; + + if (!psp_master || !psp_master->sev_data) + return NULL; + + sev = psp_master->sev_data; + + order = get_order(PMD_SIZE * num_2mb_pages); + + /* + * SNP_INIT_EX is protected by sev_cmd_mutex, therefore this list + * also needs to be protected using the same mutex. + */ + guard(mutex)(&sev_cmd_mutex); + + /* + * This API uses SNP_INIT_EX to transition allocated pages to HV_Fixed + * page state, fail if SNP is already initialized. + */ + if (sev->snp_initialized) + return NULL; + + /* Re-use freed pages that match the request */ + list_for_each_entry(entry, &snp_hv_fixed_pages, list) { + /* Hypervisor fixed page allocator implements exact fit policy */ + if (entry->order == order && entry->free) { + entry->free = false; + memset(page_address(entry->page), 0, + (1 << entry->order) * PAGE_SIZE); + return entry->page; + } + } + + page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order); + if (!page) + return NULL; + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + __free_pages(page, order); + return NULL; + } + + entry->page = page; + entry->order = order; + list_add_tail(&entry->list, &snp_hv_fixed_pages); + + return page; +} + +void snp_free_hv_fixed_pages(struct page *page) +{ + struct psp_device *psp_master = psp_get_master_device(); + struct snp_hv_fixed_pages_entry *entry, *nentry; + + if (!psp_master || !psp_master->sev_data) + return; + + /* + * SNP_INIT_EX is protected by sev_cmd_mutex, therefore this list + * also needs to be protected using the same mutex. + */ + guard(mutex)(&sev_cmd_mutex); + + list_for_each_entry_safe(entry, nentry, &snp_hv_fixed_pages, list) { + if (entry->page != page) + continue; + + /* + * HV_FIXED page state cannot be changed until reboot + * and they cannot be used by an SNP guest, so they cannot + * be returned back to the page allocator. + * Mark the pages as free internally to allow possible re-use. + */ + if (entry->page_state == HV_FIXED) { + entry->free = true; + } else { + __free_pages(page, entry->order); + list_del(&entry->list); + kfree(entry); + } + return; + } +} + +static void snp_add_hv_fixed_pages(struct sev_device *sev, struct sev_data_range_list *range_list) +{ + struct snp_hv_fixed_pages_entry *entry; + struct sev_data_range *range; + int num_elements; + + lockdep_assert_held(&sev_cmd_mutex); + + if (list_empty(&snp_hv_fixed_pages)) + return; + + num_elements = list_count_nodes(&snp_hv_fixed_pages) + + range_list->num_elements; + + /* + * Ensure the list of HV_FIXED pages that will be passed to firmware + * do not exceed the page-sized argument buffer. + */ + if (num_elements * sizeof(*range) + sizeof(*range_list) > PAGE_SIZE) { + dev_warn(sev->dev, "Additional HV_Fixed pages cannot be accommodated, omitting\n"); + return; + } + + range = &range_list->ranges[range_list->num_elements]; + list_for_each_entry(entry, &snp_hv_fixed_pages, list) { + range->base = page_to_pfn(entry->page) << PAGE_SHIFT; + range->page_count = 1 << entry->order; + range++; + } + range_list->num_elements = num_elements; +} + +static void snp_leak_hv_fixed_pages(void) +{ + struct snp_hv_fixed_pages_entry *entry; + + /* List is protected by sev_cmd_mutex */ + lockdep_assert_held(&sev_cmd_mutex); + + if (list_empty(&snp_hv_fixed_pages)) + return; + + list_for_each_entry(entry, &snp_hv_fixed_pages, list) + if (entry->page_state == HV_FIXED) + __snp_leak_pages(page_to_pfn(entry->page), + 1 << entry->order, false); +} + +bool sev_is_snp_ciphertext_hiding_supported(void) { - int rc = 0, psp_ret = SEV_RET_NO_FW_CALL; struct psp_device *psp = psp_master; struct sev_device *sev; if (!psp || !psp->sev_data) + return false; + + sev = psp->sev_data; + + /* + * Feature information indicates if CipherTextHiding feature is + * supported by the SEV firmware and additionally platform status + * indicates if CipherTextHiding feature is enabled in the + * Platform BIOS. + */ + return ((sev->snp_feat_info_0.ecx & SNP_CIPHER_TEXT_HIDING_SUPPORTED) && + sev->snp_plat_status.ciphertext_hiding_cap); +} +EXPORT_SYMBOL_GPL(sev_is_snp_ciphertext_hiding_supported); + +static int snp_get_platform_data(struct sev_device *sev, int *error) +{ + struct sev_data_snp_feature_info snp_feat_info; + struct snp_feature_info *feat_info; + struct sev_data_snp_addr buf; + struct page *page; + int rc; + + /* + * This function is expected to be called before SNP is + * initialized. + */ + if (sev->snp_initialized) + return -EINVAL; + + buf.address = __psp_pa(&sev->snp_plat_status); + rc = sev_do_cmd(SEV_CMD_SNP_PLATFORM_STATUS, &buf, error); + if (rc) { + dev_err(sev->dev, "SNP PLATFORM_STATUS command failed, ret = %d, error = %#x\n", + rc, *error); + return rc; + } + + sev->api_major = sev->snp_plat_status.api_major; + sev->api_minor = sev->snp_plat_status.api_minor; + sev->build = sev->snp_plat_status.build_id; + + /* + * Do feature discovery of the currently loaded firmware, + * and cache feature information from CPUID 0x8000_0024, + * sub-function 0. + */ + if (!sev->snp_plat_status.feature_info) + return 0; + + /* + * Use dynamically allocated structure for the SNP_FEATURE_INFO + * command to ensure structure is 8-byte aligned, and does not + * cross a page boundary. + */ + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + + feat_info = page_address(page); + snp_feat_info.length = sizeof(snp_feat_info); + snp_feat_info.ecx_in = 0; + snp_feat_info.feature_info_paddr = __psp_pa(feat_info); + + rc = sev_do_cmd(SEV_CMD_SNP_FEATURE_INFO, &snp_feat_info, error); + if (!rc) + sev->snp_feat_info_0 = *feat_info; + else + dev_err(sev->dev, "SNP FEATURE_INFO command failed, ret = %d, error = %#x\n", + rc, *error); + + __free_page(page); + + return rc; +} + +static int snp_filter_reserved_mem_regions(struct resource *rs, void *arg) +{ + struct sev_data_range_list *range_list = arg; + struct sev_data_range *range = &range_list->ranges[range_list->num_elements]; + size_t size; + + /* + * Ensure the list of HV_FIXED pages that will be passed to firmware + * do not exceed the page-sized argument buffer. + */ + if ((range_list->num_elements * sizeof(struct sev_data_range) + + sizeof(struct sev_data_range_list)) > PAGE_SIZE) + return -E2BIG; + + switch (rs->desc) { + case E820_TYPE_RESERVED: + case E820_TYPE_PMEM: + case E820_TYPE_ACPI: + range->base = rs->start & PAGE_MASK; + size = PAGE_ALIGN((rs->end + 1) - rs->start); + range->page_count = size >> PAGE_SHIFT; + range_list->num_elements++; + break; + default: + break; + } + + return 0; +} + +static int __sev_snp_init_locked(int *error, unsigned int max_snp_asid) +{ + struct psp_device *psp = psp_master; + struct sev_data_snp_init_ex data; + struct sev_device *sev; + void *arg = &data; + int cmd, rc = 0; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) return -ENODEV; sev = psp->sev_data; - if (sev->state == SEV_STATE_INIT) + if (sev->snp_initialized) return 0; - if (sev_init_ex_buffer) { - rc = sev_read_init_ex_file(); - if (rc) + if (!sev_version_greater_or_equal(SNP_MIN_API_MAJOR, SNP_MIN_API_MINOR)) { + dev_dbg(sev->dev, "SEV-SNP support requires firmware version >= %d:%d\n", + SNP_MIN_API_MAJOR, SNP_MIN_API_MINOR); + return -EOPNOTSUPP; + } + + /* SNP_INIT requires MSR_VM_HSAVE_PA to be cleared on all CPUs. */ + on_each_cpu(snp_set_hsave_pa, NULL, 1); + + /* + * Starting in SNP firmware v1.52, the SNP_INIT_EX command takes a list + * of system physical address ranges to convert into HV-fixed page + * states during the RMP initialization. For instance, the memory that + * UEFI reserves should be included in the that list. This allows system + * components that occasionally write to memory (e.g. logging to UEFI + * reserved regions) to not fail due to RMP initialization and SNP + * enablement. + * + */ + if (sev_version_greater_or_equal(SNP_MIN_API_MAJOR, 52)) { + bool tio_supp = !!(sev->snp_feat_info_0.ebx & SNP_SEV_TIO_SUPPORTED); + + /* + * Firmware checks that the pages containing the ranges enumerated + * in the RANGES structure are either in the default page state or in the + * firmware page state. + */ + snp_range_list = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!snp_range_list) { + dev_err(sev->dev, + "SEV: SNP_INIT_EX range list memory allocation failed\n"); + return -ENOMEM; + } + + /* + * Retrieve all reserved memory regions from the e820 memory map + * to be setup as HV-fixed pages. + */ + rc = walk_iomem_res_desc(IORES_DESC_NONE, IORESOURCE_MEM, 0, ~0, + snp_range_list, snp_filter_reserved_mem_regions); + if (rc) { + dev_err(sev->dev, + "SEV: SNP_INIT_EX walk_iomem_res_desc failed rc = %d\n", rc); return rc; + } + + /* + * Add HV_Fixed pages from other PSP sub-devices, such as SFS to the + * HV_Fixed page list. + */ + snp_add_hv_fixed_pages(sev, snp_range_list); + + memset(&data, 0, sizeof(data)); + + if (max_snp_asid) { + data.ciphertext_hiding_en = 1; + data.max_snp_asid = max_snp_asid; + } + + data.init_rmp = 1; + data.list_paddr_en = 1; + data.list_paddr = __psp_pa(snp_range_list); + + data.tio_en = tio_supp && sev_tio_enabled && amd_iommu_sev_tio_supported(); + + /* + * When psp_init_on_probe is disabled, the userspace calling + * SEV ioctl can inadvertently shut down SNP and SEV-TIO causing + * unexpected state loss. + */ + if (data.tio_en && !psp_init_on_probe) + dev_warn(sev->dev, "SEV-TIO as incompatible with psp_init_on_probe=0\n"); + + cmd = SEV_CMD_SNP_INIT_EX; + } else { + cmd = SEV_CMD_SNP_INIT; + arg = NULL; + } + + /* + * The following sequence must be issued before launching the first SNP + * guest to ensure all dirty cache lines are flushed, including from + * updates to the RMP table itself via the RMPUPDATE instruction: + * + * - WBINVD on all running CPUs + * - SEV_CMD_SNP_INIT[_EX] firmware command + * - WBINVD on all running CPUs + * - SEV_CMD_SNP_DF_FLUSH firmware command + */ + wbinvd_on_all_cpus(); + + rc = __sev_do_cmd_locked(cmd, arg, error); + if (rc) { + dev_err(sev->dev, "SEV-SNP: %s failed rc %d, error %#x\n", + cmd == SEV_CMD_SNP_INIT_EX ? "SNP_INIT_EX" : "SNP_INIT", + rc, *error); + return rc; + } + + /* Prepare for first SNP guest launch after INIT. */ + wbinvd_on_all_cpus(); + rc = __sev_do_cmd_locked(SEV_CMD_SNP_DF_FLUSH, NULL, error); + if (rc) { + dev_err(sev->dev, "SEV-SNP: SNP_DF_FLUSH failed rc %d, error %#x\n", + rc, *error); + return rc; + } + + snp_hv_fixed_pages_state_update(sev, HV_FIXED); + sev->snp_initialized = true; + dev_dbg(sev->dev, "SEV-SNP firmware initialized, SEV-TIO is %s\n", + data.tio_en ? "enabled" : "disabled"); + + dev_info(sev->dev, "SEV-SNP API:%d.%d build:%d\n", sev->api_major, + sev->api_minor, sev->build); + + atomic_notifier_chain_register(&panic_notifier_list, + &snp_panic_notifier); + + if (data.tio_en) { + /* + * This executes with the sev_cmd_mutex held so down the stack + * snp_reclaim_pages(locked=false) might be needed (which is extremely + * unlikely) but will cause a deadlock. + * Instead of exporting __snp_alloc_firmware_pages(), allocate a page + * for this one call here. + */ + void *tio_status = page_address(__snp_alloc_firmware_pages( + GFP_KERNEL_ACCOUNT | __GFP_ZERO, 0, true)); + + if (tio_status) { + sev_tsm_init_locked(sev, tio_status); + __snp_free_firmware_pages(virt_to_page(tio_status), 0, true); + } + } + + sev_es_tmr_size = SNP_TMR_SIZE; + + return 0; +} + +static void __sev_platform_init_handle_tmr(struct sev_device *sev) +{ + if (sev_es_tmr) + return; + + /* Obtain the TMR memory area for SEV-ES use */ + sev_es_tmr = sev_fw_alloc(sev_es_tmr_size); + if (sev_es_tmr) { + /* Must flush the cache before giving it to the firmware */ + if (!sev->snp_initialized) + clflush_cache_range(sev_es_tmr, sev_es_tmr_size); + } else { + dev_warn(sev->dev, "SEV: TMR allocation failed, SEV-ES support unavailable\n"); + } +} + +/* + * If an init_ex_path is provided allocate a buffer for the file and + * read in the contents. Additionally, if SNP is initialized, convert + * the buffer pages to firmware pages. + */ +static int __sev_platform_init_handle_init_ex_path(struct sev_device *sev) +{ + struct page *page; + int rc; + + if (!init_ex_path) + return 0; + + if (sev_init_ex_buffer) + return 0; + + page = alloc_pages(GFP_KERNEL, get_order(NV_LENGTH)); + if (!page) { + dev_err(sev->dev, "SEV: INIT_EX NV memory allocation failed\n"); + return -ENOMEM; + } + + sev_init_ex_buffer = page_address(page); + + rc = sev_read_init_ex_file(); + if (rc) + return rc; + + /* If SEV-SNP is initialized, transition to firmware page. */ + if (sev->snp_initialized) { + unsigned long npages; + + npages = 1UL << get_order(NV_LENGTH); + if (rmp_mark_pages_firmware(__pa(sev_init_ex_buffer), npages, false)) { + dev_err(sev->dev, "SEV: INIT_EX NV memory page state change failed.\n"); + return -ENOMEM; + } } + return 0; +} + +static int __sev_platform_init_locked(int *error) +{ + int rc, psp_ret, dfflush_error; + struct sev_device *sev; + + psp_ret = dfflush_error = SEV_RET_NO_FW_CALL; + + if (!psp_master || !psp_master->sev_data) + return -ENODEV; + + sev = psp_master->sev_data; + + if (sev->sev_plat_status.state == SEV_STATE_INIT) + return 0; + + __sev_platform_init_handle_tmr(sev); + + rc = __sev_platform_init_handle_init_ex_path(sev); + if (rc) + return rc; + rc = __sev_do_init_locked(&psp_ret); if (rc && psp_ret == SEV_RET_SECURE_DATA_INVALID) { /* @@ -487,16 +1612,22 @@ static int __sev_platform_init_locked(int *error) if (error) *error = psp_ret; - if (rc) + if (rc) { + dev_err(sev->dev, "SEV: %s failed %#x, rc %d\n", + sev_init_ex_buffer ? "INIT_EX" : "INIT", psp_ret, rc); return rc; + } - sev->state = SEV_STATE_INIT; + sev->sev_plat_status.state = SEV_STATE_INIT; /* Prepare for first SEV guest launch after INIT */ wbinvd_on_all_cpus(); - rc = __sev_do_cmd_locked(SEV_CMD_DF_FLUSH, NULL, error); - if (rc) + rc = __sev_do_cmd_locked(SEV_CMD_DF_FLUSH, NULL, &dfflush_error); + if (rc) { + dev_err(sev->dev, "SEV: DF_FLUSH failed %#x, rc %d\n", + dfflush_error, rc); return rc; + } dev_dbg(sev->dev, "SEV firmware initialized\n"); @@ -506,12 +1637,45 @@ static int __sev_platform_init_locked(int *error) return 0; } -int sev_platform_init(int *error) +static int _sev_platform_init_locked(struct sev_platform_init_args *args) +{ + struct sev_device *sev; + int rc; + + if (!psp_master || !psp_master->sev_data) + return -ENODEV; + + /* + * Skip SNP/SEV initialization under a kdump kernel as SEV/SNP + * may already be initialized in the previous kernel. Since no + * SNP/SEV guests are run under a kdump kernel, there is no + * need to initialize SNP or SEV during kdump boot. + */ + if (is_kdump_kernel()) + return 0; + + sev = psp_master->sev_data; + + if (sev->sev_plat_status.state == SEV_STATE_INIT) + return 0; + + rc = __sev_snp_init_locked(&args->error, args->max_snp_asid); + if (rc && rc != -ENODEV) + return rc; + + /* Defer legacy SEV/SEV-ES support if allowed by caller/module. */ + if (args->probe && !psp_init_on_probe) + return 0; + + return __sev_platform_init_locked(&args->error); +} + +int sev_platform_init(struct sev_platform_init_args *args) { int rc; mutex_lock(&sev_cmd_mutex); - rc = __sev_platform_init_locked(error); + rc = _sev_platform_init_locked(args); mutex_unlock(&sev_cmd_mutex); return rc; @@ -520,44 +1684,73 @@ EXPORT_SYMBOL_GPL(sev_platform_init); static int __sev_platform_shutdown_locked(int *error) { - struct sev_device *sev = psp_master->sev_data; + struct psp_device *psp = psp_master; + struct sev_device *sev; int ret; - if (!sev || sev->state == SEV_STATE_UNINIT) + if (!psp || !psp->sev_data) + return 0; + + sev = psp->sev_data; + + if (sev->sev_plat_status.state == SEV_STATE_UNINIT) return 0; ret = __sev_do_cmd_locked(SEV_CMD_SHUTDOWN, NULL, error); - if (ret) + if (ret) { + dev_err(sev->dev, "SEV: failed to SHUTDOWN error %#x, rc %d\n", + *error, ret); return ret; + } - sev->state = SEV_STATE_UNINIT; + sev->sev_plat_status.state = SEV_STATE_UNINIT; dev_dbg(sev->dev, "SEV firmware shutdown\n"); return ret; } -static int sev_platform_shutdown(int *error) +static int sev_get_platform_state(int *state, int *error) { + struct sev_user_data_status data; int rc; - mutex_lock(&sev_cmd_mutex); - rc = __sev_platform_shutdown_locked(NULL); - mutex_unlock(&sev_cmd_mutex); + rc = __sev_do_cmd_locked(SEV_CMD_PLATFORM_STATUS, &data, error); + if (rc) + return rc; + *state = data.state; return rc; } -static int sev_get_platform_state(int *state, int *error) +static int sev_move_to_init_state(struct sev_issue_cmd *argp, bool *shutdown_required) { - struct sev_user_data_status data; + struct sev_platform_init_args init_args = {0}; int rc; - rc = __sev_do_cmd_locked(SEV_CMD_PLATFORM_STATUS, &data, error); - if (rc) + rc = _sev_platform_init_locked(&init_args); + if (rc) { + argp->error = SEV_RET_INVALID_PLATFORM_STATE; return rc; + } - *state = data.state; - return rc; + *shutdown_required = true; + + return 0; +} + +static int snp_move_to_init_state(struct sev_issue_cmd *argp, bool *shutdown_required) +{ + int error, rc; + + rc = __sev_snp_init_locked(&error, 0); + if (rc) { + argp->error = SEV_RET_INVALID_PLATFORM_STATE; + return rc; + } + + *shutdown_required = true; + + return 0; } static int sev_ioctl_do_reset(struct sev_issue_cmd *argp, bool writable) @@ -612,24 +1805,31 @@ static int sev_ioctl_do_platform_status(struct sev_issue_cmd *argp) static int sev_ioctl_do_pek_pdh_gen(int cmd, struct sev_issue_cmd *argp, bool writable) { struct sev_device *sev = psp_master->sev_data; + bool shutdown_required = false; int rc; if (!writable) return -EPERM; - if (sev->state == SEV_STATE_UNINIT) { - rc = __sev_platform_init_locked(&argp->error); + if (sev->sev_plat_status.state == SEV_STATE_UNINIT) { + rc = sev_move_to_init_state(argp, &shutdown_required); if (rc) return rc; } - return __sev_do_cmd_locked(cmd, NULL, &argp->error); + rc = __sev_do_cmd_locked(cmd, NULL, &argp->error); + + if (shutdown_required) + __sev_firmware_shutdown(sev, false); + + return rc; } static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp, bool writable) { struct sev_device *sev = psp_master->sev_data; struct sev_user_data_pek_csr input; + bool shutdown_required = false; struct sev_data_pek_csr data; void __user *input_address; void *blob = NULL; @@ -660,8 +1860,8 @@ static int sev_ioctl_do_pek_csr(struct sev_issue_cmd *argp, bool writable) data.len = input.length; cmd: - if (sev->state == SEV_STATE_UNINIT) { - ret = __sev_platform_init_locked(&argp->error); + if (sev->sev_plat_status.state == SEV_STATE_UNINIT) { + ret = sev_move_to_init_state(argp, &shutdown_required); if (ret) goto e_free_blob; } @@ -682,6 +1882,9 @@ cmd: } e_free_blob: + if (shutdown_required) + __sev_firmware_shutdown(sev, false); + kfree(blob); return ret; } @@ -705,6 +1908,16 @@ static int sev_get_api_version(void) struct sev_user_data_status status; int error = 0, ret; + /* + * Cache SNP platform status and SNP feature information + * if SNP is available. + */ + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) { + ret = snp_get_platform_data(sev, &error); + if (ret) + return 1; + } + ret = sev_platform_status(&status, &error); if (ret) { dev_err(sev->dev, @@ -712,10 +1925,12 @@ static int sev_get_api_version(void) return 1; } + /* Cache SEV platform status */ + sev->sev_plat_status = status; + sev->api_major = status.api_major; sev->api_minor = status.api_minor; sev->build = status.build; - sev->state = status.state; return 0; } @@ -811,8 +2026,6 @@ static int sev_update_firmware(struct device *dev) if (ret) dev_dbg(dev, "Failed to update SEV firmware: %#x\n", error); - else - dev_info(dev, "SEV firmware update successful\n"); __free_pages(p, order); @@ -822,11 +2035,101 @@ fw_err: return ret; } +static int __sev_snp_shutdown_locked(int *error, bool panic) +{ + struct psp_device *psp = psp_master; + struct sev_device *sev; + struct sev_data_snp_shutdown_ex data; + int ret; + + if (!psp || !psp->sev_data) + return 0; + + sev = psp->sev_data; + + if (!sev->snp_initialized) + return 0; + + memset(&data, 0, sizeof(data)); + data.len = sizeof(data); + data.iommu_snp_shutdown = 1; + + /* + * If invoked during panic handling, local interrupts are disabled + * and all CPUs are stopped, so wbinvd_on_all_cpus() can't be called. + * In that case, a wbinvd() is done on remote CPUs via the NMI + * callback, so only a local wbinvd() is needed here. + */ + if (!panic) + wbinvd_on_all_cpus(); + else + wbinvd(); + + ret = __sev_do_cmd_locked(SEV_CMD_SNP_SHUTDOWN_EX, &data, error); + /* SHUTDOWN may require DF_FLUSH */ + if (*error == SEV_RET_DFFLUSH_REQUIRED) { + int dfflush_error = SEV_RET_NO_FW_CALL; + + ret = __sev_do_cmd_locked(SEV_CMD_SNP_DF_FLUSH, NULL, &dfflush_error); + if (ret) { + dev_err(sev->dev, "SEV-SNP DF_FLUSH failed, ret = %d, error = %#x\n", + ret, dfflush_error); + return ret; + } + /* reissue the shutdown command */ + ret = __sev_do_cmd_locked(SEV_CMD_SNP_SHUTDOWN_EX, &data, + error); + } + if (ret) { + dev_err(sev->dev, "SEV-SNP firmware shutdown failed, rc %d, error %#x\n", + ret, *error); + return ret; + } + + /* + * SNP_SHUTDOWN_EX with IOMMU_SNP_SHUTDOWN set to 1 disables SNP + * enforcement by the IOMMU and also transitions all pages + * associated with the IOMMU to the Reclaim state. + * Firmware was transitioning the IOMMU pages to Hypervisor state + * before version 1.53. But, accounting for the number of assigned + * 4kB pages in a 2M page was done incorrectly by not transitioning + * to the Reclaim state. This resulted in RMP #PF when later accessing + * the 2M page containing those pages during kexec boot. Hence, the + * firmware now transitions these pages to Reclaim state and hypervisor + * needs to transition these pages to shared state. SNP Firmware + * version 1.53 and above are needed for kexec boot. + */ + ret = amd_iommu_snp_disable(); + if (ret) { + dev_err(sev->dev, "SNP IOMMU shutdown failed\n"); + return ret; + } + + snp_leak_hv_fixed_pages(); + sev->snp_initialized = false; + dev_dbg(sev->dev, "SEV-SNP firmware shutdown\n"); + + /* + * __sev_snp_shutdown_locked() deadlocks when it tries to unregister + * itself during panic as the panic notifier is called with RCU read + * lock held and notifier unregistration does RCU synchronization. + */ + if (!panic) + atomic_notifier_chain_unregister(&panic_notifier_list, + &snp_panic_notifier); + + /* Reset TMR size back to default */ + sev_es_tmr_size = SEV_TMR_SIZE; + + return ret; +} + static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp, bool writable) { struct sev_device *sev = psp_master->sev_data; struct sev_user_data_pek_cert_import input; struct sev_data_pek_cert_import data; + bool shutdown_required = false; void *pek_blob, *oca_blob; int ret; @@ -856,8 +2159,8 @@ static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp, bool writable) data.oca_cert_len = input.oca_cert_len; /* If platform is not in INIT state then transition it to INIT */ - if (sev->state != SEV_STATE_INIT) { - ret = __sev_platform_init_locked(&argp->error); + if (sev->sev_plat_status.state != SEV_STATE_INIT) { + ret = sev_move_to_init_state(argp, &shutdown_required); if (ret) goto e_free_oca; } @@ -865,6 +2168,9 @@ static int sev_ioctl_do_pek_import(struct sev_issue_cmd *argp, bool writable) ret = __sev_do_cmd_locked(SEV_CMD_PEK_CERT_IMPORT, &data, &argp->error); e_free_oca: + if (shutdown_required) + __sev_firmware_shutdown(sev, false); + kfree(oca_blob); e_free_pek: kfree(pek_blob); @@ -892,7 +2198,7 @@ static int sev_ioctl_do_get_id2(struct sev_issue_cmd *argp) /* * The length of the ID shouldn't be assumed by software since * it may change in the future. The allocation size is limited - * to 1 << (PAGE_SHIFT + MAX_ORDER) by the page allocator. + * to 1 << (PAGE_SHIFT + MAX_PAGE_ORDER) by the page allocator. * If the allocation fails, simply return ENOMEM rather than * warning in the kernel log. */ @@ -981,32 +2287,23 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable) struct sev_data_pdh_cert_export data; void __user *input_cert_chain_address; void __user *input_pdh_cert_address; + bool shutdown_required = false; int ret; - /* If platform is not in INIT state then transition it to INIT. */ - if (sev->state != SEV_STATE_INIT) { - if (!writable) - return -EPERM; - - ret = __sev_platform_init_locked(&argp->error); - if (ret) - return ret; - } - if (copy_from_user(&input, (void __user *)argp->data, sizeof(input))) return -EFAULT; memset(&data, 0, sizeof(data)); + input_pdh_cert_address = (void __user *)input.pdh_cert_address; + input_cert_chain_address = (void __user *)input.cert_chain_address; + /* Userspace wants to query the certificate length. */ if (!input.pdh_cert_address || !input.pdh_cert_len || !input.cert_chain_address) goto cmd; - input_pdh_cert_address = (void __user *)input.pdh_cert_address; - input_cert_chain_address = (void __user *)input.cert_chain_address; - /* Allocate a physically contiguous buffer to store the PDH blob. */ if (input.pdh_cert_len > SEV_FW_BLOB_MAX_SIZE) return -EFAULT; @@ -1032,6 +2329,17 @@ static int sev_ioctl_do_pdh_export(struct sev_issue_cmd *argp, bool writable) data.cert_chain_len = input.cert_chain_len; cmd: + /* If platform is not in INIT state then transition it to INIT. */ + if (sev->sev_plat_status.state != SEV_STATE_INIT) { + if (!writable) { + ret = -EPERM; + goto e_free_cert; + } + ret = sev_move_to_init_state(argp, &shutdown_required); + if (ret) + goto e_free_cert; + } + ret = __sev_do_cmd_locked(SEV_CMD_PDH_CERT_EXPORT, &data, &argp->error); /* If we query the length, FW responded with expected data. */ @@ -1058,12 +2366,171 @@ cmd: } e_free_cert: + if (shutdown_required) + __sev_firmware_shutdown(sev, false); + kfree(cert_blob); e_free_pdh: kfree(pdh_blob); return ret; } +static int sev_ioctl_do_snp_platform_status(struct sev_issue_cmd *argp) +{ + struct sev_device *sev = psp_master->sev_data; + bool shutdown_required = false; + struct sev_data_snp_addr buf; + struct page *status_page; + int ret, error; + void *data; + + if (!argp->data) + return -EINVAL; + + status_page = alloc_page(GFP_KERNEL_ACCOUNT); + if (!status_page) + return -ENOMEM; + + data = page_address(status_page); + + if (!sev->snp_initialized) { + ret = snp_move_to_init_state(argp, &shutdown_required); + if (ret) + goto cleanup; + } + + /* + * Firmware expects status page to be in firmware-owned state, otherwise + * it will report firmware error code INVALID_PAGE_STATE (0x1A). + */ + if (rmp_mark_pages_firmware(__pa(data), 1, true)) { + ret = -EFAULT; + goto cleanup; + } + + buf.address = __psp_pa(data); + ret = __sev_do_cmd_locked(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &argp->error); + + /* + * Status page will be transitioned to Reclaim state upon success, or + * left in Firmware state in failure. Use snp_reclaim_pages() to + * transition either case back to Hypervisor-owned state. + */ + if (snp_reclaim_pages(__pa(data), 1, true)) + return -EFAULT; + + if (ret) + goto cleanup; + + if (copy_to_user((void __user *)argp->data, data, + sizeof(struct sev_user_data_snp_status))) + ret = -EFAULT; + +cleanup: + if (shutdown_required) + __sev_snp_shutdown_locked(&error, false); + + __free_pages(status_page, 0); + return ret; +} + +static int sev_ioctl_do_snp_commit(struct sev_issue_cmd *argp) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_data_snp_commit buf; + bool shutdown_required = false; + int ret, error; + + if (!sev->snp_initialized) { + ret = snp_move_to_init_state(argp, &shutdown_required); + if (ret) + return ret; + } + + buf.len = sizeof(buf); + + ret = __sev_do_cmd_locked(SEV_CMD_SNP_COMMIT, &buf, &argp->error); + + if (shutdown_required) + __sev_snp_shutdown_locked(&error, false); + + return ret; +} + +static int sev_ioctl_do_snp_set_config(struct sev_issue_cmd *argp, bool writable) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_user_data_snp_config config; + bool shutdown_required = false; + int ret, error; + + if (!argp->data) + return -EINVAL; + + if (!writable) + return -EPERM; + + if (copy_from_user(&config, (void __user *)argp->data, sizeof(config))) + return -EFAULT; + + if (!sev->snp_initialized) { + ret = snp_move_to_init_state(argp, &shutdown_required); + if (ret) + return ret; + } + + ret = __sev_do_cmd_locked(SEV_CMD_SNP_CONFIG, &config, &argp->error); + + if (shutdown_required) + __sev_snp_shutdown_locked(&error, false); + + return ret; +} + +static int sev_ioctl_do_snp_vlek_load(struct sev_issue_cmd *argp, bool writable) +{ + struct sev_device *sev = psp_master->sev_data; + struct sev_user_data_snp_vlek_load input; + bool shutdown_required = false; + int ret, error; + void *blob; + + if (!argp->data) + return -EINVAL; + + if (!writable) + return -EPERM; + + if (copy_from_user(&input, u64_to_user_ptr(argp->data), sizeof(input))) + return -EFAULT; + + if (input.len != sizeof(input) || input.vlek_wrapped_version != 0) + return -EINVAL; + + blob = psp_copy_user_blob(input.vlek_wrapped_address, + sizeof(struct sev_user_data_snp_wrapped_vlek_hashstick)); + if (IS_ERR(blob)) + return PTR_ERR(blob); + + input.vlek_wrapped_address = __psp_pa(blob); + + if (!sev->snp_initialized) { + ret = snp_move_to_init_state(argp, &shutdown_required); + if (ret) + goto cleanup; + } + + ret = __sev_do_cmd_locked(SEV_CMD_SNP_VLEK_LOAD, &input, &argp->error); + + if (shutdown_required) + __sev_snp_shutdown_locked(&error, false); + +cleanup: + kfree(blob); + + return ret; +} + static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { void __user *argp = (void __user *)arg; @@ -1115,6 +2582,18 @@ static long sev_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) case SEV_GET_ID2: ret = sev_ioctl_do_get_id2(&input); break; + case SNP_PLATFORM_STATUS: + ret = sev_ioctl_do_snp_platform_status(&input); + break; + case SNP_COMMIT: + ret = sev_ioctl_do_snp_commit(&input); + break; + case SNP_SET_CONFIG: + ret = sev_ioctl_do_snp_set_config(&input, writable); + break; + case SNP_VLEK_LOAD: + ret = sev_ioctl_do_snp_vlek_load(&input, writable); + break; default: ret = -EINVAL; goto out; @@ -1225,10 +2704,12 @@ int sev_dev_init(struct psp_device *psp) if (!sev) goto e_err; - sev->cmd_buf = (void *)devm_get_free_pages(dev, GFP_KERNEL, 0); + sev->cmd_buf = (void *)devm_get_free_pages(dev, GFP_KERNEL, 1); if (!sev->cmd_buf) goto e_sev; + sev->cmd_buf_backup = (uint8_t *)sev->cmd_buf + PAGE_SIZE; + psp->sev_data = sev; sev->dev = dev; @@ -1267,26 +2748,111 @@ e_err: return ret; } -static void sev_firmware_shutdown(struct sev_device *sev) +static void __sev_firmware_shutdown(struct sev_device *sev, bool panic) { - sev_platform_shutdown(NULL); + int error; + + __sev_platform_shutdown_locked(&error); if (sev_es_tmr) { - /* The TMR area was encrypted, flush it from the cache */ - wbinvd_on_all_cpus(); + /* + * The TMR area was encrypted, flush it from the cache. + * + * If invoked during panic handling, local interrupts are + * disabled and all CPUs are stopped, so wbinvd_on_all_cpus() + * can't be used. In that case, wbinvd() is done on remote CPUs + * via the NMI callback, and done for this CPU later during + * SNP shutdown, so wbinvd_on_all_cpus() can be skipped. + */ + if (!panic) + wbinvd_on_all_cpus(); - free_pages((unsigned long)sev_es_tmr, - get_order(SEV_ES_TMR_SIZE)); + __snp_free_firmware_pages(virt_to_page(sev_es_tmr), + get_order(sev_es_tmr_size), + true); sev_es_tmr = NULL; } if (sev_init_ex_buffer) { - free_pages((unsigned long)sev_init_ex_buffer, - get_order(NV_LENGTH)); + __snp_free_firmware_pages(virt_to_page(sev_init_ex_buffer), + get_order(NV_LENGTH), + true); sev_init_ex_buffer = NULL; } + + if (snp_range_list) { + kfree(snp_range_list); + snp_range_list = NULL; + } + + __sev_snp_shutdown_locked(&error, panic); } +static void sev_firmware_shutdown(struct sev_device *sev) +{ + /* + * Calling without sev_cmd_mutex held as TSM will likely try disconnecting + * IDE and this ends up calling sev_do_cmd() which locks sev_cmd_mutex. + */ + if (sev->tio_status) + sev_tsm_uninit(sev); + + mutex_lock(&sev_cmd_mutex); + + __sev_firmware_shutdown(sev, false); + + kfree(sev->tio_status); + sev->tio_status = NULL; + + mutex_unlock(&sev_cmd_mutex); +} + +void sev_platform_shutdown(void) +{ + if (!psp_master || !psp_master->sev_data) + return; + + sev_firmware_shutdown(psp_master->sev_data); +} +EXPORT_SYMBOL_GPL(sev_platform_shutdown); + +u64 sev_get_snp_policy_bits(void) +{ + struct psp_device *psp = psp_master; + struct sev_device *sev; + u64 policy_bits; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return 0; + + if (!psp || !psp->sev_data) + return 0; + + sev = psp->sev_data; + + policy_bits = SNP_POLICY_MASK_BASE; + + if (sev->snp_plat_status.feature_info) { + if (sev->snp_feat_info_0.ecx & SNP_RAPL_DISABLE_SUPPORTED) + policy_bits |= SNP_POLICY_MASK_RAPL_DIS; + + if (sev->snp_feat_info_0.ecx & SNP_CIPHER_TEXT_HIDING_SUPPORTED) + policy_bits |= SNP_POLICY_MASK_CIPHERTEXT_HIDING_DRAM; + + if (sev->snp_feat_info_0.ecx & SNP_AES_256_XTS_POLICY_SUPPORTED) + policy_bits |= SNP_POLICY_MASK_MEM_AES_256_XTS; + + if (sev->snp_feat_info_0.ecx & SNP_CXL_ALLOW_POLICY_SUPPORTED) + policy_bits |= SNP_POLICY_MASK_CXL_ALLOW; + + if (sev_version_greater_or_equal(1, 58)) + policy_bits |= SNP_POLICY_MASK_PAGE_SWAP_DISABLE; + } + + return policy_bits; +} +EXPORT_SYMBOL_GPL(sev_get_snp_policy_bits); + void sev_dev_destroy(struct psp_device *psp) { struct sev_device *sev = psp->sev_data; @@ -1302,6 +2868,25 @@ void sev_dev_destroy(struct psp_device *psp) psp_clear_sev_irq_handler(psp); } +static int snp_shutdown_on_panic(struct notifier_block *nb, + unsigned long reason, void *arg) +{ + struct sev_device *sev = psp_master->sev_data; + + /* + * If sev_cmd_mutex is already acquired, then it's likely + * another PSP command is in flight and issuing a shutdown + * would fail in unexpected ways. Rather than create even + * more confusion during a panic, just bail out here. + */ + if (mutex_is_locked(&sev_cmd_mutex)) + return NOTIFY_DONE; + + __sev_firmware_shutdown(sev, true); + + return NOTIFY_DONE; +} + int sev_issue_cmd_external_user(struct file *filep, unsigned int cmd, void *data, int *error) { @@ -1315,7 +2900,7 @@ EXPORT_SYMBOL_GPL(sev_issue_cmd_external_user); void sev_pci_init(void) { struct sev_device *sev = psp_master->sev_data; - int error, rc; + u8 api_major, api_minor, build; if (!sev) return; @@ -1325,42 +2910,24 @@ void sev_pci_init(void) if (sev_get_api_version()) goto err; + api_major = sev->api_major; + api_minor = sev->api_minor; + build = sev->build; + if (sev_update_firmware(sev->dev) == 0) sev_get_api_version(); - /* If an init_ex_path is provided rely on INIT_EX for PSP initialization - * instead of INIT. - */ - if (init_ex_path) { - sev_init_ex_buffer = sev_fw_alloc(NV_LENGTH); - if (!sev_init_ex_buffer) { - dev_err(sev->dev, - "SEV: INIT_EX NV memory allocation failed\n"); - goto err; - } - } - - /* Obtain the TMR memory area for SEV-ES use */ - sev_es_tmr = sev_fw_alloc(SEV_ES_TMR_SIZE); - if (sev_es_tmr) - /* Must flush the cache before giving it to the firmware */ - clflush_cache_range(sev_es_tmr, SEV_ES_TMR_SIZE); - else - dev_warn(sev->dev, - "SEV: TMR allocation failed, SEV-ES support unavailable\n"); - - if (!psp_init_on_probe) - return; - - /* Initialize the platform */ - rc = sev_platform_init(&error); - if (rc) - dev_err(sev->dev, "SEV: failed to INIT error %#x, rc %d\n", - error, rc); + if (api_major != sev->api_major || api_minor != sev->api_minor || + build != sev->build) + dev_info(sev->dev, "SEV firmware updated from %d.%d.%d to %d.%d.%d\n", + api_major, api_minor, build, + sev->api_major, sev->api_minor, sev->build); return; err: + sev_dev_destroy(psp_master); + psp_master->sev_data = NULL; } |