diff options
Diffstat (limited to 'drivers/virt')
| -rw-r--r-- | drivers/virt/acrn/irqfd.c | 2 | ||||
| -rw-r--r-- | drivers/virt/coco/Kconfig | 6 | ||||
| -rw-r--r-- | drivers/virt/coco/Makefile | 2 | ||||
| -rw-r--r-- | drivers/virt/coco/arm-cca-guest/arm-cca-guest.c | 16 | ||||
| -rw-r--r-- | drivers/virt/coco/efi_secret/efi_secret.c | 10 | ||||
| -rw-r--r-- | drivers/virt/coco/guest/Kconfig | 17 | ||||
| -rw-r--r-- | drivers/virt/coco/guest/Makefile | 4 | ||||
| -rw-r--r-- | drivers/virt/coco/guest/report.c (renamed from drivers/virt/coco/tsm.c) | 63 | ||||
| -rw-r--r-- | drivers/virt/coco/guest/tsm-mr.c | 251 | ||||
| -rw-r--r-- | drivers/virt/coco/sev-guest/Kconfig | 1 | ||||
| -rw-r--r-- | drivers/virt/coco/sev-guest/sev-guest.c | 530 | ||||
| -rw-r--r-- | drivers/virt/coco/tdx-guest/Kconfig | 1 | ||||
| -rw-r--r-- | drivers/virt/coco/tdx-guest/tdx-guest.c | 259 | ||||
| -rw-r--r-- | drivers/virt/vboxguest/Kconfig | 3 | ||||
| -rw-r--r-- | drivers/virt/vboxguest/vboxguest_core.c | 4 |
15 files changed, 567 insertions, 602 deletions
diff --git a/drivers/virt/acrn/irqfd.c b/drivers/virt/acrn/irqfd.c index b7da24ca1475..64d32c8fbf79 100644 --- a/drivers/virt/acrn/irqfd.c +++ b/drivers/virt/acrn/irqfd.c @@ -16,8 +16,6 @@ #include "acrn_drv.h" -static LIST_HEAD(acrn_irqfd_clients); - /** * struct hsm_irqfd - Properties of HSM irqfd * @vm: Associated VM pointer diff --git a/drivers/virt/coco/Kconfig b/drivers/virt/coco/Kconfig index ff869d883d95..819a97e8ba99 100644 --- a/drivers/virt/coco/Kconfig +++ b/drivers/virt/coco/Kconfig @@ -3,10 +3,6 @@ # Confidential computing related collateral # -config TSM_REPORTS - select CONFIGFS_FS - tristate - source "drivers/virt/coco/efi_secret/Kconfig" source "drivers/virt/coco/pkvm-guest/Kconfig" @@ -16,3 +12,5 @@ source "drivers/virt/coco/sev-guest/Kconfig" source "drivers/virt/coco/tdx-guest/Kconfig" source "drivers/virt/coco/arm-cca-guest/Kconfig" + +source "drivers/virt/coco/guest/Kconfig" diff --git a/drivers/virt/coco/Makefile b/drivers/virt/coco/Makefile index c3d07cfc087e..f918bbb61737 100644 --- a/drivers/virt/coco/Makefile +++ b/drivers/virt/coco/Makefile @@ -2,9 +2,9 @@ # # Confidential computing related collateral # -obj-$(CONFIG_TSM_REPORTS) += tsm.o obj-$(CONFIG_EFI_SECRET) += efi_secret/ obj-$(CONFIG_ARM_PKVM_GUEST) += pkvm-guest/ obj-$(CONFIG_SEV_GUEST) += sev-guest/ obj-$(CONFIG_INTEL_TDX_GUEST) += tdx-guest/ obj-$(CONFIG_ARM_CCA_GUEST) += arm-cca-guest/ +obj-$(CONFIG_TSM_GUEST) += guest/ diff --git a/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c b/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c index 488153879ec9..0c9ea24a200c 100644 --- a/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c +++ b/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c @@ -6,6 +6,7 @@ #include <linux/arm-smccc.h> #include <linux/cc_platform.h> #include <linux/kernel.h> +#include <linux/mod_devicetable.h> #include <linux/module.h> #include <linux/smp.h> #include <linux/tsm.h> @@ -95,7 +96,7 @@ static int arm_cca_report_new(struct tsm_report *report, void *data) struct arm_cca_token_info info; void *buf; u8 *token __free(kvfree) = NULL; - struct tsm_desc *desc = &report->desc; + struct tsm_report_desc *desc = &report->desc; if (desc->inblob_len < 32 || desc->inblob_len > 64) return -EINVAL; @@ -180,7 +181,7 @@ exit_free_granule_page: return ret; } -static const struct tsm_ops arm_cca_tsm_ops = { +static const struct tsm_report_ops arm_cca_tsm_ops = { .name = KBUILD_MODNAME, .report_new = arm_cca_report_new, }; @@ -201,7 +202,7 @@ static int __init arm_cca_guest_init(void) if (!is_realm_world()) return -ENODEV; - ret = tsm_register(&arm_cca_tsm_ops, NULL); + ret = tsm_report_register(&arm_cca_tsm_ops, NULL); if (ret < 0) pr_err("Error %d registering with TSM\n", ret); @@ -215,10 +216,17 @@ module_init(arm_cca_guest_init); */ static void __exit arm_cca_guest_exit(void) { - tsm_unregister(&arm_cca_tsm_ops); + tsm_report_unregister(&arm_cca_tsm_ops); } module_exit(arm_cca_guest_exit); +/* modalias, so userspace can autoload this module when RSI is available */ +static const struct platform_device_id arm_cca_match[] __maybe_unused = { + { RSI_PDEV_NAME, 0}, + { } +}; + +MODULE_DEVICE_TABLE(platform, arm_cca_match); MODULE_AUTHOR("Sami Mujawar <sami.mujawar@arm.com>"); MODULE_DESCRIPTION("Arm CCA Guest TSM Driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/virt/coco/efi_secret/efi_secret.c b/drivers/virt/coco/efi_secret/efi_secret.c index 1864f9f80617..f2da4819ec3b 100644 --- a/drivers/virt/coco/efi_secret/efi_secret.c +++ b/drivers/virt/coco/efi_secret/efi_secret.c @@ -136,15 +136,7 @@ static int efi_secret_unlink(struct inode *dir, struct dentry *dentry) if (s->fs_files[i] == dentry) s->fs_files[i] = NULL; - /* - * securityfs_remove tries to lock the directory's inode, but we reach - * the unlink callback when it's already locked - */ - inode_unlock(dir); - securityfs_remove(dentry); - inode_lock(dir); - - return 0; + return simple_unlink(inode, dentry); } static const struct inode_operations efi_secret_dir_inode_operations = { diff --git a/drivers/virt/coco/guest/Kconfig b/drivers/virt/coco/guest/Kconfig new file mode 100644 index 000000000000..3d5e1d05bf34 --- /dev/null +++ b/drivers/virt/coco/guest/Kconfig @@ -0,0 +1,17 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Confidential computing shared guest collateral +# +config TSM_GUEST + bool + +config TSM_REPORTS + select TSM_GUEST + select CONFIGFS_FS + tristate + +config TSM_MEASUREMENTS + select TSM_GUEST + select CRYPTO_HASH_INFO + select CRYPTO + bool diff --git a/drivers/virt/coco/guest/Makefile b/drivers/virt/coco/guest/Makefile new file mode 100644 index 000000000000..9ec4860bd213 --- /dev/null +++ b/drivers/virt/coco/guest/Makefile @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_TSM_REPORTS) += tsm_report.o +tsm_report-y := report.o +obj-$(CONFIG_TSM_MEASUREMENTS) += tsm-mr.o diff --git a/drivers/virt/coco/tsm.c b/drivers/virt/coco/guest/report.c index 9432d4e303f1..d3d18fc22bc2 100644 --- a/drivers/virt/coco/tsm.c +++ b/drivers/virt/coco/guest/report.c @@ -13,8 +13,9 @@ #include <linux/configfs.h> static struct tsm_provider { - const struct tsm_ops *ops; + const struct tsm_report_ops *ops; void *data; + atomic_t count; } provider; static DECLARE_RWSEM(tsm_rwsem); @@ -92,16 +93,19 @@ static ssize_t tsm_report_privlevel_store(struct config_item *cfg, if (rc) return rc; + guard(rwsem_write)(&tsm_rwsem); + if (!provider.ops) + return -ENXIO; + /* * The valid privilege levels that a TSM might accept, if it accepts a * privilege level setting at all, are a max of TSM_PRIVLEVEL_MAX (see * SEV-SNP GHCB) and a minimum of a TSM selected floor value no less * than 0. */ - if (provider.ops->privlevel_floor > val || val > TSM_PRIVLEVEL_MAX) + if (provider.ops->privlevel_floor > val || val > TSM_REPORT_PRIVLEVEL_MAX) return -EINVAL; - guard(rwsem_write)(&tsm_rwsem); rc = try_advance_write_generation(report); if (rc) return rc; @@ -115,6 +119,10 @@ static ssize_t tsm_report_privlevel_floor_show(struct config_item *cfg, char *buf) { guard(rwsem_read)(&tsm_rwsem); + + if (!provider.ops) + return -ENXIO; + return sysfs_emit(buf, "%u\n", provider.ops->privlevel_floor); } CONFIGFS_ATTR_RO(tsm_report_, privlevel_floor); @@ -202,7 +210,7 @@ static ssize_t tsm_report_inblob_write(struct config_item *cfg, memcpy(report->desc.inblob, buf, count); return count; } -CONFIGFS_BIN_ATTR_WO(tsm_report_, inblob, NULL, TSM_INBLOB_MAX); +CONFIGFS_BIN_ATTR_WO(tsm_report_, inblob, NULL, TSM_REPORT_INBLOB_MAX); static ssize_t tsm_report_generation_show(struct config_item *cfg, char *buf) { @@ -217,6 +225,9 @@ CONFIGFS_ATTR_RO(tsm_report_, generation); static ssize_t tsm_report_provider_show(struct config_item *cfg, char *buf) { guard(rwsem_read)(&tsm_rwsem); + if (!provider.ops) + return -ENXIO; + return sysfs_emit(buf, "%s\n", provider.ops->name); } CONFIGFS_ATTR_RO(tsm_report_, provider); @@ -272,7 +283,7 @@ static ssize_t tsm_report_read(struct tsm_report *report, void *buf, size_t count, enum tsm_data_select select) { struct tsm_report_state *state = to_state(report); - const struct tsm_ops *ops; + const struct tsm_report_ops *ops; ssize_t rc; /* try to read from the existing report if present and valid... */ @@ -284,7 +295,7 @@ static ssize_t tsm_report_read(struct tsm_report *report, void *buf, guard(rwsem_write)(&tsm_rwsem); ops = provider.ops; if (!ops) - return -ENOTTY; + return -ENXIO; if (!report->desc.inblob_len) return -EINVAL; @@ -314,7 +325,7 @@ static ssize_t tsm_report_outblob_read(struct config_item *cfg, void *buf, return tsm_report_read(report, buf, count, TSM_REPORT); } -CONFIGFS_BIN_ATTR_RO(tsm_report_, outblob, NULL, TSM_OUTBLOB_MAX); +CONFIGFS_BIN_ATTR_RO(tsm_report_, outblob, NULL, TSM_REPORT_OUTBLOB_MAX); static ssize_t tsm_report_auxblob_read(struct config_item *cfg, void *buf, size_t count) @@ -323,7 +334,7 @@ static ssize_t tsm_report_auxblob_read(struct config_item *cfg, void *buf, return tsm_report_read(report, buf, count, TSM_CERTS); } -CONFIGFS_BIN_ATTR_RO(tsm_report_, auxblob, NULL, TSM_OUTBLOB_MAX); +CONFIGFS_BIN_ATTR_RO(tsm_report_, auxblob, NULL, TSM_REPORT_OUTBLOB_MAX); static ssize_t tsm_report_manifestblob_read(struct config_item *cfg, void *buf, size_t count) @@ -332,7 +343,7 @@ static ssize_t tsm_report_manifestblob_read(struct config_item *cfg, void *buf, return tsm_report_read(report, buf, count, TSM_MANIFEST); } -CONFIGFS_BIN_ATTR_RO(tsm_report_, manifestblob, NULL, TSM_OUTBLOB_MAX); +CONFIGFS_BIN_ATTR_RO(tsm_report_, manifestblob, NULL, TSM_REPORT_OUTBLOB_MAX); static struct configfs_attribute *tsm_report_attrs[] = { [TSM_REPORT_GENERATION] = &tsm_report_attr_generation, @@ -421,12 +432,20 @@ static struct config_item *tsm_report_make_item(struct config_group *group, if (!state) return ERR_PTR(-ENOMEM); + atomic_inc(&provider.count); config_item_init_type_name(&state->cfg, name, &tsm_report_type); return &state->cfg; } +static void tsm_report_drop_item(struct config_group *group, struct config_item *item) +{ + config_item_put(item); + atomic_dec(&provider.count); +} + static struct configfs_group_operations tsm_report_group_ops = { .make_item = tsm_report_make_item, + .drop_item = tsm_report_drop_item, }; static const struct config_item_type tsm_reports_type = { @@ -448,9 +467,9 @@ static struct configfs_subsystem tsm_configfs = { .su_mutex = __MUTEX_INITIALIZER(tsm_configfs.su_mutex), }; -int tsm_register(const struct tsm_ops *ops, void *priv) +int tsm_report_register(const struct tsm_report_ops *ops, void *priv) { - const struct tsm_ops *conflict; + const struct tsm_report_ops *conflict; guard(rwsem_write)(&tsm_rwsem); conflict = provider.ops; @@ -459,26 +478,34 @@ int tsm_register(const struct tsm_ops *ops, void *priv) return -EBUSY; } + if (atomic_read(&provider.count)) { + pr_err("configfs/tsm/report not empty\n"); + return -EBUSY; + } + provider.ops = ops; provider.data = priv; return 0; } -EXPORT_SYMBOL_GPL(tsm_register); +EXPORT_SYMBOL_GPL(tsm_report_register); -int tsm_unregister(const struct tsm_ops *ops) +int tsm_report_unregister(const struct tsm_report_ops *ops) { guard(rwsem_write)(&tsm_rwsem); if (ops != provider.ops) return -EBUSY; + if (atomic_read(&provider.count)) + pr_warn("\"%s\" unregistered with items present in configfs/tsm/report\n", + provider.ops->name); provider.ops = NULL; provider.data = NULL; return 0; } -EXPORT_SYMBOL_GPL(tsm_unregister); +EXPORT_SYMBOL_GPL(tsm_report_unregister); static struct config_group *tsm_report_group; -static int __init tsm_init(void) +static int __init tsm_report_init(void) { struct config_group *root = &tsm_configfs.su_group; struct config_group *tsm; @@ -499,14 +526,14 @@ static int __init tsm_init(void) return 0; } -module_init(tsm_init); +module_init(tsm_report_init); -static void __exit tsm_exit(void) +static void __exit tsm_report_exit(void) { configfs_unregister_default_group(tsm_report_group); configfs_unregister_subsystem(&tsm_configfs); } -module_exit(tsm_exit); +module_exit(tsm_report_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Provide Trusted Security Module attestation reports via configfs"); diff --git a/drivers/virt/coco/guest/tsm-mr.c b/drivers/virt/coco/guest/tsm-mr.c new file mode 100644 index 000000000000..feb30af90a20 --- /dev/null +++ b/drivers/virt/coco/guest/tsm-mr.c @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2024-2025 Intel Corporation. All rights reserved. */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/sysfs.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/tsm_mr.h> + +/* + * struct tm_context - contains everything necessary to implement sysfs + * attributes for MRs. + * @rwsem: protects the MR cache from concurrent access. + * @agrp: contains all MR attributes created by tsm_mr_create_attribute_group(). + * @tm: input to tsm_mr_create_attribute_group() containing MR definitions/ops. + * @in_sync: %true if MR cache is up-to-date. + * @mrs: array of &struct bin_attribute, one for each MR. + * + * This internal structure contains everything needed to implement + * tm_digest_read() and tm_digest_write(). + * + * Given tm->refresh() is potentially expensive, tm_digest_read() caches MR + * values and calls tm->refresh() only when necessary. Only live MRs (i.e., with + * %TSM_MR_F_LIVE set) can trigger tm->refresh(), while others are assumed to + * retain their values from the last tm->write(). @in_sync tracks if there have + * been tm->write() calls since the last tm->refresh(). That is, tm->refresh() + * will be called only when a live MR is being read and the cache is stale + * (@in_sync is %false). + * + * tm_digest_write() sets @in_sync to %false and calls tm->write(), whose + * semantics is arch and MR specific. Most (if not all) writable MRs support the + * extension semantics (i.e., tm->write() extends the input buffer into the MR). + */ +struct tm_context { + struct rw_semaphore rwsem; + struct attribute_group agrp; + const struct tsm_measurements *tm; + bool in_sync; + struct bin_attribute mrs[]; +}; + +static ssize_t tm_digest_read(struct file *filp, struct kobject *kobj, + const struct bin_attribute *attr, char *buffer, + loff_t off, size_t count) +{ + struct tm_context *ctx; + const struct tsm_measurement_register *mr; + int rc; + + ctx = attr->private; + rc = down_read_interruptible(&ctx->rwsem); + if (rc) + return rc; + + mr = &ctx->tm->mrs[attr - ctx->mrs]; + + /* + * @ctx->in_sync indicates if the MR cache is stale. It is a global + * instead of a per-MR flag for simplicity, as most (if not all) archs + * allow reading all MRs in oneshot. + * + * ctx->refresh() is necessary only for LIVE MRs, while others retain + * their values from their respective last ctx->write(). + */ + if ((mr->mr_flags & TSM_MR_F_LIVE) && !ctx->in_sync) { + up_read(&ctx->rwsem); + + rc = down_write_killable(&ctx->rwsem); + if (rc) + return rc; + + if (!ctx->in_sync) { + rc = ctx->tm->refresh(ctx->tm); + ctx->in_sync = !rc; + trace_tsm_mr_refresh(mr, rc); + } + + downgrade_write(&ctx->rwsem); + } + + memcpy(buffer, mr->mr_value + off, count); + trace_tsm_mr_read(mr); + + up_read(&ctx->rwsem); + return rc ?: count; +} + +static ssize_t tm_digest_write(struct file *filp, struct kobject *kobj, + const struct bin_attribute *attr, char *buffer, + loff_t off, size_t count) +{ + struct tm_context *ctx; + const struct tsm_measurement_register *mr; + ssize_t rc; + + /* partial writes are not supported */ + if (off != 0 || count != attr->size) + return -EINVAL; + + ctx = attr->private; + mr = &ctx->tm->mrs[attr - ctx->mrs]; + + rc = down_write_killable(&ctx->rwsem); + if (rc) + return rc; + + rc = ctx->tm->write(ctx->tm, mr, buffer); + + /* mark MR cache stale */ + if (!rc) { + ctx->in_sync = false; + trace_tsm_mr_write(mr, buffer); + } + + up_write(&ctx->rwsem); + return rc ?: count; +} + +/** + * tsm_mr_create_attribute_group() - creates an attribute group for measurement + * registers (MRs) + * @tm: pointer to &struct tsm_measurements containing the MR definitions. + * + * This function creates attributes corresponding to the MR definitions + * provided by @tm->mrs. + * + * The created attributes will reference @tm and its members. The caller must + * not free @tm until after tsm_mr_free_attribute_group() is called. + * + * Context: Process context. May sleep due to memory allocation. + * + * Return: + * * On success, the pointer to a an attribute group is returned; otherwise + * * %-EINVAL - Invalid MR definitions. + * * %-ENOMEM - Out of memory. + */ +const struct attribute_group * +tsm_mr_create_attribute_group(const struct tsm_measurements *tm) +{ + size_t nlen; + + if (!tm || !tm->mrs) + return ERR_PTR(-EINVAL); + + /* aggregated length of all MR names */ + nlen = 0; + for (size_t i = 0; i < tm->nr_mrs; ++i) { + if ((tm->mrs[i].mr_flags & TSM_MR_F_LIVE) && !tm->refresh) + return ERR_PTR(-EINVAL); + + if ((tm->mrs[i].mr_flags & TSM_MR_F_WRITABLE) && !tm->write) + return ERR_PTR(-EINVAL); + + if (!tm->mrs[i].mr_name) + return ERR_PTR(-EINVAL); + + if (tm->mrs[i].mr_flags & TSM_MR_F_NOHASH) + continue; + + if (tm->mrs[i].mr_hash >= HASH_ALGO__LAST) + return ERR_PTR(-EINVAL); + + /* MR sysfs attribute names have the form of MRNAME:HASH */ + nlen += strlen(tm->mrs[i].mr_name) + 1 + + strlen(hash_algo_name[tm->mrs[i].mr_hash]) + 1; + } + + /* + * @attrs and the MR name strings are combined into a single allocation + * so that we don't have to free MR names one-by-one in + * tsm_mr_free_attribute_group() + */ + const struct bin_attribute **attrs __free(kfree) = + kzalloc(sizeof(*attrs) * (tm->nr_mrs + 1) + nlen, GFP_KERNEL); + struct tm_context *ctx __free(kfree) = + kzalloc(struct_size(ctx, mrs, tm->nr_mrs), GFP_KERNEL); + char *name, *end; + + if (!ctx || !attrs) + return ERR_PTR(-ENOMEM); + + /* @attrs is followed immediately by MR name strings */ + name = (char *)&attrs[tm->nr_mrs + 1]; + end = name + nlen; + + for (size_t i = 0; i < tm->nr_mrs; ++i) { + struct bin_attribute *bap = &ctx->mrs[i]; + + sysfs_bin_attr_init(bap); + + if (tm->mrs[i].mr_flags & TSM_MR_F_NOHASH) + bap->attr.name = tm->mrs[i].mr_name; + else if (name < end) { + bap->attr.name = name; + name += snprintf(name, end - name, "%s:%s", + tm->mrs[i].mr_name, + hash_algo_name[tm->mrs[i].mr_hash]); + ++name; + } else + return ERR_PTR(-EINVAL); + + /* check for duplicated MR definitions */ + for (size_t j = 0; j < i; ++j) + if (!strcmp(bap->attr.name, attrs[j]->attr.name)) + return ERR_PTR(-EINVAL); + + if (tm->mrs[i].mr_flags & TSM_MR_F_READABLE) { + bap->attr.mode |= 0444; + bap->read_new = tm_digest_read; + } + + if (tm->mrs[i].mr_flags & TSM_MR_F_WRITABLE) { + bap->attr.mode |= 0200; + bap->write_new = tm_digest_write; + } + + bap->size = tm->mrs[i].mr_size; + bap->private = ctx; + + attrs[i] = bap; + } + + if (name != end) + return ERR_PTR(-EINVAL); + + init_rwsem(&ctx->rwsem); + ctx->agrp.name = "measurements"; + ctx->agrp.bin_attrs_new = no_free_ptr(attrs); + ctx->tm = tm; + return &no_free_ptr(ctx)->agrp; +} +EXPORT_SYMBOL_GPL(tsm_mr_create_attribute_group); + +/** + * tsm_mr_free_attribute_group() - frees the attribute group returned by + * tsm_mr_create_attribute_group() + * @attr_grp: attribute group returned by tsm_mr_create_attribute_group() + * + * Context: Process context. + */ +void tsm_mr_free_attribute_group(const struct attribute_group *attr_grp) +{ + if (!IS_ERR_OR_NULL(attr_grp)) { + kfree(attr_grp->bin_attrs_new); + kfree(container_of(attr_grp, struct tm_context, agrp)); + } +} +EXPORT_SYMBOL_GPL(tsm_mr_free_attribute_group); diff --git a/drivers/virt/coco/sev-guest/Kconfig b/drivers/virt/coco/sev-guest/Kconfig index 0b772bd921d8..a6405ab6c2c3 100644 --- a/drivers/virt/coco/sev-guest/Kconfig +++ b/drivers/virt/coco/sev-guest/Kconfig @@ -2,7 +2,6 @@ config SEV_GUEST tristate "AMD SEV Guest driver" default m depends on AMD_MEM_ENCRYPT - select CRYPTO_LIB_AESGCM select TSM_REPORTS help SEV-SNP firmware provides the guest a mechanism to communicate with diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c index af64e6191f74..7a4e2188f109 100644 --- a/drivers/virt/coco/sev-guest/sev-guest.c +++ b/drivers/virt/coco/sev-guest/sev-guest.c @@ -23,6 +23,7 @@ #include <linux/cleanup.h> #include <linux/uuid.h> #include <linux/configfs.h> +#include <linux/mm.h> #include <uapi/linux/sev-guest.h> #include <uapi/linux/psp-sev.h> @@ -31,9 +32,6 @@ #define DEVICE_NAME "sev-guest" -#define SNP_REQ_MAX_RETRY_DURATION (60*HZ) -#define SNP_REQ_RETRY_DELAY (2*HZ) - #define SVSM_MAX_RETRIES 3 struct snp_guest_dev { @@ -54,86 +52,6 @@ static int vmpck_id = -1; module_param(vmpck_id, int, 0444); MODULE_PARM_DESC(vmpck_id, "The VMPCK ID to use when communicating with the PSP."); -/* Mutex to serialize the shared buffer access and command handling. */ -static DEFINE_MUTEX(snp_cmd_mutex); - -static bool is_vmpck_empty(struct snp_msg_desc *mdesc) -{ - char zero_key[VMPCK_KEY_LEN] = {0}; - - if (mdesc->vmpck) - return !memcmp(mdesc->vmpck, zero_key, VMPCK_KEY_LEN); - - return true; -} - -/* - * If an error is received from the host or AMD Secure Processor (ASP) there - * are two options. Either retry the exact same encrypted request or discontinue - * using the VMPCK. - * - * This is because in the current encryption scheme GHCB v2 uses AES-GCM to - * encrypt the requests. The IV for this scheme is the sequence number. GCM - * cannot tolerate IV reuse. - * - * The ASP FW v1.51 only increments the sequence numbers on a successful - * guest<->ASP back and forth and only accepts messages at its exact sequence - * number. - * - * So if the sequence number were to be reused the encryption scheme is - * vulnerable. If the sequence number were incremented for a fresh IV the ASP - * will reject the request. - */ -static void snp_disable_vmpck(struct snp_msg_desc *mdesc) -{ - pr_alert("Disabling VMPCK%d communication key to prevent IV reuse.\n", - vmpck_id); - memzero_explicit(mdesc->vmpck, VMPCK_KEY_LEN); - mdesc->vmpck = NULL; -} - -static inline u64 __snp_get_msg_seqno(struct snp_msg_desc *mdesc) -{ - u64 count; - - lockdep_assert_held(&snp_cmd_mutex); - - /* Read the current message sequence counter from secrets pages */ - count = *mdesc->os_area_msg_seqno; - - return count + 1; -} - -/* Return a non-zero on success */ -static u64 snp_get_msg_seqno(struct snp_msg_desc *mdesc) -{ - u64 count = __snp_get_msg_seqno(mdesc); - - /* - * The message sequence counter for the SNP guest request is a 64-bit - * value but the version 2 of GHCB specification defines a 32-bit storage - * for it. If the counter exceeds the 32-bit value then return zero. - * The caller should check the return value, but if the caller happens to - * not check the value and use it, then the firmware treats zero as an - * invalid number and will fail the message request. - */ - if (count >= UINT_MAX) { - pr_err("request message sequence counter overflow\n"); - return 0; - } - - return count; -} - -static void snp_inc_msg_seqno(struct snp_msg_desc *mdesc) -{ - /* - * The counter is also incremented by the PSP, so increment it by 2 - * and save in secrets page. - */ - *mdesc->os_area_msg_seqno += 2; -} - static inline struct snp_guest_dev *to_snp_dev(struct file *file) { struct miscdevice *dev = file->private_data; @@ -141,242 +59,6 @@ static inline struct snp_guest_dev *to_snp_dev(struct file *file) return container_of(dev, struct snp_guest_dev, misc); } -static struct aesgcm_ctx *snp_init_crypto(u8 *key, size_t keylen) -{ - struct aesgcm_ctx *ctx; - - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT); - if (!ctx) - return NULL; - - if (aesgcm_expandkey(ctx, key, keylen, AUTHTAG_LEN)) { - pr_err("Crypto context initialization failed\n"); - kfree(ctx); - return NULL; - } - - return ctx; -} - -static int verify_and_dec_payload(struct snp_msg_desc *mdesc, struct snp_guest_req *req) -{ - struct snp_guest_msg *resp_msg = &mdesc->secret_response; - struct snp_guest_msg *req_msg = &mdesc->secret_request; - struct snp_guest_msg_hdr *req_msg_hdr = &req_msg->hdr; - struct snp_guest_msg_hdr *resp_msg_hdr = &resp_msg->hdr; - struct aesgcm_ctx *ctx = mdesc->ctx; - u8 iv[GCM_AES_IV_SIZE] = {}; - - pr_debug("response [seqno %lld type %d version %d sz %d]\n", - resp_msg_hdr->msg_seqno, resp_msg_hdr->msg_type, resp_msg_hdr->msg_version, - resp_msg_hdr->msg_sz); - - /* Copy response from shared memory to encrypted memory. */ - memcpy(resp_msg, mdesc->response, sizeof(*resp_msg)); - - /* Verify that the sequence counter is incremented by 1 */ - if (unlikely(resp_msg_hdr->msg_seqno != (req_msg_hdr->msg_seqno + 1))) - return -EBADMSG; - - /* Verify response message type and version number. */ - if (resp_msg_hdr->msg_type != (req_msg_hdr->msg_type + 1) || - resp_msg_hdr->msg_version != req_msg_hdr->msg_version) - return -EBADMSG; - - /* - * If the message size is greater than our buffer length then return - * an error. - */ - if (unlikely((resp_msg_hdr->msg_sz + ctx->authsize) > req->resp_sz)) - return -EBADMSG; - - /* Decrypt the payload */ - memcpy(iv, &resp_msg_hdr->msg_seqno, min(sizeof(iv), sizeof(resp_msg_hdr->msg_seqno))); - if (!aesgcm_decrypt(ctx, req->resp_buf, resp_msg->payload, resp_msg_hdr->msg_sz, - &resp_msg_hdr->algo, AAD_LEN, iv, resp_msg_hdr->authtag)) - return -EBADMSG; - - return 0; -} - -static int enc_payload(struct snp_msg_desc *mdesc, u64 seqno, struct snp_guest_req *req) -{ - struct snp_guest_msg *msg = &mdesc->secret_request; - struct snp_guest_msg_hdr *hdr = &msg->hdr; - struct aesgcm_ctx *ctx = mdesc->ctx; - u8 iv[GCM_AES_IV_SIZE] = {}; - - memset(msg, 0, sizeof(*msg)); - - hdr->algo = SNP_AEAD_AES_256_GCM; - hdr->hdr_version = MSG_HDR_VER; - hdr->hdr_sz = sizeof(*hdr); - hdr->msg_type = req->msg_type; - hdr->msg_version = req->msg_version; - hdr->msg_seqno = seqno; - hdr->msg_vmpck = req->vmpck_id; - hdr->msg_sz = req->req_sz; - - /* Verify the sequence number is non-zero */ - if (!hdr->msg_seqno) - return -ENOSR; - - pr_debug("request [seqno %lld type %d version %d sz %d]\n", - hdr->msg_seqno, hdr->msg_type, hdr->msg_version, hdr->msg_sz); - - if (WARN_ON((req->req_sz + ctx->authsize) > sizeof(msg->payload))) - return -EBADMSG; - - memcpy(iv, &hdr->msg_seqno, min(sizeof(iv), sizeof(hdr->msg_seqno))); - aesgcm_encrypt(ctx, msg->payload, req->req_buf, req->req_sz, &hdr->algo, - AAD_LEN, iv, hdr->authtag); - - return 0; -} - -static int __handle_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, - struct snp_guest_request_ioctl *rio) -{ - unsigned long req_start = jiffies; - unsigned int override_npages = 0; - u64 override_err = 0; - int rc; - -retry_request: - /* - * Call firmware to process the request. In this function the encrypted - * message enters shared memory with the host. So after this call the - * sequence number must be incremented or the VMPCK must be deleted to - * prevent reuse of the IV. - */ - rc = snp_issue_guest_request(req, &mdesc->input, rio); - switch (rc) { - case -ENOSPC: - /* - * If the extended guest request fails due to having too - * small of a certificate data buffer, retry the same - * guest request without the extended data request in - * order to increment the sequence number and thus avoid - * IV reuse. - */ - override_npages = mdesc->input.data_npages; - req->exit_code = SVM_VMGEXIT_GUEST_REQUEST; - - /* - * Override the error to inform callers the given extended - * request buffer size was too small and give the caller the - * required buffer size. - */ - override_err = SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN); - - /* - * If this call to the firmware succeeds, the sequence number can - * be incremented allowing for continued use of the VMPCK. If - * there is an error reflected in the return value, this value - * is checked further down and the result will be the deletion - * of the VMPCK and the error code being propagated back to the - * user as an ioctl() return code. - */ - goto retry_request; - - /* - * The host may return SNP_GUEST_VMM_ERR_BUSY if the request has been - * throttled. Retry in the driver to avoid returning and reusing the - * message sequence number on a different message. - */ - case -EAGAIN: - if (jiffies - req_start > SNP_REQ_MAX_RETRY_DURATION) { - rc = -ETIMEDOUT; - break; - } - schedule_timeout_killable(SNP_REQ_RETRY_DELAY); - goto retry_request; - } - - /* - * Increment the message sequence number. There is no harm in doing - * this now because decryption uses the value stored in the response - * structure and any failure will wipe the VMPCK, preventing further - * use anyway. - */ - snp_inc_msg_seqno(mdesc); - - if (override_err) { - rio->exitinfo2 = override_err; - - /* - * If an extended guest request was issued and the supplied certificate - * buffer was not large enough, a standard guest request was issued to - * prevent IV reuse. If the standard request was successful, return -EIO - * back to the caller as would have originally been returned. - */ - if (!rc && override_err == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN)) - rc = -EIO; - } - - if (override_npages) - mdesc->input.data_npages = override_npages; - - return rc; -} - -static int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req, - struct snp_guest_request_ioctl *rio) -{ - u64 seqno; - int rc; - - guard(mutex)(&snp_cmd_mutex); - - /* Check if the VMPCK is not empty */ - if (is_vmpck_empty(mdesc)) { - pr_err_ratelimited("VMPCK is disabled\n"); - return -ENOTTY; - } - - /* Get message sequence and verify that its a non-zero */ - seqno = snp_get_msg_seqno(mdesc); - if (!seqno) - return -EIO; - - /* Clear shared memory's response for the host to populate. */ - memset(mdesc->response, 0, sizeof(struct snp_guest_msg)); - - /* Encrypt the userspace provided payload in mdesc->secret_request. */ - rc = enc_payload(mdesc, seqno, req); - if (rc) - return rc; - - /* - * Write the fully encrypted request to the shared unencrypted - * request page. - */ - memcpy(mdesc->request, &mdesc->secret_request, - sizeof(mdesc->secret_request)); - - rc = __handle_guest_request(mdesc, req, rio); - if (rc) { - if (rc == -EIO && - rio->exitinfo2 == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN)) - return rc; - - pr_alert("Detected error from ASP request. rc: %d, exitinfo2: 0x%llx\n", - rc, rio->exitinfo2); - - snp_disable_vmpck(mdesc); - return rc; - } - - rc = verify_and_dec_payload(mdesc, req); - if (rc) { - pr_alert("Detected unexpected decode failure from ASP. rc: %d\n", rc); - snp_disable_vmpck(mdesc); - return rc; - } - - return 0; -} - struct snp_req_resp { sockptr_t req_data; sockptr_t resp_data; @@ -412,7 +94,7 @@ static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_io req.msg_version = arg->msg_version; req.msg_type = SNP_MSG_REPORT_REQ; - req.vmpck_id = vmpck_id; + req.vmpck_id = mdesc->vmpck_id; req.req_buf = report_req; req.req_sz = sizeof(*report_req); req.resp_buf = report_resp->data; @@ -463,7 +145,7 @@ static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_reque req.msg_version = arg->msg_version; req.msg_type = SNP_MSG_KEY_REQ; - req.vmpck_id = vmpck_id; + req.vmpck_id = mdesc->vmpck_id; req.req_buf = derived_key_req; req.req_sz = sizeof(*derived_key_req); req.resp_buf = buf; @@ -495,6 +177,7 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques struct snp_guest_req req = {}; int ret, npages = 0, resp_len; sockptr_t certs_address; + struct page *page; if (sockptr_is_null(io->req_data) || sockptr_is_null(io->resp_data)) return -EINVAL; @@ -528,8 +211,20 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques * the host. If host does not supply any certs in it, then copy * zeros to indicate that certificate data was not provided. */ - memset(mdesc->certs_data, 0, report_req->certs_len); npages = report_req->certs_len >> PAGE_SHIFT; + page = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, + get_order(report_req->certs_len)); + if (!page) + return -ENOMEM; + + req.certs_data = page_address(page); + ret = set_memory_decrypted((unsigned long)req.certs_data, npages); + if (ret) { + pr_err("failed to mark page shared, ret=%d\n", ret); + __free_pages(page, get_order(report_req->certs_len)); + return -EFAULT; + } + cmd: /* * The intermediate response buffer is used while decrypting the @@ -538,14 +233,16 @@ cmd: */ resp_len = sizeof(report_resp->data) + mdesc->ctx->authsize; report_resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT); - if (!report_resp) - return -ENOMEM; + if (!report_resp) { + ret = -ENOMEM; + goto e_free_data; + } - mdesc->input.data_npages = npages; + req.input.data_npages = npages; req.msg_version = arg->msg_version; req.msg_type = SNP_MSG_REPORT_REQ; - req.vmpck_id = vmpck_id; + req.vmpck_id = mdesc->vmpck_id; req.req_buf = &report_req->data; req.req_sz = sizeof(report_req->data); req.resp_buf = report_resp->data; @@ -556,7 +253,7 @@ cmd: /* If certs length is invalid then copy the returned length */ if (arg->vmm_error == SNP_GUEST_VMM_ERR_INVALID_LEN) { - report_req->certs_len = mdesc->input.data_npages << PAGE_SHIFT; + report_req->certs_len = req.input.data_npages << PAGE_SHIFT; if (copy_to_sockptr(io->req_data, report_req, sizeof(*report_req))) ret = -EFAULT; @@ -565,7 +262,7 @@ cmd: if (ret) goto e_free; - if (npages && copy_to_sockptr(certs_address, mdesc->certs_data, report_req->certs_len)) { + if (npages && copy_to_sockptr(certs_address, req.certs_data, report_req->certs_len)) { ret = -EFAULT; goto e_free; } @@ -575,6 +272,13 @@ cmd: e_free: kfree(report_resp); +e_free_data: + if (npages) { + if (set_memory_encrypted((unsigned long)req.certs_data, npages)) + WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n"); + else + __free_pages(page, get_order(report_req->certs_len)); + } return ret; } @@ -622,76 +326,11 @@ static long snp_guest_ioctl(struct file *file, unsigned int ioctl, unsigned long return ret; } -static void free_shared_pages(void *buf, size_t sz) -{ - unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; - int ret; - - if (!buf) - return; - - ret = set_memory_encrypted((unsigned long)buf, npages); - if (ret) { - WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n"); - return; - } - - __free_pages(virt_to_page(buf), get_order(sz)); -} - -static void *alloc_shared_pages(struct device *dev, size_t sz) -{ - unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT; - struct page *page; - int ret; - - page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(sz)); - if (!page) - return NULL; - - ret = set_memory_decrypted((unsigned long)page_address(page), npages); - if (ret) { - dev_err(dev, "failed to mark page shared, ret=%d\n", ret); - __free_pages(page, get_order(sz)); - return NULL; - } - - return page_address(page); -} - static const struct file_operations snp_guest_fops = { .owner = THIS_MODULE, .unlocked_ioctl = snp_guest_ioctl, }; -static u8 *get_vmpck(int id, struct snp_secrets_page *secrets, u32 **seqno) -{ - u8 *key = NULL; - - switch (id) { - case 0: - *seqno = &secrets->os_area.msg_seqno_0; - key = secrets->vmpck0; - break; - case 1: - *seqno = &secrets->os_area.msg_seqno_1; - key = secrets->vmpck1; - break; - case 2: - *seqno = &secrets->os_area.msg_seqno_2; - key = secrets->vmpck2; - break; - case 3: - *seqno = &secrets->os_area.msg_seqno_3; - key = secrets->vmpck3; - break; - default: - break; - } - - return key; -} - struct snp_msg_report_resp_hdr { u32 status; u32 report_size; @@ -707,7 +346,7 @@ struct snp_msg_cert_entry { static int sev_svsm_report_new(struct tsm_report *report, void *data) { unsigned int rep_len, man_len, certs_len; - struct tsm_desc *desc = &report->desc; + struct tsm_report_desc *desc = &report->desc; struct svsm_attest_call ac = {}; unsigned int retry_count; void *rep, *man, *certs; @@ -842,7 +481,7 @@ retry: static int sev_report_new(struct tsm_report *report, void *data) { struct snp_msg_cert_entry *cert_table; - struct tsm_desc *desc = &report->desc; + struct tsm_report_desc *desc = &report->desc; struct snp_guest_dev *snp_dev = data; struct snp_msg_report_resp_hdr hdr; const u32 report_size = SZ_4K; @@ -971,7 +610,7 @@ static bool sev_report_bin_attr_visible(int n) return false; } -static struct tsm_ops sev_tsm_ops = { +static struct tsm_report_ops sev_tsm_report_ops = { .name = KBUILD_MODNAME, .report_new = sev_report_new, .report_attr_visible = sev_report_attr_visible, @@ -980,18 +619,15 @@ static struct tsm_ops sev_tsm_ops = { static void unregister_sev_tsm(void *data) { - tsm_unregister(&sev_tsm_ops); + tsm_report_unregister(&sev_tsm_report_ops); } static int __init sev_guest_probe(struct platform_device *pdev) { - struct sev_guest_platform_data *data; - struct snp_secrets_page *secrets; struct device *dev = &pdev->dev; struct snp_guest_dev *snp_dev; struct snp_msg_desc *mdesc; struct miscdevice *misc; - void __iomem *mapping; int ret; BUILD_BUG_ON(sizeof(struct snp_guest_msg) > PAGE_SIZE); @@ -999,115 +635,57 @@ static int __init sev_guest_probe(struct platform_device *pdev) if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) return -ENODEV; - if (!dev->platform_data) - return -ENODEV; - - data = (struct sev_guest_platform_data *)dev->platform_data; - mapping = ioremap_encrypted(data->secrets_gpa, PAGE_SIZE); - if (!mapping) - return -ENODEV; - - secrets = (__force void *)mapping; - - ret = -ENOMEM; snp_dev = devm_kzalloc(&pdev->dev, sizeof(struct snp_guest_dev), GFP_KERNEL); if (!snp_dev) - goto e_unmap; - - mdesc = devm_kzalloc(&pdev->dev, sizeof(struct snp_msg_desc), GFP_KERNEL); - if (!mdesc) - goto e_unmap; - - /* Adjust the default VMPCK key based on the executing VMPL level */ - if (vmpck_id == -1) - vmpck_id = snp_vmpl; + return -ENOMEM; - ret = -EINVAL; - mdesc->vmpck = get_vmpck(vmpck_id, secrets, &mdesc->os_area_msg_seqno); - if (!mdesc->vmpck) { - dev_err(dev, "Invalid VMPCK%d communication key\n", vmpck_id); - goto e_unmap; - } + mdesc = snp_msg_alloc(); + if (IS_ERR_OR_NULL(mdesc)) + return -ENOMEM; - /* Verify that VMPCK is not zero. */ - if (is_vmpck_empty(mdesc)) { - dev_err(dev, "Empty VMPCK%d communication key\n", vmpck_id); - goto e_unmap; - } + ret = snp_msg_init(mdesc, vmpck_id); + if (ret) + goto e_msg_init; platform_set_drvdata(pdev, snp_dev); snp_dev->dev = dev; - mdesc->secrets = secrets; - - /* Allocate the shared page used for the request and response message. */ - mdesc->request = alloc_shared_pages(dev, sizeof(struct snp_guest_msg)); - if (!mdesc->request) - goto e_unmap; - - mdesc->response = alloc_shared_pages(dev, sizeof(struct snp_guest_msg)); - if (!mdesc->response) - goto e_free_request; - - mdesc->certs_data = alloc_shared_pages(dev, SEV_FW_BLOB_MAX_SIZE); - if (!mdesc->certs_data) - goto e_free_response; - - ret = -EIO; - mdesc->ctx = snp_init_crypto(mdesc->vmpck, VMPCK_KEY_LEN); - if (!mdesc->ctx) - goto e_free_cert_data; misc = &snp_dev->misc; misc->minor = MISC_DYNAMIC_MINOR; misc->name = DEVICE_NAME; misc->fops = &snp_guest_fops; - /* Initialize the input addresses for guest request */ - mdesc->input.req_gpa = __pa(mdesc->request); - mdesc->input.resp_gpa = __pa(mdesc->response); - mdesc->input.data_gpa = __pa(mdesc->certs_data); - /* Set the privlevel_floor attribute based on the vmpck_id */ - sev_tsm_ops.privlevel_floor = vmpck_id; + sev_tsm_report_ops.privlevel_floor = mdesc->vmpck_id; - ret = tsm_register(&sev_tsm_ops, snp_dev); + ret = tsm_report_register(&sev_tsm_report_ops, snp_dev); if (ret) - goto e_free_cert_data; + goto e_msg_init; ret = devm_add_action_or_reset(&pdev->dev, unregister_sev_tsm, NULL); if (ret) - goto e_free_cert_data; + goto e_msg_init; ret = misc_register(misc); if (ret) - goto e_free_ctx; + goto e_msg_init; snp_dev->msg_desc = mdesc; - dev_info(dev, "Initialized SEV guest driver (using VMPCK%d communication key)\n", vmpck_id); + dev_info(dev, "Initialized SEV guest driver (using VMPCK%d communication key)\n", + mdesc->vmpck_id); return 0; -e_free_ctx: - kfree(mdesc->ctx); -e_free_cert_data: - free_shared_pages(mdesc->certs_data, SEV_FW_BLOB_MAX_SIZE); -e_free_response: - free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg)); -e_free_request: - free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg)); -e_unmap: - iounmap(mapping); +e_msg_init: + snp_msg_free(mdesc); + return ret; } static void __exit sev_guest_remove(struct platform_device *pdev) { struct snp_guest_dev *snp_dev = platform_get_drvdata(pdev); - struct snp_msg_desc *mdesc = snp_dev->msg_desc; - free_shared_pages(mdesc->certs_data, SEV_FW_BLOB_MAX_SIZE); - free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg)); - free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg)); - kfree(mdesc->ctx); + snp_msg_free(snp_dev->msg_desc); misc_deregister(&snp_dev->misc); } diff --git a/drivers/virt/coco/tdx-guest/Kconfig b/drivers/virt/coco/tdx-guest/Kconfig index 22dd59e19431..dbbdc14383b1 100644 --- a/drivers/virt/coco/tdx-guest/Kconfig +++ b/drivers/virt/coco/tdx-guest/Kconfig @@ -2,6 +2,7 @@ config TDX_GUEST_DRIVER tristate "TDX Guest driver" depends on INTEL_TDX_GUEST select TSM_REPORTS + select TSM_MEASUREMENTS help The driver provides userspace interface to communicate with the TDX module to request the TDX guest details like attestation diff --git a/drivers/virt/coco/tdx-guest/tdx-guest.c b/drivers/virt/coco/tdx-guest/tdx-guest.c index 224e7dde9cde..4e239ec960c9 100644 --- a/drivers/virt/coco/tdx-guest/tdx-guest.c +++ b/drivers/virt/coco/tdx-guest/tdx-guest.c @@ -5,6 +5,8 @@ * Copyright (C) 2022 Intel Corporation */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/miscdevice.h> #include <linux/mm.h> @@ -15,14 +17,146 @@ #include <linux/set_memory.h> #include <linux/io.h> #include <linux/delay.h> +#include <linux/sockptr.h> #include <linux/tsm.h> -#include <linux/sizes.h> +#include <linux/tsm-mr.h> #include <uapi/linux/tdx-guest.h> #include <asm/cpu_device_id.h> #include <asm/tdx.h> +/* TDREPORT buffer */ +static u8 *tdx_report_buf; + +/* Lock to serialize TDG.MR.REPORT and TDG.MR.RTMR.EXTEND TDCALLs */ +static DEFINE_MUTEX(mr_lock); + +/* TDREPORT fields */ +enum { + TDREPORT_reportdata = 128, + TDREPORT_tee_tcb_info = 256, + TDREPORT_tdinfo = TDREPORT_tee_tcb_info + 256, + TDREPORT_attributes = TDREPORT_tdinfo, + TDREPORT_xfam = TDREPORT_attributes + sizeof(u64), + TDREPORT_mrtd = TDREPORT_xfam + sizeof(u64), + TDREPORT_mrconfigid = TDREPORT_mrtd + SHA384_DIGEST_SIZE, + TDREPORT_mrowner = TDREPORT_mrconfigid + SHA384_DIGEST_SIZE, + TDREPORT_mrownerconfig = TDREPORT_mrowner + SHA384_DIGEST_SIZE, + TDREPORT_rtmr0 = TDREPORT_mrownerconfig + SHA384_DIGEST_SIZE, + TDREPORT_rtmr1 = TDREPORT_rtmr0 + SHA384_DIGEST_SIZE, + TDREPORT_rtmr2 = TDREPORT_rtmr1 + SHA384_DIGEST_SIZE, + TDREPORT_rtmr3 = TDREPORT_rtmr2 + SHA384_DIGEST_SIZE, + TDREPORT_servtd_hash = TDREPORT_rtmr3 + SHA384_DIGEST_SIZE, +}; + +static int tdx_do_report(sockptr_t data, sockptr_t tdreport) +{ + scoped_cond_guard(mutex_intr, return -EINTR, &mr_lock) { + u8 *reportdata = tdx_report_buf + TDREPORT_reportdata; + int ret; + + if (!sockptr_is_null(data) && + copy_from_sockptr(reportdata, data, TDX_REPORTDATA_LEN)) + return -EFAULT; + + ret = tdx_mcall_get_report0(reportdata, tdx_report_buf); + if (WARN_ONCE(ret, "tdx_mcall_get_report0() failed: %d", ret)) + return ret; + + if (!sockptr_is_null(tdreport) && + copy_to_sockptr(tdreport, tdx_report_buf, TDX_REPORT_LEN)) + return -EFAULT; + } + return 0; +} + +static int tdx_do_extend(u8 mr_ind, const u8 *data) +{ + scoped_cond_guard(mutex_intr, return -EINTR, &mr_lock) { + /* + * TDX requires @extend_buf to be 64-byte aligned. + * It's safe to use REPORTDATA buffer for that purpose because + * tdx_mr_report/extend_lock() are mutually exclusive. + */ + u8 *extend_buf = tdx_report_buf + TDREPORT_reportdata; + int ret; + + memcpy(extend_buf, data, SHA384_DIGEST_SIZE); + + ret = tdx_mcall_extend_rtmr(mr_ind, extend_buf); + if (WARN_ONCE(ret, "tdx_mcall_extend_rtmr(%u) failed: %d", mr_ind, ret)) + return ret; + } + return 0; +} + +#define TDX_MR_(r) .mr_value = (void *)TDREPORT_##r, TSM_MR_(r, SHA384) +static struct tsm_measurement_register tdx_mrs[] = { + { TDX_MR_(rtmr0) | TSM_MR_F_RTMR }, + { TDX_MR_(rtmr1) | TSM_MR_F_RTMR }, + { TDX_MR_(rtmr2) | TSM_MR_F_RTMR }, + { TDX_MR_(rtmr3) | TSM_MR_F_RTMR }, + { TDX_MR_(mrtd) }, + { TDX_MR_(mrconfigid) | TSM_MR_F_NOHASH }, + { TDX_MR_(mrowner) | TSM_MR_F_NOHASH }, + { TDX_MR_(mrownerconfig) | TSM_MR_F_NOHASH }, +}; +#undef TDX_MR_ + +static int tdx_mr_refresh(const struct tsm_measurements *tm) +{ + return tdx_do_report(KERNEL_SOCKPTR(NULL), KERNEL_SOCKPTR(NULL)); +} + +static int tdx_mr_extend(const struct tsm_measurements *tm, + const struct tsm_measurement_register *mr, + const u8 *data) +{ + return tdx_do_extend(mr - tm->mrs, data); +} + +static struct tsm_measurements tdx_measurements = { + .mrs = tdx_mrs, + .nr_mrs = ARRAY_SIZE(tdx_mrs), + .refresh = tdx_mr_refresh, + .write = tdx_mr_extend, +}; + +static const struct attribute_group *tdx_mr_init(void) +{ + const struct attribute_group *g; + int rc; + + u8 *buf __free(kfree) = kzalloc(TDX_REPORT_LEN, GFP_KERNEL); + if (!buf) + return ERR_PTR(-ENOMEM); + + tdx_report_buf = buf; + rc = tdx_mr_refresh(&tdx_measurements); + if (rc) + return ERR_PTR(rc); + + /* + * @mr_value was initialized with the offset only, while the base + * address is being added here. + */ + for (size_t i = 0; i < ARRAY_SIZE(tdx_mrs); ++i) + *(long *)&tdx_mrs[i].mr_value += (long)buf; + + g = tsm_mr_create_attribute_group(&tdx_measurements); + if (!IS_ERR(g)) + tdx_report_buf = no_free_ptr(buf); + + return g; +} + +static void tdx_mr_deinit(const struct attribute_group *mr_grp) +{ + tsm_mr_free_attribute_group(mr_grp); + kfree(tdx_report_buf); +} + /* * Intel's SGX QE implementation generally uses Quote size less * than 8K (2K Quote data + ~5K of certificate blob). @@ -68,37 +202,8 @@ static u32 getquote_timeout = 30; static long tdx_get_report0(struct tdx_report_req __user *req) { - u8 *reportdata, *tdreport; - long ret; - - reportdata = kmalloc(TDX_REPORTDATA_LEN, GFP_KERNEL); - if (!reportdata) - return -ENOMEM; - - tdreport = kzalloc(TDX_REPORT_LEN, GFP_KERNEL); - if (!tdreport) { - ret = -ENOMEM; - goto out; - } - - if (copy_from_user(reportdata, req->reportdata, TDX_REPORTDATA_LEN)) { - ret = -EFAULT; - goto out; - } - - /* Generate TDREPORT0 using "TDG.MR.REPORT" TDCALL */ - ret = tdx_mcall_get_report0(reportdata, tdreport); - if (ret) - goto out; - - if (copy_to_user(req->tdreport, tdreport, TDX_REPORT_LEN)) - ret = -EFAULT; - -out: - kfree(reportdata); - kfree(tdreport); - - return ret; + return tdx_do_report(USER_SOCKPTR(req->reportdata), + USER_SOCKPTR(req->tdreport)); } static void free_quote_buf(void *buf) @@ -157,53 +262,24 @@ static int wait_for_quote_completion(struct tdx_quote_buf *quote_buf, u32 timeou return (i == timeout) ? -ETIMEDOUT : 0; } -static int tdx_report_new(struct tsm_report *report, void *data) +static int tdx_report_new_locked(struct tsm_report *report, void *data) { - u8 *buf, *reportdata = NULL, *tdreport = NULL; + u8 *buf; struct tdx_quote_buf *quote_buf = quote_data; - struct tsm_desc *desc = &report->desc; + struct tsm_report_desc *desc = &report->desc; int ret; u64 err; - /* TODO: switch to guard(mutex_intr) */ - if (mutex_lock_interruptible("e_lock)) - return -EINTR; - /* * If the previous request is timedout or interrupted, and the * Quote buf status is still in GET_QUOTE_IN_FLIGHT (owned by * VMM), don't permit any new request. */ - if (quote_buf->status == GET_QUOTE_IN_FLIGHT) { - ret = -EBUSY; - goto done; - } - - if (desc->inblob_len != TDX_REPORTDATA_LEN) { - ret = -EINVAL; - goto done; - } - - reportdata = kmalloc(TDX_REPORTDATA_LEN, GFP_KERNEL); - if (!reportdata) { - ret = -ENOMEM; - goto done; - } + if (quote_buf->status == GET_QUOTE_IN_FLIGHT) + return -EBUSY; - tdreport = kzalloc(TDX_REPORT_LEN, GFP_KERNEL); - if (!tdreport) { - ret = -ENOMEM; - goto done; - } - - memcpy(reportdata, desc->inblob, desc->inblob_len); - - /* Generate TDREPORT0 using "TDG.MR.REPORT" TDCALL */ - ret = tdx_mcall_get_report0(reportdata, tdreport); - if (ret) { - pr_err("GetReport call failed\n"); - goto done; - } + if (desc->inblob_len != TDX_REPORTDATA_LEN) + return -EINVAL; memset(quote_data, 0, GET_QUOTE_BUF_SIZE); @@ -211,26 +287,26 @@ static int tdx_report_new(struct tsm_report *report, void *data) quote_buf->version = GET_QUOTE_CMD_VER; quote_buf->in_len = TDX_REPORT_LEN; - memcpy(quote_buf->data, tdreport, TDX_REPORT_LEN); + ret = tdx_do_report(KERNEL_SOCKPTR(desc->inblob), + KERNEL_SOCKPTR(quote_buf->data)); + if (ret) + return ret; err = tdx_hcall_get_quote(quote_data, GET_QUOTE_BUF_SIZE); if (err) { pr_err("GetQuote hypercall failed, status:%llx\n", err); - ret = -EIO; - goto done; + return -EIO; } ret = wait_for_quote_completion(quote_buf, getquote_timeout); if (ret) { pr_err("GetQuote request timedout\n"); - goto done; + return ret; } buf = kvmemdup(quote_buf->data, quote_buf->out_len, GFP_KERNEL); - if (!buf) { - ret = -ENOMEM; - goto done; - } + if (!buf) + return -ENOMEM; report->outblob = buf; report->outblob_len = quote_buf->out_len; @@ -239,14 +315,16 @@ static int tdx_report_new(struct tsm_report *report, void *data) * TODO: parse the PEM-formatted cert chain out of the quote buffer when * provided */ -done: - mutex_unlock("e_lock); - kfree(reportdata); - kfree(tdreport); return ret; } +static int tdx_report_new(struct tsm_report *report, void *data) +{ + scoped_cond_guard(mutex_intr, return -EINTR, "e_lock) + return tdx_report_new_locked(report, data); +} + static bool tdx_report_attr_visible(int n) { switch (n) { @@ -285,10 +363,16 @@ static const struct file_operations tdx_guest_fops = { .unlocked_ioctl = tdx_guest_ioctl, }; +static const struct attribute_group *tdx_attr_groups[] = { + NULL, /* measurements */ + NULL +}; + static struct miscdevice tdx_misc_dev = { .name = KBUILD_MODNAME, .minor = MISC_DYNAMIC_MINOR, .fops = &tdx_guest_fops, + .groups = tdx_attr_groups, }; static const struct x86_cpu_id tdx_guest_ids[] = { @@ -297,7 +381,7 @@ static const struct x86_cpu_id tdx_guest_ids[] = { }; MODULE_DEVICE_TABLE(x86cpu, tdx_guest_ids); -static const struct tsm_ops tdx_tsm_ops = { +static const struct tsm_report_ops tdx_tsm_ops = { .name = KBUILD_MODNAME, .report_new = tdx_report_new, .report_attr_visible = tdx_report_attr_visible, @@ -311,9 +395,13 @@ static int __init tdx_guest_init(void) if (!x86_match_cpu(tdx_guest_ids)) return -ENODEV; + tdx_attr_groups[0] = tdx_mr_init(); + if (IS_ERR(tdx_attr_groups[0])) + return PTR_ERR(tdx_attr_groups[0]); + ret = misc_register(&tdx_misc_dev); if (ret) - return ret; + goto deinit_mr; quote_data = alloc_quote_buf(); if (!quote_data) { @@ -322,7 +410,7 @@ static int __init tdx_guest_init(void) goto free_misc; } - ret = tsm_register(&tdx_tsm_ops, NULL); + ret = tsm_report_register(&tdx_tsm_ops, NULL); if (ret) goto free_quote; @@ -332,6 +420,8 @@ free_quote: free_quote_buf(quote_data); free_misc: misc_deregister(&tdx_misc_dev); +deinit_mr: + tdx_mr_deinit(tdx_attr_groups[0]); return ret; } @@ -339,9 +429,10 @@ module_init(tdx_guest_init); static void __exit tdx_guest_exit(void) { - tsm_unregister(&tdx_tsm_ops); + tsm_report_unregister(&tdx_tsm_ops); free_quote_buf(quote_data); misc_deregister(&tdx_misc_dev); + tdx_mr_deinit(tdx_attr_groups[0]); } module_exit(tdx_guest_exit); diff --git a/drivers/virt/vboxguest/Kconfig b/drivers/virt/vboxguest/Kconfig index cc329887bfae..eaba28c95e73 100644 --- a/drivers/virt/vboxguest/Kconfig +++ b/drivers/virt/vboxguest/Kconfig @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only config VBOXGUEST tristate "Virtual Box Guest integration support" - depends on X86 && PCI && INPUT + depends on (ARM64 || X86 || COMPILE_TEST) && PCI && INPUT + depends on HAS_IOPORT help This is a driver for the Virtual Box Guest PCI device used in Virtual Box virtual machines. Enabling this driver will add diff --git a/drivers/virt/vboxguest/vboxguest_core.c b/drivers/virt/vboxguest/vboxguest_core.c index c6e9855998ab..b177a534b6a4 100644 --- a/drivers/virt/vboxguest/vboxguest_core.c +++ b/drivers/virt/vboxguest/vboxguest_core.c @@ -419,7 +419,7 @@ static void vbg_balloon_work(struct work_struct *work) */ static void vbg_heartbeat_timer(struct timer_list *t) { - struct vbg_dev *gdev = from_timer(gdev, t, heartbeat_timer); + struct vbg_dev *gdev = timer_container_of(gdev, t, heartbeat_timer); vbg_req_perform(gdev, gdev->guest_heartbeat_req); mod_timer(&gdev->heartbeat_timer, @@ -495,7 +495,7 @@ static int vbg_heartbeat_init(struct vbg_dev *gdev) */ static void vbg_heartbeat_exit(struct vbg_dev *gdev) { - del_timer_sync(&gdev->heartbeat_timer); + timer_delete_sync(&gdev->heartbeat_timer); vbg_heartbeat_host_config(gdev, false); vbg_req_free(gdev->guest_heartbeat_req, sizeof(*gdev->guest_heartbeat_req)); |