diff options
Diffstat (limited to 'arch')
| -rw-r--r-- | arch/x86/Kconfig | 1 | ||||
| -rw-r--r-- | arch/x86/kernel/setup.c | 2 | ||||
| -rw-r--r-- | arch/x86/virt/vmx/tdx/tdx.c | 167 | ||||
| -rw-r--r-- | arch/x86/virt/vmx/tdx/tdx.h | 6 |
4 files changed, 174 insertions, 2 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index eb6e63956d51..2c69ef844805 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1971,6 +1971,7 @@ config INTEL_TDX_HOST depends on X86_64 depends on KVM_INTEL depends on X86_X2APIC + select ARCH_KEEP_MEMBLOCK help Intel Trust Domain Extensions (TDX) protects guest VMs from malicious host and certain physical attacks. This option enables necessary TDX diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 1526747bedf2..9597c002b3c4 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1033,6 +1033,8 @@ void __init setup_arch(char **cmdline_p) * * Moreover, on machines with SandyBridge graphics or in setups that use * crashkernel the entire 1M is reserved anyway. + * + * Note the host kernel TDX also requires the first 1MB being reserved. */ x86_platform.realmode_reserve(); diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c index ecb0df8ff8b8..6a3585bc8aa4 100644 --- a/arch/x86/virt/vmx/tdx/tdx.c +++ b/arch/x86/virt/vmx/tdx/tdx.c @@ -16,6 +16,12 @@ #include <linux/spinlock.h> #include <linux/percpu-defs.h> #include <linux/mutex.h> +#include <linux/list.h> +#include <linux/memblock.h> +#include <linux/memory.h> +#include <linux/minmax.h> +#include <linux/sizes.h> +#include <linux/pfn.h> #include <asm/msr-index.h> #include <asm/msr.h> #include <asm/cpufeature.h> @@ -31,6 +37,9 @@ static DEFINE_PER_CPU(bool, tdx_lp_initialized); static enum tdx_module_status_t tdx_module_status; static DEFINE_MUTEX(tdx_module_lock); +/* All TDX-usable memory regions. Protected by mem_hotplug_lock. */ +static LIST_HEAD(tdx_memlist); + typedef void (*sc_err_func_t)(u64 fn, u64 err, struct tdx_module_args *args); static inline void seamcall_err(u64 fn, u64 err, struct tdx_module_args *args) @@ -155,12 +164,102 @@ int tdx_cpu_enable(void) } EXPORT_SYMBOL_GPL(tdx_cpu_enable); +/* + * Add a memory region as a TDX memory block. The caller must make sure + * all memory regions are added in address ascending order and don't + * overlap. + */ +static int add_tdx_memblock(struct list_head *tmb_list, unsigned long start_pfn, + unsigned long end_pfn) +{ + struct tdx_memblock *tmb; + + tmb = kmalloc(sizeof(*tmb), GFP_KERNEL); + if (!tmb) + return -ENOMEM; + + INIT_LIST_HEAD(&tmb->list); + tmb->start_pfn = start_pfn; + tmb->end_pfn = end_pfn; + + /* @tmb_list is protected by mem_hotplug_lock */ + list_add_tail(&tmb->list, tmb_list); + return 0; +} + +static void free_tdx_memlist(struct list_head *tmb_list) +{ + /* @tmb_list is protected by mem_hotplug_lock */ + while (!list_empty(tmb_list)) { + struct tdx_memblock *tmb = list_first_entry(tmb_list, + struct tdx_memblock, list); + + list_del(&tmb->list); + kfree(tmb); + } +} + +/* + * Ensure that all memblock memory regions are convertible to TDX + * memory. Once this has been established, stash the memblock + * ranges off in a secondary structure because memblock is modified + * in memory hotplug while TDX memory regions are fixed. + */ +static int build_tdx_memlist(struct list_head *tmb_list) +{ + unsigned long start_pfn, end_pfn; + int i, ret; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { + /* + * The first 1MB is not reported as TDX convertible memory. + * Although the first 1MB is always reserved and won't end up + * to the page allocator, it is still in memblock's memory + * regions. Skip them manually to exclude them as TDX memory. + */ + start_pfn = max(start_pfn, PHYS_PFN(SZ_1M)); + if (start_pfn >= end_pfn) + continue; + + /* + * Add the memory regions as TDX memory. The regions in + * memblock has already guaranteed they are in address + * ascending order and don't overlap. + */ + ret = add_tdx_memblock(tmb_list, start_pfn, end_pfn); + if (ret) + goto err; + } + + return 0; +err: + free_tdx_memlist(tmb_list); + return ret; +} + static int init_tdx_module(void) { + int ret; + + /* + * To keep things simple, assume that all TDX-protected memory + * will come from the page allocator. Make sure all pages in the + * page allocator are TDX-usable memory. + * + * Build the list of "TDX-usable" memory regions which cover all + * pages in the page allocator to guarantee that. Do it while + * holding mem_hotplug_lock read-lock as the memory hotplug code + * path reads the @tdx_memlist to reject any new memory. + */ + get_online_mems(); + + ret = build_tdx_memlist(&tdx_memlist); + if (ret) + goto out_put_tdxmem; + /* * TODO: * - * - Build the list of TDX-usable memory regions. * - Get TDX module "TD Memory Region" (TDMR) global metadata. * - Construct a list of TDMRs to cover all TDX-usable memory * regions. @@ -170,7 +269,14 @@ static int init_tdx_module(void) * * Return error before all steps are done. */ - return -EINVAL; + ret = -EINVAL; +out_put_tdxmem: + /* + * @tdx_memlist is written here and read at memory hotplug time. + * Lock out memory hotplug code while building it. + */ + put_online_mems(); + return ret; } static int __tdx_enable(void) @@ -257,6 +363,56 @@ static __init int record_keyid_partitioning(u32 *tdx_keyid_start, return 0; } +static bool is_tdx_memory(unsigned long start_pfn, unsigned long end_pfn) +{ + struct tdx_memblock *tmb; + + /* + * This check assumes that the start_pfn<->end_pfn range does not + * cross multiple @tdx_memlist entries. A single memory online + * event across multiple memblocks (from which @tdx_memlist + * entries are derived at the time of module initialization) is + * not possible. This is because memory offline/online is done + * on granularity of 'struct memory_block', and the hotpluggable + * memory region (one memblock) must be multiple of memory_block. + */ + list_for_each_entry(tmb, &tdx_memlist, list) { + if (start_pfn >= tmb->start_pfn && end_pfn <= tmb->end_pfn) + return true; + } + return false; +} + +static int tdx_memory_notifier(struct notifier_block *nb, unsigned long action, + void *v) +{ + struct memory_notify *mn = v; + + if (action != MEM_GOING_ONLINE) + return NOTIFY_OK; + + /* + * Empty list means TDX isn't enabled. Allow any memory + * to go online. + */ + if (list_empty(&tdx_memlist)) + return NOTIFY_OK; + + /* + * The TDX memory configuration is static and can not be + * changed. Reject onlining any memory which is outside of + * the static configuration whether it supports TDX or not. + */ + if (is_tdx_memory(mn->start_pfn, mn->start_pfn + mn->nr_pages)) + return NOTIFY_OK; + + return NOTIFY_BAD; +} + +static struct notifier_block tdx_memory_nb = { + .notifier_call = tdx_memory_notifier, +}; + void __init tdx_init(void) { u32 tdx_keyid_start, nr_tdx_keyids; @@ -280,6 +436,13 @@ void __init tdx_init(void) return; } + err = register_memory_notifier(&tdx_memory_nb); + if (err) { + pr_err("initialization failed: register_memory_notifier() failed (%d)\n", + err); + return; + } + /* * Just use the first TDX KeyID as the 'global KeyID' and * leave the rest for TDX guests. diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h index a3c52270df5b..c11e0a7ca664 100644 --- a/arch/x86/virt/vmx/tdx/tdx.h +++ b/arch/x86/virt/vmx/tdx/tdx.h @@ -27,4 +27,10 @@ enum tdx_module_status_t { TDX_MODULE_ERROR }; +struct tdx_memblock { + struct list_head list; + unsigned long start_pfn; + unsigned long end_pfn; +}; + #endif |