@@ -17,6 +17,8 @@
#include <linux/atomic.h>
#include <linux/sizes.h>
#include <linux/memblock.h>
+#include <linux/gfp.h>
+#include <linux/align.h>
#include <asm/cpufeatures.h>
#include <asm/cpufeature.h>
#include <asm/msr-index.h>
@@ -425,6 +427,55 @@ static int check_memblock_tdx_convertible(void)
return 0;
}
+/* Calculate the actual TDMR_INFO size */
+static inline int cal_tdmr_size(void)
+{
+ int tdmr_sz;
+
+ /*
+ * The actual size of TDMR_INFO depends on the maximum number
+ * of reserved areas.
+ */
+ tdmr_sz = sizeof(struct tdmr_info);
+ tdmr_sz += sizeof(struct tdmr_reserved_area) *
+ tdx_sysinfo.max_reserved_per_tdmr;
+
+ /*
+ * TDX requires each TDMR_INFO to be 512-byte aligned. Always
+ * round up TDMR_INFO size to the 512-byte boundary.
+ */
+ return ALIGN(tdmr_sz, TDMR_INFO_ALIGNMENT);
+}
+
+static struct tdmr_info *alloc_tdmr_array(int *array_sz)
+{
+ /*
+ * TDX requires each TDMR_INFO to be 512-byte aligned.
+ * Use alloc_pages_exact() to allocate all TDMRs at once.
+ * Each TDMR_INFO will still be 512-byte aligned since
+ * cal_tdmr_size() always return 512-byte aligned size.
+ */
+ *array_sz = cal_tdmr_size() * tdx_sysinfo.max_tdmrs;
+
+ /*
+ * Zero the buffer so 'struct tdmr_info::size' can be
+ * used to determine whether a TDMR is valid.
+ */
+ return alloc_pages_exact(*array_sz, GFP_KERNEL | __GFP_ZERO);
+}
+
+/*
+ * Construct an array of TDMRs to cover all memory regions in memblock.
+ * This makes sure all pages managed by the page allocator are TDX
+ * memory. The actual number of TDMRs is kept to @tdmr_num.
+ */
+static int construct_tdmrs_memeblock(struct tdmr_info *tdmr_array,
+ int *tdmr_num)
+{
+ /* Return -EINVAL until constructing TDMRs is done */
+ return -EINVAL;
+}
+
/*
* Detect and initialize the TDX module.
*
@@ -434,6 +485,9 @@ static int check_memblock_tdx_convertible(void)
*/
static int init_tdx_module(void)
{
+ struct tdmr_info *tdmr_array;
+ int tdmr_array_sz;
+ int tdmr_num;
int ret;
/*
@@ -471,11 +525,30 @@ static int init_tdx_module(void)
if (ret)
goto out;
+ /* Prepare enough space to construct TDMRs */
+ tdmr_array = alloc_tdmr_array(&tdmr_array_sz);
+ if (!tdmr_array) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /* Construct TDMRs to cover all memory regions in memblock */
+ ret = construct_tdmrs_memeblock(tdmr_array, &tdmr_num);
+ if (ret)
+ goto out_free_tdmrs;
+
/*
* Return -EINVAL until all steps of TDX module initialization
* process are done.
*/
ret = -EINVAL;
+out_free_tdmrs:
+ /*
+ * The array of TDMRs is freed no matter the initialization is
+ * successful or not. They are not needed anymore after the
+ * module initialization.
+ */
+ free_pages_exact(tdmr_array, tdmr_array_sz);
out:
return ret;
}
@@ -114,6 +114,29 @@ struct tdsysinfo_struct {
};
} __packed __aligned(TDSYSINFO_STRUCT_ALIGNMENT);
+struct tdmr_reserved_area {
+ u64 offset;
+ u64 size;
+} __packed;
+
+#define TDMR_INFO_ALIGNMENT 512
+
+struct tdmr_info {
+ u64 base;
+ u64 size;
+ u64 pamt_1g_base;
+ u64 pamt_1g_size;
+ u64 pamt_2m_base;
+ u64 pamt_2m_size;
+ u64 pamt_4k_base;
+ u64 pamt_4k_size;
+ /*
+ * Actual number of reserved areas depends on
+ * 'struct tdsysinfo_struct'::max_reserved_per_tdmr.
+ */
+ struct tdmr_reserved_area reserved_areas[0];
+} __packed __aligned(TDMR_INFO_ALIGNMENT);
+
/*
* Do not put any hardware-defined TDX structure representations below this
* comment!
TDX provides increased levels of memory confidentiality and integrity. This requires special hardware support for features like memory encryption and storage of memory integrity checksums. Not all memory satisfies these requirements. As a result, the TDX introduced the concept of a "Convertible Memory Region" (CMR). During boot, the firmware builds a list of all of the memory ranges which can provide the TDX security guarantees. The list of these ranges is available to the kernel by querying the TDX module. The TDX architecture needs additional metadata to record things like which TD guest "owns" a given page of memory. This metadata essentially serves as the 'struct page' for the TDX module. The space for this metadata is not reserved by the hardware up front and must be allocated by the kernel and given to the TDX module. Since this metadata consumes space, the VMM can choose whether or not to allocate it for a given area of convertible memory. If it chooses not to, the memory cannot receive TDX protections and can not be used by TDX guests as private memory. For every memory region that the VMM wants to use as TDX memory, it sets up a "TD Memory Region" (TDMR). Each TDMR represents a physically contiguous convertible range and must also have its own physically contiguous metadata table, referred to as a Physical Address Metadata Table (PAMT), to track status for each page in the TDMR range. Unlike a CMR, each TDMR requires 1G granularity and alignment. To support physical RAM areas that don't meet those strict requirements, each TDMR permits a number of internal "reserved areas" which can be placed over memory holes. If PAMT metadata is placed within a TDMR it must be covered by one of these reserved areas. Let's summarize the concepts: CMR - Firmware-enumerated physical ranges that support TDX. CMRs are 4K aligned. TDMR - Physical address range which is chosen by the kernel to support TDX. 1G granularity and alignment required. Each TDMR has reserved areas where TDX memory holes and overlapping PAMTs can be put into. PAMT - Physically contiguous TDX metadata. One table for each page size per TDMR. Roughly 1/256th of TDMR in size. 256G TDMR = ~1G PAMT. As one step of initializing the TDX module, the kernel configures TDX-usable memory by passing an array of TDMRs to the TDX module. Constructing the array of TDMRs consists below steps: 1) Create TDMRs to cover all memory regions that TDX module can use; 2) Allocate and set up PAMT for each TDMR; 3) Set up reserved areas for each TDMR. Add a placeholder to construct TDMRs to do the above steps after all memblock memory regions are verified to be convertible. Always free TDMRs at the end of the initialization (no matter successful or not) as TDMRs are only used during the initialization. Signed-off-by: Kai Huang <kai.huang@intel.com> --- - v3 -> v5 (no feedback on v4): - Moved calculating TDMR size to this patch. - Changed to use alloc_pages_exact() to allocate buffer for all TDMRs once, instead of allocating each TDMR individually. - Removed "crypto protection" in the changelog. - -EFAULT -> -EINVAL in couple of places. --- arch/x86/virt/vmx/tdx/tdx.c | 73 +++++++++++++++++++++++++++++++++++++ arch/x86/virt/vmx/tdx/tdx.h | 23 ++++++++++++ 2 files changed, 96 insertions(+)