[PATCH v7 2/2] x86/tdx: Support vmalloc() for tdx_enc_status_changed()

[Dexuan Cui <decui@microsoft.com>]

When a TDX guest runs on Hyper-V, the hv_netvsc driver's netvsc_init_buf()
allocates buffers using vzalloc(), and needs to share the buffers with the
host OS by calling set_memory_decrypted(), which is not working for
vmalloc() yet. Add the support by handling the pages one by one.

Co-developed-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
---
 arch/x86/coco/tdx/tdx.c | 76 ++++++++++++++++++++++++++++-------------
 1 file changed, 52 insertions(+), 24 deletions(-)


Changes in v2:
  Changed tdx_enc_status_changed() in place.

Changes in v3:
  No change since v2.

Changes in v4:
  Added Kirill's Co-developed-by since Kirill helped to improve the
    code by adding tdx_enc_status_changed_phys().

  Thanks Kirill for the clarification on load_unaligned_zeropad()!

Changes in v5:
  Added Kirill's Signed-off-by.
  Added Michael's Reviewed-by.

Changes in v6: None.

Changes in v7: None.
  Note: there was a race between set_memory_encrypted() and
  load_unaligned_zeropad(), which has been fixed by the 3 patches of
  Kirill in the x86/tdx branch of the tip tree.


diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 5b62a1f5bd79..8b2a2dcb2efd 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -7,6 +7,7 @@
 #include <linux/cpufeature.h>
 #include <linux/export.h>
 #include <linux/io.h>
+#include <linux/mm.h>
 #include <asm/coco.h>
 #include <asm/tdx.h>
 #include <asm/vmx.h>
@@ -778,6 +779,34 @@ static bool try_accept_one(phys_addr_t *start, unsigned long len,
 	return true;
 }
 
+static bool try_accept_page(phys_addr_t start, phys_addr_t end)
+{
+	/*
+	 * For shared->private conversion, accept the page using
+	 * TDX_ACCEPT_PAGE TDX module call.
+	 */
+	while (start < end) {
+		unsigned long len = end - start;
+
+		/*
+		 * Try larger accepts first. It gives chance to VMM to keep
+		 * 1G/2M SEPT entries where possible and speeds up process by
+		 * cutting number of hypercalls (if successful).
+		 */
+
+		if (try_accept_one(&start, len, PG_LEVEL_1G))
+			continue;
+
+		if (try_accept_one(&start, len, PG_LEVEL_2M))
+			continue;
+
+		if (!try_accept_one(&start, len, PG_LEVEL_4K))
+			return false;
+	}
+
+	return true;
+}
+
 /*
  * Notify the VMM about page mapping conversion. More info about ABI
  * can be found in TDX Guest-Host-Communication Interface (GHCI),
@@ -828,6 +857,19 @@ static bool tdx_map_gpa(phys_addr_t start, phys_addr_t end, bool enc)
 	return false;
 }
 
+static bool tdx_enc_status_changed_phys(phys_addr_t start, phys_addr_t end,
+					bool enc)
+{
+	if (!tdx_map_gpa(start, end, enc))
+		return false;
+
+	/* private->shared conversion requires only MapGPA call */
+	if (!enc)
+		return true;
+
+	return try_accept_page(start, end);
+}
+
 /*
  * Inform the VMM of the guest's intent for this physical page: shared with
  * the VMM or private to the guest. The VMM is expected to change its mapping
@@ -835,37 +877,23 @@ static bool tdx_map_gpa(phys_addr_t start, phys_addr_t end, bool enc)
  */
 static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc)
 {
-	phys_addr_t start = __pa(vaddr);
-	phys_addr_t end   = __pa(vaddr + numpages * PAGE_SIZE);
+	unsigned long start = vaddr;
+	unsigned long end = start + numpages * PAGE_SIZE;
 
-	if (!tdx_map_gpa(start, end, enc))
+	if (offset_in_page(start) != 0)
 		return false;
 
-	/* private->shared conversion  requires only MapGPA call */
-	if (!enc)
-		return true;
+	if (!is_vmalloc_addr((void *)start))
+		return tdx_enc_status_changed_phys(__pa(start), __pa(end), enc);
 
-	/*
-	 * For shared->private conversion, accept the page using
-	 * TDX_ACCEPT_PAGE TDX module call.
-	 */
 	while (start < end) {
-		unsigned long len = end - start;
+		phys_addr_t start_pa = slow_virt_to_phys((void *)start);
+		phys_addr_t end_pa = start_pa + PAGE_SIZE;
 
-		/*
-		 * Try larger accepts first. It gives chance to VMM to keep
-		 * 1G/2M SEPT entries where possible and speeds up process by
-		 * cutting number of hypercalls (if successful).
-		 */
-
-		if (try_accept_one(&start, len, PG_LEVEL_1G))
-			continue;
-
-		if (try_accept_one(&start, len, PG_LEVEL_2M))
-			continue;
-
-		if (!try_accept_one(&start, len, PG_LEVEL_4K))
+		if (!tdx_enc_status_changed_phys(start_pa, end_pa, enc))
 			return false;
+
+		start += PAGE_SIZE;
 	}
 
 	return true;
-- 
2.25.1