The kernel will convert all shared memory back to private during kexec.
The direct mapping page tables will provide information on which memory
is shared.
It is extremely important to convert all shared memory. If a page is
missed, it will cause the target kernel to crash when it accesses it.
Keep track of the number of shared pages. This will allow for
cross-checking against the shared information in the direct mapping and
reporting if the shared bit is lost.
Include a debugfs interface that allows for the check to be performed at
any point.
Signed-off-by: Kirill A. Shutemov <[email protected]>
---
arch/x86/coco/tdx/tdx.c | 67 +++++++++++++++++++++++++++++++++++++++++
1 file changed, 67 insertions(+)
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index 46022283d955..56e152126f20 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -5,6 +5,7 @@
#define pr_fmt(fmt) "tdx: " fmt
#include <linux/cpufeature.h>
+#include <linux/debugfs.h>
#include <linux/export.h>
#include <linux/io.h>
#include <asm/coco.h>
@@ -37,6 +38,13 @@
#define TDREPORT_SUBTYPE_0 0
+static atomic_long_t nr_shared;
+
+static inline bool pte_decrypted(pte_t pte)
+{
+ return cc_mkdec(pte_val(pte)) == pte_val(pte);
+}
+
/* Called from __tdx_hypercall() for unrecoverable failure */
noinstr void __noreturn __tdx_hypercall_failed(void)
{
@@ -799,6 +807,11 @@ static int tdx_enc_status_change_finish(unsigned long vaddr, int numpages,
if (!enc && !tdx_enc_status_changed(vaddr, numpages, enc))
return -EIO;
+ if (enc)
+ atomic_long_sub(numpages, &nr_shared);
+ else
+ atomic_long_add(numpages, &nr_shared);
+
return 0;
}
@@ -871,3 +884,57 @@ void __init tdx_early_init(void)
pr_info("Guest detected\n");
}
+
+#ifdef CONFIG_DEBUG_FS
+static int tdx_shared_memory_show(struct seq_file *m, void *p)
+{
+ unsigned long addr, end;
+ unsigned long found = 0;
+
+ addr = PAGE_OFFSET;
+ end = PAGE_OFFSET + get_max_mapped();
+
+ while (addr < end) {
+ unsigned long size;
+ unsigned int level;
+ pte_t *pte;
+
+ pte = lookup_address(addr, &level);
+ size = page_level_size(level);
+
+ if (pte && pte_decrypted(*pte))
+ found += size / PAGE_SIZE;
+
+ addr += size;
+ }
+
+ seq_printf(m, "Number of unshared pages in kernel page tables: %16lu\n",
+ found);
+ seq_printf(m, "Number of pages accounted as unshared: %16ld\n",
+ atomic_long_read(&nr_shared));
+ return 0;
+}
+
+static int tdx_shared_memory_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, tdx_shared_memory_show, NULL);
+}
+
+static const struct file_operations tdx_shared_memory_fops = {
+ .open = tdx_shared_memory_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static __init int debug_tdx_shared_memory(void)
+{
+ if (!cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+ return 0;
+
+ debugfs_create_file("tdx_shared_memory", S_IRUSR, arch_debugfs_dir,
+ NULL, &tdx_shared_memory_fops);
+ return 0;
+}
+fs_initcall(debug_tdx_shared_memory);
+#endif
--
2.41.0
> +#ifdef CONFIG_DEBUG_FS
> +static int tdx_shared_memory_show(struct seq_file *m, void *p)
> +{
> + unsigned long addr, end;
> + unsigned long found = 0;
> +
> + addr = PAGE_OFFSET;
> + end = PAGE_OFFSET + get_max_mapped();
> +
> + while (addr < end) {
> + unsigned long size;
> + unsigned int level;
> + pte_t *pte;
> +
> + pte = lookup_address(addr, &level);
> + size = page_level_size(level);
> +
> + if (pte && pte_decrypted(*pte))
> + found += size / PAGE_SIZE;
> +
> + addr += size;
This could be a long loop, perhaps add cond_resched() here?
> + }
> +
> + seq_printf(m, "Number of unshared pages in kernel page tables: %16lu\n",
> + found);
> + seq_printf(m, "Number of pages accounted as unshared: %16ld\n",
> + atomic_long_read(&nr_shared));
> + return 0;
> +}
> +
On Tue, Oct 10, 2023 at 10:05:21AM +0000, Huang, Kai wrote:
>
> > +#ifdef CONFIG_DEBUG_FS
> > +static int tdx_shared_memory_show(struct seq_file *m, void *p)
> > +{
> > + unsigned long addr, end;
> > + unsigned long found = 0;
> > +
> > + addr = PAGE_OFFSET;
> > + end = PAGE_OFFSET + get_max_mapped();
> > +
> > + while (addr < end) {
> > + unsigned long size;
> > + unsigned int level;
> > + pte_t *pte;
> > +
> > + pte = lookup_address(addr, &level);
> > + size = page_level_size(level);
> > +
> > + if (pte && pte_decrypted(*pte))
> > + found += size / PAGE_SIZE;
> > +
> > + addr += size;
>
> This could be a long loop, perhaps add cond_resched() here?
Sure.
--
Kiryl Shutsemau / Kirill A. Shutemov