There is a limited amount of SGX memory (EPC) on each system. When that
memory is used up, SGX has its own swapping mechanism which is similar
in concept but totally separate from the core mm/* code. Instead of
swapping to disk, SGX swaps from EPC to normal RAM. That normal RAM
comes from a shared memory pseudo-file and can itself be swapped by the
core mm code. There is a hierarchy like this:
EPC <-> shmem <-> disk
After data is swapped back in from shmem to EPC, the shmem backing
storage needs to be freed. Currently, the backing shmem is not freed.
This effectively wastes the shmem while the enclave is running. The
memory is recovered when the enclave is destroyed and the backing
storage freed.
Sort this out by freeing memory with shmem_truncate_range(), as soon as
a page is faulted back to the EPC. In addition, free the memory for
PCMD pages as soon as all PCMD's in a page have been marked as unused
by zeroing its contents.
Reported-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Fixes: 1728ab54b4be ("x86/sgx: Add a page reclaimer")
Signed-off-by: Jarkko Sakkinen <jarkko@xxxxxxxxxx>
---
v4:
* Sanitized the offset calculations.
v3:
* Resend.
v2:
* Rewrite commit message as proposed by Dave.
* Truncate PCMD pages (Dave).
---
arch/x86/kernel/cpu/sgx/encl.c | 44 +++++++++++++++++++++++++++-------
1 file changed, 36 insertions(+), 8 deletions(-)
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index 8be6f0592bdc..94319190efb1 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -12,6 +12,17 @@
#include "encls.h"
#include "sgx.h"
+
+/*
+ * Free a page from the backing storage in the given page index.
+ */
+static inline void sgx_encl_truncate_backing_page(struct sgx_encl *encl, pgoff_t index)
+{
+ struct inode *inode = file_inode(encl->backing);
+
+ shmem_truncate_range(inode, PFN_PHYS(index), PFN_PHYS(index) + PAGE_SIZE - 1);
+}
+
/*
* ELDU: Load an EPC page as unblocked. For more info, see "OS Management of EPC
* Pages" in the SDM.
@@ -24,7 +35,9 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page,
struct sgx_encl *encl = encl_page->encl;
struct sgx_pageinfo pginfo;
struct sgx_backing b;
+ bool pcmd_page_empty;
pgoff_t page_index;
+ u8 *pcmd_page;
int ret;
if (secs_page)
@@ -38,8 +51,8 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page,
pginfo.addr = encl_page->desc & PAGE_MASK;
pginfo.contents = (unsigned long)kmap_atomic(b.contents);
- pginfo.metadata = (unsigned long)kmap_atomic(b.pcmd) +
- b.pcmd_offset;
+ pcmd_page = kmap_atomic(b.pcmd);
+ pginfo.metadata = (unsigned long)pcmd_page + b.pcmd_offset;
if (secs_page)
pginfo.secs = (u64)sgx_get_epc_virt_addr(secs_page);
@@ -55,11 +68,28 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page,
ret = -EFAULT;
}
- kunmap_atomic((void *)(unsigned long)(pginfo.metadata - b.pcmd_offset));
+ memset(pcmd_page + b.pcmd_offset, 0, sizeof(struct sgx_pcmd));
+
+ /*
+ * The area for the PCMD in the page was zeroed above. Check if the
+ * whole page is now empty meaning that all PCMD's have been zeroed:
+ */
+ pcmd_page_empty = !memchr_inv(pcmd_page, 0, PAGE_SIZE);
+
+ kunmap_atomic(pcmd_page);
kunmap_atomic((void *)(unsigned long)pginfo.contents);
sgx_encl_put_backing(&b, false);
+ sgx_encl_truncate_backing_page(encl, page_index);
+
+ if (pcmd_page_empty) {
+ pgoff_t pcmd_off = encl->size + PAGE_SIZE /* SECS */ +
+ page_index * sizeof(struct sgx_pcmd);
+
+ sgx_encl_truncate_backing_page(encl, PFN_DOWN(pcmd_off));
+ }
+
return ret;
}
@@ -583,7 +613,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
static int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
struct sgx_backing *backing)
{
- pgoff_t pcmd_index = PFN_DOWN(encl->size) + 1 + (page_index >> 5);
+ pgoff_t pcmd_off = encl->size + PAGE_SIZE /* SECS */ + page_index * sizeof(struct sgx_pcmd);
struct page *contents;
struct page *pcmd;
@@ -591,7 +621,7 @@ static int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
if (IS_ERR(contents))
return PTR_ERR(contents);
- pcmd = sgx_encl_get_backing_page(encl, pcmd_index);
+ pcmd = sgx_encl_get_backing_page(encl, PFN_DOWN(pcmd_off));
if (IS_ERR(pcmd)) {
put_page(contents);
return PTR_ERR(pcmd);
@@ -600,9 +630,7 @@ static int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
backing->page_index = page_index;
backing->contents = contents;
backing->pcmd = pcmd;
- backing->pcmd_offset =
- (page_index & (PAGE_SIZE / sizeof(struct sgx_pcmd) - 1)) *
- sizeof(struct sgx_pcmd);
+ backing->pcmd_offset = pcmd_off & (PAGE_SIZE - 1);
return 0;
}
--
2.35.1
