Support madvise(..., MADV_WILLNEED) by adding EPC pages with EAUG in
the newly added fops->fadvise() callback implementation, sgx_fadvise().
Change the return type and values of the sgx_encl_eaug_page function
so that more specific error codes are returned for different treatment
by the page fault handler and the fadvise callback.
On any error, sgx_fadvise() will discontinue further operations
and return as normal. The page fault handler allows a PF retried
by returning VM_FAULT_NOPAGE in handling -EBUSY returned from
sgx_encl_eaug_page.
Signed-off-by: Haitao Huang <haitao.huang@xxxxxxxxxxxxxxx>
---
arch/x86/kernel/cpu/sgx/driver.c | 81 ++++++++++++++++++++++++++++++++
arch/x86/kernel/cpu/sgx/encl.c | 46 +++++++++++-------
arch/x86/kernel/cpu/sgx/encl.h | 4 +-
3 files changed, 113 insertions(+), 18 deletions(-)
diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c
index aa9b8b868867..54b24897605b 100644
--- a/arch/x86/kernel/cpu/sgx/driver.c
+++ b/arch/x86/kernel/cpu/sgx/driver.c
@@ -2,6 +2,7 @@
/* Copyright(c) 2016-20 Intel Corporation. */
#include <linux/acpi.h>
+#include <linux/fadvise.h>
#include <linux/miscdevice.h>
#include <linux/mman.h>
#include <linux/security.h>
@@ -9,6 +10,7 @@
#include <asm/traps.h>
#include "driver.h"
#include "encl.h"
+#include "encls.h"
u64 sgx_attributes_reserved_mask;
u64 sgx_xfrm_reserved_mask = ~0x3;
@@ -97,10 +99,88 @@ static int sgx_mmap(struct file *file, struct vm_area_struct *vma)
vma->vm_ops = &sgx_vm_ops;
vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO;
vma->vm_private_data = encl;
+ /* Anchor vm_pgoff to the enclave base.
+ * So offset passed back to sgx_fadvise hook
+ * is relative to the enclave base
+ */
+ vma->vm_pgoff = (vma->vm_start - encl->base) >> PAGE_SHIFT;
return 0;
}
+/*
+ * Add new pages to the enclave sequentially with ENCLS[EAUG] for the WILLNEED advice.
+ * Only do this to existing VMAs in the same enclave and reject the request.
+ * Returns: 0 if EAUG done with best effort, -EINVAL if any sub-range given
+ * is not in the enclave, or enclave is not initialized..
+ */
+static int sgx_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
+{
+ struct sgx_encl *encl = file->private_data;
+ unsigned long start, end, pos;
+ int ret = -EINVAL;
+ struct vm_area_struct *vma = NULL;
+
+ /* Only support WILLNEED */
+ if (advice != POSIX_FADV_WILLNEED)
+ return -EINVAL;
+ if (!encl)
+ return -EINVAL;
+ if (!cpu_feature_enabled(X86_FEATURE_SGX2))
+ return -EINVAL;
+
+ if (offset + len < offset)
+ return -EINVAL;
+ if (encl->base + offset < encl->base)
+ return -EINVAL;
+ start = offset + encl->base;
+ end = start + len;
+ if (end < start)
+ return -EINVAL;
+ if (end > encl->base + encl->size)
+ return -EINVAL;
+
+ /* EAUG works only for initialized enclaves. */
+ if (!test_bit(SGX_ENCL_INITIALIZED, &encl->flags))
+ return -EINVAL;
+
+ mmap_read_lock(current->mm);
+
+ vma = find_vma(current->mm, start);
+ if (!vma)
+ goto unlock;
+ if (vma->vm_private_data != encl)
+ goto unlock;
+
+ pos = start;
+ if (pos < vma->vm_start || end > vma->vm_end) {
+ /* Don't allow any gaps */
+ goto unlock;
+ }
+ /* Here: vm_start <= pos < end <= vm_end */
+ while (pos < end) {
+ if (xa_load(&encl->page_array, PFN_DOWN(pos)))
+ continue;
+ if (signal_pending(current)) {
+ if (pos == start)
+ ret = -ERESTARTSYS;
+ else
+ ret = -EINTR;
+ goto unlock;
+ }
+ ret = sgx_encl_eaug_page(vma, encl, pos);
+ /* It's OK to not finish */
+ if (ret)
+ break;
+ pos = pos + PAGE_SIZE;
+ cond_resched();
+ }
+ ret = 0;
+unlock:
+ mmap_read_unlock(current->mm);
+ return ret;
+}
+
static unsigned long sgx_get_unmapped_area(struct file *file,
unsigned long addr,
unsigned long len,
@@ -133,6 +213,7 @@ static const struct file_operations sgx_encl_fops = {
.compat_ioctl = sgx_compat_ioctl,
#endif
.mmap = sgx_mmap,
+ .fadvise = sgx_fadvise,
.get_unmapped_area = sgx_get_unmapped_area,
};
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index 1abc5e7f2660..c57e60d5a0aa 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -305,11 +305,11 @@ struct sgx_encl_page *sgx_encl_load_page(struct sgx_encl *encl,
* on a SGX2 system then the EPC can be added dynamically via the SGX2
* ENCLS[EAUG] instruction.
*
- * Returns: Appropriate vm_fault_t: VM_FAULT_NOPAGE when PTE was installed
- * successfully, VM_FAULT_SIGBUS or VM_FAULT_OOM as error otherwise.
+ * Returns: 0 when PTE was installed successfully, -EBUSY for waiting on
+ * reclaimer to free EPC, -ENOMEM for out of RAM, -EFAULT as error otherwise.
*/
-vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
- struct sgx_encl *encl, unsigned long addr)
+int sgx_encl_eaug_page(struct vm_area_struct *vma,
+ struct sgx_encl *encl, unsigned long addr)
{
vm_fault_t vmret = VM_FAULT_SIGBUS;
struct sgx_pageinfo pginfo = {0};
@@ -318,10 +318,10 @@ vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
struct sgx_va_page *va_page;
unsigned long phys_addr;
u64 secinfo_flags;
- int ret;
+ int ret = -EFAULT;
if (!test_bit(SGX_ENCL_INITIALIZED, &encl->flags))
- return VM_FAULT_SIGBUS;
+ return -EFAULT;
/*
* Ignore internal permission checking for dynamically added pages.
@@ -332,21 +332,21 @@ vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
secinfo_flags = SGX_SECINFO_R | SGX_SECINFO_W | SGX_SECINFO_X;
encl_page = sgx_encl_page_alloc(encl, addr - encl->base, secinfo_flags);
if (IS_ERR(encl_page))
- return VM_FAULT_OOM;
+ return -ENOMEM;
mutex_lock(&encl->lock);
epc_page = sgx_alloc_epc_page(encl_page, false);
if (IS_ERR(epc_page)) {
if (PTR_ERR(epc_page) == -EBUSY)
- vmret = VM_FAULT_NOPAGE;
+ ret = -EBUSY;
goto err_out_unlock;
}
va_page = sgx_encl_grow(encl, false);
if (IS_ERR(va_page)) {
if (PTR_ERR(va_page) == -EBUSY)
- vmret = VM_FAULT_NOPAGE;
+ ret = -EBUSY;
goto err_out_epc;
}
@@ -359,16 +359,20 @@ vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
* If ret == -EBUSY then page was created in another flow while
* running without encl->lock
*/
- if (ret)
+ if (ret) {
+ ret = -EFAULT;
goto err_out_shrink;
+ }
pginfo.secs = (unsigned long)sgx_get_epc_virt_addr(encl->secs.epc_page);
pginfo.addr = encl_page->desc & PAGE_MASK;
pginfo.metadata = 0;
ret = __eaug(&pginfo, sgx_get_epc_virt_addr(epc_page));
- if (ret)
+ if (ret) {
+ ret = -EFAULT;
goto err_out;
+ }
encl_page->encl = encl;
encl_page->epc_page = epc_page;
@@ -385,10 +389,10 @@ vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
vmret = vmf_insert_pfn(vma, addr, PFN_DOWN(phys_addr));
if (vmret != VM_FAULT_NOPAGE) {
mutex_unlock(&encl->lock);
- return VM_FAULT_SIGBUS;
+ return -EFAULT;
}
mutex_unlock(&encl->lock);
- return VM_FAULT_NOPAGE;
+ return 0;
err_out:
xa_erase(&encl->page_array, PFN_DOWN(encl_page->desc));
@@ -401,7 +405,7 @@ vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
mutex_unlock(&encl->lock);
kfree(encl_page);
- return vmret;
+ return ret;
}
static vm_fault_t sgx_vma_fault(struct vm_fault *vmf)
@@ -431,8 +435,18 @@ static vm_fault_t sgx_vma_fault(struct vm_fault *vmf)
* enclave that will be checked for right away.
*/
if (cpu_feature_enabled(X86_FEATURE_SGX2) &&
- (!xa_load(&encl->page_array, PFN_DOWN(addr))))
- return sgx_encl_eaug_page(vma, encl, addr);
+ (!xa_load(&encl->page_array, PFN_DOWN(addr)))) {
+ switch (sgx_encl_eaug_page(vma, encl, addr)) {
+ case 0:
+ case -EBUSY:
+ return VM_FAULT_NOPAGE;
+ case -ENOMEM:
+ return VM_FAULT_OOM;
+ case -EFAULT:
+ default:
+ return VM_FAULT_SIGBUS;
+ }
+ }
mutex_lock(&encl->lock);
diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h
index 500437981161..36059d35e1bc 100644
--- a/arch/x86/kernel/cpu/sgx/encl.h
+++ b/arch/x86/kernel/cpu/sgx/encl.h
@@ -127,6 +127,6 @@ struct sgx_encl_page *sgx_encl_load_page(struct sgx_encl *encl,
unsigned long addr);
struct sgx_va_page *sgx_encl_grow(struct sgx_encl *encl, bool reclaim);
void sgx_encl_shrink(struct sgx_encl *encl, struct sgx_va_page *va_page);
-vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma,
- struct sgx_encl *encl, unsigned long addr)
+int sgx_encl_eaug_page(struct vm_area_struct *vma,
+ struct sgx_encl *encl, unsigned long addr);
#endif /* _X86_ENCL_H */
--
2.25.1
