zicfiss protects shadow stack using new page table encodings PTE.W=1,
PTE.R=0 and PTE.X=0. This encoding is reserved if zicfiss is not
implemented or if shadow stack are not enabled.
Loads on shadow stack memory are allowed while stores to shadow stack
memory leads to access faults. Shadow stack accesses to RO memory
leads to store page fault.

To implement special nature of shadow stack memory where only selected
stores (shadow stack stores from sspush) have to be allowed while rest
of regular stores disallowed, new MMU TLB index is created for shadow
stack.

Signed-off-by: Deepak Gupta <debug@rivosinc.com>
Suggested-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/riscv/cpu_helper.c | 46 +++++++++++++++++++++++++++++++++------
 target/riscv/internals.h  |  3 +++
 2 files changed, 42 insertions(+), 7 deletions(-)

diff --git a/target/riscv/cpu_helper.c b/target/riscv/cpu_helper.c
index 93d199748e..5580f5f3f3 100644
--- a/target/riscv/cpu_helper.c
+++ b/target/riscv/cpu_helper.c
@@ -898,6 +898,8 @@ static int get_physical_address(CPURISCVState *env, hwaddr *physical,
     hwaddr ppn;
     int napot_bits = 0;
     target_ulong napot_mask;
+    bool is_sstack_idx = ((mmu_idx & MMU_IDX_SS_WRITE) == MMU_IDX_SS_WRITE);
+    bool sstack_page = false;
 
     /*
      * Check if we should use the background registers for the two
@@ -1106,21 +1108,40 @@ restart:
         return TRANSLATE_FAIL;
     }
 
+    target_ulong rwx = pte & (PTE_R | PTE_W | PTE_X);
     /* Check for reserved combinations of RWX flags. */
-    switch (pte & (PTE_R | PTE_W | PTE_X)) {
-    case PTE_W:
+    switch (rwx) {
     case PTE_W | PTE_X:
         return TRANSLATE_FAIL;
+    case PTE_W:
+        /* if bcfi enabled, PTE_W is not reserved and shadow stack page */
+        if (cpu_get_bcfien(env) && first_stage) {
+            sstack_page = true;
+            /* if ss index, read and write allowed. else only read allowed */
+            rwx = is_sstack_idx ? PTE_R | PTE_W : PTE_R;
+            break;
+        }
+        return TRANSLATE_FAIL;
+    case PTE_R:
+        /*
+         * no matter what's the `access_type`, shadow stack access to readonly
+         * memory are always store page faults. During unwind, loads will be
+         * promoted as store fault.
+         */
+        if (is_sstack_idx) {
+            return TRANSLATE_FAIL;
+        }
+        break;
     }
 
     int prot = 0;
-    if (pte & PTE_R) {
+    if (rwx & PTE_R) {
         prot |= PAGE_READ;
     }
-    if (pte & PTE_W) {
+    if (rwx & PTE_W) {
         prot |= PAGE_WRITE;
     }
-    if (pte & PTE_X) {
+    if (rwx & PTE_X) {
         bool mxr = false;
 
         /*
@@ -1164,8 +1185,11 @@ restart:
     }
 
     if (!((prot >> access_type) & 1)) {
-        /* Access check failed */
-        return TRANSLATE_FAIL;
+        /*
+         * Access check failed, access check failures for shadow stack are
+         * access faults.
+         */
+        return sstack_page ? TRANSLATE_PMP_FAIL : TRANSLATE_FAIL;
     }
 
     target_ulong updated_pte = pte;
@@ -1352,9 +1376,17 @@ void riscv_cpu_do_unaligned_access(CPUState *cs, vaddr addr,
         break;
     case MMU_DATA_LOAD:
         cs->exception_index = RISCV_EXCP_LOAD_ADDR_MIS;
+        /* shadow stack mis aligned accesses are access faults */
+        if (mmu_idx & MMU_IDX_SS_WRITE) {
+            cs->exception_index = RISCV_EXCP_LOAD_ACCESS_FAULT;
+        }
         break;
     case MMU_DATA_STORE:
         cs->exception_index = RISCV_EXCP_STORE_AMO_ADDR_MIS;
+        /* shadow stack mis aligned accesses are access faults */
+        if (mmu_idx & MMU_IDX_SS_WRITE) {
+            cs->exception_index = RISCV_EXCP_STORE_AMO_ACCESS_FAULT;
+        }
         break;
     default:
         g_assert_not_reached();
diff --git a/target/riscv/internals.h b/target/riscv/internals.h
index 0ac17bc5ad..ddbdee885b 100644
--- a/target/riscv/internals.h
+++ b/target/riscv/internals.h
@@ -30,12 +30,15 @@
  *  - U+2STAGE          0b100
  *  - S+2STAGE          0b101
  *  - S+SUM+2STAGE      0b110
+ *  - Shadow stack+U   0b1000
+ *  - Shadow stack+S   0b1001
  */
 #define MMUIdx_U            0
 #define MMUIdx_S            1
 #define MMUIdx_S_SUM        2
 #define MMUIdx_M            3
 #define MMU_2STAGE_BIT      (1 << 2)
+#define MMU_IDX_SS_WRITE    (1 << 3)
 
 static inline int mmuidx_priv(int mmu_idx)
 {
-- 
2.45.0