[Xen-devel] [PATCH 08/10] x86/hvm: pkeys, add pkeys support for do_page_fault

[Huaitong Han <huaitong.han@xxxxxxxxx>]

This patch adds pkeys support for do_page_fault.

the protection keys architecture define a new status bit in the PFEC. PFEC.PK
(bit 5) is set to 1 if an only if protection keys block the access.

Protection keys block an access and induce a page fault if and only if
1.Protection keys are enabled (CR4.PKE=1 and EFER.LMA=1), and
2.The page has a valid translation (page is present with no reserved bit
  violations), and
3.The access is not an instruction fetch, and
4.The access is to a user page, and
5.At least one of the following restrictions apply:
    --The access is a data read or data write and AD=1
    --The access is a data write and WD=1 and either CR0.WP=1 or (CR0.WP=0 and
    it is a user access)

Signed-off-by: Huaitong Han <huaitong.han@xxxxxxxxx>

diff --git a/xen/arch/x86/traps.c b/xen/arch/x86/traps.c
index 9f5a6c6..73abb3b 100644
--- a/xen/arch/x86/traps.c
+++ b/xen/arch/x86/traps.c
@@ -1287,7 +1287,7 @@ enum pf_type {
     spurious_fault
 };
 
-static enum pf_type __page_fault_type(
+static enum pf_type __page_fault_type(struct vcpu *vcpu,
     unsigned long addr, const struct cpu_user_regs *regs)
 {
     unsigned long mfn, cr3 = read_cr3();
@@ -1295,7 +1295,7 @@ static enum pf_type __page_fault_type(
     l3_pgentry_t l3e, *l3t;
     l2_pgentry_t l2e, *l2t;
     l1_pgentry_t l1e, *l1t;
-    unsigned int required_flags, disallowed_flags, page_user;
+    unsigned int required_flags, disallowed_flags, page_user, pte_pkeys;
     unsigned int error_code = regs->error_code;
 
     /*
@@ -1340,6 +1340,7 @@ static enum pf_type __page_fault_type(
     if ( ((l3e_get_flags(l3e) & required_flags) != required_flags) ||
          (l3e_get_flags(l3e) & disallowed_flags) )
         return real_fault;
+    pte_pkeys = l3e_get_pkeys(l3e);
     page_user &= l3e_get_flags(l3e);
     if ( l3e_get_flags(l3e) & _PAGE_PSE )
         goto leaf;
@@ -1351,6 +1352,7 @@ static enum pf_type __page_fault_type(
     if ( ((l2e_get_flags(l2e) & required_flags) != required_flags) ||
          (l2e_get_flags(l2e) & disallowed_flags) )
         return real_fault;
+    pte_pkeys = l2e_get_pkeys(l2e);
     page_user &= l2e_get_flags(l2e);
     if ( l2e_get_flags(l2e) & _PAGE_PSE )
         goto leaf;
@@ -1362,12 +1364,22 @@ static enum pf_type __page_fault_type(
     if ( ((l1e_get_flags(l1e) & required_flags) != required_flags) ||
          (l1e_get_flags(l1e) & disallowed_flags) )
         return real_fault;
+    pte_pkeys = l1e_get_pkeys(l1e);
     page_user &= l1e_get_flags(l1e);
 
 leaf:
     if ( page_user )
     {
         unsigned long cr4 = read_cr4();
+        unsigned int ff, wf, uf, rsvdf, pkuf;
+        unsigned int pkru_ad, pkru_wd;
+
+        uf = error_code & PFEC_user_mode;
+        wf = error_code & PFEC_write_access;
+        rsvdf = error_code & PFEC_reserved_bit;
+        ff = error_code & PFEC_insn_fetch;
+        pkuf = error_code & PFEC_protection_key;
+
         /*
          * Supervisor Mode Execution Prevention (SMEP):
          * Disallow supervisor execution from user-accessible mappings
@@ -1386,15 +1398,35 @@ leaf:
          *   - CPL=3 or X86_EFLAGS_AC is clear
          *   - Page fault in kernel mode
          */
-        if ( (cr4 & X86_CR4_SMAP) && !(error_code & PFEC_user_mode) &&
+        if ( (cr4 & X86_CR4_SMAP) && !uf &&
              (((regs->cs & 3) == 3) || !(regs->eflags & X86_EFLAGS_AC)) )
             return smap_fault;
+         /*
+         * PKU:  additional mechanism by which the paging controls
+         * access to user-mode addresses based on the value in the
+         * PKRU register. A fault is considered as a PKU violation if all
+         * of the following conditions are ture:
+         * 1.CR4_PKE=1.
+         * 2.EFER_LMA=1.
+         * 3.page is present with no reserved bit violations.
+         * 4.the access is not an instruction fetch.
+         * 5.the access is to a user page.
+         * 6.PKRU.AD=1
+         *       or The access is a data write and PKRU.WD=1
+         *           and either CR0.WP=1 or it is a user access.
+         */
+         pkru_ad = READ_PKRU_AD(pte_pkeys);
+         pkru_wd = READ_PKRU_AD(pte_pkeys);
+         if ( pkuf && (cr4 & X86_CR4_PKE) && hvm_long_mode_enabled(vcpu) &&
+             !rsvdf && !ff && (pkru_ad ||
+             (pkru_wd && wf && (hvm_wp_enabled(vcpu) || uf))))
+             return real_fault;
     }
 
     return spurious_fault;
 }
 
-static enum pf_type spurious_page_fault(
+static enum pf_type spurious_page_fault(struct vcpu *vcpu,
     unsigned long addr, const struct cpu_user_regs *regs)
 {
     unsigned long flags;
@@ -1405,7 +1437,7 @@ static enum pf_type spurious_page_fault(
      * page tables from becoming invalid under our feet during the walk.
      */
     local_irq_save(flags);
-    pf_type = __page_fault_type(addr, regs);
+    pf_type = __page_fault_type(vcpu, addr, regs);
     local_irq_restore(flags);
 
     return pf_type;
@@ -1479,6 +1511,7 @@ static int fixup_page_fault(unsigned long addr, struct 
cpu_user_regs *regs)
  *  Bit 2: User mode (=1) ; Supervisor mode (=0)
  *  Bit 3: Reserved bit violation
  *  Bit 4: Instruction fetch
+ *  Bit 5: Protection-key violations
  */
 void do_page_fault(struct cpu_user_regs *regs)
 {
@@ -1500,7 +1533,7 @@ void do_page_fault(struct cpu_user_regs *regs)
 
     if ( unlikely(!guest_mode(regs)) )
     {
-        pf_type = spurious_page_fault(addr, regs);
+        pf_type = spurious_page_fault(current, addr, regs);
         if ( (pf_type == smep_fault) || (pf_type == smap_fault) )
         {
             console_start_sync();
@@ -1533,7 +1566,7 @@ void do_page_fault(struct cpu_user_regs *regs)
 
     if ( unlikely(current->domain->arch.suppress_spurious_page_faults) )
     {
-        pf_type = spurious_page_fault(addr, regs);
+        pf_type = spurious_page_fault(current, addr, regs);
         if ( (pf_type == smep_fault) || (pf_type == smap_fault))
         {
             printk(XENLOG_G_ERR "%pv fatal SM%cP violation\n",
diff --git a/xen/include/asm-x86/processor.h b/xen/include/asm-x86/processor.h
index 427eb84..e8090fb 100644
--- a/xen/include/asm-x86/processor.h
+++ b/xen/include/asm-x86/processor.h
@@ -135,13 +135,14 @@
 #define TF_kernel_mode         (1<<_TF_kernel_mode)
 
 /* #PF error code values. */
-#define PFEC_page_present   (1U<<0)
-#define PFEC_write_access   (1U<<1)
-#define PFEC_user_mode      (1U<<2)
-#define PFEC_reserved_bit   (1U<<3)
-#define PFEC_insn_fetch     (1U<<4)
-#define PFEC_page_paged     (1U<<5)
-#define PFEC_page_shared    (1U<<6)
+#define PFEC_page_present       (1U<<0)
+#define PFEC_write_access       (1U<<1)
+#define PFEC_user_mode          (1U<<2)
+#define PFEC_reserved_bit       (1U<<3)
+#define PFEC_insn_fetch         (1U<<4)
+#define PFEC_protection_key     (1U<<5)
+#define PFEC_page_paged         (1U<<6)
+#define PFEC_page_shared        (1U<<7)
 
 #define XEN_MINIMAL_CR4 (X86_CR4_PGE | X86_CR4_PAE)
 
-- 
2.4.3


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel