[PATCH] enable SMP Opterons boot an NX-enabled x86 kernel

This fixes a corner-case NX bug: the x86 SMP kernel doesnt boot on SMP
Opterons if NX is enabled [and mem=nopentium is specified], due to
kernel-space NX protection preventing the SMP trampoline from being
executable.

Since the SMP trampoline is a rare case of 'dynamic code' executed by
the kernel (it has to be below 640K so it cannot be part of the kernel
text itself), i've added the necessary infrastructure to enable/disable
executability of specific kernel pages.

We cannot simply disable NX via the MSR because we've got the NX bits in
the kernel pagetables, which are set up before we do the SMP bootup.
The NX bit in the pagetables is undefined if EFER.NXE is 0, so we cannot
count on NX-capable CPUs not faulting when they encounter them.

I've tested the x86 kernel on a non-NX SMP x86 box and on an NX UP box,
on which i've also tested a simulated SMP trampoline, it all works fine.

- add infrastructure to enable/disable executability of kernel pages

- make the SMP trampoline page executable.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index 27bda2a137d58f999627f55bb2103955e25dde71..1a9b081904928c2561fcaaf155c94e97f8feb2c6 100644 (file)
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -82,6 +82,7 @@ int smp_threads_ready;
 extern unsigned char trampoline_data [];
 extern unsigned char trampoline_end  [];
 static unsigned char *trampoline_base;
+static int trampoline_exec;
 
 /*
  * Currently trivial. Write the real->protected mode
@@ -108,6 +109,10 @@ void __init smp_alloc_memory(void)
         */
        if (__pa(trampoline_base) >= 0x9F000)
                BUG();
+       /*
+        * Make the SMP trampoline executable:
+        */
+       trampoline_exec = set_kernel_exec((unsigned long)trampoline_base, 1);
 }
 
 /*
@@ -1375,6 +1380,10 @@ void __init smp_cpus_done(unsigned int max_cpus)
        setup_ioapic_dest();
 #endif
        zap_low_mappings();
+       /*
+        * Disable executability of the SMP trampoline:
+        */
+       set_kernel_exec((unsigned long)trampoline_base, trampoline_exec);
 }
 
 void __init smp_intr_init(void)

diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c
index f8661fd97303fc8bcb02f1ca5ce255f5f77131cf..d492599dac6acebee7820c25989f3365a28db553 100644 (file)
--- a/arch/i386/mm/init.c
+++ b/arch/i386/mm/init.c
@@ -455,6 +455,33 @@ static void __init set_nx(void)
        }
 }
 
+/*
+ * Enables/disables executability of a given kernel page and
+ * returns the previous setting.
+ */
+int __init set_kernel_exec(unsigned long vaddr, int enable)
+{
+       pte_t *pte;
+       int ret = 1;
+
+       if (!nx_enabled)
+               goto out;
+
+       pte = lookup_address(vaddr);
+       BUG_ON(!pte);
+
+       if (pte_val(*pte) & _PAGE_NX)
+               ret = 0;
+
+       if (enable)
+               pte->pte_high &= ~(1 << (_PAGE_BIT_NX - 32));
+       else
+               pte->pte_high |= 1 << (_PAGE_BIT_NX - 32);
+       __flush_tlb_all();
+out:
+       return ret;
+}
+
 #endif
 
 /*

diff --git a/arch/i386/mm/pageattr.c b/arch/i386/mm/pageattr.c
index af7c602852379a2ba10594fe71960364752fb5a8..8eb95be7d771e7f9d05838d68f4276ae17a76501 100644 (file)
--- a/arch/i386/mm/pageattr.c
+++ b/arch/i386/mm/pageattr.c
@@ -17,7 +17,7 @@ static spinlock_t cpa_lock = SPIN_LOCK_UNLOCKED;
 static struct list_head df_list = LIST_HEAD_INIT(df_list);
 
 
-static inline pte_t *lookup_address(unsigned long address) 
+pte_t *lookup_address(unsigned long address) 
 { 
        pgd_t *pgd = pgd_offset_k(address); 
        pmd_t *pmd;

diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h
index b95fedb5b32deaeaeb1b68f4cd213a298564c3b5..a22128c2604e6a11678072c37d9fa7fbdcf09f6b 100644 (file)
--- a/include/asm-i386/pgtable.h
+++ b/include/asm-i386/pgtable.h
@@ -285,7 +285,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
         * Chop off the NX bit (if present), and add the NX portion of
         * the newprot (if present):
         */
-       pte.pte_high &= -1 ^ (1 << (_PAGE_BIT_NX - 32));
+       pte.pte_high &= ~(1 << (_PAGE_BIT_NX - 32));
        pte.pte_high |= (pgprot_val(newprot) >> 32) & \
                                        (__supported_pte_mask >> 32);
 #endif
@@ -344,6 +344,26 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 #define pte_offset_kernel(dir, address) \
        ((pte_t *) pmd_page_kernel(*(dir)) +  pte_index(address))
 
+/*
+ * Helper function that returns the kernel pagetable entry controlling
+ * the virtual address 'address'. NULL means no pagetable entry present.
+ * NOTE: the return type is pte_t but if the pmd is PSE then we return it
+ * as a pte too.
+ */
+extern pte_t *lookup_address(unsigned long address);
+
+/*
+ * Make a given kernel text page executable/non-executable.
+ * Returns the previous executability setting of that page (which
+ * is used to restore the previous state). Used by the SMP bootup code.
+ * NOTE: this is an __init function for security reasons.
+ */
+#ifdef CONFIG_X86_PAE
+ extern int set_kernel_exec(unsigned long vaddr, int enable);
+#else
+ static inline int set_kernel_exec(unsigned long vaddr, int enable) { return 0;}
+#endif
+
 #if defined(CONFIG_HIGHPTE)
 #define pte_offset_map(dir, address) \
        ((pte_t *)kmap_atomic(pmd_page(*(dir)),KM_PTE0) + pte_index(address))