x86: enhance DEBUG_RODATA support - alternatives

Fix a memcpy that should be a text_poke (in apply_alternatives).

Use kernel_wp_save/kernel_wp_restore in text_poke to support DEBUG_RODATA
correctly and so the CPU HOTPLUG special case can be removed.

Add text_poke_early, for alternatives and paravirt boot-time and module load
time patching.

Changelog:

- Fix text_set and text_poke alignment check (mixed up bitwise and and or)
- Remove text_set
- Export add_nops, so it can be used by others.
- Document text_poke_early.
- Remove clflush, since it breaks some VIA architectures and is not strictly
  necessary.
- Add kerneldoc to text_poke and text_poke_early.
- Create a second vmap instead of using the WP bit to support Xen and VMI.
- Move local_irq disable within text_poke and text_poke_early to be able to
  be sleepable in these functions.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
CC: Andi Kleen <andi@firstfloor.org>
CC: pageexec@freemail.hu
CC: H. Peter Anvin <hpa@zytor.com>
CC: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 65 insertions, 23 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index e2d30b8e08a2..0c92ad4d257a 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -11,6 +11,8 @@
 #include <asm/mce.h>
 #include <asm/nmi.h>
 #include <asm/vsyscall.h>
+#include <asm/cacheflush.h>
+#include <asm/io.h>
 
 #define MAX_PATCH_LEN (255-1)
 
@@ -177,7 +179,7 @@ static const unsigned char*const * find_nop_table(void)
 #endif /* CONFIG_X86_64 */
 
 /* Use this to add nops to a buffer, then text_poke the whole buffer. */
-static void add_nops(void *insns, unsigned int len)
+void add_nops(void *insns, unsigned int len)
 {
         const unsigned char *const *noptable = find_nop_table();
 
@@ -190,6 +192,7 @@ static void add_nops(void *insns, unsigned int len)
                 len -= noplen;
         }
 }
+EXPORT_SYMBOL_GPL(add_nops);
 
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern u8 *__smp_locks[], *__smp_locks_end[];
@@ -223,7 +226,7 @@ void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
                 memcpy(insnbuf, a->replacement, a->replacementlen);
                 add_nops(insnbuf + a->replacementlen,
                          a->instrlen - a->replacementlen);
-                text_poke(instr, insnbuf, a->instrlen);
+                text_poke_early(instr, insnbuf, a->instrlen);
         }
 }
 
@@ -284,7 +287,6 @@ void alternatives_smp_module_add(struct module *mod, char *name,
                                  void *text,  void *text_end)
 {
         struct smp_alt_module *smp;
-        unsigned long flags;
 
         if (noreplace_smp)
                 return;
@@ -310,39 +312,37 @@ void alternatives_smp_module_add(struct module *mod, char *name,
                 __func__, smp->locks, smp->locks_end,
                 smp->text, smp->text_end, smp->name);
 
-        spin_lock_irqsave(&smp_alt, flags);
+        spin_lock(&smp_alt);
         list_add_tail(&smp->next, &smp_alt_modules);
         if (boot_cpu_has(X86_FEATURE_UP))
                 alternatives_smp_unlock(smp->locks, smp->locks_end,
                                         smp->text, smp->text_end);
-        spin_unlock_irqrestore(&smp_alt, flags);
+        spin_unlock(&smp_alt);
 }
 
 void alternatives_smp_module_del(struct module *mod)
 {
         struct smp_alt_module *item;
-        unsigned long flags;
 
         if (smp_alt_once || noreplace_smp)
                 return;
 
-        spin_lock_irqsave(&smp_alt, flags);
+        spin_lock(&smp_alt);
         list_for_each_entry(item, &smp_alt_modules, next) {
                 if (mod != item->mod)
                         continue;
                 list_del(&item->next);
-                spin_unlock_irqrestore(&smp_alt, flags);
+                spin_unlock(&smp_alt);
                 DPRINTK("%s: %s\n", __func__, item->name);
                 kfree(item);
                 return;
         }
-        spin_unlock_irqrestore(&smp_alt, flags);
+        spin_unlock(&smp_alt);
 }
 
 void alternatives_smp_switch(int smp)
 {
         struct smp_alt_module *mod;
-        unsigned long flags;
 
 #ifdef CONFIG_LOCKDEP
         /*
@@ -359,7 +359,7 @@ void alternatives_smp_switch(int smp)
                 return;
         BUG_ON(!smp && (num_online_cpus() > 1));
 
-        spin_lock_irqsave(&smp_alt, flags);
+        spin_lock(&smp_alt);
 
         /*
          * Avoid unnecessary switches because it forces JIT based VMs to
@@ -383,7 +383,7 @@ void alternatives_smp_switch(int smp)
                                                 mod->text, mod->text_end);
         }
         smp_mode = smp;
-        spin_unlock_irqrestore(&smp_alt, flags);
+        spin_unlock(&smp_alt);
 }
 
 #endif
@@ -411,7 +411,7 @@ void apply_paravirt(struct paravirt_patch_site *start,
 
                 /* Pad the rest with nops */
                 add_nops(insnbuf + used, p->len - used);
-                text_poke(p->instr, insnbuf, p->len);
+                text_poke_early(p->instr, insnbuf, p->len);
         }
 }
 extern struct paravirt_patch_site __start_parainstructions[],
@@ -420,8 +420,6 @@ extern struct paravirt_patch_site __start_parainstructions[],
 
 void __init alternative_instructions(void)
 {
-        unsigned long flags;
-
         /* The patching is not fully atomic, so try to avoid local interruptions
            that might execute the to be patched code.
            Other CPUs are not running. */
@@ -430,7 +428,6 @@ void __init alternative_instructions(void)
         stop_mce();
 #endif
 
-        local_irq_save(flags);
         apply_alternatives(__alt_instructions, __alt_instructions_end);
 
         /* switch to patch-once-at-boottime-only mode and free the
@@ -462,7 +459,6 @@ void __init alternative_instructions(void)
         }
 #endif
         apply_paravirt(__parainstructions, __parainstructions_end);
-        local_irq_restore(flags);
 
         if (smp_alt_once)
                 free_init_pages("SMP alternatives",
@@ -475,18 +471,64 @@ void __init alternative_instructions(void)
 #endif
 }
 
-/*
- * Warning:
+/**
+ * text_poke_early - Update instructions on a live kernel at boot time
+ * @addr: address to modify
+ * @opcode: source of the copy
+ * @len: length to copy
+ *
  * When you use this code to patch more than one byte of an instruction
  * you need to make sure that other CPUs cannot execute this code in parallel.
- * Also no thread must be currently preempted in the middle of these instructions.
- * And on the local CPU you need to be protected again NMI or MCE handlers
- * seeing an inconsistent instruction while you patch.
+ * Also no thread must be currently preempted in the middle of these
+ * instructions. And on the local CPU you need to be protected again NMI or MCE
+ * handlers seeing an inconsistent instruction while you patch.
  */
-void __kprobes text_poke(void *addr, unsigned char *opcode, int len)
+void *text_poke_early(void *addr, const void *opcode, size_t len)
 {
+        unsigned long flags;
+        local_irq_save(flags);
         memcpy(addr, opcode, len);
+        local_irq_restore(flags);
+        sync_core();
+        /* Could also do a CLFLUSH here to speed up CPU recovery; but
+           that causes hangs on some VIA CPUs. */
+        return addr;
+}
+
+/**
+ * text_poke - Update instructions on a live kernel
+ * @addr: address to modify
+ * @opcode: source of the copy
+ * @len: length to copy
+ *
+ * Only atomic text poke/set should be allowed when not doing early patching.
+ * It means the size must be writable atomically and the address must be aligned
+ * in a way that permits an atomic write. It also makes sure we fit on a single
+ * page.
+ */
+void *__kprobes text_poke(void *addr, const void *opcode, size_t len)
+{
+        unsigned long flags;
+        char *vaddr;
+        int nr_pages = 2;
+
+        BUG_ON(len > sizeof(long));
+        BUG_ON((((long)addr + len - 1) & ~(sizeof(long) - 1))
+                - ((long)addr & ~(sizeof(long) - 1)));
+        {
+                struct page *pages[2] = { virt_to_page(addr),
+                        virt_to_page(addr + PAGE_SIZE) };
+                if (!pages[1])
+                        nr_pages = 1;
+                vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
+                BUG_ON(!vaddr);
+                local_irq_save(flags);
+                memcpy(&vaddr[(unsigned long)addr & ~PAGE_MASK], opcode, len);
+                local_irq_restore(flags);
+                vunmap(vaddr);
+        }
         sync_core();
         /* Could also do a CLFLUSH here to speed up CPU recovery; but
            that causes hangs on some VIA CPUs. */
+        return addr;
 }