Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 PTI preparatory patches from Thomas Gleixner:
 "Todays Advent calendar window contains twentyfour easy to digest
  patches. The original plan was to have twenty three matching the date,
  but a late fixup made that moot.

   - Move the cpu_entry_area mapping out of the fixmap into a separate
     address space. That's necessary because the fixmap becomes too big
     with NRCPUS=8192 and this caused already subtle and hard to
     diagnose failures.

     The top most patch is fresh from today and cures a brain slip of
     that tall grumpy german greybeard, who ignored the intricacies of
     32bit wraparounds.

   - Limit the number of CPUs on 32bit to 64. That's insane big already,
     but at least it's small enough to prevent address space issues with
     the cpu_entry_area map, which have been observed and debugged with
     the fixmap code

   - A few TLB flush fixes in various places plus documentation which of
     the TLB functions should be used for what.

   - Rename the SYSENTER stack to CPU_ENTRY_AREA stack as it is used for
     more than sysenter now and keeping the name makes backtraces
     confusing.

   - Prevent LDT inheritance on exec() by moving it to arch_dup_mmap(),
     which is only invoked on fork().

   - Make vysycall more robust.

   - A few fixes and cleanups of the debug_pagetables code. Check
     PAGE_PRESENT instead of checking the PTE for 0 and a cleanup of the
     C89 initialization of the address hint array which already was out
     of sync with the index enums.

   - Move the ESPFIX init to a different place to prepare for PTI.

   - Several code moves with no functional change to make PTI
     integration simpler and header files less convoluted.

   - Documentation fixes and clarifications"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  x86/cpu_entry_area: Prevent wraparound in setup_cpu_entry_area_ptes() on 32bit
  init: Invoke init_espfix_bsp() from mm_init()
  x86/cpu_entry_area: Move it out of the fixmap
  x86/cpu_entry_area: Move it to a separate unit
  x86/mm: Create asm/invpcid.h
  x86/mm: Put MMU to hardware ASID translation in one place
  x86/mm: Remove hard-coded ASID limit checks
  x86/mm: Move the CR3 construction functions to tlbflush.h
  x86/mm: Add comments to clarify which TLB-flush functions are supposed to flush what
  x86/mm: Remove superfluous barriers
  x86/mm: Use __flush_tlb_one() for kernel memory
  x86/microcode: Dont abuse the TLB-flush interface
  x86/uv: Use the right TLB-flush API
  x86/entry: Rename SYSENTER_stack to CPU_ENTRY_AREA_entry_stack
  x86/doc: Remove obvious weirdnesses from the x86 MM layout documentation
  x86/mm/64: Improve the memory map documentation
  x86/ldt: Prevent LDT inheritance on exec
  x86/ldt: Rework locking
  arch, mm: Allow arch_dup_mmap() to fail
  x86/vsyscall/64: Warn and fail vsyscall emulation in NATIVE mode
  ...

1 files changed, 72 insertions, 64 deletions

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 877b5c1a1b12..e1884cf35257 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -9,70 +9,66 @@
 #include <asm/cpufeature.h>
 #include <asm/special_insns.h>
 #include <asm/smp.h>
+#include <asm/invpcid.h>
 
-static inline void __invpcid(unsigned long pcid, unsigned long addr,
-			     unsigned long type)
+static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
 {
-	struct { u64 d[2]; } desc = { { pcid, addr } };
-
 	/*
-	 * The memory clobber is because the whole point is to invalidate
-	 * stale TLB entries and, especially if we're flushing global
-	 * mappings, we don't want the compiler to reorder any subsequent
-	 * memory accesses before the TLB flush.
-	 *
-	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
-	 * invpcid (%rcx), %rax in long mode.
+	 * Bump the generation count.  This also serves as a full barrier
+	 * that synchronizes with switch_mm(): callers are required to order
+	 * their read of mm_cpumask after their writes to the paging
+	 * structures.
 	 */
-	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
-		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+	return atomic64_inc_return(&mm->context.tlb_gen);
 }
 
-#define INVPCID_TYPE_INDIV_ADDR		0
-#define INVPCID_TYPE_SINGLE_CTXT	1
-#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
-#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+/* There are 12 bits of space for ASIDS in CR3 */
+#define CR3_HW_ASID_BITS		12
+/*
+ * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
+ * user/kernel switches
+ */
+#define PTI_CONSUMED_ASID_BITS		0
 
-/* Flush all mappings for a given pcid and addr, not including globals. */
-static inline void invpcid_flush_one(unsigned long pcid,
-				     unsigned long addr)
-{
-	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
-}
+#define CR3_AVAIL_ASID_BITS (CR3_HW_ASID_BITS - PTI_CONSUMED_ASID_BITS)
+/*
+ * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid.  -1 below to account
+ * for them being zero-based.  Another -1 is because ASID 0 is reserved for
+ * use by non-PCID-aware users.
+ */
+#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_ASID_BITS) - 2)
 
-/* Flush all mappings for a given PCID, not including globals. */
-static inline void invpcid_flush_single_context(unsigned long pcid)
+static inline u16 kern_pcid(u16 asid)
 {
-	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+	/*
+	 * If PCID is on, ASID-aware code paths put the ASID+1 into the
+	 * PCID bits.  This serves two purposes.  It prevents a nasty
+	 * situation in which PCID-unaware code saves CR3, loads some other
+	 * value (with PCID == 0), and then restores CR3, thus corrupting
+	 * the TLB for ASID 0 if the saved ASID was nonzero.  It also means
+	 * that any bugs involving loading a PCID-enabled CR3 with
+	 * CR4.PCIDE off will trigger deterministically.
+	 */
+	return asid + 1;
 }
 
-/* Flush all mappings, including globals, for all PCIDs. */
-static inline void invpcid_flush_all(void)
+struct pgd_t;
+static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
 {
-	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+	if (static_cpu_has(X86_FEATURE_PCID)) {
+		return __sme_pa(pgd) | kern_pcid(asid);
+	} else {
+		VM_WARN_ON_ONCE(asid != 0);
+		return __sme_pa(pgd);
+	}
 }
 
-/* Flush all mappings for all PCIDs except globals. */
-static inline void invpcid_flush_all_nonglobals(void)
+static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
 {
-	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
-}
-
-static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
-{
-	u64 new_tlb_gen;
-
-	/*
-	 * Bump the generation count.  This also serves as a full barrier
-	 * that synchronizes with switch_mm(): callers are required to order
-	 * their read of mm_cpumask after their writes to the paging
-	 * structures.
-	 */
-	smp_mb__before_atomic();
-	new_tlb_gen = atomic64_inc_return(&mm->context.tlb_gen);
-	smp_mb__after_atomic();
-
-	return new_tlb_gen;
+	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+	VM_WARN_ON_ONCE(!this_cpu_has(X86_FEATURE_PCID));
+	return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH;
 }
 
 #ifdef CONFIG_PARAVIRT
@@ -237,6 +233,9 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
 
 extern void initialize_tlbstate_and_flush(void);
 
+/*
+ * flush the entire current user mapping
+ */
 static inline void __native_flush_tlb(void)
 {
 	/*
@@ -249,20 +248,12 @@ static inline void __native_flush_tlb(void)
 	preempt_enable();
 }
 
-static inline void __native_flush_tlb_global_irq_disabled(void)
-{
-	unsigned long cr4;
-
-	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	/* clear PGE */
-	native_write_cr4(cr4 & ~X86_CR4_PGE);
-	/* write old PGE again and flush TLBs */
-	native_write_cr4(cr4);
-}
-
+/*
+ * flush everything
+ */
 static inline void __native_flush_tlb_global(void)
 {
-	unsigned long flags;
+	unsigned long cr4, flags;
 
 	if (static_cpu_has(X86_FEATURE_INVPCID)) {
 		/*
@@ -280,22 +271,36 @@ static inline void __native_flush_tlb_global(void)
 	 */
 	raw_local_irq_save(flags);
 
-	__native_flush_tlb_global_irq_disabled();
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	/* toggle PGE */
+	native_write_cr4(cr4 ^ X86_CR4_PGE);
+	/* write old PGE again and flush TLBs */
+	native_write_cr4(cr4);
 
 	raw_local_irq_restore(flags);
 }
 
+/*
+ * flush one page in the user mapping
+ */
 static inline void __native_flush_tlb_single(unsigned long addr)
 {
 	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
 }
 
+/*
+ * flush everything
+ */
 static inline void __flush_tlb_all(void)
 {
-	if (boot_cpu_has(X86_FEATURE_PGE))
+	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		__flush_tlb_global();
-	else
+	} else {
+		/*
+		 * !PGE -> !PCID (setup_pcid()), thus every flush is total.
+		 */
 		__flush_tlb();
+	}
 
 	/*
 	 * Note: if we somehow had PCID but not PGE, then this wouldn't work --
@@ -306,6 +311,9 @@ static inline void __flush_tlb_all(void)
 	 */
 }
 
+/*
+ * flush one page in the kernel mapping
+ */
 static inline void __flush_tlb_one(unsigned long addr)
 {
 	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);