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

Pull x86 iopl updates from Ingo Molnar:
 "This implements a nice simplification of the iopl and ioperm code that
  Thomas Gleixner discovered: we can implement the IO privilege features
  of the iopl system call by using the IO permission bitmap in
  permissive mode, while trapping CLI/STI/POPF/PUSHF uses in user-space
  if they change the interrupt flag.

  This implements that feature, with testing facilities and related
  cleanups"

[ "Simplification" may be an over-statement. The main goal is to avoid
  the cli/sti of iopl by effectively implementing the IO port access
  parts of iopl in terms of ioperm.

  This may end up not workign well in case people actually depend on
  cli/sti being available, or if there are mixed uses of iopl and
  ioperm. We will see..       - Linus ]

* 'x86-iopl-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (22 commits)
  x86/ioperm: Fix use of deprecated config option
  x86/entry/32: Clarify register saving in __switch_to_asm()
  selftests/x86/iopl: Extend test to cover IOPL emulation
  x86/ioperm: Extend IOPL config to control ioperm() as well
  x86/iopl: Remove legacy IOPL option
  x86/iopl: Restrict iopl() permission scope
  x86/iopl: Fixup misleading comment
  selftests/x86/ioperm: Extend testing so the shared bitmap is exercised
  x86/ioperm: Share I/O bitmap if identical
  x86/ioperm: Remove bitmap if all permissions dropped
  x86/ioperm: Move TSS bitmap update to exit to user work
  x86/ioperm: Add bitmap sequence number
  x86/ioperm: Move iobitmap data into a struct
  x86/tss: Move I/O bitmap data into a seperate struct
  x86/io: Speedup schedule out of I/O bitmap user
  x86/ioperm: Avoid bitmap allocation if no permissions are set
  x86/ioperm: Simplify first ioperm() invocation logic
  x86/iopl: Cleanup include maze
  x86/tss: Fix and move VMX BUILD_BUG_ON()
  x86/cpu: Unify cpu_init()
  ...

Author: torvalds

arch/x86/Kconfig

@@ -1224,6 +1224,24 @@ config X86_VSYSCALL_EMULATION
 	 Disabling this option saves about 7K of kernel size and
 	 possibly 4K of additional runtime pagetable memory.
 
+config X86_IOPL_IOPERM
+	bool "IOPERM and IOPL Emulation"
+	default y
+	---help---
+	  This enables the ioperm() and iopl() syscalls which are necessary
+	  for legacy applications.
+
+	  Legacy IOPL support is an overbroad mechanism which allows user
+	  space aside of accessing all 65536 I/O ports also to disable
+	  interrupts. To gain this access the caller needs CAP_SYS_RAWIO
+	  capabilities and permission from potentially active security
+	  modules.
+
+	  The emulation restricts the functionality of the syscall to
+	  only allowing the full range I/O port access, but prevents the
+	  ability to disable interrupts from user space which would be
+	  granted if the hardware IOPL mechanism would be used.
+
 config TOSHIBA
 	tristate "Toshiba Laptop support"
 	depends on X86_32

arch/x86/entry/common.c

@@ -33,6 +33,7 @@
 #include <asm/cpufeature.h>
 #include <asm/fpu/api.h>
 #include <asm/nospec-branch.h>
+#include <asm/io_bitmap.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -196,6 +197,9 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	/* Reload ti->flags; we may have rescheduled above. */
 	cached_flags = READ_ONCE(ti->flags);
 
+	if (unlikely(cached_flags & _TIF_IO_BITMAP))
+		tss_update_io_bitmap();
+
 	fpregs_assert_state_consistent();
 	if (unlikely(cached_flags & _TIF_NEED_FPU_LOAD))
 		switch_fpu_return();

arch/x86/entry/entry_32.S

@@ -739,6 +739,11 @@ SYM_CODE_START(__switch_to_asm)
 	pushl	%ebx
 	pushl	%edi
 	pushl	%esi
+	/*
+	 * Flags are saved to prevent AC leakage. This could go
+	 * away if objtool would have 32bit support to verify
+	 * the STAC/CLAC correctness.
+	 */
 	pushfl
 
 	/* switch stack */
@@ -761,8 +766,9 @@ SYM_CODE_START(__switch_to_asm)
 	FILL_RETURN_BUFFER %ebx, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
 #endif
 
-	/* restore callee-saved registers */
+	/* Restore flags or the incoming task to restore AC state. */
 	popfl
+	/* restore callee-saved registers */
 	popl	%esi
 	popl	%edi
 	popl	%ebx

arch/x86/include/asm/io_bitmap.h

@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_IOBITMAP_H
+#define _ASM_X86_IOBITMAP_H
+
+#include <linux/refcount.h>
+#include <asm/processor.h>
+
+struct io_bitmap {
+	u64		sequence;
+	refcount_t	refcnt;
+	/* The maximum number of bytes to copy so all zero bits are covered */
+	unsigned int	max;
+	unsigned long	bitmap[IO_BITMAP_LONGS];
+};
+
+struct task_struct;
+
+#ifdef CONFIG_X86_IOPL_IOPERM
+void io_bitmap_share(struct task_struct *tsk);
+void io_bitmap_exit(void);
+
+void tss_update_io_bitmap(void);
+#else
+static inline void io_bitmap_share(struct task_struct *tsk) { }
+static inline void io_bitmap_exit(void) { }
+static inline void tss_update_io_bitmap(void) { }
+#endif
+
+#endif

arch/x86/include/asm/paravirt.h

@@ -294,10 +294,6 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
 {
 	PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g);
 }
-static inline void set_iopl_mask(unsigned mask)
-{
-	PVOP_VCALL1(cpu.set_iopl_mask, mask);
-}
 
 static inline void paravirt_activate_mm(struct mm_struct *prev,
 					struct mm_struct *next)

arch/x86/include/asm/paravirt_types.h

@@ -140,8 +140,6 @@ struct pv_cpu_ops {
 
 	void (*load_sp0)(unsigned long sp0);
 
-	void (*set_iopl_mask)(unsigned mask);
-
 	void (*wbinvd)(void);
 
 	/* cpuid emulation, mostly so that caps bits can be disabled */

arch/x86/include/asm/pgtable_32_types.h

@@ -44,7 +44,7 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
  * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
  * to avoid include recursion hell
  */
-#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 39)
+#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 41)
 
 /* The +1 is for the readonly IDT page: */
 #define CPU_ENTRY_AREA_BASE	\

arch/x86/include/asm/processor.h

@@ -7,6 +7,7 @@
 /* Forward declaration, a strange C thing */
 struct task_struct;
 struct mm_struct;
+struct io_bitmap;
 struct vm86;
 
 #include <asm/math_emu.h>
@@ -336,10 +337,32 @@ struct x86_hw_tss {
  * IO-bitmap sizes:
  */
 #define IO_BITMAP_BITS			65536
-#define IO_BITMAP_BYTES			(IO_BITMAP_BITS/8)
-#define IO_BITMAP_LONGS			(IO_BITMAP_BYTES/sizeof(long))
-#define IO_BITMAP_OFFSET		(offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss))
-#define INVALID_IO_BITMAP_OFFSET	0x8000
+#define IO_BITMAP_BYTES			(IO_BITMAP_BITS / BITS_PER_BYTE)
+#define IO_BITMAP_LONGS			(IO_BITMAP_BYTES / sizeof(long))
+
+#define IO_BITMAP_OFFSET_VALID_MAP				\
+	(offsetof(struct tss_struct, io_bitmap.bitmap) -	\
+	 offsetof(struct tss_struct, x86_tss))
+
+#define IO_BITMAP_OFFSET_VALID_ALL				\
+	(offsetof(struct tss_struct, io_bitmap.mapall) -	\
+	 offsetof(struct tss_struct, x86_tss))
+
+#ifdef CONFIG_X86_IOPL_IOPERM
+/*
+ * sizeof(unsigned long) coming from an extra "long" at the end of the
+ * iobitmap. The limit is inclusive, i.e. the last valid byte.
+ */
+# define __KERNEL_TSS_LIMIT	\
+	(IO_BITMAP_OFFSET_VALID_ALL + IO_BITMAP_BYTES + \
+	 sizeof(unsigned long) - 1)
+#else
+# define __KERNEL_TSS_LIMIT	\
+	(offsetof(struct tss_struct, x86_tss) + sizeof(struct x86_hw_tss) - 1)
+#endif
+
+/* Base offset outside of TSS_LIMIT so unpriviledged IO causes #GP */
+#define IO_BITMAP_OFFSET_INVALID	(__KERNEL_TSS_LIMIT + 1)
 
 struct entry_stack {
 	unsigned long		words[64];
@@ -349,35 +372,52 @@ struct entry_stack_page {
 	struct entry_stack stack;
 } __aligned(PAGE_SIZE);
 
-struct tss_struct {
+/*
+ * All IO bitmap related data stored in the TSS:
+ */
+struct x86_io_bitmap {
+	/* The sequence number of the last active bitmap. */
+	u64			prev_sequence;
+
 	/*
-	 * The fixed hardware portion.  This must not cross a page boundary
-	 * at risk of violating the SDM's advice and potentially triggering
-	 * errata.
+	 * Store the dirty size of the last io bitmap offender. The next
+	 * one will have to do the cleanup as the switch out to a non io
+	 * bitmap user will just set x86_tss.io_bitmap_base to a value
+	 * outside of the TSS limit. So for sane tasks there is no need to
+	 * actually touch the io_bitmap at all.
 	 */
-	struct x86_hw_tss	x86_tss;
+	unsigned int		prev_max;
 
 	/*
 	 * The extra 1 is there because the CPU will access an
 	 * additional byte beyond the end of the IO permission
 	 * bitmap. The extra byte must be all 1 bits, and must
 	 * be within the limit.
 	 */
-	unsigned long		io_bitmap[IO_BITMAP_LONGS + 1];
+	unsigned long		bitmap[IO_BITMAP_LONGS + 1];
+
+	/*
+	 * Special I/O bitmap to emulate IOPL(3). All bytes zero,
+	 * except the additional byte at the end.
+	 */
+	unsigned long		mapall[IO_BITMAP_LONGS + 1];
+};
+
+struct tss_struct {
+	/*
+	 * The fixed hardware portion.  This must not cross a page boundary
+	 * at risk of violating the SDM's advice and potentially triggering
+	 * errata.
+	 */
+	struct x86_hw_tss	x86_tss;
+
+#ifdef CONFIG_X86_IOPL_IOPERM
+	struct x86_io_bitmap	io_bitmap;
+#endif
 } __aligned(PAGE_SIZE);
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);
 
-/*
- * sizeof(unsigned long) coming from an extra "long" at the end
- * of the iobitmap.
- *
- * -1? seg base+limit should be pointing to the address of the
- * last valid byte
- */
-#define __KERNEL_TSS_LIMIT	\
-	(IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1)
-
 /* Per CPU interrupt stacks */
 struct irq_stack {
 	char		stack[IRQ_STACK_SIZE];
@@ -488,10 +528,14 @@ struct thread_struct {
 	struct vm86		*vm86;
 #endif
 	/* IO permissions: */
-	unsigned long		*io_bitmap_ptr;
-	unsigned long		iopl;
-	/* Max allowed port in the bitmap, in bytes: */
-	unsigned		io_bitmap_max;
+	struct io_bitmap	*io_bitmap;
+
+	/*
+	 * IOPL. Priviledge level dependent I/O permission which is
+	 * emulated via the I/O bitmap to prevent user space from disabling
+	 * interrupts.
+	 */
+	unsigned long		iopl_emul;
 
 	mm_segment_t		addr_limit;
 
@@ -523,25 +567,6 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset,
  */
 #define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
 
-/*
- * Set IOPL bits in EFLAGS from given mask
- */
-static inline void native_set_iopl_mask(unsigned mask)
-{
-#ifdef CONFIG_X86_32
-	unsigned int reg;
-
-	asm volatile ("pushfl;"
-		      "popl %0;"
-		      "andl %1, %0;"
-		      "orl %2, %0;"
-		      "pushl %0;"
-		      "popfl"
-		      : "=&r" (reg)
-		      : "i" (~X86_EFLAGS_IOPL), "r" (mask));
-#endif
-}
-
 static inline void
 native_load_sp0(unsigned long sp0)
 {
@@ -581,7 +606,6 @@ static inline void load_sp0(unsigned long sp0)
 	native_load_sp0(sp0);
 }
 
-#define set_iopl_mask native_set_iopl_mask
 #endif /* CONFIG_PARAVIRT_XXL */
 
 /* Free all resources held by a thread. */
@@ -849,7 +873,6 @@ static inline void spin_lock_prefetch(const void *x)
 #define INIT_THREAD  {							  \
 	.sp0			= TOP_OF_INIT_STACK,			  \
 	.sysenter_cs		= __KERNEL_CS,				  \
-	.io_bitmap_ptr		= NULL,					  \
 	.addr_limit		= KERNEL_DS,				  \
 }
 

arch/x86/include/asm/ptrace.h

@@ -361,5 +361,11 @@ extern int do_get_thread_area(struct task_struct *p, int idx,
 extern int do_set_thread_area(struct task_struct *p, int idx,
 			      struct user_desc __user *info, int can_allocate);
 
+#ifdef CONFIG_X86_64
+# define do_set_thread_area_64(p, s, t)	do_arch_prctl_64(p, s, t)
+#else
+# define do_set_thread_area_64(p, s, t)	(0)
+#endif
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_PTRACE_H */

arch/x86/include/asm/switch_to.h

@@ -103,7 +103,17 @@ static inline void update_task_stack(struct task_struct *task)
 	if (static_cpu_has(X86_FEATURE_XENPV))
 		load_sp0(task_top_of_stack(task));
 #endif
+}
 
+static inline void kthread_frame_init(struct inactive_task_frame *frame,
+				      unsigned long fun, unsigned long arg)
+{
+	frame->bx = fun;
+#ifdef CONFIG_X86_32
+	frame->di = arg;
+#else
+	frame->r12 = arg;
+#endif
 }
 
 #endif /* _ASM_X86_SWITCH_TO_H */