Patch "kaiser: add "nokaiser" boot option, using ALTERNATIVE" has been added to the 4.4-stable tree

@@ -200,6 +200,9 @@
 #define X86_FEATURE_HWP_PKG_REQ ( 7*32+14) /* Intel HWP_PKG_REQ */
 #define X86_FEATURE_INTEL_PT	( 7*32+15) /* Intel Processor Trace */
 
+/* Because the ALTERNATIVE scheme is for members of the X86_FEATURE club... */
+#define X86_FEATURE_KAISER	( 7*32+31) /* CONFIG_KAISER w/o nokaiser */
+
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  ( 8*32+ 0) /* Intel TPR Shadow */
 #define X86_FEATURE_VNMI        ( 8*32+ 1) /* Intel Virtual NMI */

@@ -46,28 +46,33 @@ movq \reg, %cr3
 .endm
 
 .macro SWITCH_KERNEL_CR3
-pushq %rax
+ALTERNATIVE "jmp 8f", "pushq %rax", X86_FEATURE_KAISER
 _SWITCH_TO_KERNEL_CR3 %rax
 popq %rax
+8:
 .endm
 
 .macro SWITCH_USER_CR3
-pushq %rax
+ALTERNATIVE "jmp 8f", "pushq %rax", X86_FEATURE_KAISER
 _SWITCH_TO_USER_CR3 %rax %al
 popq %rax
+8:
 .endm
 
 .macro SWITCH_KERNEL_CR3_NO_STACK
-movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)
+ALTERNATIVE "jmp 8f", \
+	__stringify(movq %rax, PER_CPU_VAR(unsafe_stack_register_backup)), \
+	X86_FEATURE_KAISER
 _SWITCH_TO_KERNEL_CR3 %rax
 movq PER_CPU_VAR(unsafe_stack_register_backup), %rax
+8:
 .endm
 
 #else /* CONFIG_KAISER */
 
-.macro SWITCH_KERNEL_CR3 reg
+.macro SWITCH_KERNEL_CR3
 .endm
-.macro SWITCH_USER_CR3 reg regb
+.macro SWITCH_USER_CR3
 .endm
 .macro SWITCH_KERNEL_CR3_NO_STACK
 .endm

@@ -90,6 +95,16 @@ DECLARE_PER_CPU(unsigned long, x86_cr3_p
 
 extern char __per_cpu_user_mapped_start[], __per_cpu_user_mapped_end[];
 
+extern int kaiser_enabled;
+#else
+#define kaiser_enabled	0
+#endif /* CONFIG_KAISER */
+
+/*
+ * Kaiser function prototypes are needed even when CONFIG_KAISER is not set,
+ * so as to build with tests on kaiser_enabled instead of #ifdefs.
+ */
+
 /**
  *  kaiser_add_mapping - map a virtual memory part to the shadow (user) mapping
  *  @addr: the start address of the range

@@ -119,8 +134,6 @@ extern void kaiser_remove_mapping(unsign
  */
 extern void kaiser_init(void);
 
-#endif /* CONFIG_KAISER */
-
 #endif /* __ASSEMBLY */
 
 #endif /* _ASM_X86_KAISER_H */

@@ -18,6 +18,12 @@
 #ifndef __ASSEMBLY__
 #include <asm/x86_init.h>
 
+#ifdef CONFIG_KAISER
+extern int kaiser_enabled;
+#else
+#define kaiser_enabled 0
+#endif
+
 void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
 void ptdump_walk_pgd_level_checkwx(void);
 

@@ -660,7 +666,7 @@ static inline int pgd_bad(pgd_t pgd)
 	 * page table by accident; it will fault on the first
 	 * instruction it tries to run.  See native_set_pgd().
 	 */
-	if (IS_ENABLED(CONFIG_KAISER))
+	if (kaiser_enabled)
 		ignore_flags |= _PAGE_NX;
 
 	return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;

@@ -865,12 +871,14 @@ static inline void pmdp_set_wrprotect(st
  */
 static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
 {
-       memcpy(dst, src, count * sizeof(pgd_t));
+	memcpy(dst, src, count * sizeof(pgd_t));
 #ifdef CONFIG_KAISER
-	/* Clone the shadow pgd part as well */
-	memcpy(native_get_shadow_pgd(dst),
-	       native_get_shadow_pgd(src),
-	       count * sizeof(pgd_t));
+	if (kaiser_enabled) {
+		/* Clone the shadow pgd part as well */
+		memcpy(native_get_shadow_pgd(dst),
+			native_get_shadow_pgd(src),
+			count * sizeof(pgd_t));
+	}
 #endif
 }
 

@@ -111,13 +111,12 @@ extern pgd_t kaiser_set_shadow_pgd(pgd_t
 
 static inline pgd_t *native_get_shadow_pgd(pgd_t *pgdp)
 {
+#ifdef CONFIG_DEBUG_VM
+	/* linux/mmdebug.h may not have been included at this point */
+	BUG_ON(!kaiser_enabled);
+#endif
 	return (pgd_t *)((unsigned long)pgdp | (unsigned long)PAGE_SIZE);
 }
-
-static inline pgd_t *native_get_normal_pgd(pgd_t *pgdp)
-{
-	return (pgd_t *)((unsigned long)pgdp & ~(unsigned long)PAGE_SIZE);
-}
 #else
 static inline pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
 {

@@ -128,10 +127,6 @@ static inline pgd_t *native_get_shadow_p
 	BUILD_BUG_ON(1);
 	return NULL;
 }
-static inline pgd_t *native_get_normal_pgd(pgd_t *pgdp)
-{
-	return pgdp;
-}
 #endif /* CONFIG_KAISER */
 
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)

@@ -39,11 +39,7 @@
 #define _PAGE_ACCESSED	(_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
 #define _PAGE_DIRTY	(_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
 #define _PAGE_PSE	(_AT(pteval_t, 1) << _PAGE_BIT_PSE)
-#ifdef CONFIG_KAISER
-#define _PAGE_GLOBAL	(_AT(pteval_t, 0))
-#else
 #define _PAGE_GLOBAL	(_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
-#endif
 #define _PAGE_SOFTW1	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1)
 #define _PAGE_SOFTW2	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2)
 #define _PAGE_PAT	(_AT(pteval_t, 1) << _PAGE_BIT_PAT)

@@ -136,9 +136,11 @@ static inline void cr4_set_bits_and_upda
  * to avoid the need for asm/kaiser.h in unexpected places.
  */
 #ifdef CONFIG_KAISER
+extern int kaiser_enabled;
 extern void kaiser_setup_pcid(void);
 extern void kaiser_flush_tlb_on_return_to_user(void);
 #else
+#define kaiser_enabled 0
 static inline void kaiser_setup_pcid(void)
 {
 }

@@ -163,7 +165,7 @@ static inline void __native_flush_tlb(vo
 	 * back:
 	 */
 	preempt_disable();
-	if (this_cpu_has(X86_FEATURE_PCID))
+	if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID))
 		kaiser_flush_tlb_on_return_to_user();
 	native_write_cr3(native_read_cr3());
 	preempt_enable();

@@ -174,20 +176,30 @@ static inline void __native_flush_tlb_gl
 	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);
+	if (cr4 & X86_CR4_PGE) {
+		/* clear PGE and flush TLB of all entries */
+		native_write_cr4(cr4 & ~X86_CR4_PGE);
+		/* restore PGE as it was before */
+		native_write_cr4(cr4);
+	} else {
+		/*
+		 * x86_64 microcode update comes this way when CR4.PGE is not
+		 * enabled, and it's safer for all callers to allow this case.
+		 */
+		native_write_cr3(native_read_cr3());
+	}
 }
 
 static inline void __native_flush_tlb_global(void)
 {
-#ifdef CONFIG_KAISER
-	/* Globals are not used at all */
-	__native_flush_tlb();
-#else
 	unsigned long flags;
 
+	if (kaiser_enabled) {
+		/* Globals are not used at all */
+		__native_flush_tlb();
+		return;
+	}
+
 	if (this_cpu_has(X86_FEATURE_INVPCID)) {
 		/*
 		 * Using INVPCID is considerably faster than a pair of writes

@@ -207,7 +219,6 @@ static inline void __native_flush_tlb_gl
 	raw_local_irq_save(flags);
 	__native_flush_tlb_global_irq_disabled();
 	raw_local_irq_restore(flags);
-#endif
 }
 
 static inline void __native_flush_tlb_single(unsigned long addr)

@@ -222,7 +233,7 @@ static inline void __native_flush_tlb_si
 	 */
 
 	if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE)) {
-		if (this_cpu_has(X86_FEATURE_PCID))
+		if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID))
 			kaiser_flush_tlb_on_return_to_user();
 		asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
 		return;

@@ -237,9 +248,9 @@ static inline void __native_flush_tlb_si
 	 * Make sure to do only a single invpcid when KAISER is
 	 * disabled and we have only a single ASID.
 	 */
-	if (X86_CR3_PCID_ASID_KERN != X86_CR3_PCID_ASID_USER)
-		invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr);
-	invpcid_flush_one(X86_CR3_PCID_ASID_USER, addr);
+	if (kaiser_enabled)
+		invpcid_flush_one(X86_CR3_PCID_ASID_USER, addr);
+	invpcid_flush_one(X86_CR3_PCID_ASID_KERN, addr);
 }
 
 static inline void __flush_tlb_all(void)

@@ -178,6 +178,20 @@ static int __init x86_pcid_setup(char *s
 	return 1;
 }
 __setup("nopcid", x86_pcid_setup);
+
+static int __init x86_nokaiser_setup(char *s)
+{
+	/* nokaiser doesn't accept parameters */
+	if (s)
+		return -EINVAL;
+#ifdef CONFIG_KAISER
+	kaiser_enabled = 0;
+	setup_clear_cpu_cap(X86_FEATURE_KAISER);
+	pr_info("nokaiser: KAISER feature disabled\n");
+#endif
+	return 0;
+}
+early_param("nokaiser", x86_nokaiser_setup);
 #endif
 
 static int __init x86_noinvpcid_setup(char *s)

@@ -324,7 +338,7 @@ static __always_inline void setup_smap(s
 static void setup_pcid(struct cpuinfo_x86 *c)
 {
 	if (cpu_has(c, X86_FEATURE_PCID)) {
-		if (cpu_has(c, X86_FEATURE_PGE)) {
+		if (cpu_has(c, X86_FEATURE_PGE) || kaiser_enabled) {
 			cr4_set_bits(X86_CR4_PCIDE);
 			/*
 			 * INVPCID has two "groups" of types:

@@ -747,6 +761,10 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_power = cpuid_edx(0x80000007);
 
 	init_scattered_cpuid_features(c);
+#ifdef CONFIG_KAISER
+	if (kaiser_enabled)
+		set_cpu_cap(c, X86_FEATURE_KAISER);
+#endif
 }
 
 static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)

@@ -1406,6 +1424,14 @@ void cpu_init(void)
 	 * try to read it.
 	 */
 	cr4_init_shadow();
+	if (!kaiser_enabled) {
+		/*
+		 * secondary_startup_64() deferred setting PGE in cr4:
+		 * probe_page_size_mask() sets it on the boot cpu,
+		 * but it needs to be set on each secondary cpu.
+		 */
+		cr4_set_bits(X86_CR4_PGE);
+	}
 
 	/*
 	 * Load microcode on this cpu if a valid microcode is available.

@@ -132,9 +132,10 @@ void __init init_espfix_bsp(void)
 	 * area to ensure it is mapped into the shadow user page
 	 * tables.
 	 */
-	if (IS_ENABLED(CONFIG_KAISER))
+	if (kaiser_enabled) {
 		set_pgd(native_get_shadow_pgd(pgd_p),
 			__pgd(_KERNPG_TABLE | __pa((pud_t *)espfix_pud_page)));
+	}
 
 	/* Randomize the locations */
 	init_espfix_random();

@@ -165,7 +165,7 @@ static void __init probe_page_size_mask(
 		cr4_set_bits_and_update_boot(X86_CR4_PSE);
 
 	/* Enable PGE if available */
-	if (cpu_has_pge) {
+	if (cpu_has_pge && !kaiser_enabled) {
 		cr4_set_bits_and_update_boot(X86_CR4_PGE);
 		__supported_pte_mask |= _PAGE_GLOBAL;
 	} else

@@ -395,6 +395,16 @@ void __init cleanup_highmap(void)
 			continue;
 		if (vaddr < (unsigned long) _text || vaddr > end)
 			set_pmd(pmd, __pmd(0));
+		else if (kaiser_enabled) {
+			/*
+			 * level2_kernel_pgt is initialized with _PAGE_GLOBAL:
+			 * clear that now.  This is not important, so long as
+			 * CR4.PGE remains clear, but it removes an anomaly.
+			 * Physical mapping setup below avoids _PAGE_GLOBAL
+			 * by use of massage_pgprot() inside pfn_pte() etc.
+			 */
+			set_pmd(pmd, pmd_clear_flags(*pmd, _PAGE_GLOBAL));
+		}
 	}
 }
 

@@ -17,7 +17,9 @@
 #include <asm/pgalloc.h>
 #include <asm/desc.h>
 
-#ifdef CONFIG_KAISER
+int kaiser_enabled __read_mostly = 1;
+EXPORT_SYMBOL(kaiser_enabled);	/* for inlined TLB flush functions */
+
 __visible
 DEFINE_PER_CPU_USER_MAPPED(unsigned long, unsafe_stack_register_backup);
 

@@ -168,8 +170,8 @@ static pte_t *kaiser_pagetable_walk(unsi
 	return pte_offset_kernel(pmd, address);
 }
 
-int kaiser_add_user_map(const void *__start_addr, unsigned long size,
-			unsigned long flags)
+static int kaiser_add_user_map(const void *__start_addr, unsigned long size,
+			       unsigned long flags)
 {
 	int ret = 0;
 	pte_t *pte;

@@ -178,6 +180,15 @@ int kaiser_add_user_map(const void *__st
 	unsigned long end_addr = PAGE_ALIGN(start_addr + size);
 	unsigned long target_address;
 
+	/*
+	 * It is convenient for callers to pass in __PAGE_KERNEL etc,
+	 * and there is no actual harm from setting _PAGE_GLOBAL, so
+	 * long as CR4.PGE is not set.  But it is nonetheless troubling
+	 * to see Kaiser itself setting _PAGE_GLOBAL (now that "nokaiser"
+	 * requires that not to be #defined to 0): so mask it off here.
+	 */
+	flags &= ~_PAGE_GLOBAL;
+
 	for (; address < end_addr; address += PAGE_SIZE) {
 		target_address = get_pa_from_mapping(address);
 		if (target_address == -1) {

@@ -264,6 +275,8 @@ void __init kaiser_init(void)
 {
 	int cpu;
 
+	if (!kaiser_enabled)
+		return;
 	kaiser_init_all_pgds();
 
 	for_each_possible_cpu(cpu) {

@@ -312,6 +325,8 @@ void __init kaiser_init(void)
 /* Add a mapping to the shadow mapping, and synchronize the mappings */
 int kaiser_add_mapping(unsigned long addr, unsigned long size, unsigned long flags)
 {
+	if (!kaiser_enabled)
+		return 0;
 	return kaiser_add_user_map((const void *)addr, size, flags);
 }
 

@@ -323,6 +338,8 @@ void kaiser_remove_mapping(unsigned long
 	unsigned long addr, next;
 	pgd_t *pgd;
 
+	if (!kaiser_enabled)
+		return;
 	pgd = native_get_shadow_pgd(pgd_offset_k(start));
 	for (addr = start; addr < end; pgd++, addr = next) {
 		next = pgd_addr_end(addr, end);

@@ -344,6 +361,8 @@ static inline bool is_userspace_pgd(pgd_
 
 pgd_t kaiser_set_shadow_pgd(pgd_t *pgdp, pgd_t pgd)
 {
+	if (!kaiser_enabled)
+		return pgd;
 	/*
 	 * Do we need to also populate the shadow pgd?  Check _PAGE_USER to
 	 * skip cases like kexec and EFI which make temporary low mappings.

@@ -400,4 +419,3 @@ void kaiser_flush_tlb_on_return_to_user(
 			X86_CR3_PCID_USER_FLUSH | KAISER_SHADOW_PGD_OFFSET);
 }
 EXPORT_SYMBOL(kaiser_flush_tlb_on_return_to_user);
-#endif /* CONFIG_KAISER */

@@ -341,16 +341,12 @@ static inline void _pgd_free(pgd_t *pgd)
 }
 #else
 
-#ifdef CONFIG_KAISER
 /*
- * Instead of one pmd, we aquire two pmds.  Being order-1, it is
+ * Instead of one pgd, Kaiser acquires two pgds.  Being order-1, it is
  * both 8k in size and 8k-aligned.  That lets us just flip bit 12
  * in a pointer to swap between the two 4k halves.
  */
-#define PGD_ALLOCATION_ORDER 1
-#else
-#define PGD_ALLOCATION_ORDER 0
-#endif
+#define PGD_ALLOCATION_ORDER	kaiser_enabled
 
 static inline pgd_t *_pgd_alloc(void)
 {

@@ -39,8 +39,7 @@ static void load_new_mm_cr3(pgd_t *pgdir
 {
 	unsigned long new_mm_cr3 = __pa(pgdir);
 
-#ifdef CONFIG_KAISER
-	if (this_cpu_has(X86_FEATURE_PCID)) {
+	if (kaiser_enabled && this_cpu_has(X86_FEATURE_PCID)) {
 		/*
 		 * We reuse the same PCID for different tasks, so we must
 		 * flush all the entries for the PCID out when we change tasks.

@@ -57,7 +56,6 @@ static void load_new_mm_cr3(pgd_t *pgdir
 		new_mm_cr3 |= X86_CR3_PCID_KERN_FLUSH;
 		kaiser_flush_tlb_on_return_to_user();
 	}
-#endif /* CONFIG_KAISER */
 
 	/*
 	 * Caution: many callers of this function expect