kaiser: merged update

Merged fixes and cleanups, rebased to 4.4.89 tree (no 5-level paging).

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

4 files changed, 50 insertions, 11 deletions

diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index bd1358d55146..54de4c70cbd6 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -127,11 +127,14 @@ void __init init_espfix_bsp(void)
 	/* Install the espfix pud into the kernel page directory */
 	pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)];
 	pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page);
-#ifdef CONFIG_KAISER
-	// add the esp stack pud to the shadow mapping here.
-	// This can be done directly, because the fixup stack has its own pud
-	set_pgd(native_get_shadow_pgd(pgd_p), __pgd(_PAGE_TABLE | __pa((pud_t *)espfix_pud_page)));
-#endif
+	/*
+	 * Just copy the top-level PGD that is mapping the espfix
+	 * area to ensure it is mapped into the shadow user page
+	 * tables.
+	 */
+	if (IS_ENABLED(CONFIG_KAISER))
+		set_pgd(native_get_shadow_pgd(pgd_p),
+			__pgd(_KERNPG_TABLE | __pa((pud_t *)espfix_pud_page)));
 
 	/* Randomize the locations */
 	init_espfix_random();
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 0a8d18ac63eb..abbbcfbb5e26 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -442,11 +442,24 @@ early_idt_ripmsg:
 GLOBAL(name)
 
 #ifdef CONFIG_KAISER
+/*
+ * Each PGD needs to be 8k long and 8k aligned.  We do not
+ * ever go out to userspace with these, so we do not
+ * strictly *need* the second page, but this allows us to
+ * have a single set_pgd() implementation that does not
+ * need to worry about whether it has 4k or 8k to work
+ * with.
+ *
+ * This ensures PGDs are 8k long:
+ */
+#define KAISER_USER_PGD_FILL	512
+/* This ensures they are 8k-aligned: */
 #define NEXT_PGD_PAGE(name) \
 	.balign 2 * PAGE_SIZE; \
 GLOBAL(name)
 #else
 #define NEXT_PGD_PAGE(name) NEXT_PAGE(name)
+#define KAISER_USER_PGD_FILL	0
 #endif
 
 /* Automate the creation of 1 to 1 mapping pmd entries */
@@ -461,6 +474,7 @@ GLOBAL(name)
 NEXT_PGD_PAGE(early_level4_pgt)
 	.fill	511,8,0
 	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.fill	KAISER_USER_PGD_FILL,8,0
 
 NEXT_PAGE(early_dynamic_pgts)
 	.fill	512*EARLY_DYNAMIC_PAGE_TABLES,8,0
@@ -469,7 +483,8 @@ NEXT_PAGE(early_dynamic_pgts)
 
 #ifndef CONFIG_XEN
 NEXT_PGD_PAGE(init_level4_pgt)
-	.fill	2*512,8,0
+	.fill	512,8,0
+	.fill	KAISER_USER_PGD_FILL,8,0
 #else
 NEXT_PGD_PAGE(init_level4_pgt)
 	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
@@ -478,6 +493,7 @@ NEXT_PGD_PAGE(init_level4_pgt)
 	.org    init_level4_pgt + L4_START_KERNEL*8, 0
 	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
 	.quad   level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE
+	.fill	KAISER_USER_PGD_FILL,8,0
 
 NEXT_PAGE(level3_ident_pgt)
 	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE
@@ -488,6 +504,7 @@ NEXT_PAGE(level2_ident_pgt)
 	 */
 	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
 #endif
+	.fill	KAISER_USER_PGD_FILL,8,0
 
 NEXT_PAGE(level3_kernel_pgt)
 	.fill	L3_START_KERNEL,8,0
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index d6279593bcdd..1062e88ff040 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -18,6 +18,7 @@
 #include <linux/uaccess.h>
 
 #include <asm/ldt.h>
+#include <asm/kaiser.h>
 #include <asm/desc.h>
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
@@ -34,11 +35,21 @@ static void flush_ldt(void *current_mm)
 	set_ldt(pc->ldt->entries, pc->ldt->size);
 }
 
+static void __free_ldt_struct(struct ldt_struct *ldt)
+{
+	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
+		vfree(ldt->entries);
+	else
+		free_page((unsigned long)ldt->entries);
+	kfree(ldt);
+}
+
 /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
 static struct ldt_struct *alloc_ldt_struct(int size)
 {
 	struct ldt_struct *new_ldt;
 	int alloc_size;
+	int ret = 0;
 
 	if (size > LDT_ENTRIES)
 		return NULL;
@@ -66,6 +77,14 @@ static struct ldt_struct *alloc_ldt_struct(int size)
 		return NULL;
 	}
 
+	// FIXME: make kaiser_add_mapping() return an error code
+	// when it fails
+	kaiser_add_mapping((unsigned long)new_ldt->entries, alloc_size,
+			   __PAGE_KERNEL);
+	if (ret) {
+		__free_ldt_struct(new_ldt);
+		return NULL;
+	}
 	new_ldt->size = size;
 	return new_ldt;
 }
@@ -92,12 +111,10 @@ static void free_ldt_struct(struct ldt_struct *ldt)
 	if (likely(!ldt))
 		return;
 
+	kaiser_remove_mapping((unsigned long)ldt->entries,
+			      ldt->size * LDT_ENTRY_SIZE);
 	paravirt_free_ldt(ldt->entries, ldt->size);
-	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
-		vfree(ldt->entries);
-	else
-		free_page((unsigned long)ldt->entries);
-	kfree(ldt);
+	__free_ldt_struct(ldt);
 }
 
 /*
diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c
index 1c113db9ed57..2bb5ee464df3 100644
--- a/arch/x86/kernel/tracepoint.c
+++ b/arch/x86/kernel/tracepoint.c
@@ -9,10 +9,12 @@
 #include <linux/atomic.h>
 
 atomic_t trace_idt_ctr = ATOMIC_INIT(0);
+__aligned(PAGE_SIZE)
 struct desc_ptr trace_idt_descr = { NR_VECTORS * 16 - 1,
 				(unsigned long) trace_idt_table };
 
 /* No need to be aligned, but done to keep all IDTs defined the same way. */
+__aligned(PAGE_SIZE)
 gate_desc trace_idt_table[NR_VECTORS] __page_aligned_bss;
 
 static int trace_irq_vector_refcount;