[PATCHv4 OPTIONAL 8/8] x86/mm: Extend LAM to support to LAM_U48

[Kirill A. Shutemov]

LAM_U48 allows to encode 15 bits of tags into address.

LAM_U48 steals bits above 47-bit for tags and makes it impossible for
userspace to use full address space on 5-level paging machine.

Make these features mutually exclusive: whichever gets enabled first
blocks the other one.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
---
 arch/x86/include/asm/elf.h         |  3 ++-
 arch/x86/include/asm/mmu_context.h | 13 +++++++++++++
 arch/x86/kernel/process_64.c       | 23 +++++++++++++++++++++++
 arch/x86/kernel/sys_x86_64.c       |  5 +++--
 arch/x86/mm/hugetlbpage.c          |  6 ++++--
 arch/x86/mm/mmap.c                 |  9 ++++++++-
 6 files changed, 53 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index cb0ff1055ab1..4df13497a770 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -317,7 +317,8 @@ static inline int mmap_is_ia32(void)
 extern unsigned long task_size_32bit(void);
 extern unsigned long task_size_64bit(int full_addr_space);
 extern unsigned long get_mmap_base(int is_legacy);
-extern bool mmap_address_hint_valid(unsigned long addr, unsigned long len);
+extern bool mmap_address_hint_valid(struct mm_struct *mm,
+				    unsigned long addr, unsigned long len);
 extern unsigned long get_sigframe_size(void);
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index a6cded0f5e64..17d31988edd6 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -263,6 +263,19 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 
 unsigned long __get_current_cr3_fast(void);
 
+#ifdef CONFIG_X86_5LEVEL
+static inline bool full_va_allowed(struct mm_struct *mm)
+{
+	/* LAM_U48 steals VA bits above 47-bit for tags */
+	return mm->context.lam_cr3_mask != X86_CR3_LAM_U48;
+}
+#else
+static inline bool full_va_allowed(struct mm_struct *mm)
+{
+	return false;
+}
+#endif
+
 #include <asm-generic/mmu_context.h>
 
 #endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e328b91d1492..427ebef3f64b 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -756,6 +756,16 @@ static void enable_lam_func(void *mm)
 	switch_mm(loaded_mm, loaded_mm, current);
 }
 
+static bool lam_u48_allowed(void)
+{
+	struct mm_struct *mm = current->mm;
+
+	if (!full_va_allowed(mm))
+		return true;
+
+	return find_vma(mm, DEFAULT_MAP_WINDOW) == NULL;
+}
+
 static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
 {
 	int ret = 0;
@@ -763,6 +773,10 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
 	if (!cpu_feature_enabled(X86_FEATURE_LAM))
 		return -ENODEV;
 
+	/* lam_u48_allowed() requires mmap_lock */
+	if (mmap_write_lock_killable(mm))
+		return -EINTR;
+
 	mutex_lock(&mm->context.lock);
 
 	/* Already enabled? */
@@ -777,6 +791,14 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
 	} else if (nr_bits <= 6) {
 		mm->context.lam_cr3_mask = X86_CR3_LAM_U57;
 		mm->context.untag_mask =  ~GENMASK(62, 57);
+	} else if (nr_bits <= 15) {
+		if (!lam_u48_allowed()) {
+			ret = -EBUSY;
+			goto out;
+		}
+
+		mm->context.lam_cr3_mask = X86_CR3_LAM_U48;
+		mm->context.untag_mask =  ~GENMASK(62, 48);
 	} else {
 		ret = -EINVAL;
 		goto out;
@@ -788,6 +810,7 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
 	on_each_cpu_mask(mm_cpumask(mm), enable_lam_func, mm, true);
 out:
 	mutex_unlock(&mm->context.lock);
+	mmap_write_unlock(mm);
 	return ret;
 }
 
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 8cc653ffdccd..5ea6aaed89ba 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -21,6 +21,7 @@
 
 #include <asm/elf.h>
 #include <asm/ia32.h>
+#include <asm/mmu_context.h>
 
 /*
  * Align a virtual address to avoid aliasing in the I$ on AMD F15h.
@@ -182,7 +183,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	/* requesting a specific address */
 	if (addr) {
 		addr &= PAGE_MASK;
-		if (!mmap_address_hint_valid(addr, len))
+		if (!mmap_address_hint_valid(mm, addr, len))
 			goto get_unmapped_area;
 
 		vma = find_vma(mm, addr);
@@ -203,7 +204,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	 * !in_32bit_syscall() check to avoid high addresses for x32
 	 * (and make it no op on native i386).
 	 */
-	if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall())
+	if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall() && full_va_allowed(mm))
 		info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
 
 	info.align_mask = 0;
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index a0d023cb4292..9fdc8db42365 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -18,6 +18,7 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/elf.h>
+#include <asm/mmu_context.h>
 
 #if 0	/* This is just for testing */
 struct page *
@@ -103,6 +104,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 		unsigned long pgoff, unsigned long flags)
 {
 	struct hstate *h = hstate_file(file);
+	struct mm_struct *mm = current->mm;
 	struct vm_unmapped_area_info info;
 
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
@@ -114,7 +116,7 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
 	 * If hint address is above DEFAULT_MAP_WINDOW, look for unmapped area
 	 * in the full address space.
 	 */
-	if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall())
+	if (addr > DEFAULT_MAP_WINDOW && !in_32bit_syscall() && full_va_allowed(mm))
 		info.high_limit += TASK_SIZE_MAX - DEFAULT_MAP_WINDOW;
 
 	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
@@ -161,7 +163,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 
 	if (addr) {
 		addr &= huge_page_mask(h);
-		if (!mmap_address_hint_valid(addr, len))
+		if (!mmap_address_hint_valid(mm, addr, len))
 			goto get_unmapped_area;
 
 		vma = find_vma(mm, addr);
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index c90c20904a60..f9ca824729de 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -21,6 +21,7 @@
 #include <linux/elf-randomize.h>
 #include <asm/elf.h>
 #include <asm/io.h>
+#include <asm/mmu_context.h>
 
 #include "physaddr.h"
 
@@ -35,6 +36,8 @@ unsigned long task_size_32bit(void)
 
 unsigned long task_size_64bit(int full_addr_space)
 {
+	if (!full_va_allowed(current->mm))
+		return DEFAULT_MAP_WINDOW;
 	return full_addr_space ? TASK_SIZE_MAX : DEFAULT_MAP_WINDOW;
 }
 
@@ -206,11 +209,15 @@ const char *arch_vma_name(struct vm_area_struct *vma)
  * the failure of such a fixed mapping request, so the restriction is not
  * applied.
  */
-bool mmap_address_hint_valid(unsigned long addr, unsigned long len)
+bool mmap_address_hint_valid(struct mm_struct *mm,
+			     unsigned long addr, unsigned long len)
 {
 	if (TASK_SIZE - len < addr)
 		return false;
 
+	if (addr + len > DEFAULT_MAP_WINDOW && !full_va_allowed(mm))
+		return false;
+
 	return (addr > DEFAULT_MAP_WINDOW) == (addr + len > DEFAULT_MAP_WINDOW);
 }
 
-- 
2.35.1