[PATCH v3 14/22] x86/mm: enable page table sharing

[Anthony Yznaga <anthony.yznaga@oracle.com>]

Enable x86 support for handling page faults in an mshare region by
redirecting page faults to operate on the mshare mm_struct and vmas
contained in it.
Some permissions checks are done using vma flags in architecture-specfic
fault handling code so the actual vma needed to complete the handling
is acquired before calling handle_mm_fault(). Because of this an
ARCH_SUPPORTS_MSHARE config option is added.

Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
---
 arch/Kconfig        |  3 +++
 arch/x86/Kconfig    |  1 +
 arch/x86/mm/fault.c | 40 +++++++++++++++++++++++++++++++++++++++-
 mm/Kconfig          |  2 +-
 4 files changed, 44 insertions(+), 2 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index d1b4ffd6e085..2e10a11fc442 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -1676,6 +1676,9 @@ config HAVE_ARCH_PFN_VALID
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	bool
 
+config ARCH_SUPPORTS_MSHARE
+	bool
+
 config ARCH_SUPPORTS_PAGE_TABLE_CHECK
 	bool
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 58d890fe2100..1ad252eec417 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -124,6 +124,7 @@ config X86
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	select ARCH_SUPPORTS_HUGETLBFS
+	select ARCH_SUPPORTS_MSHARE		if X86_64
 	select ARCH_SUPPORTS_PAGE_TABLE_CHECK	if X86_64
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
 	select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP	if NR_CPUS <= 4096
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 998bd807fc7b..2a7df3aa13b4 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1215,6 +1215,8 @@ void do_user_addr_fault(struct pt_regs *regs,
 	struct mm_struct *mm;
 	vm_fault_t fault;
 	unsigned int flags = FAULT_FLAG_DEFAULT;
+	bool is_shared_vma;
+	unsigned long addr;
 
 	tsk = current;
 	mm = tsk->mm;
@@ -1328,6 +1330,12 @@ void do_user_addr_fault(struct pt_regs *regs,
 	if (!vma)
 		goto lock_mmap;
 
+	/* mshare does not support per-VMA locks yet */
+	if (vma_is_mshare(vma)) {
+		vma_end_read(vma);
+		goto lock_mmap;
+	}
+
 	if (unlikely(access_error(error_code, vma))) {
 		bad_area_access_error(regs, error_code, address, NULL, vma);
 		count_vm_vma_lock_event(VMA_LOCK_SUCCESS);
@@ -1356,17 +1364,38 @@ void do_user_addr_fault(struct pt_regs *regs,
 lock_mmap:
 
 retry:
+	addr = address;
+	is_shared_vma = false;
 	vma = lock_mm_and_find_vma(mm, address, regs);
 	if (unlikely(!vma)) {
 		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
 
+	if (unlikely(vma_is_mshare(vma))) {
+		fault = find_shared_vma(&vma, &addr);
+
+		if (fault) {
+			mmap_read_unlock(mm);
+			goto done;
+		}
+
+		if (!vma) {
+			mmap_read_unlock(mm);
+			bad_area_nosemaphore(regs, error_code, address);
+			return;
+		}
+
+		is_shared_vma = true;
+	}
+
 	/*
 	 * Ok, we have a good vm_area for this memory access, so
 	 * we can handle it..
 	 */
 	if (unlikely(access_error(error_code, vma))) {
+		if (unlikely(is_shared_vma))
+			mmap_read_unlock(vma->vm_mm);
 		bad_area_access_error(regs, error_code, address, mm, vma);
 		return;
 	}
@@ -1384,7 +1413,14 @@ void do_user_addr_fault(struct pt_regs *regs,
 	 * userland). The return to userland is identified whenever
 	 * FAULT_FLAG_USER|FAULT_FLAG_KILLABLE are both set in flags.
 	 */
-	fault = handle_mm_fault(vma, address, flags, regs);
+	fault = handle_mm_fault(vma, addr, flags, regs);
+
+	/*
+	 * If the lock on the shared mm has been released, release the lock
+	 * on the task's mm now.
+	 */
+	if (unlikely(is_shared_vma) && (fault & (VM_FAULT_COMPLETED | VM_FAULT_RETRY)))
+		mmap_read_unlock(mm);
 
 	if (fault_signal_pending(fault, regs)) {
 		/*
@@ -1412,6 +1448,8 @@ void do_user_addr_fault(struct pt_regs *regs,
 		goto retry;
 	}
 
+	if (unlikely(is_shared_vma))
+		mmap_read_unlock(vma->vm_mm);
 	mmap_read_unlock(mm);
 done:
 	if (likely(!(fault & VM_FAULT_ERROR)))
diff --git a/mm/Kconfig b/mm/Kconfig
index 8b50e9785729..824da2a481f9 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1402,7 +1402,7 @@ config FIND_NORMAL_PAGE
 
 config MSHARE
 	bool "Mshare"
-	depends on MMU
+	depends on MMU && ARCH_SUPPORTS_MSHARE
 	help
 	  Enable msharefs: A pseudo filesystem that allows multiple processes
 	  to share kernel resources for mapping shared pages. A file created on
-- 
2.47.1