Merge branch 'l1tf-final' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Merge L1 Terminal Fault fixes from Thomas Gleixner:
 "L1TF, aka L1 Terminal Fault, is yet another speculative hardware
  engineering trainwreck. It's a hardware vulnerability which allows
  unprivileged speculative access to data which is available in the
  Level 1 Data Cache when the page table entry controlling the virtual
  address, which is used for the access, has the Present bit cleared or
  other reserved bits set.

  If an instruction accesses a virtual address for which the relevant
  page table entry (PTE) has the Present bit cleared or other reserved
  bits set, then speculative execution ignores the invalid PTE and loads
  the referenced data if it is present in the Level 1 Data Cache, as if
  the page referenced by the address bits in the PTE was still present
  and accessible.

  While this is a purely speculative mechanism and the instruction will
  raise a page fault when it is retired eventually, the pure act of
  loading the data and making it available to other speculative
  instructions opens up the opportunity for side channel attacks to
  unprivileged malicious code, similar to the Meltdown attack.

  While Meltdown breaks the user space to kernel space protection, L1TF
  allows to attack any physical memory address in the system and the
  attack works across all protection domains. It allows an attack of SGX
  and also works from inside virtual machines because the speculation
  bypasses the extended page table (EPT) protection mechanism.

  The assoicated CVEs are: CVE-2018-3615, CVE-2018-3620, CVE-2018-3646

  The mitigations provided by this pull request include:

   - Host side protection by inverting the upper address bits of a non
     present page table entry so the entry points to uncacheable memory.

   - Hypervisor protection by flushing L1 Data Cache on VMENTER.

   - SMT (HyperThreading) control knobs, which allow to 'turn off' SMT
     by offlining the sibling CPU threads. The knobs are available on
     the kernel command line and at runtime via sysfs

   - Control knobs for the hypervisor mitigation, related to L1D flush
     and SMT control. The knobs are available on the kernel command line
     and at runtime via sysfs

   - Extensive documentation about L1TF including various degrees of
     mitigations.

  Thanks to all people who have contributed to this in various ways -
  patches, review, testing, backporting - and the fruitful, sometimes
  heated, but at the end constructive discussions.

  There is work in progress to provide other forms of mitigations, which
  might be less horrible performance wise for a particular kind of
  workloads, but this is not yet ready for consumption due to their
  complexity and limitations"

* 'l1tf-final' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (75 commits)
  x86/microcode: Allow late microcode loading with SMT disabled
  tools headers: Synchronise x86 cpufeatures.h for L1TF additions
  x86/mm/kmmio: Make the tracer robust against L1TF
  x86/mm/pat: Make set_memory_np() L1TF safe
  x86/speculation/l1tf: Make pmd/pud_mknotpresent() invert
  x86/speculation/l1tf: Invert all not present mappings
  cpu/hotplug: Fix SMT supported evaluation
  KVM: VMX: Tell the nested hypervisor to skip L1D flush on vmentry
  x86/speculation: Use ARCH_CAPABILITIES to skip L1D flush on vmentry
  x86/speculation: Simplify sysfs report of VMX L1TF vulnerability
  Documentation/l1tf: Remove Yonah processors from not vulnerable list
  x86/KVM/VMX: Don't set l1tf_flush_l1d from vmx_handle_external_intr()
  x86/irq: Let interrupt handlers set kvm_cpu_l1tf_flush_l1d
  x86: Don't include linux/irq.h from asm/hardirq.h
  x86/KVM/VMX: Introduce per-host-cpu analogue of l1tf_flush_l1d
  x86/irq: Demote irq_cpustat_t::__softirq_pending to u16
  x86/KVM/VMX: Move the l1tf_flush_l1d test to vmx_l1d_flush()
  x86/KVM/VMX: Replace 'vmx_l1d_flush_always' with 'vmx_l1d_flush_cond'
  x86/KVM/VMX: Don't set l1tf_flush_l1d to true from vmx_l1d_flush()
  cpu/hotplug: detect SMT disabled by BIOS
  ...

3 files changed, 106 insertions, 26 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 3d0a74ab70f2..6d175057cfd0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1890,6 +1890,9 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return -EFAULT;
 
+	if (!pfn_modify_allowed(pfn, pgprot))
+		return -EACCES;
+
 	track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV));
 
 	ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot,
@@ -1925,6 +1928,9 @@ static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 
 	track_pfn_insert(vma, &pgprot, pfn);
 
+	if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot))
+		return -EACCES;
+
 	/*
 	 * If we don't have pte special, then we have to use the pfn_valid()
 	 * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
@@ -1986,6 +1992,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 {
 	pte_t *pte;
 	spinlock_t *ptl;
+	int err = 0;
 
 	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (!pte)
@@ -1993,12 +2000,16 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 	arch_enter_lazy_mmu_mode();
 	do {
 		BUG_ON(!pte_none(*pte));
+		if (!pfn_modify_allowed(pfn, prot)) {
+			err = -EACCES;
+			break;
+		}
 		set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
-	return 0;
+	return err;
 }
 
 static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
@@ -2007,6 +2018,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
 {
 	pmd_t *pmd;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	pmd = pmd_alloc(mm, pud, addr);
@@ -2015,9 +2027,10 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
 	VM_BUG_ON(pmd_trans_huge(*pmd));
 	do {
 		next = pmd_addr_end(addr, end);
-		if (remap_pte_range(mm, pmd, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pte_range(mm, pmd, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (pmd++, addr = next, addr != end);
 	return 0;
 }
@@ -2028,6 +2041,7 @@ static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
 {
 	pud_t *pud;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	pud = pud_alloc(mm, p4d, addr);
@@ -2035,9 +2049,10 @@ static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
 		return -ENOMEM;
 	do {
 		next = pud_addr_end(addr, end);
-		if (remap_pmd_range(mm, pud, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pmd_range(mm, pud, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (pud++, addr = next, addr != end);
 	return 0;
 }
@@ -2048,6 +2063,7 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 {
 	p4d_t *p4d;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	p4d = p4d_alloc(mm, pgd, addr);
@@ -2055,9 +2071,10 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 		return -ENOMEM;
 	do {
 		next = p4d_addr_end(addr, end);
-		if (remap_pud_range(mm, p4d, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pud_range(mm, p4d, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (p4d++, addr = next, addr != end);
 	return 0;
 }
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 625608bc8962..6d331620b9e5 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -306,6 +306,42 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 	return pages;
 }
 
+static int prot_none_pte_entry(pte_t *pte, unsigned long addr,
+			       unsigned long next, struct mm_walk *walk)
+{
+	return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
+		0 : -EACCES;
+}
+
+static int prot_none_hugetlb_entry(pte_t *pte, unsigned long hmask,
+				   unsigned long addr, unsigned long next,
+				   struct mm_walk *walk)
+{
+	return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
+		0 : -EACCES;
+}
+
+static int prot_none_test(unsigned long addr, unsigned long next,
+			  struct mm_walk *walk)
+{
+	return 0;
+}
+
+static int prot_none_walk(struct vm_area_struct *vma, unsigned long start,
+			   unsigned long end, unsigned long newflags)
+{
+	pgprot_t new_pgprot = vm_get_page_prot(newflags);
+	struct mm_walk prot_none_walk = {
+		.pte_entry = prot_none_pte_entry,
+		.hugetlb_entry = prot_none_hugetlb_entry,
+		.test_walk = prot_none_test,
+		.mm = current->mm,
+		.private = &new_pgprot,
+	};
+
+	return walk_page_range(start, end, &prot_none_walk);
+}
+
 int
 mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	unsigned long start, unsigned long end, unsigned long newflags)
@@ -324,6 +360,19 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	}
 
 	/*
+	 * Do PROT_NONE PFN permission checks here when we can still
+	 * bail out without undoing a lot of state. This is a rather
+	 * uncommon case, so doesn't need to be very optimized.
+	 */
+	if (arch_has_pfn_modify_check() &&
+	    (vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
+	    (newflags & (VM_READ|VM_WRITE|VM_EXEC)) == 0) {
+		error = prot_none_walk(vma, start, end, newflags);
+		if (error)
+			return error;
+	}
+
+	/*
 	 * If we make a private mapping writable we increase our commit;
 	 * but (without finer accounting) cannot reduce our commit if we
 	 * make it unwritable again. hugetlb mapping were accounted for
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2cc2972eedaf..18185ae4f223 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2909,6 +2909,35 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 	return 0;
 }
 
+
+/*
+ * Find out how many pages are allowed for a single swap device. There
+ * are two limiting factors:
+ * 1) the number of bits for the swap offset in the swp_entry_t type, and
+ * 2) the number of bits in the swap pte, as defined by the different
+ * architectures.
+ *
+ * In order to find the largest possible bit mask, a swap entry with
+ * swap type 0 and swap offset ~0UL is created, encoded to a swap pte,
+ * decoded to a swp_entry_t again, and finally the swap offset is
+ * extracted.
+ *
+ * This will mask all the bits from the initial ~0UL mask that can't
+ * be encoded in either the swp_entry_t or the architecture definition
+ * of a swap pte.
+ */
+unsigned long generic_max_swapfile_size(void)
+{
+	return swp_offset(pte_to_swp_entry(
+			swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+}
+
+/* Can be overridden by an architecture for additional checks. */
+__weak unsigned long max_swapfile_size(void)
+{
+	return generic_max_swapfile_size();
+}
+
 static unsigned long read_swap_header(struct swap_info_struct *p,
 					union swap_header *swap_header,
 					struct inode *inode)
@@ -2944,22 +2973,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
 	p->cluster_next = 1;
 	p->cluster_nr = 0;
 
-	/*
-	 * Find out how many pages are allowed for a single swap
-	 * device. There are two limiting factors: 1) the number
-	 * of bits for the swap offset in the swp_entry_t type, and
-	 * 2) the number of bits in the swap pte as defined by the
-	 * different architectures. In order to find the
-	 * largest possible bit mask, a swap entry with swap type 0
-	 * and swap offset ~0UL is created, encoded to a swap pte,
-	 * decoded to a swp_entry_t again, and finally the swap
-	 * offset is extracted. This will mask all the bits from
-	 * the initial ~0UL mask that can't be encoded in either
-	 * the swp_entry_t or the architecture definition of a
-	 * swap pte.
-	 */
-	maxpages = swp_offset(pte_to_swp_entry(
-			swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+	maxpages = max_swapfile_size();
 	last_page = swap_header->info.last_page;
 	if (!last_page) {
 		pr_warn("Empty swap-file\n");