x86/speculation/l1tf: Limit swap file size to MAX_PA/2

For the L1TF workaround its necessary to limit the swap file size to below
MAX_PA/2, so that the higher bits of the swap offset inverted never point
to valid memory.

Add a mechanism for the architecture to override the swap file size check
in swapfile.c and add a x86 specific max swapfile check function that
enforces that limit.

The check is only enabled if the CPU is vulnerable to L1TF.

In VMs with 42bit MAX_PA the typical limit is 2TB now, on a native system
with 46bit PA it is 32TB. The limit is only per individual swap file, so
it's always possible to exceed these limits with multiple swap files or
partitions.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index cee58a972cb20ff948e6384df5d9fc25f3e47ab7..1b530197d1149048feaee93eca7acca12927abb2 100644 (file)
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -4,6 +4,8 @@
 #include <linux/swap.h>
 #include <linux/memblock.h>
 #include <linux/bootmem.h>     /* for max_low_pfn */
+#include <linux/swapfile.h>
+#include <linux/swapops.h>
 
 #include <asm/set_memory.h>
 #include <asm/e820/api.h>
@@ -880,3 +882,16 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
        __cachemode2pte_tbl[cache] = __cm_idx2pte(entry);
        __pte2cachemode_tbl[entry] = cache;
 }
+
+unsigned long max_swapfile_size(void)
+{
+       unsigned long pages;
+
+       pages = generic_max_swapfile_size();
+
+       if (boot_cpu_has_bug(X86_BUG_L1TF)) {
+               /* Limit the swap file size to MAX_PA/2 for L1TF workaround */
+               pages = min_t(unsigned long, l1tf_pfn_limit() + 1, pages);
+       }
+       return pages;
+}

diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h
index 06bd7b096167fdc3d4b1c69d3c178d47b26aeb60..e06febf629788b10833ac1b4be94001357b3ca8c 100644 (file)
--- a/include/linux/swapfile.h
+++ b/include/linux/swapfile.h
@@ -10,5 +10,7 @@ extern spinlock_t swap_lock;
 extern struct plist_head swap_active_head;
 extern struct swap_info_struct *swap_info[];
 extern int try_to_unuse(unsigned int, bool, unsigned long);
+extern unsigned long generic_max_swapfile_size(void);
+extern unsigned long max_swapfile_size(void);
 
 #endif /* _LINUX_SWAPFILE_H */

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2cc2972eedaf1088e8a1ea0017f701b18c729494..18185ae4f223a3c24126c5ecce9ff189f498b2bb 100644 (file)
--- 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");