[POWERPC] Provide a way to protect 4k subpages when using 64k pages

Using 64k pages on 64-bit PowerPC systems makes life difficult for
emulators that are trying to emulate an ISA, such as x86, which use a
smaller page size, since the emulator can no longer use the MMU and
the normal system calls for controlling page protections.  Of course,
the emulator can emulate the MMU by checking and possibly remapping
the address for each memory access in software, but that is pretty
slow.

This provides a facility for such programs to control the access
permissions on individual 4k sub-pages of 64k pages.  The idea is
that the emulator supplies an array of protection masks to apply to a
specified range of virtual addresses.  These masks are applied at the
level where hardware PTEs are inserted into the hardware page table
based on the Linux PTEs, so the Linux PTEs are not affected.  Note
that this new mechanism does not allow any access that would otherwise
be prohibited; it can only prohibit accesses that would otherwise be
allowed.  This new facility is only available on 64-bit PowerPC and
only when the kernel is configured for 64k pages.

The masks are supplied using a new subpage_prot system call, which
takes a starting virtual address and length, and a pointer to an array
of protection masks in memory.  The array has a 32-bit word per 64k
page to be protected; each 32-bit word consists of 16 2-bit fields,
for which 0 allows any access (that is otherwise allowed), 1 prevents
write accesses, and 2 or 3 prevent any access.

Implicit in this is that the regions of the address space that are
protected are switched to use 4k hardware pages rather than 64k
hardware pages (on machines with hardware 64k page support).  In fact
the whole process is switched to use 4k hardware pages when the
subpage_prot system call is used, but this could be improved in future
to switch only the affected segments.

The subpage protection bits are stored in a 3 level tree akin to the
page table tree.  The top level of this tree is stored in a structure
that is appended to the top level of the page table tree, i.e., the
pgd array.  Since it will often only be 32-bit addresses (below 4GB)
that are protected, the pointers to the first four bottom level pages
are also stored in this structure (each bottom level page contains the
protection bits for 1GB of address space), so the protection bits for
addresses below 4GB can be accessed with one fewer loads than those
for higher addresses.

Signed-off-by: Paul Mackerras <paulus@samba.org>

5 files changed, 48 insertions, 3 deletions

diff --git a/include/asm-powerpc/mmu-hash64.h b/include/asm-powerpc/mmu-hash64.h
index 2a1b4040e20d..2864fa3989ea 100644
--- a/include/asm-powerpc/mmu-hash64.h
+++ b/include/asm-powerpc/mmu-hash64.h
@@ -265,7 +265,7 @@ static inline unsigned long hpt_hash(unsigned long va, unsigned int shift,
 
 extern int __hash_page_4K(unsigned long ea, unsigned long access,
                           unsigned long vsid, pte_t *ptep, unsigned long trap,
-                          unsigned int local, int ssize);
+                          unsigned int local, int ssize, int subpage_prot);
 extern int __hash_page_64K(unsigned long ea, unsigned long access,
                            unsigned long vsid, pte_t *ptep, unsigned long trap,
                            unsigned int local, int ssize);
@@ -279,6 +279,7 @@ extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
                              unsigned long pstart, unsigned long mode,
                              int psize, int ssize);
 extern void set_huge_psize(int psize);
+extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
 
 extern void htab_initialize(void);
 extern void htab_initialize_secondary(void);
diff --git a/include/asm-powerpc/pgalloc-64.h b/include/asm-powerpc/pgalloc-64.h
index 94d0294341d6..43214c8085b7 100644
--- a/include/asm-powerpc/pgalloc-64.h
+++ b/include/asm-powerpc/pgalloc-64.h
@@ -12,6 +12,10 @@
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
 
+#ifndef CONFIG_PPC_SUBPAGE_PROT
+static inline void subpage_prot_free(pgd_t *pgd) {}
+#endif
+
 extern struct kmem_cache *pgtable_cache[];
 
 #define PGD_CACHE_NUM           0
@@ -27,6 +31,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 
 static inline void pgd_free(pgd_t *pgd)
 {
+        subpage_prot_free(pgd);
         kmem_cache_free(pgtable_cache[PGD_CACHE_NUM], pgd);
 }
 
diff --git a/include/asm-powerpc/pgtable-64k.h b/include/asm-powerpc/pgtable-64k.h
index bd54b772fbc6..1cbd6b377eea 100644
--- a/include/asm-powerpc/pgtable-64k.h
+++ b/include/asm-powerpc/pgtable-64k.h
@@ -13,12 +13,49 @@
 #define PTE_TABLE_SIZE  (sizeof(real_pte_t) << PTE_INDEX_SIZE)
 #define PMD_TABLE_SIZE  (sizeof(pmd_t) << PMD_INDEX_SIZE)
 #define PGD_TABLE_SIZE  (sizeof(pgd_t) << PGD_INDEX_SIZE)
-#endif  /* __ASSEMBLY__ */
 
 #define PTRS_PER_PTE    (1 << PTE_INDEX_SIZE)
 #define PTRS_PER_PMD    (1 << PMD_INDEX_SIZE)
 #define PTRS_PER_PGD    (1 << PGD_INDEX_SIZE)
 
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+/*
+ * For the sub-page protection option, we extend the PGD with one of
+ * these.  Basically we have a 3-level tree, with the top level being
+ * the protptrs array.  To optimize speed and memory consumption when
+ * only addresses < 4GB are being protected, pointers to the first
+ * four pages of sub-page protection words are stored in the low_prot
+ * array.
+ * Each page of sub-page protection words protects 1GB (4 bytes
+ * protects 64k).  For the 3-level tree, each page of pointers then
+ * protects 8TB.
+ */
+struct subpage_prot_table {
+        unsigned long maxaddr;  /* only addresses < this are protected */
+        unsigned int **protptrs[2];
+        unsigned int *low_prot[4];
+};
+
+#undef PGD_TABLE_SIZE
+#define PGD_TABLE_SIZE          ((sizeof(pgd_t) << PGD_INDEX_SIZE) + \
+                                 sizeof(struct subpage_prot_table))
+
+#define SBP_L1_BITS             (PAGE_SHIFT - 2)
+#define SBP_L2_BITS             (PAGE_SHIFT - 3)
+#define SBP_L1_COUNT            (1 << SBP_L1_BITS)
+#define SBP_L2_COUNT            (1 << SBP_L2_BITS)
+#define SBP_L2_SHIFT            (PAGE_SHIFT + SBP_L1_BITS)
+#define SBP_L3_SHIFT            (SBP_L2_SHIFT + SBP_L2_BITS)
+
+extern void subpage_prot_free(pgd_t *pgd);
+
+static inline struct subpage_prot_table *pgd_subpage_prot(pgd_t *pgd)
+{
+        return (struct subpage_prot_table *)(pgd + PTRS_PER_PGD);
+}
+#endif /* CONFIG_PPC_SUBPAGE_PROT */
+#endif  /* __ASSEMBLY__ */
+
 /* With 4k base page size, hugepage PTEs go at the PMD level */
 #define MIN_HUGEPTE_SHIFT       PAGE_SHIFT
 
diff --git a/include/asm-powerpc/systbl.h b/include/asm-powerpc/systbl.h
index 11d5383b2f09..0c8b0d679139 100644
--- a/include/asm-powerpc/systbl.h
+++ b/include/asm-powerpc/systbl.h
@@ -313,3 +313,4 @@ COMPAT_SYS_SPU(timerfd)
 SYSCALL_SPU(eventfd)
 COMPAT_SYS_SPU(sync_file_range2)
 COMPAT_SYS(fallocate)
+SYSCALL(subpage_prot)
diff --git a/include/asm-powerpc/unistd.h b/include/asm-powerpc/unistd.h
index 97d82b6a9406..fedc4b8e49e2 100644
--- a/include/asm-powerpc/unistd.h
+++ b/include/asm-powerpc/unistd.h
@@ -332,10 +332,11 @@
 #define __NR_eventfd            307
 #define __NR_sync_file_range2   308
 #define __NR_fallocate          309
+#define __NR_subpage_prot       310
 
 #ifdef __KERNEL__
 
-#define __NR_syscalls           310
+#define __NR_syscalls           311
 
 #define __NR__exit __NR_exit
 #define NR_syscalls     __NR_syscalls