kvm: arm64: Get rid of fake page table levels

On arm64, the hardware supports concatenation of upto 16 tables,
at entry level for stage2 translations and we make use that whenever
possible. This could lead to reduced number of translation levels than
the normal (stage1 table) table. Also, since the IPA(40bit) is smaller
than the some of the supported VA_BITS (e.g, 48bit), there could be
different number of levels in stage-1 vs stage-2 tables. To reuse the
kernel host page table walker for stage2 we have been using a fake
software page table level, not known to the hardware. But with 16K
translations, there could be upto 2 fake software levels (with 48bit VA
and 40bit IPA), which complicates the code. Hence, we want to get rid of
the hack.

Now that we have explicit accessors for hyp vs stage2 page tables,
define the stage2 walker helpers accordingly based on the actual
table used by the hardware.

Once we know the number of translation levels used by the hardware,
it is merely a job of defining the helpers based on whether a
particular level is folded or not, looking at the number of levels.

Some facts before we calculate the translation levels:

1) Smallest page size supported by arm64 is 4K.
2) The minimum number of bits resolved at any page table level
   is (PAGE_SHIFT - 3) at intermediate levels.
Both of them implies, minimum number of bits required for a level
change is 9.

Since we can concatenate upto 16 tables at stage2 entry, the total
number of page table levels used by the hardware for resolving N bits
is same as that for (N - 4) bits (with concatenation), as there cannot
be a level in between (N, N-4) as per the above rules.

Hence, we have

 STAGE2_PGTABLE_LEVELS = PGTABLE_LEVELS(KVM_PHYS_SHIFT - 4)

With the current IPA limit (40bit), for all supported translations
and VA_BITS, we have the following condition (even for 36bit VA with
16K page size):

 CONFIG_PGTABLE_LEVELS >= STAGE2_PGTABLE_LEVELS.

So, for e.g,  if PUD is present in stage2, it is present in the hyp(host).
Hence, we fall back to the host definition if we find that a level is not
folded. Otherwise we redefine it accordingly. A build time check is added
to make sure the above condition holds. If this condition breaks in future,
we can rearrange the host level helpers and fix our code easily.

Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Christoffer Dall <christoffer.dall@linaro.org>
Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>

1 files changed, 89 insertions, 33 deletions

diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h
index 0ec218fe83c5..8b68099348e5 100644
--- a/arch/arm64/include/asm/stage2_pgtable.h
+++ b/arch/arm64/include/asm/stage2_pgtable.h
@@ -22,32 +22,61 @@
 #include <asm/pgtable.h>
 
 /*
- * In the case where PGDIR_SHIFT is larger than KVM_PHYS_SHIFT, we can address
- * the entire IPA input range with a single pgd entry, and we would only need
- * one pgd entry.  Note that in this case, the pgd is actually not used by
- * the MMU for Stage-2 translations, but is merely a fake pgd used as a data
- * structure for the kernel pgtable macros to work.
+ * The hardware supports concatenation of up to 16 tables at stage2 entry level
+ * and we use the feature whenever possible.
+ *
+ * Now, the minimum number of bits resolved at any level is (PAGE_SHIFT - 3).
+ * On arm64, the smallest PAGE_SIZE supported is 4k, which means
+ *             (PAGE_SHIFT - 3) > 4 holds for all page sizes.
+ * This implies, the total number of page table levels at stage2 expected
+ * by the hardware is actually the number of levels required for (KVM_PHYS_SHIFT - 4)
+ * in normal translations(e.g, stage1), since we cannot have another level in
+ * the range (KVM_PHYS_SHIFT, KVM_PHYS_SHIFT - 4).
  */
-#if PGDIR_SHIFT > KVM_PHYS_SHIFT
-#define PTRS_PER_S2_PGD_SHIFT	0
-#else
-#define PTRS_PER_S2_PGD_SHIFT	(KVM_PHYS_SHIFT - PGDIR_SHIFT)
-#endif
-#define PTRS_PER_S2_PGD		(1 << PTRS_PER_S2_PGD_SHIFT)
+#define STAGE2_PGTABLE_LEVELS		ARM64_HW_PGTABLE_LEVELS(KVM_PHYS_SHIFT - 4)
 
 /*
- * If we are concatenating first level stage-2 page tables, we would have less
- * than or equal to 16 pointers in the fake PGD, because that's what the
- * architecture allows.  In this case, (4 - CONFIG_PGTABLE_LEVELS)
- * represents the first level for the host, and we add 1 to go to the next
- * level (which uses contatenation) for the stage-2 tables.
+ * With all the supported VA_BITs and 40bit guest IPA, the following condition
+ * is always true:
+ *
+ *       STAGE2_PGTABLE_LEVELS <= CONFIG_PGTABLE_LEVELS
+ *
+ * We base our stage-2 page table walker helpers on this assumption and
+ * fall back to using the host version of the helper wherever possible.
+ * i.e, if a particular level is not folded (e.g, PUD) at stage2, we fall back
+ * to using the host version, since it is guaranteed it is not folded at host.
+ *
+ * If the condition breaks in the future, we can rearrange the host level
+ * definitions and reuse them for stage2. Till then...
  */
-#if PTRS_PER_S2_PGD <= 16
-#define KVM_PREALLOC_LEVEL	(4 - CONFIG_PGTABLE_LEVELS + 1)
-#else
-#define KVM_PREALLOC_LEVEL	(0)
+#if STAGE2_PGTABLE_LEVELS > CONFIG_PGTABLE_LEVELS
+#error "Unsupported combination of guest IPA and host VA_BITS."
 #endif
 
+/* S2_PGDIR_SHIFT is the size mapped by top-level stage2 entry */
+#define S2_PGDIR_SHIFT			ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - STAGE2_PGTABLE_LEVELS)
+#define S2_PGDIR_SIZE			(_AC(1, UL) << S2_PGDIR_SHIFT)
+#define S2_PGDIR_MASK			(~(S2_PGDIR_SIZE - 1))
+
+/*
+ * The number of PTRS across all concatenated stage2 tables given by the
+ * number of bits resolved at the initial level.
+ */
+#define PTRS_PER_S2_PGD			(1 << (KVM_PHYS_SHIFT - S2_PGDIR_SHIFT))
+
+/*
+ * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation
+ * levels in addition to the PGD.
+ */
+#define KVM_MMU_CACHE_MIN_PAGES		(STAGE2_PGTABLE_LEVELS - 1)
+
+
+#if STAGE2_PGTABLE_LEVELS > 3
+
+#define S2_PUD_SHIFT			ARM64_HW_PGTABLE_LEVEL_SHIFT(1)
+#define S2_PUD_SIZE			(_AC(1, UL) << S2_PUD_SHIFT)
+#define S2_PUD_MASK			(~(S2_PUD_SIZE - 1))
+
 #define stage2_pgd_none(pgd)				pgd_none(pgd)
 #define stage2_pgd_clear(pgd)				pgd_clear(pgd)
 #define stage2_pgd_present(pgd)				pgd_present(pgd)
@@ -55,6 +84,24 @@
 #define stage2_pud_offset(pgd, address)			pud_offset(pgd, address)
 #define stage2_pud_free(pud)				pud_free(NULL, pud)
 
+#define stage2_pud_table_empty(pudp)			kvm_page_empty(pudp)
+
+static inline phys_addr_t stage2_pud_addr_end(phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t boundary = (addr + S2_PUD_SIZE) & S2_PUD_MASK;
+
+	return (boundary - 1 < end - 1) ? boundary : end;
+}
+
+#endif		/* STAGE2_PGTABLE_LEVELS > 3 */
+
+
+#if STAGE2_PGTABLE_LEVELS > 2
+
+#define S2_PMD_SHIFT			ARM64_HW_PGTABLE_LEVEL_SHIFT(2)
+#define S2_PMD_SIZE			(_AC(1, UL) << S2_PMD_SHIFT)
+#define S2_PMD_MASK			(~(S2_PMD_SIZE - 1))
+
 #define stage2_pud_none(pud)				pud_none(pud)
 #define stage2_pud_clear(pud)				pud_clear(pud)
 #define stage2_pud_present(pud)				pud_present(pud)
@@ -63,24 +110,33 @@
 #define stage2_pmd_free(pmd)				pmd_free(NULL, pmd)
 
 #define stage2_pud_huge(pud)				pud_huge(pud)
+#define stage2_pmd_table_empty(pmdp)			kvm_page_empty(pmdp)
+
+static inline phys_addr_t stage2_pmd_addr_end(phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t boundary = (addr + S2_PMD_SIZE) & S2_PMD_MASK;
 
-#define stage2_pgd_addr_end(address, end)		pgd_addr_end(address, end)
-#define stage2_pud_addr_end(address, end)		pud_addr_end(address, end)
-#define stage2_pmd_addr_end(address, end)		pmd_addr_end(address, end)
+	return (boundary - 1 < end - 1) ? boundary : end;
+}
+
+#endif		/* STAGE2_PGTABLE_LEVELS > 2 */
 
 #define stage2_pte_table_empty(ptep)			kvm_page_empty(ptep)
-#ifdef __PGTABLE_PMD_FOLDED
-#define stage2_pmd_table_empty(pmdp)			(0)
-#else
-#define stage2_pmd_table_empty(pmdp)			((KVM_PREALLOC_LEVEL < 2) && kvm_page_empty(pmdp))
-#endif
 
-#ifdef __PGTABLE_PUD_FOLDED
-#define stage2_pud_table_empty(pudp)			(0)
-#else
-#define stage2_pud_table_empty(pudp)			((KVM_PREALLOC_LEVEL < 1) && kvm_page_empty(pudp))
+#if STAGE2_PGTABLE_LEVELS == 2
+#include <asm/stage2_pgtable-nopmd.h>
+#elif STAGE2_PGTABLE_LEVELS == 3
+#include <asm/stage2_pgtable-nopud.h>
 #endif
 
-#define stage2_pgd_index(addr)				(((addr) >> PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))
+
+#define stage2_pgd_index(addr)				(((addr) >> S2_PGDIR_SHIFT) & (PTRS_PER_S2_PGD - 1))
+
+static inline phys_addr_t stage2_pgd_addr_end(phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t boundary = (addr + S2_PGDIR_SIZE) & S2_PGDIR_MASK;
+
+	return (boundary - 1 < end - 1) ? boundary : end;
+}
 
 #endif	/* __ARM64_S2_PGTABLE_H_ */