Merge branch kvm-arm64/52bit-fixes into kvmarm-master/next

* kvm-arm64/52bit-fixes:
  : .
  : 52bit PA fixes, courtesy of Ryan Roberts. From the cover letter:
  :
  : "I've been adding support for FEAT_LPA2 to KVM and as part of that work have been
  : testing various (84) configurations of HW, host and guest kernels on FVP. This
  : has thrown up a couple of pre-existing bugs, for which the fixes are provided."
  : .
  KVM: arm64: Fix benign bug with incorrect use of VA_BITS
  KVM: arm64: Fix PAR_TO_HPFAR() to work independently of PA_BITS.
  KVM: arm64: Fix kvm init failure when mode!=vhe and VA_BITS=52.
Signed-off-by: Marc Zyngier <maz@kernel.org>

arch/arm64/include/asm/kvm_arm.h

@@ -340,9 +340,13 @@
  * We have
  *	PAR	[PA_Shift - 1	: 12] = PA	[PA_Shift - 1 : 12]
  *	HPFAR	[PA_Shift - 9	: 4]  = FIPA	[PA_Shift - 1 : 12]
+ *
+ * Always assume 52 bit PA since at this point, we don't know how many PA bits
+ * the page table has been set up for. This should be safe since unused address
+ * bits in PAR are res0.
  */
 #define PAR_TO_HPFAR(par)		\
-	(((par) & GENMASK_ULL(PHYS_MASK_SHIFT - 1, 12)) >> 8)
+	(((par) & GENMASK_ULL(52 - 1, 12)) >> 8)
 
 #define ECN(x) { ESR_ELx_EC_##x, #x }
 

arch/arm64/kvm/arm.c

@@ -1518,7 +1518,7 @@ static int kvm_init_vector_slots(void)
 	return 0;
 }
 
-static void cpu_prepare_hyp_mode(int cpu)
+static void cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 {
 	struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
 	unsigned long tcr;
@@ -1534,23 +1534,9 @@ static void cpu_prepare_hyp_mode(int cpu)
 
 	params->mair_el2 = read_sysreg(mair_el1);
 
-	/*
-	 * The ID map may be configured to use an extended virtual address
-	 * range. This is only the case if system RAM is out of range for the
-	 * currently configured page size and VA_BITS, in which case we will
-	 * also need the extended virtual range for the HYP ID map, or we won't
-	 * be able to enable the EL2 MMU.
-	 *
-	 * However, at EL2, there is only one TTBR register, and we can't switch
-	 * between translation tables *and* update TCR_EL2.T0SZ at the same
-	 * time. Bottom line: we need to use the extended range with *both* our
-	 * translation tables.
-	 *
-	 * So use the same T0SZ value we use for the ID map.
-	 */
 	tcr = (read_sysreg(tcr_el1) & TCR_EL2_MASK) | TCR_EL2_RES1;
 	tcr &= ~TCR_T0SZ_MASK;
-	tcr |= (idmap_t0sz & GENMASK(TCR_TxSZ_WIDTH - 1, 0)) << TCR_T0SZ_OFFSET;
+	tcr |= TCR_T0SZ(hyp_va_bits);
 	params->tcr_el2 = tcr;
 
 	params->pgd_pa = kvm_mmu_get_httbr();
@@ -2054,7 +2040,7 @@ static int init_hyp_mode(void)
 		}
 
 		/* Prepare the CPU initialization parameters */
-		cpu_prepare_hyp_mode(cpu);
+		cpu_prepare_hyp_mode(cpu, hyp_va_bits);
 	}
 
 	if (is_protected_kvm_enabled()) {

arch/arm64/kvm/mmu.c

@@ -641,7 +641,7 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr)
 {
 	struct kvm_pgtable pgt = {
 		.pgd		= (kvm_pte_t *)kvm->mm->pgd,
-		.ia_bits	= VA_BITS,
+		.ia_bits	= vabits_actual,
 		.start_level	= (KVM_PGTABLE_MAX_LEVELS -
 				   CONFIG_PGTABLE_LEVELS),
 		.mm_ops		= &kvm_user_mm_ops,
@@ -1618,6 +1618,8 @@ static struct kvm_pgtable_mm_ops kvm_hyp_mm_ops = {
 int kvm_mmu_init(u32 *hyp_va_bits)
 {
 	int err;
+	u32 idmap_bits;
+	u32 kernel_bits;
 
 	hyp_idmap_start = __pa_symbol(__hyp_idmap_text_start);
 	hyp_idmap_start = ALIGN_DOWN(hyp_idmap_start, PAGE_SIZE);
@@ -1631,7 +1633,31 @@ int kvm_mmu_init(u32 *hyp_va_bits)
 	 */
 	BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK);
 
-	*hyp_va_bits = 64 - ((idmap_t0sz & TCR_T0SZ_MASK) >> TCR_T0SZ_OFFSET);
+	/*
+	 * The ID map may be configured to use an extended virtual address
+	 * range. This is only the case if system RAM is out of range for the
+	 * currently configured page size and VA_BITS_MIN, in which case we will
+	 * also need the extended virtual range for the HYP ID map, or we won't
+	 * be able to enable the EL2 MMU.
+	 *
+	 * However, in some cases the ID map may be configured for fewer than
+	 * the number of VA bits used by the regular kernel stage 1. This
+	 * happens when VA_BITS=52 and the kernel image is placed in PA space
+	 * below 48 bits.
+	 *
+	 * At EL2, there is only one TTBR register, and we can't switch between
+	 * translation tables *and* update TCR_EL2.T0SZ at the same time. Bottom
+	 * line: we need to use the extended range with *both* our translation
+	 * tables.
+	 *
+	 * So use the maximum of the idmap VA bits and the regular kernel stage
+	 * 1 VA bits to assure that the hypervisor can both ID map its code page
+	 * and map any kernel memory.
+	 */
+	idmap_bits = 64 - ((idmap_t0sz & TCR_T0SZ_MASK) >> TCR_T0SZ_OFFSET);
+	kernel_bits = vabits_actual;
+	*hyp_va_bits = max(idmap_bits, kernel_bits);
+
 	kvm_debug("Using %u-bit virtual addresses at EL2\n", *hyp_va_bits);
 	kvm_debug("IDMAP page: %lx\n", hyp_idmap_start);
 	kvm_debug("HYP VA range: %lx:%lx\n",