ARM: KVM: switch to a dual-step HYP init code

Our HYP init code suffers from two major design issues:
- it cannot support CPU hotplug, as we tear down the idmap very early
- it cannot perform a TLB invalidation when switching from init to
  runtime mappings, as pages are manipulated from PL1 exclusively

The hotplug problem mandates that we keep two sets of page tables
(boot and runtime). The TLB problem mandates that we're able to
transition from one PGD to another while in HYP, invalidating the TLBs
in the process.

To be able to do this, we need to share a page between the two page
tables. A page that will have the same VA in both configurations. All we
need is a VA that has the following properties:
- This VA can't be used to represent a kernel mapping.
- This VA will not conflict with the physical address of the kernel text

The vectors page seems to satisfy this requirement:
- The kernel never maps anything else there
- The kernel text being copied at the beginning of the physical memory,
  it is unlikely to use the last 64kB (I doubt we'll ever support KVM
  on a system with something like 4MB of RAM, but patches are very
  welcome).

Let's call this VA the trampoline VA.

Now, we map our init page at 3 locations:
- idmap in the boot pgd
- trampoline VA in the boot pgd
- trampoline VA in the runtime pgd

The init scenario is now the following:
- We jump in HYP with four parameters: boot HYP pgd, runtime HYP pgd,
  runtime stack, runtime vectors
- Enable the MMU with the boot pgd
- Jump to a target into the trampoline page (remember, this is the same
  physical page!)
- Now switch to the runtime pgd (same VA, and still the same physical
  page!)
- Invalidate TLBs
- Set stack and vectors
- Profit! (or eret, if you only care about the code).

Note that we keep the boot mapping permanently (it is not strictly an
idmap anymore) to allow for CPU hotplug in later patches.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Christoffer Dall <cdall@cs.columbia.edu>

2 files changed, 40 insertions, 15 deletions

diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 78813b8fad32..6c2a35da867e 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -188,23 +188,30 @@ int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
 int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
                 int exception_index);
 
-static inline void __cpu_init_hyp_mode(unsigned long long pgd_ptr,
+static inline void __cpu_init_hyp_mode(unsigned long long boot_pgd_ptr,
+                                       unsigned long long pgd_ptr,
                                        unsigned long hyp_stack_ptr,
                                        unsigned long vector_ptr)
 {
-        unsigned long pgd_low, pgd_high;
-
-        pgd_low = (pgd_ptr & ((1ULL << 32) - 1));
-        pgd_high = (pgd_ptr >> 32ULL);
-
         /*
-         * Call initialization code, and switch to the full blown
-         * HYP code. The init code doesn't need to preserve these registers as
-         * r1-r3 and r12 are already callee save according to the AAPCS.
-         * Note that we slightly misuse the prototype by casing the pgd_low to
-         * a void *.
+         * Call initialization code, and switch to the full blown HYP
+         * code. The init code doesn't need to preserve these
+         * registers as r0-r3 are already callee saved according to
+         * the AAPCS.
+         * Note that we slightly misuse the prototype by casing the
+         * stack pointer to a void *.
+         *
+         * We don't have enough registers to perform the full init in
+         * one go.  Install the boot PGD first, and then install the
+         * runtime PGD, stack pointer and vectors. The PGDs are always
+         * passed as the third argument, in order to be passed into
+         * r2-r3 to the init code (yes, this is compliant with the
+         * PCS!).
          */
-        kvm_call_hyp((void *)pgd_low, pgd_high, hyp_stack_ptr, vector_ptr);
+
+        kvm_call_hyp(NULL, 0, boot_pgd_ptr);
+
+        kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);
 }
 
 int kvm_perf_init(void);
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 92eb20d57942..24b767a8cdb9 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -19,17 +19,29 @@
 #ifndef __ARM_KVM_MMU_H__
 #define __ARM_KVM_MMU_H__
 
-#include <asm/cacheflush.h>
-#include <asm/pgalloc.h>
+#include <asm/memory.h>
+#include <asm/page.h>
 
 /*
  * We directly use the kernel VA for the HYP, as we can directly share
  * the mapping (HTTBR "covers" TTBR1).
  */
-#define HYP_PAGE_OFFSET_MASK    (~0UL)
+#define HYP_PAGE_OFFSET_MASK    UL(~0)
 #define HYP_PAGE_OFFSET         PAGE_OFFSET
 #define KERN_TO_HYP(kva)        (kva)
 
+/*
+ * Our virtual mapping for the boot-time MMU-enable code. Must be
+ * shared across all the page-tables. Conveniently, we use the vectors
+ * page, where no kernel data will ever be shared with HYP.
+ */
+#define TRAMPOLINE_VA           UL(CONFIG_VECTORS_BASE)
+
+#ifndef __ASSEMBLY__
+
+#include <asm/cacheflush.h>
+#include <asm/pgalloc.h>
+
 int create_hyp_mappings(void *from, void *to);
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
 void free_hyp_pgds(void);
@@ -44,6 +56,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
 void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 
 phys_addr_t kvm_mmu_get_httbr(void);
+phys_addr_t kvm_mmu_get_boot_httbr(void);
+phys_addr_t kvm_get_idmap_vector(void);
 int kvm_mmu_init(void);
 void kvm_clear_hyp_idmap(void);
 
@@ -113,4 +127,8 @@ static inline void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn)
         }
 }
 
+#define kvm_flush_dcache_to_poc(a,l)    __cpuc_flush_dcache_area((a), (l))
+
+#endif  /* !__ASSEMBLY__ */
+
 #endif /* __ARM_KVM_MMU_H__ */