#include "exec/hwaddr.h"
#endif
#include "exec/memattrs.h"
+#include "qom/cpu.h"
+
+#include "cpu-param.h"
#ifndef TARGET_LONG_BITS
-#error TARGET_LONG_BITS must be defined before including this header
+# error TARGET_LONG_BITS must be defined in cpu-param.h
+#endif
+#ifndef NB_MMU_MODES
+# error NB_MMU_MODES must be defined in cpu-param.h
+#endif
+#ifndef TARGET_PHYS_ADDR_SPACE_BITS
+# error TARGET_PHYS_ADDR_SPACE_BITS must be defined in cpu-param.h
+#endif
+#ifndef TARGET_VIRT_ADDR_SPACE_BITS
+# error TARGET_VIRT_ADDR_SPACE_BITS must be defined in cpu-param.h
+#endif
+#ifndef TARGET_PAGE_BITS
+# ifdef TARGET_PAGE_BITS_VARY
+# ifndef TARGET_PAGE_BITS_MIN
+# error TARGET_PAGE_BITS_MIN must be defined in cpu-param.h
+# endif
+# else
+# error TARGET_PAGE_BITS must be defined in cpu-param.h
+# endif
#endif
#define TARGET_LONG_SIZE (TARGET_LONG_BITS / 8)
#endif
#if !defined(CONFIG_USER_ONLY) && defined(CONFIG_TCG)
+
/* use a fully associative victim tlb of 8 entries */
#define CPU_VTLB_SIZE 8
#define CPU_TLB_ENTRY_BITS 5
#endif
-/* TCG_TARGET_TLB_DISPLACEMENT_BITS is used in CPU_TLB_BITS to ensure that
- * the TLB is not unnecessarily small, but still small enough for the
- * TLB lookup instruction sequence used by the TCG target.
- *
- * TCG will have to generate an operand as large as the distance between
- * env and the tlb_table[NB_MMU_MODES - 1][0].addend. For simplicity,
- * the TCG targets just round everything up to the next power of two, and
- * count bits. This works because: 1) the size of each TLB is a largish
- * power of two, 2) and because the limit of the displacement is really close
- * to a power of two, 3) the offset of tlb_table[0][0] inside env is smaller
- * than the size of a TLB.
- *
- * For example, the maximum displacement 0xFFF0 on PPC and MIPS, but TCG
- * just says "the displacement is 16 bits". TCG_TARGET_TLB_DISPLACEMENT_BITS
- * then ensures that tlb_table at least 0x8000 bytes large ("not unnecessarily
- * small": 2^15). The operand then will come up smaller than 0xFFF0 without
- * any particular care, because the TLB for a single MMU mode is larger than
- * 0x10000-0xFFF0=16 bytes. In the end, the maximum value of the operand
- * could be something like 0xC000 (the offset of the last TLB table) plus
- * 0x18 (the offset of the addend field in each TLB entry) plus the offset
- * of tlb_table inside env (which is non-trivial but not huge).
- */
-#define CPU_TLB_BITS \
- MIN(8, \
- TCG_TARGET_TLB_DISPLACEMENT_BITS - CPU_TLB_ENTRY_BITS - \
- (NB_MMU_MODES <= 1 ? 0 : \
- NB_MMU_MODES <= 2 ? 1 : \
- NB_MMU_MODES <= 4 ? 2 : \
- NB_MMU_MODES <= 8 ? 3 : 4))
+#define CPU_TLB_DYN_MIN_BITS 6
+#define CPU_TLB_DYN_DEFAULT_BITS 8
-#define CPU_TLB_SIZE (1 << CPU_TLB_BITS)
+# if HOST_LONG_BITS == 32
+/* Make sure we do not require a double-word shift for the TLB load */
+# define CPU_TLB_DYN_MAX_BITS (32 - TARGET_PAGE_BITS)
+# else /* HOST_LONG_BITS == 64 */
+/*
+ * Assuming TARGET_PAGE_BITS==12, with 2**22 entries we can cover 2**(22+12) ==
+ * 2**34 == 16G of address space. This is roughly what one would expect a
+ * TLB to cover in a modern (as of 2018) x86_64 CPU. For instance, Intel
+ * Skylake's Level-2 STLB has 16 1G entries.
+ * Also, make sure we do not size the TLB past the guest's address space.
+ */
+# define CPU_TLB_DYN_MAX_BITS \
+ MIN(22, TARGET_VIRT_ADDR_SPACE_BITS - TARGET_PAGE_BITS)
+# endif
typedef struct CPUTLBEntry {
/* bit TARGET_LONG_BITS to TARGET_PAGE_BITS : virtual address
MemTxAttrs attrs;
} CPUIOTLBEntry;
-#define CPU_COMMON_TLB \
- /* The meaning of the MMU modes is defined in the target code. */ \
- /* tlb_lock serializes updates to tlb_table and tlb_v_table */ \
- QemuSpin tlb_lock; \
- CPUTLBEntry tlb_table[NB_MMU_MODES][CPU_TLB_SIZE]; \
- CPUTLBEntry tlb_v_table[NB_MMU_MODES][CPU_VTLB_SIZE]; \
- CPUIOTLBEntry iotlb[NB_MMU_MODES][CPU_TLB_SIZE]; \
- CPUIOTLBEntry iotlb_v[NB_MMU_MODES][CPU_VTLB_SIZE]; \
- size_t tlb_flush_count; \
- target_ulong tlb_flush_addr; \
- target_ulong tlb_flush_mask; \
- target_ulong vtlb_index; \
+/*
+ * Data elements that are per MMU mode, minus the bits accessed by
+ * the TCG fast path.
+ */
+typedef struct CPUTLBDesc {
+ /*
+ * Describe a region covering all of the large pages allocated
+ * into the tlb. When any page within this region is flushed,
+ * we must flush the entire tlb. The region is matched if
+ * (addr & large_page_mask) == large_page_addr.
+ */
+ target_ulong large_page_addr;
+ target_ulong large_page_mask;
+ /* host time (in ns) at the beginning of the time window */
+ int64_t window_begin_ns;
+ /* maximum number of entries observed in the window */
+ size_t window_max_entries;
+ size_t n_used_entries;
+ /* The next index to use in the tlb victim table. */
+ size_t vindex;
+ /* The tlb victim table, in two parts. */
+ CPUTLBEntry vtable[CPU_VTLB_SIZE];
+ CPUIOTLBEntry viotlb[CPU_VTLB_SIZE];
+ /* The iotlb. */
+ CPUIOTLBEntry *iotlb;
+} CPUTLBDesc;
+
+/*
+ * Data elements that are per MMU mode, accessed by the fast path.
+ * The structure is aligned to aid loading the pair with one insn.
+ */
+typedef struct CPUTLBDescFast {
+ /* Contains (n_entries - 1) << CPU_TLB_ENTRY_BITS */
+ uintptr_t mask;
+ /* The array of tlb entries itself. */
+ CPUTLBEntry *table;
+} CPUTLBDescFast QEMU_ALIGNED(2 * sizeof(void *));
+
+/*
+ * Data elements that are shared between all MMU modes.
+ */
+typedef struct CPUTLBCommon {
+ /* Serialize updates to f.table and d.vtable, and others as noted. */
+ QemuSpin lock;
+ /*
+ * Within dirty, for each bit N, modifications have been made to
+ * mmu_idx N since the last time that mmu_idx was flushed.
+ * Protected by tlb_c.lock.
+ */
+ uint16_t dirty;
+ /*
+ * Statistics. These are not lock protected, but are read and
+ * written atomically. This allows the monitor to print a snapshot
+ * of the stats without interfering with the cpu.
+ */
+ size_t full_flush_count;
+ size_t part_flush_count;
+ size_t elide_flush_count;
+} CPUTLBCommon;
+
+/*
+ * The entire softmmu tlb, for all MMU modes.
+ * The meaning of each of the MMU modes is defined in the target code.
+ * Since this is placed within CPUNegativeOffsetState, the smallest
+ * negative offsets are at the end of the struct.
+ */
+typedef struct CPUTLB {
+ CPUTLBCommon c;
+ CPUTLBDesc d[NB_MMU_MODES];
+ CPUTLBDescFast f[NB_MMU_MODES];
+} CPUTLB;
+
+/* This will be used by TCG backends to compute offsets. */
+#define TLB_MASK_TABLE_OFS(IDX) \
+ ((int)offsetof(ArchCPU, neg.tlb.f[IDX]) - (int)offsetof(ArchCPU, env))
#else
-#define CPU_COMMON_TLB
+typedef struct CPUTLB { } CPUTLB;
-#endif
+#endif /* !CONFIG_USER_ONLY && CONFIG_TCG */
+#define CPU_COMMON /* Nothing */
-#define CPU_COMMON \
- /* soft mmu support */ \
- CPU_COMMON_TLB \
+/*
+ * This structure must be placed in ArchCPU immedately
+ * before CPUArchState, as a field named "neg".
+ */
+typedef struct CPUNegativeOffsetState {
+ CPUTLB tlb;
+ IcountDecr icount_decr;
+} CPUNegativeOffsetState;
#endif