Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20180615' into staging

target-arm and miscellaneous queue:
 * fix KVM state save/restore for GICv3 priority registers for high IRQ numbers
 * hw/arm/mps2-tz: Put ethernet controller behind PPC
 * hw/sh/sh7750: Convert away from old_mmio
 * hw/m68k/mcf5206: Convert away from old_mmio
 * hw/block/pflash_cfi02: Convert away from old_mmio
 * hw/watchdog/wdt_i6300esb: Convert away from old_mmio
 * hw/input/pckbd: Convert away from old_mmio
 * hw/char/parallel: Convert away from old_mmio
 * armv7m: refactor to get rid of armv7m_init() function
 * arm: Don't crash if user tries to use a Cortex-M CPU without an NVIC
 * hw/core/or-irq: Support more than 16 inputs to an OR gate
 * cpu-defs.h: Document CPUIOTLBEntry 'addr' field
 * cputlb: Pass cpu_transaction_failed() the correct physaddr
 * CODING_STYLE: Define our preferred form for multiline comments
 * Add and use new stn_*_p() and ldn_*_p() memory access functions
 * target/arm: More parts of the upcoming SVE support
 * aspeed_scu: Implement RNG register
 * m25p80: add support for two bytes WRSR for Macronix chips
 * exec.c: Handle IOMMUs being in the path of TCG CPU memory accesses
 * target/arm: Allow ARMv6-M Thumb2 instructions

# gpg: Signature made Fri 15 Jun 2018 15:24:03 BST
# gpg:                using RSA key 3C2525ED14360CDE
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>"
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>"
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>"
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20180615: (43 commits)
  target/arm: Allow ARMv6-M Thumb2 instructions
  exec.c: Handle IOMMUs in address_space_translate_for_iotlb()
  iommu: Add IOMMU index argument to translate method
  iommu: Add IOMMU index argument to notifier APIs
  iommu: Add IOMMU index concept to IOMMU API
  m25p80: add support for two bytes WRSR for Macronix chips
  aspeed_scu: Implement RNG register
  target/arm: Implement SVE Floating Point Arithmetic - Unpredicated Group
  target/arm: Implement SVE Integer Wide Immediate - Unpredicated Group
  target/arm: Implement FDUP/DUP
  target/arm: Implement SVE Integer Compare - Scalars Group
  target/arm: Implement SVE Predicate Count Group
  target/arm: Implement SVE Partition Break Group
  target/arm: Implement SVE Integer Compare - Immediate Group
  target/arm: Implement SVE Integer Compare - Vectors Group
  target/arm: Implement SVE Select Vectors Group
  target/arm: Implement SVE vector splice (predicated)
  target/arm: Implement SVE reverse within elements
  target/arm: Implement SVE copy to vector (predicated)
  target/arm: Implement SVE conditionally broadcast/extract element
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

Author: pm215

CODING_STYLE

@@ -124,6 +124,23 @@ We use traditional C-style /* */ comments and avoid // comments.
 Rationale: The // form is valid in C99, so this is purely a matter of
 consistency of style. The checkpatch script will warn you about this.
 
+Multiline comment blocks should have a row of stars on the left,
+and the initial /* and terminating */ both on their own lines:
+    /*
+     * like
+     * this
+     */
+This is the same format required by the Linux kernel coding style.
+
+(Some of the existing comments in the codebase use the GNU Coding
+Standards form which does not have stars on the left, or other
+variations; avoid these when writing new comments, but don't worry
+about converting to the preferred form unless you're editing that
+comment anyway.)
+
+Rationale: Consistency, and ease of visually picking out a multiline
+comment from the surrounding code.
+
 8. trace-events style
 
 8.1 0x prefix

accel/tcg/cputlb.c

@@ -632,7 +632,8 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr,
     }
 
     sz = size;
-    section = address_space_translate_for_iotlb(cpu, asidx, paddr, &xlat, &sz);
+    section = address_space_translate_for_iotlb(cpu, asidx, paddr, &xlat, &sz,
+                                                attrs, &prot);
     assert(sz >= TARGET_PAGE_SIZE);
 
     tlb_debug("vaddr=" TARGET_FMT_lx " paddr=0x" TARGET_FMT_plx
@@ -664,6 +665,18 @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr,
     env->iotlb_v[mmu_idx][vidx] = env->iotlb[mmu_idx][index];
 
     /* refill the tlb */
+    /*
+     * At this point iotlb contains a physical section number in the lower
+     * TARGET_PAGE_BITS, and either
+     *  + the ram_addr_t of the page base of the target RAM (if NOTDIRTY or ROM)
+     *  + the offset within section->mr of the page base (otherwise)
+     * We subtract the vaddr (which is page aligned and thus won't
+     * disturb the low bits) to give an offset which can be added to the
+     * (non-page-aligned) vaddr of the eventual memory access to get
+     * the MemoryRegion offset for the access. Note that the vaddr we
+     * subtract here is that of the page base, and not the same as the
+     * vaddr we add back in io_readx()/io_writex()/get_page_addr_code().
+     */
     env->iotlb[mmu_idx][index].addr = iotlb - vaddr;
     env->iotlb[mmu_idx][index].attrs = attrs;
 
@@ -765,13 +778,16 @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
                          target_ulong addr, uintptr_t retaddr, int size)
 {
     CPUState *cpu = ENV_GET_CPU(env);
-    hwaddr physaddr = iotlbentry->addr;
-    MemoryRegion *mr = iotlb_to_region(cpu, physaddr, iotlbentry->attrs);
+    hwaddr mr_offset;
+    MemoryRegionSection *section;
+    MemoryRegion *mr;
     uint64_t val;
     bool locked = false;
     MemTxResult r;
 
-    physaddr = (physaddr & TARGET_PAGE_MASK) + addr;
+    section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs);
+    mr = section->mr;
+    mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr;
     cpu->mem_io_pc = retaddr;
     if (mr != &io_mem_rom && mr != &io_mem_notdirty && !cpu->can_do_io) {
         cpu_io_recompile(cpu, retaddr);
@@ -783,9 +799,13 @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
         qemu_mutex_lock_iothread();
         locked = true;
     }
-    r = memory_region_dispatch_read(mr, physaddr,
+    r = memory_region_dispatch_read(mr, mr_offset,
                                     &val, size, iotlbentry->attrs);
     if (r != MEMTX_OK) {
+        hwaddr physaddr = mr_offset +
+            section->offset_within_address_space -
+            section->offset_within_region;
+
         cpu_transaction_failed(cpu, physaddr, addr, size, MMU_DATA_LOAD,
                                mmu_idx, iotlbentry->attrs, r, retaddr);
     }
@@ -802,12 +822,15 @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
                       uintptr_t retaddr, int size)
 {
     CPUState *cpu = ENV_GET_CPU(env);
-    hwaddr physaddr = iotlbentry->addr;
-    MemoryRegion *mr = iotlb_to_region(cpu, physaddr, iotlbentry->attrs);
+    hwaddr mr_offset;
+    MemoryRegionSection *section;
+    MemoryRegion *mr;
     bool locked = false;
     MemTxResult r;
 
-    physaddr = (physaddr & TARGET_PAGE_MASK) + addr;
+    section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs);
+    mr = section->mr;
+    mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr;
     if (mr != &io_mem_rom && mr != &io_mem_notdirty && !cpu->can_do_io) {
         cpu_io_recompile(cpu, retaddr);
     }
@@ -818,9 +841,13 @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry,
         qemu_mutex_lock_iothread();
         locked = true;
     }
-    r = memory_region_dispatch_write(mr, physaddr,
+    r = memory_region_dispatch_write(mr, mr_offset,
                                      val, size, iotlbentry->attrs);
     if (r != MEMTX_OK) {
+        hwaddr physaddr = mr_offset +
+            section->offset_within_address_space -
+            section->offset_within_region;
+
         cpu_transaction_failed(cpu, physaddr, addr, size, MMU_DATA_STORE,
                                mmu_idx, iotlbentry->attrs, r, retaddr);
     }
@@ -868,12 +895,13 @@ static bool victim_tlb_hit(CPUArchState *env, size_t mmu_idx, size_t index,
  */
 tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr)
 {
-    int mmu_idx, index, pd;
+    int mmu_idx, index;
     void *p;
     MemoryRegion *mr;
+    MemoryRegionSection *section;
     CPUState *cpu = ENV_GET_CPU(env);
     CPUIOTLBEntry *iotlbentry;
-    hwaddr physaddr;
+    hwaddr physaddr, mr_offset;
 
     index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1);
     mmu_idx = cpu_mmu_index(env, true);
@@ -884,8 +912,8 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr)
         }
     }
     iotlbentry = &env->iotlb[mmu_idx][index];
-    pd = iotlbentry->addr & ~TARGET_PAGE_MASK;
-    mr = iotlb_to_region(cpu, pd, iotlbentry->attrs);
+    section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs);
+    mr = section->mr;
     if (memory_region_is_unassigned(mr)) {
         qemu_mutex_lock_iothread();
         if (memory_region_request_mmio_ptr(mr, addr)) {
@@ -906,7 +934,10 @@ tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr)
          * and use the MemTXResult it produced). However it is the
          * simplest place we have currently available for the check.
          */
-        physaddr = (iotlbentry->addr & TARGET_PAGE_MASK) + addr;
+        mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr;
+        physaddr = mr_offset +
+            section->offset_within_address_space -
+            section->offset_within_region;
         cpu_transaction_failed(cpu, physaddr, addr, 0, MMU_INST_FETCH, mmu_idx,
                                iotlbentry->attrs, MEMTX_DECODE_ERROR, 0);
 

docs/devel/loads-stores.rst

@@ -53,9 +53,24 @@ The ``_{endian}`` infix is omitted for target-endian accesses.
 The target endian accessors are only available to source
 files which are built per-target.
 
+There are also functions which take the size as an argument:
+
+load: ``ldn{endian}_p(ptr, sz)``
+
+which performs an unsigned load of ``sz`` bytes from ``ptr``
+as an ``{endian}`` order value and returns it in a uint64_t.
+
+store: ``stn{endian}_p(ptr, sz, val)``
+
+which stores ``val`` to ``ptr`` as an ``{endian}`` order value
+of size ``sz`` bytes.
+
+
 Regexes for git grep
  - ``\<ldf\?[us]\?[bwlq]\(_[hbl]e\)\?_p\>``
  - ``\<stf\?[bwlq]\(_[hbl]e\)\?_p\>``
+ - ``\<ldn_\([hbl]e\)?_p\>``
+ - ``\<stn_\([hbl]e\)?_p\>``
 
 ``cpu_{ld,st}_*``
 ~~~~~~~~~~~~~~~~~