configure: unify case statements for CPU canonicalization

The CPU model has to be canonicalized to what Meson wants in the cross
file, to what Linux uses for its asm-$ARCH directories, and to what
QEMU uses for its user-mode emulation host/$ARCH directories.  Do
all three in a single case statement, and check that the Linux and
QEMU directories actually exist.

At a small cost in repeated lines, this ensures that there are no hidden
ordering requirements between the case statements.  In particular, commit
89e5b7935e9 ("configure: Fix linux-user host detection for riscv64",
2023-08-06) broke ppc64le because it assigned host_arch based on a
non-canonicalized version of $cpu.

Reported-by: Joel Stanley <joel@jms.id.au>
Fixes: 89e5b7935e9 ("configure: Fix linux-user host detection for riscv64", 2023-08-06)
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Acked-by: Ilya Leoshkevich <iii@linux.ibm.com>
Reviewed-by: Michael Tokarev <mjt@tls.msk.ru>
Tested-by: Ilya Leoshkevich <iii@linux.ibm.com>
Tested-by: Michael Tokarev <mjt@tls.msk.ru>
Message-ID: <20230808120303.585509-4-pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

configure

@@ -469,59 +469,119 @@ else
   echo "WARNING: unrecognized host CPU, proceeding with 'uname -m' output '$cpu'"
 fi
 
-case "$cpu" in
-  riscv*)
-    host_arch=riscv ;;
-  x32)
-    host_arch=x86_64 ;;
-  *)
-    host_arch="$cpu" ;;
-esac
-
-# Normalise host CPU name and set multilib cflags.  The canonicalization
-# isn't really necessary, because the architectures that we check for
-# should not hit the 'uname -m' case, but better safe than sorry.
+# Normalise host CPU name to the values used by Meson cross files and in source
+# directories, and set multilib cflags.  The canonicalization isn't really
+# necessary, because the architectures that we check for should not hit the
+# 'uname -m' case, but better safe than sorry in case --cpu= is used.
+#
 # Note that this case should only have supported host CPUs, not guests.
+# Please keep it sorted and synchronized with meson.build's host_arch.
+host_arch=
+linux_arch=
 case "$cpu" in
+  aarch64)
+    host_arch=aarch64
+    linux_arch=arm64
+    ;;
+
   armv*b|armv*l|arm)
-    cpu="arm" ;;
+    cpu=arm
+    host_arch=arm
+    linux_arch=arm
+    ;;
 
   i386|i486|i586|i686)
     cpu="i386"
-    CPU_CFLAGS="-m32" ;;
-  x32)
-    cpu="x86_64"
-    CPU_CFLAGS="-mx32" ;;
-  x86_64|amd64)
-    cpu="x86_64"
-    # ??? Only extremely old AMD cpus do not have cmpxchg16b.
-    # If we truly care, we should simply detect this case at
-    # runtime and generate the fallback to serial emulation.
-    CPU_CFLAGS="-m64 -mcx16" ;;
+    host_arch=i386
+    linux_arch=x86
+    CPU_CFLAGS="-m32"
+    ;;
 
+  loongarch*)
+    cpu=loongarch64
+    host_arch=loongarch64
+    ;;
+
+  mips64*)
+    cpu=mips64
+    host_arch=mips
+    linux_arch=mips
+    ;;
   mips*)
-    cpu="mips" ;;
+    cpu=mips
+    host_arch=mips
+    linux_arch=mips
+    ;;
 
   ppc)
-    CPU_CFLAGS="-m32" ;;
+    host_arch=ppc
+    linux_arch=powerpc
+    CPU_CFLAGS="-m32"
+    ;;
   ppc64)
-    CPU_CFLAGS="-m64 -mbig-endian" ;;
+    host_arch=ppc64
+    linux_arch=powerpc
+    CPU_CFLAGS="-m64 -mbig-endian"
+    ;;
   ppc64le)
-    cpu="ppc64"
-    CPU_CFLAGS="-m64 -mlittle-endian" ;;
+    cpu=ppc64
+    host_arch=ppc64
+    linux_arch=powerpc
+    CPU_CFLAGS="-m64 -mlittle-endian"
+    ;;
+
+  riscv32 | riscv64)
+    host_arch=riscv
+    linux_arch=riscv
+    ;;
 
   s390)
-    CPU_CFLAGS="-m31" ;;
+    linux_arch=s390
+    CPU_CFLAGS="-m31"
+    ;;
   s390x)
-    CPU_CFLAGS="-m64" ;;
+    host_arch=s390x
+    linux_arch=s390
+    CPU_CFLAGS="-m64"
+    ;;
 
   sparc|sun4[cdmuv])
-    cpu="sparc"
-    CPU_CFLAGS="-m32 -mv8plus -mcpu=ultrasparc" ;;
+    cpu=sparc
+    CPU_CFLAGS="-m32 -mv8plus -mcpu=ultrasparc"
+    ;;
   sparc64)
-    CPU_CFLAGS="-m64 -mcpu=ultrasparc" ;;
+    host_arch=sparc64
+    CPU_CFLAGS="-m64 -mcpu=ultrasparc"
+    ;;
+
+  x32)
+    cpu="x86_64"
+    host_arch=x86_64
+    linux_arch=x86
+    CPU_CFLAGS="-mx32"
+    ;;
+  x86_64|amd64)
+    cpu="x86_64"
+    host_arch=x86_64
+    linux_arch=x86
+    # ??? Only extremely old AMD cpus do not have cmpxchg16b.
+    # If we truly care, we should simply detect this case at
+    # runtime and generate the fallback to serial emulation.
+    CPU_CFLAGS="-m64 -mcx16"
+    ;;
 esac
 
+if test -n "$host_arch" && {
+    ! test -d "$source_path/linux-user/include/host/$host_arch" ||
+    ! test -d "$source_path/common-user/host/$host_arch"; }; then
+    error_exit "linux-user/include/host/$host_arch does not exist." \
+       "This is a bug in the configure script, please report it."
+fi
+if test -n "$linux_arch" && ! test -d "$source_path/linux-headers/asm-$linux_arch"; then
+    error_exit "linux-headers/asm-$linux_arch does not exist." \
+       "This is a bug in the configure script, please report it."
+fi
+
 check_py_version() {
     # We require python >= 3.7.
     # NB: a True python conditional creates a non-zero return code (Failure)
@@ -812,7 +872,7 @@ default_target_list=""
 mak_wilds=""
 
 if [ "$linux_user" != no ]; then
-    if [ "$targetos" = linux ] && [ -d "$source_path/linux-user/include/host/$host_arch" ]; then
+    if [ "$targetos" = linux ] && [ -n "$host_arch" ]; then
         linux_user=yes
     elif [ "$linux_user" = yes ]; then
         error_exit "linux-user not supported on this architecture"
@@ -1717,40 +1777,9 @@ echo "PKG_CONFIG=${pkg_config}" >> $config_host_mak
 echo "CC=$cc" >> $config_host_mak
 echo "EXESUF=$EXESUF" >> $config_host_mak
 
-# use included Linux headers
-if test "$linux" = "yes" ; then
-  mkdir -p linux-headers
-  case "$cpu" in
-  i386|x86_64)
-    linux_arch=x86
-    ;;
-  ppc|ppc64)
-    linux_arch=powerpc
-    ;;
-  s390x)
-    linux_arch=s390
-    ;;
-  aarch64)
-    linux_arch=arm64
-    ;;
-  loongarch*)
-    linux_arch=loongarch
-    ;;
-  mips64)
-    linux_arch=mips
-    ;;
-  riscv32|riscv64)
-    linux_arch=riscv
-    ;;
-  *)
-    # For most CPUs the kernel architecture name and QEMU CPU name match.
-    linux_arch="$cpu"
-    ;;
-  esac
-    # For non-KVM architectures we will not have asm headers
-    if [ -e "$source_path/linux-headers/asm-$linux_arch" ]; then
-      symlink "$source_path/linux-headers/asm-$linux_arch" linux-headers/asm
-    fi
+# use included Linux headers for KVM architectures
+if test "$linux" = "yes" && test -n "$linux_arch"; then
+  symlink "$source_path/linux-headers/asm-$linux_arch" linux-headers/asm
 fi
 
 for target in $target_list; do