diff --git a/NEWS b/NEWS index 4abd873de..c9a975219 100644 --- a/NEWS +++ b/NEWS @@ -59,6 +59,7 @@ New in 2.02: * Command for inspecting coreboot tables (`lscoreboot'). * New target default_payload.elf. * Increased maximal core size. + * Prefer pmtimer for TSC calibration. * New/improved platform support: * New `efifwsetup' and `lsefi' commands on EFI platforms. @@ -88,6 +89,13 @@ New in 2.02: * Support *-emu on Windows. * New platform `none' which builds only user level utilities. This is now default if target CPU is not supported. + * Support for booting little-endian Linux kernel on powerpc. + * Support network boot with Oracle sun4v vnet devices. + * Added SAS disks to the IEEE 1275 Open Firmware device list. + * Try multiple methods for TSC (timestamp counter) calibration - PIT, pmtimer, + EFI Stall. If everything fails, use hardcoded frequency 800MHz. + * Support Hyper-V Gen2 platforms which lack PIT for TSC calibration. + * Map UEFI Persistent Memory to E820 persistent memory. * Security: * Add optional facility to enforce that all files read by the core image @@ -150,6 +158,8 @@ New in 2.02: directly. This removes requirement for target-specific runtime on build system. * emu libusb support removed (was broken and unmaintained). + * powerpc64le compile support. + * Use fixed timestamp when generating GRUB image for reproducible builds. * Revision control moved to git. diff --git a/README b/README index b30a4b68b..685b01657 100644 --- a/README +++ b/README @@ -12,8 +12,6 @@ The URL is . More extensive documentation is available in the Info manual, accessible using 'info grub' after building and installing GRUB 2. -Please look at the GRUB Wiki for testing -procedures. There are a number of important user-visible differences from the first version of GRUB, now known as GRUB Legacy. For a summary, please diff --git a/asm-tests/i386-pc.S b/asm-tests/i386-pc.S index 97cd32ae8..f6f9a88be 100644 --- a/asm-tests/i386-pc.S +++ b/asm-tests/i386-pc.S @@ -5,6 +5,10 @@ .code16 jmp far .org 4 - .space 300 + jmp nearer + .org 6 + .space 100 +nearer: + .space 200 far: .byte 0 diff --git a/asm-tests/mips.S b/asm-tests/mips.S index 8233dfcc9..1312d47d5 100644 --- a/asm-tests/mips.S +++ b/asm-tests/mips.S @@ -4,8 +4,8 @@ .set mips3 sync - ld $t2, 0($t6) + ld $t2, 0($t1) a: - addiu $t7, $s0, (b - a) + addiu $t1, $s0, (b - a) b: nop diff --git a/autogen.sh b/autogen.sh index 5020456bc..7537561ad 100755 --- a/autogen.sh +++ b/autogen.sh @@ -23,14 +23,14 @@ fi if [ -d grub-core/lib/libgcrypt-grub/mpi/generic ]; then rm -rf grub-core/lib/libgcrypt-grub/mpi/generic fi -ln -s ../../../grub-core/lib/libgcrypt-grub/src/g10lib.h include/grub/gcrypt/g10lib.h +cp grub-core/lib/libgcrypt-grub/src/g10lib.h include/grub/gcrypt/g10lib.h cp -R grub-core/lib/libgcrypt/mpi/generic grub-core/lib/libgcrypt-grub/mpi/generic for x in mpi-asm-defs.h mpih-add1.c mpih-sub1.c mpih-mul1.c mpih-mul2.c mpih-mul3.c mpih-lshift.c mpih-rshift.c; do if [ -h grub-core/lib/libgcrypt-grub/mpi/"$x" ] || [ -f grub-core/lib/libgcrypt-grub/mpi/"$x" ]; then rm grub-core/lib/libgcrypt-grub/mpi/"$x" fi - ln -s generic/"$x" grub-core/lib/libgcrypt-grub/mpi/"$x" + cp grub-core/lib/libgcrypt-grub/mpi/generic/"$x" grub-core/lib/libgcrypt-grub/mpi/"$x" done echo "Generating Automake input..." diff --git a/conf/Makefile.common b/conf/Makefile.common index fcb8d2e1c..5083d5f1e 100644 --- a/conf/Makefile.common +++ b/conf/Makefile.common @@ -21,9 +21,6 @@ if COND_powerpc_ieee1275 CFLAGS_PLATFORM += -mcpu=powerpc endif -#FIXME: discover and check XEN headers -CPPFLAGS_XEN = -I/usr/include - # Other options CPPFLAGS_DEFAULT = -DGRUB_FILE=\"$(subst $(srcdir)/,,$<)\" diff --git a/conf/Makefile.extra-dist b/conf/Makefile.extra-dist index ea6b9df3a..9dd64fdca 100644 --- a/conf/Makefile.extra-dist +++ b/conf/Makefile.extra-dist @@ -37,7 +37,6 @@ EXTRA_DIST += grub-core/lib/libgcrypt EXTRA_DIST += grub-core/lib/libgcrypt-grub/mpi/generic EXTRA_DIST += $(shell find $(top_srcdir)/include -name '*.h') EXTRA_DIST += $(shell find $(top_srcdir)/grub-core/lib -name '*.h') -EXTRA_DIST += $(shell find $(top_srcdir)/grub-core/gnulib -name '*.h') EXTRA_DIST += grub-core/efiemu/runtime/config.h EXTRA_DIST += grub-core/lib/LzmaDec.c diff --git a/configure.ac b/configure.ac index c864311f7..3300545e0 100644 --- a/configure.ac +++ b/configure.ac @@ -315,7 +315,7 @@ AC_PROG_LN_S if test "x$LEX" = "x:"; then AC_MSG_ERROR([flex is not found]) else - version=`$LEX --version | $AWK '{ split($NF,x,"."); print x[[1]]*10000+x[[2]]*100+x[[3]]; }'` + version=`$LEX --version | $AWK '{ split($2,x,"."); print x[[1]]*10000+x[[2]]*100+x[[3]]; }'` if test -n "$version" -a "$version" -ge 20535; then : else @@ -562,12 +562,12 @@ AC_COMPILE_IFELSE( ]])], [grub_cv_cc_target_clang=no], [grub_cv_cc_target_clang=yes])]) -if test x$target_cpu = xpowerpc; then +if test x$target_cpu = xpowerpc -o x$target_cpu = xmips; then AC_CACHE_CHECK([for options to get big-endian compilation], grub_cv_target_cc_big_endian, [ grub_cv_target_cc_big_endian=no - for cand in "-target powerpc -Wl,-EB" "-target powerpc" \ - "-target powerpc-linux-gnu -Wl,-EB" "-target powerpc-linux-gnu" \ - "-mbig-endian"; do + for cand in "-target $target_cpu -Wl,-EB" "-target $target_cpu" \ + "-target $target_cpu-linux-gnu -Wl,-EB" "-target $target_cpu-linux-gnu" \ + "-EB" "-mbig-endian"; do if test x"$grub_cv_target_cc_big_endian" != xno ; then break fi @@ -577,6 +577,8 @@ if test x$target_cpu = xpowerpc; then #error still little endian #endif asm (".globl start; start:"); +asm (".globl _start; _start:"); +asm (".globl __start; __start:"); void __main (void); void __main (void) {} int main (void); @@ -595,6 +597,75 @@ int main (void); TARGET_CPPFLAGS="$TARGET_CPPFLAGS $skip_linkflags" TARGET_CCASFLAGS="$TARGET_CCASFLAGS $skip_linkflags" TARGET_LDFLAGS="$TARGET_LDFLAGS $grub_cv_target_cc_big_endian" +elif test x$target_cpu = xmipsel; then + AC_CACHE_CHECK([for options to get little-endian compilation], grub_cv_target_cc_little_endian, [ + grub_cv_target_cc_little_endian=no + for cand in "-target $target_cpu -Wl,-EL" "-target $target_cpu" \ + "-target $target_cpu-linux-gnu -Wl,-EL" "-target $target_cpu-linux-gnu" \ + "-EL"; do + if test x"$grub_cv_target_cc_little_endian" != xno ; then + break + fi + CFLAGS="$TARGET_CFLAGS $cand -Werror" + AC_LINK_IFELSE([AC_LANG_PROGRAM([[ +#if defined(__BYTE_ORDER__) && defined(__ORDER_BIG_ENDIAN__) && (__ORDER_BIG_ENDIAN__ == __BYTE_ORDER__) +#error still big endian +#endif +asm (".globl start; start:"); +asm (".globl _start; _start:"); +asm (".globl __start; __start:"); +void __main (void); +void __main (void) {} +int main (void); +]], [[]])], + [grub_cv_target_cc_little_endian="$cand"], []) + done + ]) + + if test x"$grub_cv_target_cc_little_endian" = xno ; then + AC_MSG_ERROR([could not force little-endian]) + fi + + skip_linkflags="$(echo "$grub_cv_target_cc_little_endian"|sed 's@-Wl,-EL@@')" + + TARGET_CFLAGS="$TARGET_CFLAGS $skip_linkflags" + TARGET_CPPFLAGS="$TARGET_CPPFLAGS $skip_linkflags" + TARGET_CCASFLAGS="$TARGET_CCASFLAGS $skip_linkflags" + TARGET_LDFLAGS="$TARGET_LDFLAGS $grub_cv_target_cc_little_endian" +fi + +# GRUB code is N32-compliant but it's experimental and we would prefer to +# avoid having too much variety when it doesn't result in any real improvement. +# Moreover N64 isn't supported. +if test "x$target_cpu" = xmips || test "x$target_cpu" = xmipsel ; then + AC_CACHE_CHECK([for options to force MIPS o32 ABI], grub_cv_target_cc_mips_o32_abi, [ + grub_cv_target_cc_mips_o32_abi=no + for arg in "" "-mabi=32" "-target $target_cpu -mabi=32" ; do + if test x"$grub_cv_target_cc_mips_o32_abi" != xno ; then + break + fi + CFLAGS="$TARGET_CFLAGS $arg -Werror" + AC_LINK_IFELSE([AC_LANG_PROGRAM([[ +#if !defined(_ABIO32) || !defined(_MIPS_SIM) || (_MIPS_SIM != _ABIO32) +#error not o32 ABI +#endif +asm (".globl start; start:"); +asm (".globl _start; _start:"); +asm (".globl __start; __start:"); +void __main (void); +void __main (void) {} +int main (void); +]], [[]])], + [grub_cv_target_cc_mips_o32_abi="$arg"], []) + done + ]) + + if test x"$grub_cv_target_cc_mips_o32_abi" = xno ; then + AC_MSG_ERROR([could not force MIPS o32 ABI]) + fi + + TARGET_CFLAGS="$TARGET_CFLAGS $grub_cv_target_cc_mips_o32_abi" + TARGET_CCASFLAGS="$TARGET_CCASFLAGS $grub_cv_target_cc_mips_o32_abi" fi AC_CACHE_CHECK([for options to compile assembly], [grub_cv_cc_target_asm_compile], [ @@ -712,7 +783,7 @@ fi if ( test "x$target_cpu" = xi386 || test "x$target_cpu" = xx86_64 ) && test "x$platform" != xemu; then # Some toolchains enable these features by default, but they need # registers that aren't set up properly in GRUB. - TARGET_CFLAGS="$TARGET_CFLAGS -mno-mmx -mno-sse -mno-sse2 -mno-3dnow" + TARGET_CFLAGS="$TARGET_CFLAGS -mno-mmx -mno-sse -mno-sse2 -mno-sse3 -mno-3dnow" fi # GRUB doesn't use float or doubles at all. Yet some toolchains may decide diff --git a/docs/grub.texi b/docs/grub.texi index b9f41a73e..9a25a0bdb 100644 --- a/docs/grub.texi +++ b/docs/grub.texi @@ -3038,6 +3038,8 @@ These variables have special meaning to GRUB. * cmdpath:: * color_highlight:: * color_normal:: +* config_directory:: +* config_file:: * debug:: * default:: * fallback:: @@ -3180,6 +3182,22 @@ matching colors of first half. to support whole rgb24 palette but currently there is no compelling reason to go beyond the current 16 colors. + +@node config_directory +@subsection config_directory + +This variable is automatically set by GRUB to the directory part of +current configuration file name (@pxref{config_file}). + + +@node config_file +@subsection config_file + +This variable is automatically set by GRUB to the name of configuration file that is being +processed by commands @command{configfile} (@pxref{configfile}) or @command{normal} +(@pxref{normal}). It is restored to the previous value when command completes. + + @node debug @subsection debug @@ -3839,6 +3857,11 @@ you forget a command, you can run the command @command{help} @comment * vbeinfo:: List available video modes * verify_detached:: Verify detached digital signature * videoinfo:: List available video modes +@comment * xen_*:: Xen boot commands +* xen_hypervisor:: Load xen hypervisor binary +* xen_linux:: Load dom0 kernel for xen hypervisor +* xen_initrd:: Load dom0 initrd for dom0 kernel +* xen_xsm:: Load xen security module for xen hypervisor @end menu @@ -5102,6 +5125,39 @@ successfully. If validation fails, it is set to a non-zero value. List available video modes. If resolution is given, show only matching modes. @end deffn +@node xen_hypervisor +@subsection xen_hypervisor + +@deffn Command xen_hypervisor file [arguments] @dots{} +Load a Xen hypervisor binary from @var{file}. The rest of the line is passed +verbatim as the @dfn{kernel command-line}. Any other binaries must be +reloaded after using this command. +@end deffn + +@node xen_linux +@subsection xen_linux + +@deffn Command xen_linux file [arguments] +Load a dom0 kernel image for xen hypervisor at the booting process of xen. +The rest of the line is passed verbatim as the module command line. +@end deffn + +@node xen_initrd +@subsection xen_initrd + +@deffn Command xen_initrd file +Load a initrd image for dom0 kernel at the booting process of xen. +@end deffn + +@node xen_xsm +@subsection xen_xsm + +@deffn Command xen_xsm file +Load a xen security module for xen hypervisor at the booting process of xen. +See @uref{http://wiki.xen.org/wiki/XSM} for more detail. +@end deffn + + @node Networking commands @section The list of networking commands @@ -5613,6 +5669,16 @@ BadRAM is the ability to mark some of the RAM as ``bad''. Note: due to protocol limitations mips-loongson (with Linux protocol) and mips-qemu_mips can use only memory up to first hole. +Bootlocation is ability of GRUB to automatically detect where it boots from. +``disk'' means the detection is limited to detecting the disk with partition +being discovered on install time. ``partition'' means that disk and partiton +can be automatically discovered. ``file'' means that boot image file name as +well as disk and partition can be discovered. For consistency default install ignores +partition and relies solely on disk detection. If no bootlocation discovery is available +or boot and grub-root disks are different, UUID is used instead. On ARC if no device +to install to is specified, UUID is used instead as well. + + @multitable @columnfractions .20 .20 .20 .20 .20 @item @tab BIOS @tab Coreboot @tab Multiboot @tab Qemu @item video @tab yes @tab yes @tab yes @tab yes @@ -5629,6 +5695,7 @@ and mips-qemu_mips can use only memory up to first hole. @item badram @tab yes @tab yes @tab yes @tab yes @item compression @tab always @tab pointless @tab no @tab no @item exit @tab yes @tab no @tab no @tab no +@item bootlocation @tab disk @tab no @tab no @tab no @end multitable @multitable @columnfractions .20 .20 .20 .20 .20 @@ -5647,6 +5714,7 @@ and mips-qemu_mips can use only memory up to first hole. @item badram @tab yes @tab yes @tab no @tab yes @item compression @tab no @tab no @tab no @tab no @item exit @tab yes @tab yes @tab yes @tab yes +@item bootlocation @tab file @tab file @tab file, ignored @tab file @end multitable @multitable @columnfractions .20 .20 .20 .20 .20 @@ -5665,24 +5733,26 @@ and mips-qemu_mips can use only memory up to first hole. @item badram @tab yes (*) @tab no @tab no @tab no @item compression @tab configurable @tab no @tab no @tab configurable @item exit @tab no @tab yes @tab yes @tab yes +@item bootlocation @tab no @tab partition @tab file @tab file (*) @end multitable @multitable @columnfractions .20 .20 .20 .20 .20 -@item @tab MIPS qemu @tab emu -@item video @tab no @tab yes -@item console charset @tab CP437 @tab Unicode (*) -@item network @tab no @tab yes -@item ATA/AHCI @tab yes @tab no -@item AT keyboard @tab yes @tab no -@item Speaker @tab no @tab no -@item USB @tab N/A @tab yes -@item chainloader @tab yes @tab no -@item cpuid @tab no @tab no -@item hints @tab guess @tab no -@item PCI @tab no @tab no -@item badram @tab yes (*) @tab no -@item compression @tab configurable @tab no -@item exit @tab no @tab yes +@item @tab MIPS qemu @tab emu @tab xen +@item video @tab no @tab yes @tab no +@item console charset @tab CP437 @tab Unicode (*) @tab ASCII +@item network @tab no @tab yes @tab no +@item ATA/AHCI @tab yes @tab no @tab no +@item AT keyboard @tab yes @tab no @tab no +@item Speaker @tab no @tab no @tab no +@item USB @tab N/A @tab yes @tab no +@item chainloader @tab yes @tab no @tab yes +@item cpuid @tab no @tab no @tab yes +@item hints @tab guess @tab no @tab no +@item PCI @tab no @tab no @tab no +@item badram @tab yes (*) @tab no @tab no +@item compression @tab configurable @tab no @tab no +@item exit @tab no @tab yes @tab no +@item bootlocation @tab no @tab file @tab no @end multitable @node Platform-specific operations diff --git a/grub-core/Makefile.am b/grub-core/Makefile.am index af0c7f47c..c671aed4b 100644 --- a/grub-core/Makefile.am +++ b/grub-core/Makefile.am @@ -101,6 +101,7 @@ if COND_i386_efi KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/efi/efi.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/efi/disk.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/i386/tsc.h +KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/acpi.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/pci.h endif @@ -112,10 +113,12 @@ KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/video_fb.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/gfxterm.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/font.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/bufio.h +KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/acpi.h endif if COND_i386_multiboot KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/i386/tsc.h +KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/acpi.h endif if COND_i386_qemu @@ -154,11 +157,13 @@ KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/efi/efi.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/efi/disk.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/i386/tsc.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/pci.h +KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/acpi.h endif if COND_ia64_efi KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/efi/efi.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/efi/disk.h +KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/acpi.h endif if COND_mips @@ -233,11 +238,13 @@ KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/arm/efi/loader.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/efi/efi.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/efi/disk.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/arm/system.h +KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/acpi.h endif if COND_arm64_efi KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/efi/efi.h KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/efi/disk.h +KERNEL_HEADER_FILES += $(top_srcdir)/include/grub/acpi.h endif if COND_emu diff --git a/grub-core/Makefile.core.def b/grub-core/Makefile.core.def index 3824f0fa2..8dcae96d9 100644 --- a/grub-core/Makefile.core.def +++ b/grub-core/Makefile.core.def @@ -59,9 +59,6 @@ kernel = { ia64_efi_ldflags = '-Wl,-r,-d'; ia64_efi_stripflags = '--strip-unneeded -K start -R .note -R .comment -R .note.gnu.gold-version'; - x86_64_xen_cppflags = '$(CPPFLAGS_XEN)'; - i386_xen_cppflags = '$(CPPFLAGS_XEN)'; - arm_efi_ldflags = '-Wl,-r,-d'; arm_efi_stripflags = '--strip-unneeded -K start -R .note -R .comment -R .note.gnu.gold-version'; @@ -174,8 +171,20 @@ kernel = { efi = kern/efi/init.c; efi = kern/efi/mm.c; efi = term/efi/console.c; + efi = kern/acpi.c; + efi = kern/efi/acpi.c; + i386_coreboot = kern/i386/pc/acpi.c; + i386_multiboot = kern/i386/pc/acpi.c; + i386_coreboot = kern/acpi.c; + i386_multiboot = kern/acpi.c; x86 = kern/i386/tsc.c; + x86 = kern/i386/tsc_pit.c; + i386_efi = kern/i386/efi/tsc.c; + x86_64_efi = kern/i386/efi/tsc.c; + i386_efi = kern/i386/tsc_pmtimer.c; + i386_coreboot = kern/i386/tsc_pmtimer.c; + x86_64_efi = kern/i386/tsc_pmtimer.c; i386_efi = kern/i386/efi/init.c; i386_efi = bus/pci.c; @@ -187,6 +196,7 @@ kernel = { x86_64_efi = bus/pci.c; xen = kern/i386/tsc.c; + xen = kern/i386/xen/tsc.c; x86_64_xen = kern/x86_64/xen/hypercall.S; i386_xen = kern/i386/xen/hypercall.S; xen = kern/xen/init.c; @@ -604,7 +614,6 @@ module = { module = { name = lsxen; common = commands/xen/lsxen.c; - cppflags = '$(CPPFLAGS_XEN)'; enable = xen; }; @@ -669,10 +678,8 @@ module = { name = acpi; common = commands/acpi.c; - efi = commands/efi/acpi.c; - i386_pc = commands/i386/pc/acpi.c; - i386_coreboot = commands/i386/pc/acpi.c; - i386_multiboot = commands/i386/pc/acpi.c; + i386_pc = kern/acpi.c; + i386_pc = kern/i386/pc/acpi.c; enable = efi; enable = i386_pc; @@ -847,7 +854,6 @@ module = { i386_coreboot = lib/i386/halt.c; i386_qemu = lib/i386/halt.c; xen = lib/xen/halt.c; - xen_cppflags = '$(CPPFLAGS_XEN)'; efi = lib/efi/halt.c; ieee1275 = lib/ieee1275/halt.c; emu = lib/emu/halt.c; @@ -868,7 +874,6 @@ module = { mips_loongson = lib/mips/loongson/reboot.c; mips_qemu_mips = lib/mips/qemu_mips/reboot.c; xen = lib/xen/reboot.c; - xen_cppflags = '$(CPPFLAGS_XEN)'; uboot = lib/uboot/reboot.c; common = commands/reboot.c; }; @@ -1485,7 +1490,6 @@ module = { module = { name = gfxmenu; common = gfxmenu/gfxmenu.c; - common = gfxmenu/model.c; common = gfxmenu/view.c; common = gfxmenu/font.c; common = gfxmenu/icon_manager.c; @@ -1564,7 +1568,6 @@ module = { i386_xen = lib/i386/xen/relocator.S; x86_64_xen = lib/x86_64/xen/relocator.S; xen = lib/i386/relocator_common_c.c; - xen_cppflags = '$(CPPFLAGS_XEN)'; extra_dist = lib/i386/relocator_common.S; extra_dist = kern/powerpc/cache_flush.S; @@ -1585,7 +1588,6 @@ module = { sparc64_ieee1275 = lib/ieee1275/cmos.c; powerpc_ieee1275 = lib/ieee1275/cmos.c; xen = lib/xen/datetime.c; - xen_cppflags = '$(CPPFLAGS_XEN)'; mips_arc = lib/arc/datetime.c; enable = noemu; @@ -1684,11 +1686,17 @@ module = { enable = x86; }; +module = { + name = xen_boot; + common = lib/cmdline.c; + arm64 = loader/arm64/xen_boot.c; + enable = arm64; +}; + module = { name = linux; x86 = loader/i386/linux.c; xen = loader/i386/xen.c; - xen_cppflags = '$(CPPFLAGS_XEN)'; i386_pc = lib/i386/pc/vesa_modes_table.c; mips = loader/mips/linux.c; powerpc_ieee1275 = loader/powerpc/ieee1275/linux.c; @@ -1696,12 +1704,18 @@ module = { ia64_efi = loader/ia64/efi/linux.c; arm = loader/arm/linux.c; arm64 = loader/arm64/linux.c; - fdt = lib/fdt.c; common = loader/linux.c; common = lib/cmdline.c; enable = noemu; }; +module = { + name = fdt; + arm64 = loader/arm64/fdt.c; + common = lib/fdt.c; + enable = fdt; +}; + module = { name = xnu; x86 = loader/xnu_resume.c; diff --git a/grub-core/boot/mips/startup_raw.S b/grub-core/boot/mips/startup_raw.S index ca3413bbe..6a81b3733 100644 --- a/grub-core/boot/mips/startup_raw.S +++ b/grub-core/boot/mips/startup_raw.S @@ -22,6 +22,7 @@ #include #include #include +#include #define BASE_ADDR 8 @@ -118,32 +119,32 @@ parsestr: move $v0, $zero move $t3, $t1 3: - lb $t4, 0($t2) - lb $t5, 0($t3) + lb GRUB_ASM_T4, 0($t2) + lb GRUB_ASM_T5, 0($t3) addiu $t2, $t2, 1 addiu $t3, $t3, 1 - beq $t5, $zero, 1f + beq GRUB_ASM_T5, $zero, 1f nop - beq $t5, $t4, 3b + beq GRUB_ASM_T5, GRUB_ASM_T4, 3b nop - bne $t4, $zero, 1f + bne GRUB_ASM_T4, $zero, 1f nop addiu $t3, $t3, 0xffff digcont: - lb $t5, 0($t3) + lb GRUB_ASM_T5, 0($t3) /* Substract '0' from digit. */ - addiu $t5, $t5, 0xffd0 - bltz $t5, 1f + addiu GRUB_ASM_T5, GRUB_ASM_T5, 0xffd0 + bltz GRUB_ASM_T5, 1f nop - addiu $t4, $t5, 0xfff7 - bgtz $t4, 1f + addiu GRUB_ASM_T4, GRUB_ASM_T5, 0xfff7 + bgtz GRUB_ASM_T4, 1f nop /* Multiply $v0 by 10 with bitshifts. */ sll $v0, $v0, 1 - sll $t4, $v0, 2 - addu $v0, $v0, $t4 - addu $v0, $v0, $t5 + sll GRUB_ASM_T4, $v0, 2 + addu $v0, $v0, GRUB_ASM_T4 + addu $v0, $v0, GRUB_ASM_T5 addiu $t3, $t3, 1 b digcont nop @@ -182,10 +183,10 @@ argdone: b argdone addiu $a1, $a1, 4 do_check: - lb $t4, 0($t7) - beq $t4, $zero, 1f + lb GRUB_ASM_T4, 0($t7) + beq GRUB_ASM_T4, $zero, 1f lb $t3, 0($t6) - bne $t3, $t4, 2f + bne $t3, GRUB_ASM_T4, 2f addiu $t6, $t6, 1 b do_check addiu $t7, $t7, 1 @@ -222,8 +223,8 @@ cmdlinedone: 1: beq $t1, $t3, 2f - lb $t4, 0($t2) - sb $t4, 0($t1) + lb GRUB_ASM_T4, 0($t2) + sb GRUB_ASM_T4, 0($t1) addiu $t1, $t1, 1 b 1b addiu $t2, $t2, 1 diff --git a/grub-core/commands/acpi.c b/grub-core/commands/acpi.c index c3861f594..ece49b4a9 100644 --- a/grub-core/commands/acpi.c +++ b/grub-core/commands/acpi.c @@ -61,18 +61,6 @@ static const struct grub_arg_option options[] = { {0, 0, 0, 0, 0, 0} }; -/* Simple checksum by summing all bytes. Used by ACPI and SMBIOS. */ -grub_uint8_t -grub_byte_checksum (void *base, grub_size_t size) -{ - grub_uint8_t *ptr; - grub_uint8_t ret = 0; - for (ptr = (grub_uint8_t *) base; ptr < ((grub_uint8_t *) base) + size; - ptr++) - ret += *ptr; - return ret; -} - /* rev1 is 1 if ACPIv1 is to be generated, 0 otherwise. rev2 contains the revision of ACPIv2+ to generate or 0 if none. */ static int rev1, rev2; diff --git a/grub-core/commands/efi/lsefimmap.c b/grub-core/commands/efi/lsefimmap.c index 215b45bff..c85ff7f36 100644 --- a/grub-core/commands/efi/lsefimmap.c +++ b/grub-core/commands/efi/lsefimmap.c @@ -51,7 +51,7 @@ grub_cmd_lsefimmap (grub_command_t cmd __attribute__ ((unused)), grub_printf ("Type Physical start - end #Pages " - " Size Attributes\n"); + " Size Attributes\n"); memory_map_end = ADD_MEMORY_DESCRIPTOR (memory_map, map_size); for (desc = memory_map; desc < memory_map_end; @@ -74,7 +74,8 @@ grub_cmd_lsefimmap (grub_command_t cmd __attribute__ ((unused)), "ACPI-nvs", "MMIO ", "IO-ports", - "PAL-code" + "PAL-code", + "persist ", }; if (desc->type < ARRAY_SIZE (types_str)) grub_printf ("%s ", types_str[desc->type]); @@ -87,21 +88,29 @@ grub_cmd_lsefimmap (grub_command_t cmd __attribute__ ((unused)), desc->physical_start + (desc->num_pages << 12) - 1, desc->num_pages); - size = desc->num_pages; - size <<= (12 - 10); - if (size < 1024) - grub_printf (" %4" PRIuGRUB_UINT64_T "KB", size); + size = desc->num_pages << 12; /* 4 KiB page size */ + /* + * Since size is a multiple of 4 KiB, no need to handle units + * of just Bytes (which would use a mask of 0x3ff). + * + * 14 characters would support the largest possible number of 4 KiB + * pages that are not a multiple of larger units (e.g., MiB): + * 17592186044415 (0xffffff_fffff000), but that uses a lot of + * whitespace for a rare case. 6 characters usually suffices; + * columns will be off if not, but this is preferable to rounding. + */ + if (size & 0xfffff) + grub_printf (" %6" PRIuGRUB_UINT64_T "KiB", size >> 10); + else if (size & 0x3fffffff) + grub_printf (" %6" PRIuGRUB_UINT64_T "MiB", size >> 20); + else if (size & 0xffffffffff) + grub_printf (" %6" PRIuGRUB_UINT64_T "GiB", size >> 30); + else if (size & 0x3ffffffffffff) + grub_printf (" %6" PRIuGRUB_UINT64_T "TiB", size >> 40); + else if (size & 0xfffffffffffffff) + grub_printf (" %6" PRIuGRUB_UINT64_T "PiB", size >> 50); else - { - size /= 1024; - if (size < 1024) - grub_printf (" %4" PRIuGRUB_UINT64_T "MB", size); - else - { - size /= 1024; - grub_printf (" %4" PRIuGRUB_UINT64_T "GB", size); - } - } + grub_printf (" %6" PRIuGRUB_UINT64_T "EiB", size >> 60); attr = desc->attribute; if (attr & GRUB_EFI_MEMORY_RUNTIME) @@ -122,6 +131,12 @@ grub_cmd_lsefimmap (grub_command_t cmd __attribute__ ((unused)), grub_printf (" RP"); if (attr & GRUB_EFI_MEMORY_XP) grub_printf (" XP"); + if (attr & GRUB_EFI_MEMORY_NV) + grub_printf (" NV"); + if (attr & GRUB_EFI_MEMORY_MORE_RELIABLE) + grub_printf (" MR"); + if (attr & GRUB_EFI_MEMORY_RO) + grub_printf (" RO"); grub_printf ("\n"); } diff --git a/grub-core/commands/efi/lsefisystab.c b/grub-core/commands/efi/lsefisystab.c index 8717db91e..df1030221 100644 --- a/grub-core/commands/efi/lsefisystab.c +++ b/grub-core/commands/efi/lsefisystab.c @@ -37,10 +37,20 @@ static const struct guid_mapping guid_mappings[] = { { GRUB_EFI_ACPI_20_TABLE_GUID, "ACPI-2.0"}, { GRUB_EFI_ACPI_TABLE_GUID, "ACPI-1.0"}, + { GRUB_EFI_CRC32_GUIDED_SECTION_EXTRACTION_GUID, + "CRC32 GUIDED SECTION EXTRACTION"}, + { GRUB_EFI_DEBUG_IMAGE_INFO_TABLE_GUID, "DEBUG IMAGE INFO"}, + { GRUB_EFI_DXE_SERVICES_TABLE_GUID, "DXE SERVICES"}, + { GRUB_EFI_HCDP_TABLE_GUID, "HCDP"}, + { GRUB_EFI_HOB_LIST_GUID, "HOB LIST"}, + { GRUB_EFI_LZMA_CUSTOM_DECOMPRESS_GUID, "LZMA CUSTOM DECOMPRESS"}, + { GRUB_EFI_MEMORY_TYPE_INFORMATION_GUID, "MEMORY TYPE INFO"}, + { GRUB_EFI_MPS_TABLE_GUID, "MPS"}, { GRUB_EFI_SAL_TABLE_GUID, "SAL"}, { GRUB_EFI_SMBIOS_TABLE_GUID, "SMBIOS"}, - { GRUB_EFI_MPS_TABLE_GUID, "MPS"}, - { GRUB_EFI_HCDP_TABLE_GUID, "HCDP"} + { GRUB_EFI_SYSTEM_RESOURCE_TABLE_GUID, "SYSTEM RESOURCE TABLE"}, + { GRUB_EFI_TIANO_CUSTOM_DECOMPRESS_GUID, "TIANO CUSTOM DECOMPRESS"}, + { GRUB_EFI_TSC_FREQUENCY_GUID, "TSC FREQUENCY"}, }; static grub_err_t diff --git a/grub-core/commands/lsmmap.c b/grub-core/commands/lsmmap.c index 4b504fd28..816ee47d1 100644 --- a/grub-core/commands/lsmmap.c +++ b/grub-core/commands/lsmmap.c @@ -37,6 +37,8 @@ static const char *names[] = is required to save accross hibernations. */ [GRUB_MEMORY_NVS] = N_("ACPI non-volatile storage RAM"), [GRUB_MEMORY_BADRAM] = N_("faulty RAM (BadRAM)"), + [GRUB_MEMORY_PERSISTENT] = N_("persistent RAM"), + [GRUB_MEMORY_PERSISTENT_LEGACY] = N_("persistent RAM (legacy)"), [GRUB_MEMORY_COREBOOT_TABLES] = N_("RAM holding coreboot tables"), [GRUB_MEMORY_CODE] = N_("RAM holding firmware code") }; diff --git a/grub-core/disk/cryptodisk.c b/grub-core/disk/cryptodisk.c index 82a3dcb63..1e03a091c 100644 --- a/grub-core/disk/cryptodisk.c +++ b/grub-core/disk/cryptodisk.c @@ -25,6 +25,7 @@ #include #include #include +#include #ifdef GRUB_UTIL #include @@ -718,6 +719,7 @@ grub_cryptodisk_insert (grub_cryptodisk_t newdev, const char *name, newdev->id = last_cryptodisk_id++; newdev->source_id = source->id; newdev->source_dev_id = source->dev->id; + newdev->partition_start = grub_partition_get_start (source->partition); newdev->next = cryptodisk_list; cryptodisk_list = newdev; @@ -740,7 +742,9 @@ grub_cryptodisk_get_by_source_disk (grub_disk_t disk) grub_cryptodisk_t dev; for (dev = cryptodisk_list; dev != NULL; dev = dev->next) if (dev->source_id == disk->id && dev->source_dev_id == disk->dev->id) - return dev; + if ((disk->partition && grub_partition_get_start (disk->partition) == dev->partition_start) || + (!disk->partition && dev->partition_start == 0)) + return dev; return NULL; } @@ -761,6 +765,7 @@ grub_cryptodisk_cheat_insert (grub_cryptodisk_t newdev, const char *name, newdev->cheat_fd = GRUB_UTIL_FD_INVALID; newdev->source_id = source->id; newdev->source_dev_id = source->dev->id; + newdev->partition_start = grub_partition_get_start (source->partition); newdev->id = last_cryptodisk_id++; newdev->next = cryptodisk_list; cryptodisk_list = newdev; @@ -964,33 +969,43 @@ grub_cmd_cryptomount (grub_extcmd_context_t ctxt, int argc, char **args) grub_disk_t disk; grub_cryptodisk_t dev; char *diskname; - char *disklast; + char *disklast = NULL; + grub_size_t len; search_uuid = NULL; check_boot = state[2].set; diskname = args[0]; - if (diskname[0] == '(' && *(disklast = &diskname[grub_strlen (diskname) - 1]) == ')') + len = grub_strlen (diskname); + if (len && diskname[0] == '(' && diskname[len - 1] == ')') { + disklast = &diskname[len - 1]; *disklast = '\0'; - disk = grub_disk_open (diskname + 1); - *disklast = ')'; + diskname++; } - else - disk = grub_disk_open (diskname); + + disk = grub_disk_open (diskname); if (!disk) - return grub_errno; + { + if (disklast) + *disklast = ')'; + return grub_errno; + } dev = grub_cryptodisk_get_by_source_disk (disk); if (dev) { grub_dprintf ("cryptodisk", "already mounted as crypto%lu\n", dev->id); grub_disk_close (disk); + if (disklast) + *disklast = ')'; return GRUB_ERR_NONE; } - err = grub_cryptodisk_scan_device_real (args[0], disk); + err = grub_cryptodisk_scan_device_real (diskname, disk); grub_disk_close (disk); + if (disklast) + *disklast = ')'; return err; } diff --git a/grub-core/disk/ieee1275/ofdisk.c b/grub-core/disk/ieee1275/ofdisk.c index 331769b12..235c0fe2c 100644 --- a/grub-core/disk/ieee1275/ofdisk.c +++ b/grub-core/disk/ieee1275/ofdisk.c @@ -227,7 +227,10 @@ dev_iterate (const struct grub_ieee1275_devalias *alias) if (grub_ieee1275_open (alias->path, &ihandle)) return; - + + /* This method doesn't need memory allocation for the table. Open + firmware takes care of all memory management and the result table + stays in memory and is never freed. */ INIT_IEEE1275_COMMON (&args.common, "call-method", 2, 3); args.method = (grub_ieee1275_cell_t) "vscsi-report-luns"; args.ihandle = ihandle; @@ -260,6 +263,82 @@ dev_iterate (const struct grub_ieee1275_devalias *alias) grub_free (buf); return; } + else if (grub_strcmp (alias->type, "sas_ioa") == 0) + { + /* The method returns the number of disks and a table where + * each ID is 64-bit long. Example of sas paths: + * /pci@80000002000001f/pci1014,034A@0/sas/disk@c05db70800 + * /pci@80000002000001f/pci1014,034A@0/sas/disk@a05db70800 + * /pci@80000002000001f/pci1014,034A@0/sas/disk@805db70800 */ + + struct sas_children + { + struct grub_ieee1275_common_hdr common; + grub_ieee1275_cell_t method; + grub_ieee1275_cell_t ihandle; + grub_ieee1275_cell_t max; + grub_ieee1275_cell_t table; + grub_ieee1275_cell_t catch_result; + grub_ieee1275_cell_t nentries; + } + args; + char *buf, *bufptr; + unsigned i; + grub_uint64_t *table; + grub_uint16_t table_size; + grub_ieee1275_ihandle_t ihandle; + + buf = grub_malloc (grub_strlen (alias->path) + + sizeof ("/disk@7766554433221100")); + if (!buf) + return; + bufptr = grub_stpcpy (buf, alias->path); + + /* Power machines documentation specify 672 as maximum SAS disks in + one system. Using a slightly larger value to be safe. */ + table_size = 768; + table = grub_malloc (table_size * sizeof (grub_uint64_t)); + + if (!table) + { + grub_free (buf); + return; + } + + if (grub_ieee1275_open (alias->path, &ihandle)) + { + grub_free (buf); + grub_free (table); + return; + } + + INIT_IEEE1275_COMMON (&args.common, "call-method", 4, 2); + args.method = (grub_ieee1275_cell_t) "get-sas-children"; + args.ihandle = ihandle; + args.max = table_size; + args.table = (grub_ieee1275_cell_t) table; + args.catch_result = 0; + args.nentries = 0; + + if (IEEE1275_CALL_ENTRY_FN (&args) == -1) + { + grub_ieee1275_close (ihandle); + grub_free (table); + grub_free (buf); + return; + } + + for (i = 0; i < args.nentries; i++) + { + grub_snprintf (bufptr, sizeof ("/disk@7766554433221100"), + "/disk@%" PRIxGRUB_UINT64_T, table[i]); + dev_iterate_real (buf, buf); + } + + grub_ieee1275_close (ihandle); + grub_free (table); + grub_free (buf); + } if (!grub_ieee1275_test_flag (GRUB_IEEE1275_FLAG_NO_TREE_SCANNING_FOR_DISKS) && grub_strcmp (alias->type, "block") == 0) @@ -422,16 +501,20 @@ grub_ofdisk_open (const char *name, grub_disk_t disk) op = ofdisk_hash_find (devpath); if (!op) op = ofdisk_hash_add (devpath, NULL); - else - grub_free (devpath); if (!op) - return grub_errno; + { + grub_free (devpath); + return grub_errno; + } disk->id = (unsigned long) op; disk->data = op->open_path; err = grub_ofdisk_get_block_size (devpath, &block_size, op); if (err) - return err; + { + grub_free (devpath); + return err; + } if (block_size != 0) { for (disk->log_sector_size = 0; @@ -442,6 +525,7 @@ grub_ofdisk_open (const char *name, grub_disk_t disk) disk->log_sector_size = 9; } + grub_free (devpath); return 0; } diff --git a/grub-core/disk/ldm.c b/grub-core/disk/ldm.c index 8075f2a9e..0f978ad05 100644 --- a/grub-core/disk/ldm.c +++ b/grub-core/disk/ldm.c @@ -963,7 +963,7 @@ grub_util_ldm_embed (struct grub_disk *disk, unsigned int *nsectors, if (embed_type != GRUB_EMBED_PCBIOS) return grub_error (GRUB_ERR_NOT_IMPLEMENTED_YET, - "LDM curently supports only PC-BIOS embedding"); + "LDM currently supports only PC-BIOS embedding"); if (disk->partition) return grub_error (GRUB_ERR_BUG, "disk isn't LDM"); pv = grub_diskfilter_get_pv_from_disk (disk, &vg); diff --git a/grub-core/fs/cbfs.c b/grub-core/fs/cbfs.c index a34eb88cb..0842701a6 100644 --- a/grub-core/fs/cbfs.c +++ b/grub-core/fs/cbfs.c @@ -344,8 +344,16 @@ init_cbfsdisk (void) ptr = *(grub_uint32_t *) 0xfffffffc; head = (struct cbfs_header *) (grub_addr_t) ptr; + grub_dprintf ("cbfs", "head=%p\n", head); - if (!validate_head (head)) + /* coreboot current supports only ROMs <= 16 MiB. Bigger ROMs will + have problems as RCBA is 18 MiB below end of 32-bit typically, + so either memory map would have to be rearranged or we'd need to support + reading ROMs through controller directly. + */ + if (ptr < 0xff000000 + || 0xffffffff - ptr < (grub_uint32_t) sizeof (*head) + 0xf + || !validate_head (head)) return; cbfsdisk_size = ALIGN_UP (grub_be_to_cpu32 (head->romsize), diff --git a/grub-core/fs/ufs.c b/grub-core/fs/ufs.c index 0619d6e32..293f027aa 100644 --- a/grub-core/fs/ufs.c +++ b/grub-core/fs/ufs.c @@ -394,7 +394,7 @@ grub_ufs_read_file (struct grub_ufs_data *data, return -1; } else - grub_memset (buf, UFS_BLKSZ (sblock) - skipfirst, 0); + grub_memset (buf, 0, blockend); buf += UFS_BLKSZ (sblock) - skipfirst; } diff --git a/grub-core/genmoddep.awk b/grub-core/genmoddep.awk index 2f32465c4..bd98d84cd 100644 --- a/grub-core/genmoddep.awk +++ b/grub-core/genmoddep.awk @@ -29,7 +29,7 @@ BEGIN { } } else { - printf "error: %u: unrecognized input format\n", NR; + printf "error: %u: unrecognized input format\n", NR >"/dev/stderr"; error++; } } @@ -39,6 +39,8 @@ END { if (error >= 1) exit 1; + total_depcount = 0 + for (mod in modtab) { # Remove duplications. split(modtab[mod], depmods, " "); @@ -52,14 +54,42 @@ END { uniqmods[depmod] = 1; } modlist = "" + depcount[mod] = 0 for (depmod in uniqmods) { modlist = modlist " " depmod; + inverse_dependencies[depmod] = inverse_dependencies[depmod] " " mod + depcount[mod]++ + total_depcount++ } if (mod == "all_video") { continue; } printf "%s:%s\n", mod, modlist; } + + # Check that we have no dependency circles + while (total_depcount != 0) { + something_done = 0 + for (mod in depcount) { + if (depcount[mod] == 0) { + delete depcount[mod] + split(inverse_dependencies[mod], inv_depmods, " "); + for (ctr in inv_depmods) { + depcount[inv_depmods[ctr]]-- + total_depcount-- + } + delete inverse_dependencies[mod] + something_done = 1 + } + } + if (something_done == 0) { + for (mod in depcount) { + circle = circle " " mod + } + printf "error: modules %s form a dependency circle\n", circle >"/dev/stderr"; + exit 1 + } + } modlist = "" while (getline <"video.lst") { modlist = modlist " " $1; diff --git a/grub-core/gfxmenu/model.c b/grub-core/gfxmenu/model.c deleted file mode 100644 index e69de29bb..000000000 diff --git a/grub-core/gfxmenu/theme_loader.c b/grub-core/gfxmenu/theme_loader.c index 1a6ed1d25..02978392c 100644 --- a/grub-core/gfxmenu/theme_loader.c +++ b/grub-core/gfxmenu/theme_loader.c @@ -255,7 +255,7 @@ theme_set_string (grub_gfxmenu_view_t view, { unsigned int tmp; int err = theme_get_unsigned_int_from_proportional (value, - view->screen.width, + view->screen.height, &tmp); if (err != GRUB_ERR_NONE) return err; @@ -275,7 +275,7 @@ theme_set_string (grub_gfxmenu_view_t view, { unsigned int tmp; int err = theme_get_unsigned_int_from_proportional (value, - view->screen.width, + view->screen.height, &tmp); if (err != GRUB_ERR_NONE) return err; diff --git a/grub-core/kern/acpi.c b/grub-core/kern/acpi.c new file mode 100644 index 000000000..02c1f4f6f --- /dev/null +++ b/grub-core/kern/acpi.c @@ -0,0 +1,34 @@ +/* + * GRUB -- GRand Unified Bootloader + * Copyright (C) 2012 Free Software Foundation, Inc. + * + * GRUB is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * GRUB is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GRUB. If not, see . + */ + +#include +#include +#include +#include + +/* Simple checksum by summing all bytes. Used by ACPI and SMBIOS. */ +grub_uint8_t +grub_byte_checksum (void *base, grub_size_t size) +{ + grub_uint8_t *ptr; + grub_uint8_t ret = 0; + for (ptr = (grub_uint8_t *) base; ptr < ((grub_uint8_t *) base) + size; + ptr++) + ret += *ptr; + return ret; +} diff --git a/grub-core/commands/efi/acpi.c b/grub-core/kern/efi/acpi.c similarity index 100% rename from grub-core/commands/efi/acpi.c rename to grub-core/kern/efi/acpi.c diff --git a/grub-core/kern/elf.c b/grub-core/kern/elf.c index 5f99c43cc..4f282c9cf 100644 --- a/grub-core/kern/elf.c +++ b/grub-core/kern/elf.c @@ -28,6 +28,25 @@ GRUB_MOD_LICENSE ("GPLv3+"); +#pragma GCC diagnostic ignored "-Wcast-align" + +#if defined(__powerpc__) && defined(GRUB_MACHINE_IEEE1275) +#define GRUB_ELF_ENABLE_BI_ENDIAN 1 +#else +#define GRUB_ELF_ENABLE_BI_ENDIAN 0 +#endif + +#if defined(GRUB_CPU_WORDS_BIGENDIAN) +#define GRUB_ELF_NATIVE_ENDIANNESS ELFDATA2MSB +#define GRUB_ELF_OPPOSITE_ENDIANNESS ELFDATA2LSB +#else +#define GRUB_ELF_NATIVE_ENDIANNESS ELFDATA2LSB +#define GRUB_ELF_OPPOSITE_ENDIANNESS ELFDATA2MSB +#endif + +static int grub_elf32_check_endianess_and_bswap_ehdr (grub_elf_t elf); +static int grub_elf64_check_endianess_and_bswap_ehdr (grub_elf_t elf); + /* Check if EHDR is a valid ELF header. */ static grub_err_t grub_elf_check_header (grub_elf_t elf) @@ -38,8 +57,25 @@ grub_elf_check_header (grub_elf_t elf) || e->e_ident[EI_MAG1] != ELFMAG1 || e->e_ident[EI_MAG2] != ELFMAG2 || e->e_ident[EI_MAG3] != ELFMAG3 - || e->e_ident[EI_VERSION] != EV_CURRENT - || e->e_version != EV_CURRENT) + || e->e_ident[EI_VERSION] != EV_CURRENT) + return grub_error (GRUB_ERR_BAD_OS, N_("invalid arch-independent ELF magic")); + + if (grub_elf_is_elf32 (elf)) + { + if (!grub_elf32_check_endianess_and_bswap_ehdr (elf)) { + return grub_error (GRUB_ERR_BAD_OS, "invalid ELF endianness magic"); + } + } + else if (grub_elf_is_elf64 (elf)) + { + if (!grub_elf64_check_endianess_and_bswap_ehdr (elf)) { + return grub_error (GRUB_ERR_BAD_OS, "invalid ELF endianness magic"); + } + } + else + return grub_error (GRUB_ERR_BAD_OS, "unknown ELF class"); + + if (e->e_version != EV_CURRENT) return grub_error (GRUB_ERR_BAD_OS, N_("invalid arch-independent ELF magic")); return GRUB_ERR_NONE; @@ -117,6 +153,9 @@ grub_elf_open (const char *name) } +#define grub_swap_bytes_halfXX grub_swap_bytes16 +#define grub_swap_bytes_wordXX grub_swap_bytes32 + /* 32-bit */ #define ehdrXX ehdr32 #define ELFCLASSXX ELFCLASS32 @@ -127,7 +166,12 @@ grub_elf_open (const char *name) #define grub_elf_is_elfXX grub_elf_is_elf32 #define grub_elfXX_load_phdrs grub_elf32_load_phdrs #define ElfXX_Phdr Elf32_Phdr +#define ElfXX_Ehdr Elf32_Ehdr #define grub_uintXX_t grub_uint32_t +#define grub_swap_bytes_addrXX grub_swap_bytes32 +#define grub_swap_bytes_offXX grub_swap_bytes32 +#define grub_swap_bytes_XwordXX grub_swap_bytes32 +#define grub_elfXX_check_endianess_and_bswap_ehdr grub_elf32_check_endianess_and_bswap_ehdr #include "elfXX.c" @@ -140,7 +184,12 @@ grub_elf_open (const char *name) #undef grub_elf_is_elfXX #undef grub_elfXX_load_phdrs #undef ElfXX_Phdr +#undef ElfXX_Ehdr #undef grub_uintXX_t +#undef grub_swap_bytes_addrXX +#undef grub_swap_bytes_offXX +#undef grub_swap_bytes_XwordXX +#undef grub_elfXX_check_endianess_and_bswap_ehdr /* 64-bit */ @@ -153,6 +202,11 @@ grub_elf_open (const char *name) #define grub_elf_is_elfXX grub_elf_is_elf64 #define grub_elfXX_load_phdrs grub_elf64_load_phdrs #define ElfXX_Phdr Elf64_Phdr +#define ElfXX_Ehdr Elf64_Ehdr #define grub_uintXX_t grub_uint64_t +#define grub_swap_bytes_addrXX grub_swap_bytes64 +#define grub_swap_bytes_offXX grub_swap_bytes64 +#define grub_swap_bytes_XwordXX grub_swap_bytes64 +#define grub_elfXX_check_endianess_and_bswap_ehdr grub_elf64_check_endianess_and_bswap_ehdr #include "elfXX.c" diff --git a/grub-core/kern/elfXX.c b/grub-core/kern/elfXX.c index 1d0997186..b91c39d9e 100644 --- a/grub-core/kern/elfXX.c +++ b/grub-core/kern/elfXX.c @@ -31,6 +31,25 @@ grub_elfXX_load_phdrs (grub_elf_t elf) return grub_errno; } +#if GRUB_ELF_ENABLE_BI_ENDIAN + if (elf->ehdr.ehdrXX.e_ident[EI_DATA] == GRUB_ELF_OPPOSITE_ENDIANNESS) + { + ElfXX_Phdr *phdr; + for (phdr = elf->phdrs; (char *) phdr < (char *) elf->phdrs + phdrs_size; + phdr = (ElfXX_Phdr *) ((char *) phdr + elf->ehdr.ehdrXX.e_phentsize)) + { + phdr->p_type = grub_swap_bytes_wordXX (phdr->p_type); + phdr->p_flags = grub_swap_bytes_wordXX (phdr->p_flags); + phdr->p_offset = grub_swap_bytes_offXX (phdr->p_offset); + phdr->p_vaddr = grub_swap_bytes_addrXX (phdr->p_vaddr); + phdr->p_paddr = grub_swap_bytes_addrXX (phdr->p_paddr); + phdr->p_filesz = grub_swap_bytes_XwordXX (phdr->p_filesz); + phdr->p_memsz = grub_swap_bytes_XwordXX (phdr->p_memsz); + phdr->p_align = grub_swap_bytes_XwordXX (phdr->p_align); + } + } +#endif /* GRUB_ELF_ENABLE_BI_ENDIAN */ + return GRUB_ERR_NONE; } @@ -154,3 +173,35 @@ grub_elfXX_load (grub_elf_t elf, const char *filename, return grub_errno; } + +static int +grub_elfXX_check_endianess_and_bswap_ehdr (grub_elf_t elf) +{ + ElfXX_Ehdr *e = &(elf->ehdr.ehdrXX); + if (e->e_ident[EI_DATA] == GRUB_ELF_NATIVE_ENDIANNESS) + { + return 1; + } + +#if GRUB_ELF_ENABLE_BI_ENDIAN + if (e->e_ident[EI_DATA] == GRUB_ELF_OPPOSITE_ENDIANNESS) + { + e->e_type = grub_swap_bytes_halfXX (e->e_type); + e->e_machine = grub_swap_bytes_halfXX (e->e_machine); + e->e_version = grub_swap_bytes_wordXX (e->e_version); + e->e_entry = grub_swap_bytes_addrXX (e->e_entry); + e->e_phoff = grub_swap_bytes_offXX (e->e_phoff); + e->e_shoff = grub_swap_bytes_offXX (e->e_shoff); + e->e_flags = grub_swap_bytes_wordXX (e->e_flags); + e->e_ehsize = grub_swap_bytes_halfXX (e->e_ehsize); + e->e_phentsize = grub_swap_bytes_halfXX (e->e_phentsize); + e->e_phnum = grub_swap_bytes_halfXX (e->e_phnum); + e->e_shentsize = grub_swap_bytes_halfXX (e->e_shentsize); + e->e_shnum = grub_swap_bytes_halfXX (e->e_shnum); + e->e_shstrndx = grub_swap_bytes_halfXX (e->e_shstrndx); + return 1; + } +#endif /* GRUB_ELF_ENABLE_BI_ENDIAN */ + + return 0; +} diff --git a/grub-core/kern/file.c b/grub-core/kern/file.c index 24da12bb9..668f8930b 100644 --- a/grub-core/kern/file.c +++ b/grub-core/kern/file.c @@ -89,7 +89,16 @@ grub_file_open (const char *name) file->device = device; - if (device->disk && file_name[0] != '/') + /* In case of relative pathnames and non-Unix systems (like Windows) + * name of host files may not start with `/'. Blocklists for host files + * are meaningless as well (for a start, host disk does not allow any direct + * access - it is just a marker). So skip host disk in this case. + */ + if (device->disk && file_name[0] != '/' +#if defined(GRUB_UTIL) || defined(GRUB_MACHINE_EMU) + && grub_strcmp (device->disk->name, "host") +#endif + ) /* This is a block list. */ file->fs = &grub_fs_blocklist; else diff --git a/grub-core/kern/i386/efi/tsc.c b/grub-core/kern/i386/efi/tsc.c new file mode 100644 index 000000000..4b93ba8e1 --- /dev/null +++ b/grub-core/kern/i386/efi/tsc.c @@ -0,0 +1,40 @@ +/* kern/i386/tsc.c - x86 TSC time source implementation + * Requires Pentium or better x86 CPU that supports the RDTSC instruction. + * This module uses the PIT to calibrate the TSC to + * real time. + * + * GRUB -- GRand Unified Bootloader + * Copyright (C) 2008 Free Software Foundation, Inc. + * + * GRUB is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * GRUB is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GRUB. If not, see . + */ + +#include +#include +#include +#include +#include +#include + +int +grub_tsc_calibrate_from_efi (void) +{ + grub_uint64_t start_tsc, end_tsc; + /* Use EFI Time Service to calibrate TSC */ + start_tsc = grub_get_tsc (); + efi_call_1 (grub_efi_system_table->boot_services->stall, 1000); + end_tsc = grub_get_tsc (); + grub_tsc_rate = grub_divmod64 ((1ULL << 32), end_tsc - start_tsc, 0); + return 1; +} diff --git a/grub-core/commands/i386/pc/acpi.c b/grub-core/kern/i386/pc/acpi.c similarity index 100% rename from grub-core/commands/i386/pc/acpi.c rename to grub-core/kern/i386/pc/acpi.c diff --git a/grub-core/kern/i386/tsc.c b/grub-core/kern/i386/tsc.c index bc441d0d3..82cdea491 100644 --- a/grub-core/kern/i386/tsc.c +++ b/grub-core/kern/i386/tsc.c @@ -1,7 +1,6 @@ /* kern/i386/tsc.c - x86 TSC time source implementation * Requires Pentium or better x86 CPU that supports the RDTSC instruction. - * This module uses the RTC (via grub_get_rtc()) to calibrate the TSC to - * real time. + * This module calibrates the TSC to real time. * * GRUB -- GRand Unified Bootloader * Copyright (C) 2008 Free Software Foundation, Inc. @@ -25,12 +24,6 @@ #include #include #include -#ifdef GRUB_MACHINE_XEN -#include -#else -#include -#endif -#include /* This defines the value TSC had at the epoch (that is, when we calibrated it). */ static grub_uint64_t tsc_boot_time; @@ -40,66 +33,6 @@ static grub_uint64_t tsc_boot_time; in 32-bit. */ grub_uint32_t grub_tsc_rate; -/* Read the TSC value, which increments with each CPU clock cycle. */ -static __inline grub_uint64_t -grub_get_tsc (void) -{ - grub_uint32_t lo, hi; - grub_uint32_t a,b,c,d; - - /* The CPUID instruction is a 'serializing' instruction, and - avoids out-of-order execution of the RDTSC instruction. */ - grub_cpuid (0,a,b,c,d); - /* Read TSC value. We cannot use "=A", since this would use - %rax on x86_64. */ - __asm__ __volatile__ ("rdtsc":"=a" (lo), "=d" (hi)); - - return (((grub_uint64_t) hi) << 32) | lo; -} - -#ifndef GRUB_MACHINE_XEN - -static __inline int -grub_cpu_is_tsc_supported (void) -{ - grub_uint32_t a,b,c,d; - if (! grub_cpu_is_cpuid_supported ()) - return 0; - - grub_cpuid(1,a,b,c,d); - - return (d & (1 << 4)) != 0; -} - -static void -grub_pit_wait (grub_uint16_t tics) -{ - /* Disable timer2 gate and speaker. */ - grub_outb (grub_inb (GRUB_PIT_SPEAKER_PORT) - & ~ (GRUB_PIT_SPK_DATA | GRUB_PIT_SPK_TMR2), - GRUB_PIT_SPEAKER_PORT); - - /* Set tics. */ - grub_outb (GRUB_PIT_CTRL_SELECT_2 | GRUB_PIT_CTRL_READLOAD_WORD, - GRUB_PIT_CTRL); - grub_outb (tics & 0xff, GRUB_PIT_COUNTER_2); - grub_outb (tics >> 8, GRUB_PIT_COUNTER_2); - - /* Enable timer2 gate, keep speaker disabled. */ - grub_outb ((grub_inb (GRUB_PIT_SPEAKER_PORT) & ~ GRUB_PIT_SPK_DATA) - | GRUB_PIT_SPK_TMR2, - GRUB_PIT_SPEAKER_PORT); - - /* Wait. */ - while ((grub_inb (GRUB_PIT_SPEAKER_PORT) & GRUB_PIT_SPK_TMR2_LATCH) == 0x00); - - /* Disable timer2 gate and speaker. */ - grub_outb (grub_inb (GRUB_PIT_SPEAKER_PORT) - & ~ (GRUB_PIT_SPK_DATA | GRUB_PIT_SPK_TMR2), - GRUB_PIT_SPEAKER_PORT); -} -#endif - static grub_uint64_t grub_tsc_get_time_ms (void) { @@ -110,52 +43,52 @@ grub_tsc_get_time_ms (void) return ((al * grub_tsc_rate) >> 32) + ah * grub_tsc_rate; } -#ifndef GRUB_MACHINE_XEN -/* Calibrate the TSC based on the RTC. */ -static void -calibrate_tsc (void) +static __inline int +grub_cpu_is_tsc_supported (void) { - /* First calibrate the TSC rate (relative, not absolute time). */ - grub_uint64_t end_tsc; +#ifndef GRUB_MACHINE_XEN + grub_uint32_t a,b,c,d; + if (! grub_cpu_is_cpuid_supported ()) + return 0; - tsc_boot_time = grub_get_tsc (); - grub_pit_wait (0xffff); - end_tsc = grub_get_tsc (); + grub_cpuid(1,a,b,c,d); - grub_tsc_rate = 0; - if (end_tsc > tsc_boot_time) - grub_tsc_rate = grub_divmod64 ((55ULL << 32), end_tsc - tsc_boot_time, 0); - if (grub_tsc_rate == 0) - grub_tsc_rate = 5368;/* 800 MHz */ -} + return (d & (1 << 4)) != 0; +#else + return 1; #endif +} + +static int +calibrate_tsc_hardcode (void) +{ + grub_tsc_rate = 5368;/* 800 MHz */ + return 1; +} void grub_tsc_init (void) { -#ifdef GRUB_MACHINE_XEN - grub_uint64_t t; - tsc_boot_time = grub_get_tsc (); - t = grub_xen_shared_info->vcpu_info[0].time.tsc_to_system_mul; - if (grub_xen_shared_info->vcpu_info[0].time.tsc_shift > 0) - t <<= grub_xen_shared_info->vcpu_info[0].time.tsc_shift; - else - t >>= -grub_xen_shared_info->vcpu_info[0].time.tsc_shift; - grub_tsc_rate = grub_divmod64 (t, 1000000, 0); - grub_install_get_time_ms (grub_tsc_get_time_ms); -#else - if (grub_cpu_is_tsc_supported ()) - { - calibrate_tsc (); - grub_install_get_time_ms (grub_tsc_get_time_ms); - } - else + if (!grub_cpu_is_tsc_supported ()) { #if defined (GRUB_MACHINE_PCBIOS) || defined (GRUB_MACHINE_IEEE1275) grub_install_get_time_ms (grub_rtc_get_time_ms); #else grub_fatal ("no TSC found"); #endif + return; } + + tsc_boot_time = grub_get_tsc (); + +#ifdef GRUB_MACHINE_XEN + (void) (grub_tsc_calibrate_from_xen () || calibrate_tsc_hardcode()); +#elif defined (GRUB_MACHINE_EFI) + (void) (grub_tsc_calibrate_from_pit () || grub_tsc_calibrate_from_pmtimer () || grub_tsc_calibrate_from_efi() || calibrate_tsc_hardcode()); +#elif defined (GRUB_MACHINE_COREBOOT) + (void) (grub_tsc_calibrate_from_pmtimer () || grub_tsc_calibrate_from_pit () || calibrate_tsc_hardcode()); +#else + (void) (grub_tsc_calibrate_from_pit () || calibrate_tsc_hardcode()); #endif + grub_install_get_time_ms (grub_tsc_get_time_ms); } diff --git a/grub-core/kern/i386/tsc_pit.c b/grub-core/kern/i386/tsc_pit.c new file mode 100644 index 000000000..67990bfa6 --- /dev/null +++ b/grub-core/kern/i386/tsc_pit.c @@ -0,0 +1,84 @@ +/* kern/i386/tsc.c - x86 TSC time source implementation + * Requires Pentium or better x86 CPU that supports the RDTSC instruction. + * This module uses the PIT to calibrate the TSC to + * real time. + * + * GRUB -- GRand Unified Bootloader + * Copyright (C) 2008 Free Software Foundation, Inc. + * + * GRUB is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * GRUB is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GRUB. If not, see . + */ + +#include +#include +#include +#include +#include +#include + +static int +grub_pit_wait (void) +{ + int ret = 0; + + /* Disable timer2 gate and speaker. */ + grub_outb (grub_inb (GRUB_PIT_SPEAKER_PORT) + & ~ (GRUB_PIT_SPK_DATA | GRUB_PIT_SPK_TMR2), + GRUB_PIT_SPEAKER_PORT); + + /* Set tics. */ + grub_outb (GRUB_PIT_CTRL_SELECT_2 | GRUB_PIT_CTRL_READLOAD_WORD, + GRUB_PIT_CTRL); + /* 0xffff ticks: 55ms. */ + grub_outb (0xff, GRUB_PIT_COUNTER_2); + grub_outb (0xff, GRUB_PIT_COUNTER_2); + + /* Enable timer2 gate, keep speaker disabled. */ + grub_outb ((grub_inb (GRUB_PIT_SPEAKER_PORT) & ~ GRUB_PIT_SPK_DATA) + | GRUB_PIT_SPK_TMR2, + GRUB_PIT_SPEAKER_PORT); + + if ((grub_inb (GRUB_PIT_SPEAKER_PORT) & GRUB_PIT_SPK_TMR2_LATCH) == 0x00) { + ret = 1; + /* Wait. */ + while ((grub_inb (GRUB_PIT_SPEAKER_PORT) & GRUB_PIT_SPK_TMR2_LATCH) == 0x00); + } + + /* Disable timer2 gate and speaker. */ + grub_outb (grub_inb (GRUB_PIT_SPEAKER_PORT) + & ~ (GRUB_PIT_SPK_DATA | GRUB_PIT_SPK_TMR2), + GRUB_PIT_SPEAKER_PORT); + + return ret; +} + +/* Calibrate the TSC based on the RTC. */ +int +grub_tsc_calibrate_from_pit (void) +{ + /* First calibrate the TSC rate (relative, not absolute time). */ + grub_uint64_t start_tsc, end_tsc; + + start_tsc = grub_get_tsc (); + if (!grub_pit_wait ()) + return 0; + end_tsc = grub_get_tsc (); + + grub_tsc_rate = 0; + if (end_tsc > start_tsc) + grub_tsc_rate = grub_divmod64 ((55ULL << 32), end_tsc - start_tsc, 0); + if (grub_tsc_rate == 0) + return 0; + return 1; +} diff --git a/grub-core/kern/i386/tsc_pmtimer.c b/grub-core/kern/i386/tsc_pmtimer.c new file mode 100644 index 000000000..6a47ab7be --- /dev/null +++ b/grub-core/kern/i386/tsc_pmtimer.c @@ -0,0 +1,160 @@ +/* kern/i386/tsc.c - x86 TSC time source implementation + * Requires Pentium or better x86 CPU that supports the RDTSC instruction. + * This module uses the PIT to calibrate the TSC to + * real time. + * + * GRUB -- GRand Unified Bootloader + * Copyright (C) 2008 Free Software Foundation, Inc. + * + * GRUB is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * GRUB is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GRUB. If not, see . + */ + +#include +#include +#include +#include +#include +#include + +static void * +grub_acpi_rsdt_find_table (struct grub_acpi_table_header *rsdt, const char *sig) +{ + grub_size_t s; + grub_uint32_t *ptr; + + if (!rsdt) + return 0; + + if (grub_memcmp (rsdt->signature, "RSDT", 4) != 0) + return 0; + + ptr = (grub_uint32_t *) (rsdt + 1); + s = (rsdt->length - sizeof (*rsdt)) / sizeof (grub_uint32_t); + for (; s; s--, ptr++) + { + struct grub_acpi_table_header *tbl; + tbl = (struct grub_acpi_table_header *) (grub_addr_t) *ptr; + if (grub_memcmp (tbl->signature, sig, 4) == 0) + return tbl; + } + return 0; +} + +static void * +grub_acpi_xsdt_find_table (struct grub_acpi_table_header *xsdt, const char *sig) +{ + grub_size_t s; + grub_uint64_t *ptr; + + if (!xsdt) + return 0; + + if (grub_memcmp (xsdt->signature, "XSDT", 4) != 0) + return 0; + + ptr = (grub_uint64_t *) (xsdt + 1); + s = (xsdt->length - sizeof (*xsdt)) / sizeof (grub_uint32_t); + for (; s; s--, ptr++) + { + struct grub_acpi_table_header *tbl; +#if GRUB_CPU_SIZEOF_VOID_P != 8 + if (*ptr >> 32) + continue; +#endif + tbl = (struct grub_acpi_table_header *) (grub_addr_t) *ptr; + if (grub_memcmp (tbl->signature, sig, 4) == 0) + return tbl; + } + return 0; +} + +struct grub_acpi_fadt * +grub_acpi_find_fadt (void) +{ + struct grub_acpi_fadt *fadt = 0; + struct grub_acpi_rsdp_v10 *rsdpv1; + struct grub_acpi_rsdp_v20 *rsdpv2; + rsdpv1 = grub_machine_acpi_get_rsdpv1 (); + if (rsdpv1) + fadt = grub_acpi_rsdt_find_table ((struct grub_acpi_table_header *) + (grub_addr_t) rsdpv1->rsdt_addr, + GRUB_ACPI_FADT_SIGNATURE); + if (fadt) + return fadt; + rsdpv2 = grub_machine_acpi_get_rsdpv2 (); + if (rsdpv2) + fadt = grub_acpi_rsdt_find_table ((struct grub_acpi_table_header *) + (grub_addr_t) rsdpv2->rsdpv1.rsdt_addr, + GRUB_ACPI_FADT_SIGNATURE); + if (fadt) + return fadt; + if (rsdpv2 +#if GRUB_CPU_SIZEOF_VOID_P != 8 + && !(rsdpv2->xsdt_addr >> 32) +#endif + ) + fadt = grub_acpi_xsdt_find_table ((struct grub_acpi_table_header *) + (grub_addr_t) rsdpv2->xsdt_addr, + GRUB_ACPI_FADT_SIGNATURE); + if (fadt) + return fadt; + return 0; +} + +int +grub_tsc_calibrate_from_pmtimer (void) +{ + grub_uint32_t start; + grub_uint32_t last; + grub_uint32_t cur, end; + struct grub_acpi_fadt *fadt; + grub_port_t p; + grub_uint64_t start_tsc; + grub_uint64_t end_tsc; + int num_iter = 0; + + fadt = grub_acpi_find_fadt (); + if (!fadt) + return 0; + p = fadt->pmtimer; + if (!p) + return 0; + + start = grub_inl (p) & 0xffffff; + last = start; + /* It's 3.579545 MHz clock. Wait 1 ms. */ + end = start + 3580; + start_tsc = grub_get_tsc (); + while (1) + { + cur = grub_inl (p) & 0xffffff; + if (cur < last) + cur |= 0x1000000; + num_iter++; + if (cur >= end) + { + end_tsc = grub_get_tsc (); + grub_tsc_rate = grub_divmod64 ((1ULL << 32), end_tsc - start_tsc, 0); + return 1; + } + /* Check for broken PM timer. + 50000000 TSCs is between 5 ms (10GHz) and 200 ms (250 MHz) + if after this time we still don't have 1 ms on pmtimer, then + pmtimer is broken. + */ + if ((num_iter & 0xffffff) == 0 && grub_get_tsc () - start_tsc > 5000000) { + return 0; + } + } +} diff --git a/grub-core/kern/i386/xen/tsc.c b/grub-core/kern/i386/xen/tsc.c new file mode 100644 index 000000000..8792b308d --- /dev/null +++ b/grub-core/kern/i386/xen/tsc.c @@ -0,0 +1,40 @@ +/* kern/i386/tsc.c - x86 TSC time source implementation + * Requires Pentium or better x86 CPU that supports the RDTSC instruction. + * This module uses the PIT to calibrate the TSC to + * real time. + * + * GRUB -- GRand Unified Bootloader + * Copyright (C) 2008 Free Software Foundation, Inc. + * + * GRUB is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * GRUB is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GRUB. If not, see . + */ + +#include +#include +#include +#include +#include + +int +grub_tsc_calibrate_from_xen (void) +{ + grub_uint64_t t; + t = grub_xen_shared_info->vcpu_info[0].time.tsc_to_system_mul; + if (grub_xen_shared_info->vcpu_info[0].time.tsc_shift > 0) + t <<= grub_xen_shared_info->vcpu_info[0].time.tsc_shift; + else + t >>= -grub_xen_shared_info->vcpu_info[0].time.tsc_shift; + grub_tsc_rate = grub_divmod64 (t, 1000000, 0); + return 1; +} diff --git a/grub-core/kern/ieee1275/init.c b/grub-core/kern/ieee1275/init.c index d5bd74d35..4303509f2 100644 --- a/grub-core/kern/ieee1275/init.c +++ b/grub-core/kern/ieee1275/init.c @@ -166,7 +166,7 @@ heap_init (grub_uint64_t addr, grub_uint64_t len, grub_memory_type_t type, { unsigned long *total = data; - if (type != 1) + if (type != GRUB_MEMORY_AVAILABLE) return 0; if (grub_ieee1275_test_flag (GRUB_IEEE1275_FLAG_NO_PRE1_5M_CLAIM)) diff --git a/grub-core/kern/mips/dl.c b/grub-core/kern/mips/dl.c index 8c057e01d..e320a4ee7 100644 --- a/grub-core/kern/mips/dl.c +++ b/grub-core/kern/mips/dl.c @@ -138,6 +138,10 @@ grub_arch_dl_relocate_symbols (grub_dl_t mod, void *ehdr, sym = (Elf_Sym *) ((char *) mod->symtab + mod->symsize * ELF_R_SYM (rel->r_info)); sym_value = sym->st_value; + if (s->sh_type == SHT_RELA) + { + sym_value += ((Elf_Rela *) rel)->r_addend; + } if (sym_value == (grub_addr_t) &__gnu_local_gp_dummy) sym_value = (grub_addr_t) mod->got; else if (sym_value == (grub_addr_t) &_gp_disp_dummy) diff --git a/grub-core/kern/mips/startup.S b/grub-core/kern/mips/startup.S index 339ab337e..1fdb58aca 100644 --- a/grub-core/kern/mips/startup.S +++ b/grub-core/kern/mips/startup.S @@ -22,6 +22,7 @@ #include #include #include +#include #define BASE_ADDR 8 @@ -95,8 +96,8 @@ cont: modulesmovcont: beq $t3, $0, modulesmovdone nop - lb $t4, 0($t2) - sb $t4, 0($t1) + lb GRUB_ASM_T4, 0($t2) + sb GRUB_ASM_T4, 0($t1) addiu $t2, $t2, -1 addiu $t1, $t1, -1 b modulesmovcont diff --git a/grub-core/kern/parser.c b/grub-core/kern/parser.c index b9bd12352..78175aac2 100644 --- a/grub-core/kern/parser.c +++ b/grub-core/kern/parser.c @@ -268,6 +268,7 @@ grub_parser_execute (char *source) grub_parser_execute_getline (&line, 0, &source); grub_rescue_parse_line (line, grub_parser_execute_getline, &source); grub_free (line); + grub_print_error (); } return grub_errno; diff --git a/grub-core/lib/crypto.c b/grub-core/lib/crypto.c index 010e550d1..683a8aaa7 100644 --- a/grub-core/lib/crypto.c +++ b/grub-core/lib/crypto.c @@ -470,7 +470,8 @@ grub_password_get (char buf[], unsigned buf_size) if (key == '\b') { - cur_len--; + if (cur_len) + cur_len--; continue; } diff --git a/grub-core/lib/fdt.c b/grub-core/lib/fdt.c index 7e76dc06b..b5d520f20 100644 --- a/grub-core/lib/fdt.c +++ b/grub-core/lib/fdt.c @@ -19,6 +19,9 @@ #include #include #include +#include + +GRUB_MOD_LICENSE ("GPLv3+"); #define FDT_SUPPORTED_VERSION 17 diff --git a/grub-core/lib/mips/setjmp.S b/grub-core/lib/mips/setjmp.S index f01294518..895235b78 100644 --- a/grub-core/lib/mips/setjmp.S +++ b/grub-core/lib/mips/setjmp.S @@ -18,6 +18,7 @@ #include #include +#include .file "setjmp.S" @@ -29,40 +30,42 @@ GRUB_MOD_LICENSE "GPLv3+" * int grub_setjmp (grub_jmp_buf env) */ FUNCTION(grub_setjmp) - sw $s0, 0($a0) - sw $s1, 4($a0) - sw $s2, 8($a0) - sw $s3, 12($a0) - sw $s4, 16($a0) - sw $s5, 20($a0) - sw $s6, 24($a0) - sw $s7, 28($a0) - sw $s8, 32($a0) - sw $gp, 36($a0) - sw $sp, 40($a0) - sw $ra, 44($a0) + GRUB_ASM_REG_S $s0, 0($a0) + GRUB_ASM_REG_S $s1, 8($a0) + GRUB_ASM_REG_S $s2, 16($a0) + GRUB_ASM_REG_S $s3, 24($a0) + GRUB_ASM_REG_S $s4, 32($a0) + GRUB_ASM_REG_S $s5, 40($a0) + GRUB_ASM_REG_S $s6, 48($a0) + GRUB_ASM_REG_S $s7, 56($a0) + GRUB_ASM_REG_S $s8, 64($a0) + GRUB_ASM_REG_S $gp, 72($a0) + GRUB_ASM_REG_S $sp, 80($a0) + GRUB_ASM_REG_S $ra, 88($a0) move $v0, $zero move $v1, $zero jr $ra + nop /* * int grub_longjmp (grub_jmp_buf env, int val) */ FUNCTION(grub_longjmp) - lw $s0, 0($a0) - lw $s1, 4($a0) - lw $s2, 8($a0) - lw $s3, 12($a0) - lw $s4, 16($a0) - lw $s5, 20($a0) - lw $s6, 24($a0) - lw $s7, 28($a0) - lw $s8, 32($a0) - lw $gp, 36($a0) - lw $sp, 40($a0) - lw $ra, 44($a0) + GRUB_ASM_REG_L $s0, 0($a0) + GRUB_ASM_REG_L $s1, 8($a0) + GRUB_ASM_REG_L $s2, 16($a0) + GRUB_ASM_REG_L $s3, 24($a0) + GRUB_ASM_REG_L $s4, 32($a0) + GRUB_ASM_REG_L $s5, 40($a0) + GRUB_ASM_REG_L $s6, 48($a0) + GRUB_ASM_REG_L $s7, 56($a0) + GRUB_ASM_REG_L $s8, 64($a0) + GRUB_ASM_REG_L $gp, 72($a0) + GRUB_ASM_REG_L $sp, 80($a0) + GRUB_ASM_REG_L $ra, 88($a0) move $v0, $a1 bne $v0, $zero, 1f addiu $v0, $v0, 1 1: move $v1, $zero jr $ra + nop diff --git a/grub-core/lib/progress.c b/grub-core/lib/progress.c index 63a0767d6..95a4a6281 100644 --- a/grub-core/lib/progress.c +++ b/grub-core/lib/progress.c @@ -23,6 +23,7 @@ #include #include #include +#include GRUB_MOD_LICENSE ("GPLv3+"); @@ -70,7 +71,15 @@ grub_file_progress_hook_real (grub_disk_addr_t sector __attribute__ ((unused)), percent = grub_divmod64 (100 * file->progress_offset, file->size, 0); - partial_file_name = grub_strrchr (file->name, '/'); + /* grub_net_fs_open() saves off partial file structure before name is initialized. + It already saves passed file name in net structure so just use it in this case. + */ + if (file->device->net) + partial_file_name = grub_strrchr (file->device->net->name, '/'); + else if (file->name) /* grub_file_open() may leave it as NULL */ + partial_file_name = grub_strrchr (file->name, '/'); + else + partial_file_name = NULL; if (partial_file_name) partial_file_name++; else diff --git a/grub-core/loader/arm64/fdt.c b/grub-core/loader/arm64/fdt.c new file mode 100644 index 000000000..5202c14e0 --- /dev/null +++ b/grub-core/loader/arm64/fdt.c @@ -0,0 +1,185 @@ +/* + * GRUB -- GRand Unified Bootloader + * Copyright (C) 2013-2015 Free Software Foundation, Inc. + * + * GRUB is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * GRUB is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GRUB. If not, see . + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +static void *loaded_fdt; +static void *fdt; + +static void * +get_firmware_fdt (void) +{ + grub_efi_configuration_table_t *tables; + grub_efi_guid_t fdt_guid = GRUB_EFI_DEVICE_TREE_GUID; + void *firmware_fdt = NULL; + unsigned int i; + + /* Look for FDT in UEFI config tables. */ + tables = grub_efi_system_table->configuration_table; + + for (i = 0; i < grub_efi_system_table->num_table_entries; i++) + if (grub_memcmp (&tables[i].vendor_guid, &fdt_guid, sizeof (fdt_guid)) == 0) + { + firmware_fdt = tables[i].vendor_table; + grub_dprintf ("linux", "found registered FDT @ %p\n", firmware_fdt); + break; + } + + return firmware_fdt; +} + +void * +grub_fdt_load (grub_size_t additional_size) +{ + void *raw_fdt; + grub_size_t size; + + if (fdt) + { + size = GRUB_EFI_BYTES_TO_PAGES (grub_fdt_get_totalsize (fdt)); + grub_efi_free_pages ((grub_efi_physical_address_t) fdt, size); + } + + if (loaded_fdt) + raw_fdt = loaded_fdt; + else + raw_fdt = get_firmware_fdt(); + + size = + raw_fdt ? grub_fdt_get_totalsize (raw_fdt) : GRUB_FDT_EMPTY_TREE_SZ; + size += additional_size; + + grub_dprintf ("linux", "allocating %ld bytes for fdt\n", size); + fdt = grub_efi_allocate_pages (0, GRUB_EFI_BYTES_TO_PAGES (size)); + if (!fdt) + return NULL; + + if (raw_fdt) + { + grub_memmove (fdt, raw_fdt, size); + grub_fdt_set_totalsize (fdt, size); + } + else + { + grub_fdt_create_empty_tree (fdt, size); + } + return fdt; +} + +grub_err_t +grub_fdt_install (void) +{ + grub_efi_boot_services_t *b; + grub_efi_guid_t fdt_guid = GRUB_EFI_DEVICE_TREE_GUID; + grub_efi_status_t status; + + b = grub_efi_system_table->boot_services; + status = b->install_configuration_table (&fdt_guid, fdt); + if (status != GRUB_EFI_SUCCESS) + return grub_error (GRUB_ERR_IO, "failed to install FDT"); + + grub_dprintf ("fdt", "Installed/updated FDT configuration table @ %p\n", + fdt); + return GRUB_ERR_NONE; +} + +void +grub_fdt_unload (void) { + if (!fdt) { + return; + } + grub_efi_free_pages ((grub_efi_physical_address_t) fdt, + GRUB_EFI_BYTES_TO_PAGES (grub_fdt_get_totalsize (fdt))); + fdt = NULL; +} + +static grub_err_t +grub_cmd_devicetree (grub_command_t cmd __attribute__ ((unused)), + int argc, char *argv[]) +{ + grub_file_t dtb; + void *blob = NULL; + int size; + + if (loaded_fdt) + grub_free (loaded_fdt); + loaded_fdt = NULL; + + /* No arguments means "use firmware FDT". */ + if (argc == 0) + { + return GRUB_ERR_NONE; + } + + dtb = grub_file_open (argv[0]); + if (!dtb) + goto out; + + size = grub_file_size (dtb); + blob = grub_malloc (size); + if (!blob) + goto out; + + if (grub_file_read (dtb, blob, size) < size) + { + if (!grub_errno) + grub_error (GRUB_ERR_BAD_OS, N_("premature end of file %s"), argv[0]); + goto out; + } + + if (grub_fdt_check_header (blob, size) != 0) + { + grub_error (GRUB_ERR_BAD_OS, N_("invalid device tree")); + goto out; + } + +out: + if (dtb) + grub_file_close (dtb); + + if (blob) + { + if (grub_errno == GRUB_ERR_NONE) + loaded_fdt = blob; + else + grub_free (blob); + } + + return grub_errno; +} + +static grub_command_t cmd_devicetree; + +GRUB_MOD_INIT (fdt) +{ + cmd_devicetree = + grub_register_command ("devicetree", grub_cmd_devicetree, 0, + N_("Load DTB file.")); +} + +GRUB_MOD_FINI (fdt) +{ + grub_unregister_command (cmd_devicetree); +} diff --git a/grub-core/loader/arm64/linux.c b/grub-core/loader/arm64/linux.c index 987f5b9ee..9519d2e4d 100644 --- a/grub-core/loader/arm64/linux.c +++ b/grub-core/loader/arm64/linux.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -45,69 +46,6 @@ static grub_uint32_t cmdline_size; static grub_addr_t initrd_start; static grub_addr_t initrd_end; -static void *loaded_fdt; -static void *fdt; - -static void * -get_firmware_fdt (void) -{ - grub_efi_configuration_table_t *tables; - grub_efi_guid_t fdt_guid = GRUB_EFI_DEVICE_TREE_GUID; - void *firmware_fdt = NULL; - unsigned int i; - - /* Look for FDT in UEFI config tables. */ - tables = grub_efi_system_table->configuration_table; - - for (i = 0; i < grub_efi_system_table->num_table_entries; i++) - if (grub_memcmp (&tables[i].vendor_guid, &fdt_guid, sizeof (fdt_guid)) == 0) - { - firmware_fdt = tables[i].vendor_table; - grub_dprintf ("linux", "found registered FDT @ %p\n", firmware_fdt); - break; - } - - return firmware_fdt; -} - -void * -grub_linux_get_fdt (void) -{ - void *raw_fdt; - grub_size_t size; - - if (fdt) - { - size = BYTES_TO_PAGES (grub_fdt_get_totalsize (fdt)); - grub_efi_free_pages ((grub_efi_physical_address_t) fdt, size); - } - - if (loaded_fdt) - raw_fdt = loaded_fdt; - else - raw_fdt = get_firmware_fdt(); - - size = - raw_fdt ? grub_fdt_get_totalsize (raw_fdt) : GRUB_FDT_EMPTY_TREE_SZ; - size += 0x400; - - grub_dprintf ("linux", "allocating %ld bytes for fdt\n", size); - fdt = grub_efi_allocate_pages (0, BYTES_TO_PAGES (size)); - if (!fdt) - return NULL; - - if (raw_fdt) - { - grub_memmove (fdt, raw_fdt, size); - grub_fdt_set_totalsize (fdt, size); - } - else - { - grub_fdt_create_empty_tree (fdt, size); - } - return fdt; -} - grub_err_t grub_arm64_uefi_check_image (struct grub_arm64_linux_kernel_header * lh) { @@ -129,12 +67,13 @@ grub_arm64_uefi_check_image (struct grub_arm64_linux_kernel_header * lh) static grub_err_t finalize_params_linux (void) { - grub_efi_boot_services_t *b; - grub_efi_guid_t fdt_guid = GRUB_EFI_DEVICE_TREE_GUID; - grub_efi_status_t status; int node, retval; - if (!grub_linux_get_fdt ()) + void *fdt; + + fdt = grub_fdt_load (0x400); + + if (!fdt) goto failure; node = grub_fdt_find_subnode (fdt, 0, "chosen"); @@ -160,82 +99,16 @@ finalize_params_linux (void) goto failure; } - b = grub_efi_system_table->boot_services; - status = b->install_configuration_table (&fdt_guid, fdt); - if (status != GRUB_EFI_SUCCESS) + if (grub_fdt_install() != GRUB_ERR_NONE) goto failure; - grub_dprintf ("linux", "Installed/updated FDT configuration table @ %p\n", - fdt); - return GRUB_ERR_NONE; failure: - grub_efi_free_pages ((grub_efi_physical_address_t) fdt, - BYTES_TO_PAGES (grub_fdt_get_totalsize (fdt))); - fdt = NULL; + grub_fdt_unload(); return grub_error(GRUB_ERR_BAD_OS, "failed to install/update FDT"); } -static grub_err_t -grub_cmd_devicetree (grub_command_t cmd __attribute__ ((unused)), - int argc, char *argv[]) -{ - grub_file_t dtb; - void *blob = NULL; - int size; - - if (!loaded) - { - grub_error (GRUB_ERR_BAD_ARGUMENT, - N_("you need to load the kernel first")); - return GRUB_ERR_BAD_OS; - } - - if (argc != 1) - return grub_error (GRUB_ERR_BAD_ARGUMENT, N_("filename expected")); - - if (loaded_fdt) - grub_free (loaded_fdt); - loaded_fdt = NULL; - - dtb = grub_file_open (argv[0]); - if (!dtb) - goto out; - - size = grub_file_size (dtb); - blob = grub_malloc (size); - if (!blob) - goto out; - - if (grub_file_read (dtb, blob, size) < size) - { - if (!grub_errno) - grub_error (GRUB_ERR_BAD_OS, N_("premature end of file %s"), argv[0]); - goto out; - } - - if (grub_fdt_check_header (blob, size) != 0) - { - grub_error (GRUB_ERR_BAD_OS, N_("invalid device tree")); - goto out; - } - -out: - if (dtb) - grub_file_close (dtb); - - if (blob) - { - if (grub_errno == GRUB_ERR_NONE) - loaded_fdt = blob; - else - grub_free (blob); - } - - return grub_errno; -} - grub_err_t grub_arm64_uefi_boot_image (grub_addr_t addr, grub_size_t size, char *args) { @@ -276,7 +149,7 @@ grub_arm64_uefi_boot_image (grub_addr_t addr, grub_size_t size, char *args) (grub_strlen (args) + 1) * sizeof (grub_efi_char16_t); loaded_image->load_options = grub_efi_allocate_pages (0, - BYTES_TO_PAGES (loaded_image->load_options_size)); + GRUB_EFI_BYTES_TO_PAGES (loaded_image->load_options_size)); if (!loaded_image->load_options) return grub_errno; @@ -290,7 +163,7 @@ grub_arm64_uefi_boot_image (grub_addr_t addr, grub_size_t size, char *args) /* When successful, not reached */ b->unload_image (image_handle); grub_efi_free_pages ((grub_efi_physical_address_t) loaded_image->load_options, - BYTES_TO_PAGES (loaded_image->load_options_size)); + GRUB_EFI_BYTES_TO_PAGES (loaded_image->load_options_size)); return grub_errno; } @@ -312,16 +185,13 @@ grub_linux_unload (void) loaded = 0; if (initrd_start) grub_efi_free_pages ((grub_efi_physical_address_t) initrd_start, - BYTES_TO_PAGES (initrd_end - initrd_start)); + GRUB_EFI_BYTES_TO_PAGES (initrd_end - initrd_start)); initrd_start = initrd_end = 0; grub_free (linux_args); if (kernel_addr) grub_efi_free_pages ((grub_efi_physical_address_t) kernel_addr, - BYTES_TO_PAGES (kernel_size)); - if (fdt) - grub_efi_free_pages ((grub_efi_physical_address_t) fdt, - BYTES_TO_PAGES (grub_fdt_get_totalsize (fdt))); - + GRUB_EFI_BYTES_TO_PAGES (kernel_size)); + grub_fdt_unload (); return GRUB_ERR_NONE; } @@ -352,7 +222,7 @@ grub_cmd_initrd (grub_command_t cmd __attribute__ ((unused)), initrd_size = grub_get_initrd_size (&initrd_ctx); grub_dprintf ("linux", "Loading initrd\n"); - initrd_pages = (BYTES_TO_PAGES (initrd_size)); + initrd_pages = (GRUB_EFI_BYTES_TO_PAGES (initrd_size)); initrd_mem = grub_efi_allocate_pages (0, initrd_pages); if (!initrd_mem) { @@ -407,9 +277,9 @@ grub_cmd_linux (grub_command_t cmd __attribute__ ((unused)), grub_loader_unset(); grub_dprintf ("linux", "kernel file size: %lld\n", (long long) kernel_size); - kernel_addr = grub_efi_allocate_pages (0, BYTES_TO_PAGES (kernel_size)); + kernel_addr = grub_efi_allocate_pages (0, GRUB_EFI_BYTES_TO_PAGES (kernel_size)); grub_dprintf ("linux", "kernel numpages: %lld\n", - (long long) BYTES_TO_PAGES (kernel_size)); + (long long) GRUB_EFI_BYTES_TO_PAGES (kernel_size)); if (!kernel_addr) { grub_error (GRUB_ERR_OUT_OF_MEMORY, N_("out of memory")); @@ -460,13 +330,13 @@ fail: if (kernel_addr && !loaded) grub_efi_free_pages ((grub_efi_physical_address_t) kernel_addr, - BYTES_TO_PAGES (kernel_size)); + GRUB_EFI_BYTES_TO_PAGES (kernel_size)); return grub_errno; } -static grub_command_t cmd_linux, cmd_initrd, cmd_devicetree; +static grub_command_t cmd_linux, cmd_initrd; GRUB_MOD_INIT (linux) { @@ -474,9 +344,6 @@ GRUB_MOD_INIT (linux) N_("Load Linux.")); cmd_initrd = grub_register_command ("initrd", grub_cmd_initrd, 0, N_("Load initrd.")); - cmd_devicetree = - grub_register_command ("devicetree", grub_cmd_devicetree, 0, - N_("Load DTB file.")); my_mod = mod; } @@ -484,5 +351,4 @@ GRUB_MOD_FINI (linux) { grub_unregister_command (cmd_linux); grub_unregister_command (cmd_initrd); - grub_unregister_command (cmd_devicetree); } diff --git a/grub-core/loader/arm64/xen_boot.c b/grub-core/loader/arm64/xen_boot.c new file mode 100644 index 000000000..d1a218929 --- /dev/null +++ b/grub-core/loader/arm64/xen_boot.c @@ -0,0 +1,587 @@ +/* + * GRUB -- GRand Unified Bootloader + * Copyright (C) 2014 Free Software Foundation, Inc. + * + * GRUB is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * GRUB is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GRUB. If not, see . + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include /* required by struct xen_hypervisor_header */ +#include +#include + +GRUB_MOD_LICENSE ("GPLv3+"); + +#define XEN_HYPERVISOR_NAME "xen_hypervisor" + +#define MODULE_DEFAULT_ALIGN (0x0) +#define MODULE_IMAGE_MIN_ALIGN MODULE_DEFAULT_ALIGN +#define MODULE_INITRD_MIN_ALIGN MODULE_DEFAULT_ALIGN +#define MODULE_XSM_MIN_ALIGN MODULE_DEFAULT_ALIGN +#define MODULE_CUSTOM_MIN_ALIGN MODULE_DEFAULT_ALIGN + +#define MODULE_IMAGE_COMPATIBLE "multiboot,kernel\0multiboot,module" +#define MODULE_INITRD_COMPATIBLE "multiboot,ramdisk\0multiboot,module" +#define MODULE_XSM_COMPATIBLE "xen,xsm-policy\0multiboot,module" +#define MODULE_CUSTOM_COMPATIBLE "multiboot,module" + +/* This maximum size is defined in Power.org ePAPR V1.1 + * https://www.power.org/documentation/epapr-version-1-1/ + * 2.2.1.1 Node Name Requirements + * node-name@unit-address + * 31 + 1(@) + 16(64bit address in hex format) + 1(\0) = 49 + */ +#define FDT_NODE_NAME_MAX_SIZE (49) + +struct compat_string_struct +{ + grub_size_t size; + const char *compat_string; +}; +typedef struct compat_string_struct compat_string_struct_t; +#define FDT_COMPATIBLE(x) {.size = sizeof(x), .compat_string = (x)} + +enum module_type +{ + MODULE_IMAGE, + MODULE_INITRD, + MODULE_XSM, + MODULE_CUSTOM +}; +typedef enum module_type module_type_t; + +struct fdt_node_info +{ + module_type_t type; + + const char *compat_string; + grub_size_t compat_string_size; +}; + +struct xen_hypervisor_header +{ + struct grub_arm64_linux_kernel_header efi_head; + + /* This is always PE\0\0. */ + grub_uint8_t signature[GRUB_PE32_SIGNATURE_SIZE]; + /* The COFF file header. */ + struct grub_pe32_coff_header coff_header; + /* The Optional header. */ + struct grub_pe64_optional_header optional_header; +}; + +struct xen_boot_binary +{ + struct xen_boot_binary *next; + struct xen_boot_binary **prev; + const char *name; + + grub_addr_t start; + grub_size_t size; + grub_size_t align; + + char *cmdline; + int cmdline_size; + + struct fdt_node_info node_info; +}; + +static grub_dl_t my_mod; + +static int loaded; + +static struct xen_boot_binary *xen_hypervisor; +static struct xen_boot_binary *module_head; +static const grub_size_t module_default_align[] = { + MODULE_IMAGE_MIN_ALIGN, + MODULE_INITRD_MIN_ALIGN, + MODULE_XSM_MIN_ALIGN, + MODULE_CUSTOM_MIN_ALIGN +}; + +static const compat_string_struct_t default_compat_string[] = { + FDT_COMPATIBLE (MODULE_IMAGE_COMPATIBLE), + FDT_COMPATIBLE (MODULE_INITRD_COMPATIBLE), + FDT_COMPATIBLE (MODULE_XSM_COMPATIBLE), + FDT_COMPATIBLE (MODULE_CUSTOM_COMPATIBLE) +}; + +static __inline grub_addr_t +xen_boot_address_align (grub_addr_t start, grub_size_t align) +{ + return (align ? (ALIGN_UP (start, align)) : start); +} + +/* set module type according to command name. */ +static grub_err_t +set_module_type (grub_command_t cmd, struct xen_boot_binary *module) +{ + if (!grub_strcmp (cmd->name, "xen_linux")) + module->node_info.type = MODULE_IMAGE; + else if (!grub_strcmp (cmd->name, "xen_initrd")) + module->node_info.type = MODULE_INITRD; + else if (!grub_strcmp (cmd->name, "xen_xsm")) + module->node_info.type = MODULE_XSM; + + return GRUB_ERR_NONE; +} + +static grub_err_t +prepare_xen_hypervisor_params (void *xen_boot_fdt) +{ + int chosen_node = 0; + int retval; + + chosen_node = grub_fdt_find_subnode (xen_boot_fdt, 0, "chosen"); + if (chosen_node < 0) + chosen_node = grub_fdt_add_subnode (xen_boot_fdt, 0, "chosen"); + if (chosen_node < 1) + return grub_error (GRUB_ERR_IO, "failed to get chosen node in FDT"); + + grub_dprintf ("xen_loader", + "Xen Hypervisor cmdline : %s @ %p size:%d\n", + xen_hypervisor->cmdline, xen_hypervisor->cmdline, + xen_hypervisor->cmdline_size); + + retval = grub_fdt_set_prop (xen_boot_fdt, chosen_node, "bootargs", + xen_hypervisor->cmdline, + xen_hypervisor->cmdline_size); + if (retval) + return grub_error (GRUB_ERR_IO, "failed to install/update FDT"); + + return GRUB_ERR_NONE; +} + +static grub_err_t +prepare_xen_module_params (struct xen_boot_binary *module, void *xen_boot_fdt) +{ + int retval, chosen_node = 0, module_node = 0; + char module_name[FDT_NODE_NAME_MAX_SIZE]; + + retval = grub_snprintf (module_name, FDT_NODE_NAME_MAX_SIZE, "module@%lx", + xen_boot_address_align (module->start, + module->align)); + grub_dprintf ("xen_loader", "Module node name %s \n", module_name); + + if (retval < (int) sizeof ("module@")) + return grub_error (GRUB_ERR_IO, N_("failed to get FDT")); + + chosen_node = grub_fdt_find_subnode (xen_boot_fdt, 0, "chosen"); + if (chosen_node < 0) + chosen_node = grub_fdt_add_subnode (xen_boot_fdt, 0, "chosen"); + if (chosen_node < 1) + return grub_error (GRUB_ERR_IO, "failed to get chosen node in FDT"); + + module_node = + grub_fdt_find_subnode (xen_boot_fdt, chosen_node, module_name); + if (module_node < 0) + module_node = + grub_fdt_add_subnode (xen_boot_fdt, chosen_node, module_name); + + retval = grub_fdt_set_prop (xen_boot_fdt, module_node, "compatible", + module->node_info.compat_string, + (grub_uint32_t) module-> + node_info.compat_string_size); + if (retval) + return grub_error (GRUB_ERR_IO, "failed to update FDT"); + + grub_dprintf ("xen_loader", "Module %s compatible = %s size = 0x%lx\n", + module->name, module->node_info.compat_string, + module->node_info.compat_string_size); + + retval = grub_fdt_set_reg64 (xen_boot_fdt, module_node, + xen_boot_address_align (module->start, + module->align), + module->size); + if (retval) + return grub_error (GRUB_ERR_IO, "failed to update FDT"); + + if (module->cmdline && module->cmdline_size > 0) + { + grub_dprintf ("xen_loader", + "Module %s cmdline : %s @ %p size:%d\n", module->name, + module->cmdline, module->cmdline, module->cmdline_size); + + retval = grub_fdt_set_prop (xen_boot_fdt, module_node, "bootargs", + module->cmdline, module->cmdline_size + 1); + if (retval) + return grub_error (GRUB_ERR_IO, "failed to update FDT"); + } + else + { + grub_dprintf ("xen_loader", "Module %s has not bootargs!\n", + module->name); + } + + return GRUB_ERR_NONE; +} + +static grub_err_t +finalize_params_xen_boot (void) +{ + struct xen_boot_binary *module; + void *xen_boot_fdt; + grub_size_t additional_size = 0x1000; + + /* Hypervisor. */ + additional_size += FDT_NODE_NAME_MAX_SIZE + xen_hypervisor->cmdline_size; + FOR_LIST_ELEMENTS (module, module_head) + { + additional_size += 6 * FDT_NODE_NAME_MAX_SIZE + module-> + node_info.compat_string_size + module->cmdline_size; + } + + xen_boot_fdt = grub_fdt_load (additional_size); + if (!xen_boot_fdt) + return grub_error (GRUB_ERR_IO, "failed to get FDT"); + + if (xen_hypervisor) + { + if (prepare_xen_hypervisor_params (xen_boot_fdt) != GRUB_ERR_NONE) + goto fail; + } + else + { + grub_dprintf ("xen_loader", "Failed to get Xen Hypervisor info!\n"); + goto fail; + } + + /* Set module params info */ + FOR_LIST_ELEMENTS (module, module_head) + { + if (module->start && module->size > 0) + { + grub_dprintf ("xen_loader", "Module %s @ 0x%lx size:0x%lx\n", + module->name, + xen_boot_address_align (module->start, module->align), + module->size); + if (prepare_xen_module_params (module, xen_boot_fdt) != GRUB_ERR_NONE) + goto fail; + } + else + { + grub_dprintf ("xen_loader", "Module info error: %s!\n", module->name); + goto fail; + } + } + + if (grub_fdt_install() == GRUB_ERR_NONE) + return GRUB_ERR_NONE; + +fail: + grub_fdt_unload (); + + return grub_error (GRUB_ERR_IO, "failed to install/update FDT"); +} + + +static grub_err_t +xen_boot (void) +{ + grub_err_t err = finalize_params_xen_boot (); + if (err) + return err; + + return grub_arm64_uefi_boot_image (xen_hypervisor->start, + xen_hypervisor->size, + xen_hypervisor->cmdline); +} + +static void +single_binary_unload (struct xen_boot_binary *binary) +{ + if (!binary) + return; + + if (binary->start && binary->size > 0) + { + grub_efi_free_pages ((grub_efi_physical_address_t) binary->start, + GRUB_EFI_BYTES_TO_PAGES (binary->size + binary->align)); + } + + if (binary->cmdline && binary->cmdline_size > 0) + { + grub_free (binary->cmdline); + grub_dprintf ("xen_loader", + "Module %s cmdline memory free @ %p size: %d\n", + binary->name, binary->cmdline, binary->cmdline_size); + } + + if (binary->node_info.type == MODULE_CUSTOM) + grub_free ((void *) binary->node_info.compat_string); + + if (grub_strcmp (binary->name, XEN_HYPERVISOR_NAME)) + grub_list_remove (GRUB_AS_LIST (binary)); + + grub_dprintf ("xen_loader", + "Module %s struct memory free @ %p size: 0x%lx\n", + binary->name, binary, sizeof (binary)); + grub_free (binary); + + return; +} + +static void +all_binaries_unload (void) +{ + struct xen_boot_binary *binary; + + FOR_LIST_ELEMENTS (binary, module_head) + { + single_binary_unload (binary); + } + + if (xen_hypervisor) + single_binary_unload (xen_hypervisor); + + return; +} + +static grub_err_t +xen_unload (void) +{ + loaded = 0; + all_binaries_unload (); + grub_fdt_unload (); + grub_dl_unref (my_mod); + + return GRUB_ERR_NONE; +} + +static void +xen_boot_binary_load (struct xen_boot_binary *binary, grub_file_t file, + int argc, char *argv[]) +{ + binary->size = grub_file_size (file); + grub_dprintf ("xen_loader", "Xen_boot %s file size: 0x%lx\n", + binary->name, binary->size); + + binary->start + = (grub_addr_t) grub_efi_allocate_pages (0, + GRUB_EFI_BYTES_TO_PAGES + (binary->size + + binary->align)); + if (!binary->start) + { + grub_error (GRUB_ERR_OUT_OF_MEMORY, N_("out of memory")); + return; + } + + grub_dprintf ("xen_loader", "Xen_boot %s numpages: 0x%lx\n", + binary->name, GRUB_EFI_BYTES_TO_PAGES (binary->size + binary->align)); + + if (grub_file_read (file, (void *) xen_boot_address_align (binary->start, + binary->align), + binary->size) != (grub_ssize_t) binary->size) + { + single_binary_unload (binary); + grub_error (GRUB_ERR_BAD_OS, N_("premature end of file %s"), argv[0]); + return; + } + + if (argc > 1) + { + binary->cmdline_size = grub_loader_cmdline_size (argc - 1, argv + 1); + binary->cmdline = grub_zalloc (binary->cmdline_size); + if (!binary->cmdline) + { + single_binary_unload (binary); + grub_error (GRUB_ERR_OUT_OF_MEMORY, N_("out of memory")); + return; + } + grub_create_loader_cmdline (argc - 1, argv + 1, binary->cmdline, + binary->cmdline_size); + grub_dprintf ("xen_loader", + "Xen_boot %s cmdline @ %p %s, size: %d\n", binary->name, + binary->cmdline, binary->cmdline, binary->cmdline_size); + } + else + { + binary->cmdline_size = 0; + binary->cmdline = NULL; + } + + grub_errno = GRUB_ERR_NONE; + return; +} + +static grub_err_t +grub_cmd_xen_module (grub_command_t cmd, int argc, char *argv[]) +{ + + struct xen_boot_binary *module = NULL; + grub_file_t file = 0; + + if (!argc) + { + grub_error (GRUB_ERR_BAD_ARGUMENT, N_("filename expected")); + goto fail; + } + + if (!loaded) + { + grub_error (GRUB_ERR_BAD_ARGUMENT, + N_("you need to load the Xen Hypervisor first")); + goto fail; + } + + module = + (struct xen_boot_binary *) grub_zalloc (sizeof (struct xen_boot_binary)); + if (!module) + return grub_errno; + + /* process all the options and get module type */ + if (set_module_type (cmd, module) != GRUB_ERR_NONE) + goto fail; + switch (module->node_info.type) + { + case MODULE_IMAGE: + case MODULE_INITRD: + case MODULE_XSM: + module->node_info.compat_string = + default_compat_string[module->node_info.type].compat_string; + module->node_info.compat_string_size = + default_compat_string[module->node_info.type].size; + break; + + case MODULE_CUSTOM: + /* we have set the node_info in set_module_type */ + break; + + default: + return grub_error (GRUB_ERR_BAD_ARGUMENT, N_("invalid argument")); + } + module->name = module->node_info.compat_string; + module->align = module_default_align[module->node_info.type]; + + grub_dprintf ("xen_loader", "Init %s module and node info:\n" + "compatible %s\ncompat_string_size 0x%lx\n", + module->name, module->node_info.compat_string, + module->node_info.compat_string_size); + + file = grub_file_open (argv[0]); + if (!file) + goto fail; + + xen_boot_binary_load (module, file, argc, argv); + if (grub_errno == GRUB_ERR_NONE) + grub_list_push (GRUB_AS_LIST_P (&module_head), GRUB_AS_LIST (module)); + +fail: + if (file) + grub_file_close (file); + if (grub_errno != GRUB_ERR_NONE) + single_binary_unload (module); + + return grub_errno; +} + +static grub_err_t +grub_cmd_xen_hypervisor (grub_command_t cmd __attribute__ ((unused)), + int argc, char *argv[]) +{ + struct xen_hypervisor_header sh; + grub_file_t file = NULL; + + grub_dl_ref (my_mod); + + if (!argc) + { + grub_error (GRUB_ERR_BAD_ARGUMENT, N_("filename expected")); + goto fail; + } + + file = grub_file_open (argv[0]); + if (!file) + goto fail; + + if (grub_file_read (file, &sh, sizeof (sh)) != (long) sizeof (sh)) + goto fail; + if (grub_arm64_uefi_check_image + ((struct grub_arm64_linux_kernel_header *) &sh) != GRUB_ERR_NONE) + goto fail; + grub_file_seek (file, 0); + + /* if another module has called grub_loader_set, + we need to make sure that another module is unloaded properly */ + grub_loader_unset (); + + xen_hypervisor = + (struct xen_boot_binary *) grub_zalloc (sizeof (struct xen_boot_binary)); + if (!xen_hypervisor) + return grub_errno; + + xen_hypervisor->name = XEN_HYPERVISOR_NAME; + xen_hypervisor->align = (grub_size_t) sh.optional_header.section_alignment; + + xen_boot_binary_load (xen_hypervisor, file, argc, argv); + if (grub_errno == GRUB_ERR_NONE) + { + grub_loader_set (xen_boot, xen_unload, 0); + loaded = 1; + } + +fail: + if (file) + grub_file_close (file); + if (grub_errno != GRUB_ERR_NONE) + { + loaded = 0; + all_binaries_unload (); + grub_dl_unref (my_mod); + } + + return grub_errno; +} + +static grub_command_t cmd_xen_hypervisor; +static grub_command_t cmd_xen_linux, cmd_xen_initrd, cmd_xen_xsm; + +GRUB_MOD_INIT (xen_boot) +{ + cmd_xen_hypervisor = + grub_register_command ("xen_hypervisor", grub_cmd_xen_hypervisor, 0, + N_("Load a xen hypervisor.")); + cmd_xen_linux = + grub_register_command ("xen_linux", grub_cmd_xen_module, 0, + N_("Load a xen linux kernel for dom0.")); + cmd_xen_initrd = + grub_register_command ("xen_initrd", grub_cmd_xen_module, 0, + N_("Load a xen initrd for dom0.")); + cmd_xen_xsm = + grub_register_command ("xen_xsm", grub_cmd_xen_module, 0, + N_("Load a xen security module.")); + my_mod = mod; +} + +GRUB_MOD_FINI (xen_boot) +{ + grub_unregister_command (cmd_xen_hypervisor); + grub_unregister_command (cmd_xen_linux); + grub_unregister_command (cmd_xen_initrd); + grub_unregister_command (cmd_xen_xsm); +} diff --git a/grub-core/loader/i386/multiboot_mbi.c b/grub-core/loader/i386/multiboot_mbi.c index 956d0e37b..f60b70234 100644 --- a/grub-core/loader/i386/multiboot_mbi.c +++ b/grub-core/loader/i386/multiboot_mbi.c @@ -73,6 +73,9 @@ load_kernel (grub_file_t file, const char *filename, if (grub_multiboot_quirks & GRUB_MULTIBOOT_QUIRK_BAD_KLUDGE) { err = grub_multiboot_load_elf (file, filename, buffer); + if (err == GRUB_ERR_NONE) { + return GRUB_ERR_NONE; + } if (err == GRUB_ERR_UNKNOWN_OS && (header->flags & MULTIBOOT_AOUT_KLUDGE)) grub_errno = err = GRUB_ERR_NONE; } diff --git a/grub-core/loader/multiboot.c b/grub-core/loader/multiboot.c index fd8f28e21..73aa0aa12 100644 --- a/grub-core/loader/multiboot.c +++ b/grub-core/loader/multiboot.c @@ -240,20 +240,27 @@ grub_cmd_multiboot (grub_command_t cmd __attribute__ ((unused)), #ifndef GRUB_USE_MULTIBOOT2 grub_multiboot_quirks = GRUB_MULTIBOOT_QUIRKS_NONE; + int option_found = 0; - if (argc != 0 && grub_strcmp (argv[0], "--quirk-bad-kludge") == 0) + do { - argc--; - argv++; - grub_multiboot_quirks |= GRUB_MULTIBOOT_QUIRK_BAD_KLUDGE; - } + option_found = 0; + if (argc != 0 && grub_strcmp (argv[0], "--quirk-bad-kludge") == 0) + { + argc--; + argv++; + option_found = 1; + grub_multiboot_quirks |= GRUB_MULTIBOOT_QUIRK_BAD_KLUDGE; + } - if (argc != 0 && grub_strcmp (argv[0], "--quirk-modules-after-kernel") == 0) - { - argc--; - argv++; - grub_multiboot_quirks |= GRUB_MULTIBOOT_QUIRK_MODULES_AFTER_KERNEL; - } + if (argc != 0 && grub_strcmp (argv[0], "--quirk-modules-after-kernel") == 0) + { + argc--; + argv++; + option_found = 1; + grub_multiboot_quirks |= GRUB_MULTIBOOT_QUIRK_MODULES_AFTER_KERNEL; + } + } while (option_found); #endif if (argc == 0) diff --git a/grub-core/loader/sparc64/ieee1275/linux.c b/grub-core/loader/sparc64/ieee1275/linux.c index 63d6a1f33..346d9538e 100644 --- a/grub-core/loader/sparc64/ieee1275/linux.c +++ b/grub-core/loader/sparc64/ieee1275/linux.c @@ -196,7 +196,7 @@ alloc_phys_choose (grub_uint64_t addr, grub_uint64_t len, struct alloc_phys_ctx *ctx = data; grub_addr_t end = addr + len; - if (type != 1) + if (type != GRUB_MEMORY_AVAILABLE) return 0; addr = ALIGN_UP (addr, FOUR_MB); @@ -430,7 +430,7 @@ static int get_physbase (grub_uint64_t addr, grub_uint64_t len __attribute__ ((unused)), grub_memory_type_t type, void *data __attribute__ ((unused))) { - if (type != 1) + if (type != GRUB_MEMORY_AVAILABLE) return 0; if (addr < phys_base) phys_base = addr; diff --git a/grub-core/mmap/efi/mmap.c b/grub-core/mmap/efi/mmap.c index a77efe81d..bd495a184 100644 --- a/grub-core/mmap/efi/mmap.c +++ b/grub-core/mmap/efi/mmap.c @@ -73,6 +73,7 @@ grub_efi_mmap_iterate (grub_memory_hook_t hook, void *hook_data, GRUB_MEMORY_AVAILABLE, hook_data); break; } + /* FALLTHROUGH */ case GRUB_EFI_RUNTIME_SERVICES_CODE: hook (desc->physical_start, desc->num_pages * 4096, GRUB_MEMORY_CODE, hook_data); @@ -83,10 +84,6 @@ grub_efi_mmap_iterate (grub_memory_hook_t hook, void *hook_data, GRUB_MEMORY_BADRAM, hook_data); break; - default: - grub_printf ("Unknown memory type %d, considering reserved\n", - desc->type); - case GRUB_EFI_BOOT_SERVICES_DATA: if (!avoid_efi_boot_services) { @@ -94,6 +91,7 @@ grub_efi_mmap_iterate (grub_memory_hook_t hook, void *hook_data, GRUB_MEMORY_AVAILABLE, hook_data); break; } + /* FALLTHROUGH */ case GRUB_EFI_RESERVED_MEMORY_TYPE: case GRUB_EFI_RUNTIME_SERVICES_DATA: case GRUB_EFI_MEMORY_MAPPED_IO: @@ -119,6 +117,18 @@ grub_efi_mmap_iterate (grub_memory_hook_t hook, void *hook_data, hook (desc->physical_start, desc->num_pages * 4096, GRUB_MEMORY_NVS, hook_data); break; + + case GRUB_EFI_PERSISTENT_MEMORY: + hook (desc->physical_start, desc->num_pages * 4096, + GRUB_MEMORY_PERSISTENT, hook_data); + break; + + default: + grub_printf ("Unknown memory type %d, considering reserved\n", + desc->type); + hook (desc->physical_start, desc->num_pages * 4096, + GRUB_MEMORY_RESERVED, hook_data); + break; } } @@ -142,6 +152,13 @@ make_efi_memtype (int type) /* No way to remove a chunk of memory from EFI mmap. So mark it as unusable. */ case GRUB_MEMORY_HOLE: + /* + * AllocatePages() does not support GRUB_EFI_PERSISTENT_MEMORY, + * so no translation for GRUB_MEMORY_PERSISTENT or + * GRUB_MEMORY_PERSISTENT_LEGACY. + */ + case GRUB_MEMORY_PERSISTENT: + case GRUB_MEMORY_PERSISTENT_LEGACY: case GRUB_MEMORY_RESERVED: return GRUB_EFI_UNUSABLE_MEMORY; diff --git a/grub-core/net/dns.c b/grub-core/net/dns.c index 9d0c8fcea..89741dd7d 100644 --- a/grub-core/net/dns.c +++ b/grub-core/net/dns.c @@ -437,7 +437,7 @@ grub_net_dns_lookup (const char *name, struct recv_data data = {naddresses, addresses, cache, grub_cpu_to_be16 (id++), 0, 0, name, 0}; grub_uint8_t *nbd; - int have_server = 0; + grub_size_t try_server = 0; if (!servers) { @@ -543,38 +543,35 @@ grub_net_dns_lookup (const char *name, for (i = 0; i < n_servers * 4; i++) { /* Connect to a next server. */ - while (!(i & 1) && send_servers < n_servers) + while (!(i & 1) && try_server < n_servers) { - sockets[send_servers] = grub_net_udp_open (servers[send_servers], + sockets[send_servers] = grub_net_udp_open (servers[try_server++], DNS_PORT, recv_hook, &data); - send_servers++; - if (!sockets[send_servers - 1]) + if (!sockets[send_servers]) { err = grub_errno; grub_errno = GRUB_ERR_NONE; } else { - have_server = 1; + send_servers++; break; } } - if (!have_server) + if (!send_servers) goto out; if (*data.naddresses) goto out; for (j = 0; j < send_servers; j++) { grub_err_t err2; - if (!sockets[j]) - continue; - nb->data = nbd; grub_size_t t = 0; do { + nb->data = nbd; if (servers[j].option == DNS_OPTION_IPV4 || ((servers[j].option == DNS_OPTION_PREFER_IPV4) && (t++ == 0)) || ((servers[j].option == DNS_OPTION_PREFER_IPV6) && (t++ == 1))) diff --git a/grub-core/net/drivers/efi/efinet.c b/grub-core/net/drivers/efi/efinet.c index 70b26af94..5388f952b 100644 --- a/grub-core/net/drivers/efi/efinet.c +++ b/grub-core/net/drivers/efi/efinet.c @@ -47,19 +47,19 @@ send_card_buffer (struct grub_net_card *dev, if (st != GRUB_EFI_SUCCESS) return grub_error (GRUB_ERR_IO, N_("couldn't send network packet")); - if (txbuf == dev->txbuf) + /* + Some buggy firmware could return an arbitrary address instead of the + txbuf address we trasmitted, so just check that txbuf is non NULL + for success. This is ok because we open the SNP protocol in + exclusive mode so we know we're the only ones transmitting on this + box and since we only transmit one packet at a time we know our + transmit was successfull. + */ + if (txbuf) { dev->txbusy = 0; break; } - if (txbuf) - { - st = efi_call_7 (net->transmit, net, 0, dev->last_pkt_size, - dev->txbuf, NULL, NULL, NULL); - if (st != GRUB_EFI_SUCCESS) - return grub_error (GRUB_ERR_IO, - N_("couldn't send network packet")); - } if (limit_time < grub_get_time_ms ()) return grub_error (GRUB_ERR_TIMEOUT, N_("couldn't send network packet")); @@ -84,8 +84,9 @@ send_card_buffer (struct grub_net_card *dev, we run in the GRUB_ERR_TIMEOUT case above. Perhaps a timeout in the FW has discarded the recycle buffer. */ + txbuf = NULL; st = efi_call_3 (net->get_status, net, 0, &txbuf); - dev->txbusy = !(st == GRUB_EFI_SUCCESS && txbuf == dev->txbuf); + dev->txbusy = !(st == GRUB_EFI_SUCCESS && txbuf); return GRUB_ERR_NONE; } diff --git a/grub-core/net/drivers/ieee1275/ofnet.c b/grub-core/net/drivers/ieee1275/ofnet.c index eea8e71d3..eff9085ed 100644 --- a/grub-core/net/drivers/ieee1275/ofnet.c +++ b/grub-core/net/drivers/ieee1275/ofnet.c @@ -305,6 +305,7 @@ search_net_devices (struct grub_ieee1275_devalias *alias) grub_uint64_t prop; grub_uint8_t *pprop; char *shortname; + char need_suffix = 1; if (grub_strcmp (alias->type, "network") != 0) return 0; @@ -325,7 +326,43 @@ search_net_devices (struct grub_ieee1275_devalias *alias) #define SUFFIX ":speed=auto,duplex=auto,1.1.1.1,dummy,1.1.1.1,1.1.1.1,5,5,1.1.1.1,512" - if (!grub_ieee1275_test_flag (GRUB_IEEE1275_FLAG_NO_OFNET_SUFFIX)) + if (grub_ieee1275_test_flag (GRUB_IEEE1275_FLAG_NO_OFNET_SUFFIX)) + need_suffix = 0; + + /* sun4v vnet devices do not support setting duplex/speed */ + { + char *ptr; + + grub_ieee1275_finddevice (alias->path, &devhandle); + + grub_ieee1275_get_property_length (devhandle, "compatible", &prop_size); + if (prop_size > 0) + { + pprop = grub_malloc (prop_size); + if (!pprop) + { + grub_free (card); + grub_free (ofdata); + grub_print_error (); + return 1; + } + + if (!grub_ieee1275_get_property (devhandle, "compatible", + pprop, prop_size, NULL)) + { + for (ptr = (char *) pprop; ptr - (char *) pprop < prop_size; + ptr += grub_strlen (ptr) + 1) + { + if (!grub_strcmp(ptr, "SUNW,sun4v-network")) + need_suffix = 0; + } + } + + grub_free (pprop); + } + } + + if (need_suffix) ofdata->path = grub_malloc (grub_strlen (alias->path) + sizeof (SUFFIX)); else ofdata->path = grub_malloc (grub_strlen (alias->path) + 1); @@ -335,7 +372,7 @@ search_net_devices (struct grub_ieee1275_devalias *alias) return 0; } ofdata->suffix = grub_stpcpy (ofdata->path, alias->path); - if (!grub_ieee1275_test_flag (GRUB_IEEE1275_FLAG_NO_OFNET_SUFFIX)) + if (need_suffix) grub_memcpy (ofdata->suffix, SUFFIX, sizeof (SUFFIX)); else *ofdata->suffix = '\0'; diff --git a/grub-core/net/net.c b/grub-core/net/net.c index 21a4e94d1..a0472d5d4 100644 --- a/grub-core/net/net.c +++ b/grub-core/net/net.c @@ -1341,6 +1341,43 @@ grub_net_open_real (const char *name) } if (try == 0) { + const char *prefix, *root; + char *prefdev, *comma; + int skip = 0; + grub_size_t devlen; + + /* Do not attempt to load module if it requires protocol provided + by this module - it results in infinite recursion. Just continue, + fail and cleanup on next iteration. + */ + prefix = grub_env_get ("prefix"); + if (!prefix) + continue; + + prefdev = grub_file_get_device_name (prefix); + if (!prefdev) + { + root = grub_env_get ("root"); + if (!root) + continue; + prefdev = grub_strdup (root); + if (!prefdev) + continue; + } + + comma = grub_strchr (prefdev, ','); + if (comma) + *comma = '\0'; + devlen = grub_strlen (prefdev); + + if (protnamelen == devlen && grub_memcmp (prefdev, protname, devlen) == 0) + skip = 1; + + grub_free (prefdev); + + if (skip) + continue; + if (sizeof ("http") - 1 == protnamelen && grub_memcmp ("http", protname, protnamelen) == 0) { diff --git a/grub-core/net/tcp.c b/grub-core/net/tcp.c index 1d90f1ec5..576f68498 100644 --- a/grub-core/net/tcp.c +++ b/grub-core/net/tcp.c @@ -498,11 +498,22 @@ grub_net_tcp_accept (grub_net_tcp_socket_t sock, struct grub_net_buff *nb_ack; struct tcphdr *tcph; grub_err_t err; + grub_net_network_level_address_t gateway; + struct grub_net_network_level_interface *inf; sock->recv_hook = recv_hook; sock->error_hook = error_hook; sock->fin_hook = fin_hook; sock->hook_data = hook_data; + + err = grub_net_route_address (sock->out_nla, &gateway, &inf); + if (err) + return err; + + err = grub_net_link_layer_resolve (sock->inf, &gateway, &(sock->ll_target_addr)); + if (err) + return err; + nb_ack = grub_netbuff_alloc (sizeof (*tcph) + GRUB_NET_OUR_MAX_IP_HEADER_SIZE + GRUB_NET_MAX_LINK_HEADER_SIZE); @@ -882,7 +893,10 @@ grub_net_recv_tcp_packet (struct grub_net_buff *nb, grub_priority_queue_pop (sock->pq); } if (grub_be_to_cpu32 (tcph->seqnr) != sock->their_cur_seq) - return GRUB_ERR_NONE; + { + ack (sock); + return GRUB_ERR_NONE; + } while (1) { nb_top_p = grub_priority_queue_top (sock->pq); diff --git a/grub-core/normal/auth.c b/grub-core/normal/auth.c index c6bd96e28..7338f8245 100644 --- a/grub-core/normal/auth.c +++ b/grub-core/normal/auth.c @@ -174,8 +174,11 @@ grub_username_get (char buf[], unsigned buf_size) if (key == '\b') { - cur_len--; - grub_printf ("\b"); + if (cur_len) + { + cur_len--; + grub_printf ("\b \b"); + } continue; } diff --git a/grub-core/osdep/devmapper/getroot.c b/grub-core/osdep/devmapper/getroot.c index 0a77a04b9..64419f678 100644 --- a/grub-core/osdep/devmapper/getroot.c +++ b/grub-core/osdep/devmapper/getroot.c @@ -208,8 +208,7 @@ grub_util_devmapper_part_to_disk (struct stat *st, &major, &minor, 0)) { *is_part = 1; - return grub_find_device ("/dev", - (major << 8) | minor); + return grub_find_device ("/dev", makedev (major, minor)); } *is_part = 0; return xstrdup (path); diff --git a/grub-core/osdep/unix/getroot.c b/grub-core/osdep/unix/getroot.c index 14d483fb1..1079a919d 100644 --- a/grub-core/osdep/unix/getroot.c +++ b/grub-core/osdep/unix/getroot.c @@ -45,12 +45,6 @@ #ifdef __linux__ #include /* ioctl */ #include -#ifndef MAJOR -# ifndef MINORBITS -# define MINORBITS 8 -# endif /* ! MINORBITS */ -# define MAJOR(dev) ((unsigned) ((dev) >> MINORBITS)) -#endif /* ! MAJOR */ #ifndef FLOPPY_MAJOR # define FLOPPY_MAJOR 2 #endif /* ! FLOPPY_MAJOR */ @@ -73,7 +67,6 @@ #include #if defined(__FreeBSD__) || defined(__FreeBSD_kernel__) -# define MAJOR(dev) major(dev) # define FLOPPY_MAJOR 2 #endif @@ -90,7 +83,6 @@ #endif /* defined(__NetBSD__) || defined(__FreeBSD__) || defined(__FreeBSD_kernel__) */ #if defined(__NetBSD__) || defined(__OpenBSD__) -# define MAJOR(dev) major(dev) # ifdef HAVE_GETRAWPARTITION # include /* getrawpartition */ # endif /* HAVE_GETRAWPARTITION */ diff --git a/grub-core/osdep/unix/password.c b/grub-core/osdep/unix/password.c index 4b9507bce..9996b244b 100644 --- a/grub-core/osdep/unix/password.c +++ b/grub-core/osdep/unix/password.c @@ -54,7 +54,8 @@ grub_password_get (char buf[], unsigned buf_size) grub_memset (buf, 0, buf_size); if (!fgets (buf, buf_size, stdin)) { - fclose (in); + if (in != stdin) + fclose (in); return 0; } ptr = buf + strlen (buf) - 1; @@ -67,7 +68,8 @@ grub_password_get (char buf[], unsigned buf_size) grub_xputs ("\n"); grub_refresh (); - fclose (in); + if (in != stdin) + fclose (in); return 1; } diff --git a/grub-core/partmap/msdos.c b/grub-core/partmap/msdos.c index 46c406bff..6d4b455a1 100644 --- a/grub-core/partmap/msdos.c +++ b/grub-core/partmap/msdos.c @@ -249,7 +249,7 @@ pc_partition_map_embed (struct grub_disk *disk, unsigned int *nsectors, if (embed_type != GRUB_EMBED_PCBIOS) return grub_error (GRUB_ERR_NOT_IMPLEMENTED_YET, - "PC-style partitions curently support " + "PC-style partitions currently support " "only PC-BIOS embedding"); if (disk->partition) diff --git a/grub-core/term/efi/console.c b/grub-core/term/efi/console.c index a37eb841c..7d31095b1 100644 --- a/grub-core/term/efi/console.c +++ b/grub-core/term/efi/console.c @@ -104,26 +104,12 @@ const unsigned efi_codes[] = GRUB_TERM_KEY_DC, GRUB_TERM_KEY_PPAGE, GRUB_TERM_KEY_NPAGE, GRUB_TERM_KEY_F1, GRUB_TERM_KEY_F2, GRUB_TERM_KEY_F3, GRUB_TERM_KEY_F4, GRUB_TERM_KEY_F5, GRUB_TERM_KEY_F6, GRUB_TERM_KEY_F7, GRUB_TERM_KEY_F8, GRUB_TERM_KEY_F9, - GRUB_TERM_KEY_F10, 0, 0, '\e' + GRUB_TERM_KEY_F10, GRUB_TERM_KEY_F11, GRUB_TERM_KEY_F12, '\e' }; - static int -grub_console_getkey (struct grub_term_input *term __attribute__ ((unused))) +grub_efi_translate_key (grub_efi_input_key_t key) { - grub_efi_simple_input_interface_t *i; - grub_efi_input_key_t key; - grub_efi_status_t status; - - if (grub_efi_is_finished) - return 0; - - i = grub_efi_system_table->con_in; - status = efi_call_2 (i->read_key_stroke, i, &key); - - if (status != GRUB_EFI_SUCCESS) - return GRUB_TERM_NO_KEY; - if (key.scan_code == 0) { /* Some firmware implementations use VT100-style codes against the spec. @@ -139,9 +125,100 @@ grub_console_getkey (struct grub_term_input *term __attribute__ ((unused))) else if (key.scan_code < ARRAY_SIZE (efi_codes)) return efi_codes[key.scan_code]; + if ((key.unicode_char >= 0x20 && key.unicode_char <= 0x7f) + || key.unicode_char == '\t' || key.unicode_char == '\b' + || key.unicode_char == '\n' || key.unicode_char == '\r') + return key.unicode_char; + return GRUB_TERM_NO_KEY; } +static int +grub_console_getkey_con (struct grub_term_input *term __attribute__ ((unused))) +{ + grub_efi_simple_input_interface_t *i; + grub_efi_input_key_t key; + grub_efi_status_t status; + + i = grub_efi_system_table->con_in; + status = efi_call_2 (i->read_key_stroke, i, &key); + + if (status != GRUB_EFI_SUCCESS) + return GRUB_TERM_NO_KEY; + + return grub_efi_translate_key(key); +} + +static int +grub_console_getkey_ex(struct grub_term_input *term) +{ + grub_efi_key_data_t key_data; + grub_efi_status_t status; + grub_efi_uint32_t kss; + int key = -1; + + grub_efi_simple_text_input_ex_interface_t *text_input = term->data; + + status = efi_call_2 (text_input->read_key_stroke, text_input, &key_data); + + if (status != GRUB_EFI_SUCCESS) + return GRUB_TERM_NO_KEY; + + kss = key_data.key_state.key_shift_state; + key = grub_efi_translate_key(key_data.key); + + if (key == GRUB_TERM_NO_KEY) + return GRUB_TERM_NO_KEY; + + if (kss & GRUB_EFI_SHIFT_STATE_VALID) + { + if ((kss & GRUB_EFI_LEFT_SHIFT_PRESSED + || kss & GRUB_EFI_RIGHT_SHIFT_PRESSED) + && (key & GRUB_TERM_EXTENDED)) + key |= GRUB_TERM_SHIFT; + if (kss & GRUB_EFI_LEFT_ALT_PRESSED || kss & GRUB_EFI_RIGHT_ALT_PRESSED) + key |= GRUB_TERM_ALT; + if (kss & GRUB_EFI_LEFT_CONTROL_PRESSED + || kss & GRUB_EFI_RIGHT_CONTROL_PRESSED) + key |= GRUB_TERM_CTRL; + } + + return key; +} + +static grub_err_t +grub_efi_console_input_init (struct grub_term_input *term) +{ + grub_efi_guid_t text_input_ex_guid = + GRUB_EFI_SIMPLE_TEXT_INPUT_EX_PROTOCOL_GUID; + + if (grub_efi_is_finished) + return 0; + + grub_efi_simple_text_input_ex_interface_t *text_input = term->data; + if (text_input) + return 0; + + text_input = grub_efi_open_protocol(grub_efi_system_table->console_in_handler, + &text_input_ex_guid, + GRUB_EFI_OPEN_PROTOCOL_GET_PROTOCOL); + term->data = (void *)text_input; + + return 0; +} + +static int +grub_console_getkey (struct grub_term_input *term) +{ + if (grub_efi_is_finished) + return 0; + + if (term->data) + return grub_console_getkey_ex(term); + else + return grub_console_getkey_con(term); +} + static struct grub_term_coordinate grub_console_getwh (struct grub_term_output *term __attribute__ ((unused))) { @@ -243,7 +320,7 @@ grub_console_setcursor (struct grub_term_output *term __attribute__ ((unused)), } static grub_err_t -grub_efi_console_init (struct grub_term_output *term) +grub_efi_console_output_init (struct grub_term_output *term) { grub_efi_set_text_mode (1); grub_console_setcursor (term, 1); @@ -251,7 +328,7 @@ grub_efi_console_init (struct grub_term_output *term) } static grub_err_t -grub_efi_console_fini (struct grub_term_output *term) +grub_efi_console_output_fini (struct grub_term_output *term) { grub_console_setcursor (term, 0); grub_efi_set_text_mode (0); @@ -262,13 +339,14 @@ static struct grub_term_input grub_console_term_input = { .name = "console", .getkey = grub_console_getkey, + .init = grub_efi_console_input_init, }; static struct grub_term_output grub_console_term_output = { .name = "console", - .init = grub_efi_console_init, - .fini = grub_efi_console_fini, + .init = grub_efi_console_output_init, + .fini = grub_efi_console_output_fini, .putchar = grub_console_putchar, .getwh = grub_console_getwh, .getxy = grub_console_getxy, @@ -291,8 +369,8 @@ grub_console_init (void) return; } - grub_term_register_input ("console", &grub_console_term_input); grub_term_register_output ("console", &grub_console_term_output); + grub_term_register_input ("console", &grub_console_term_input); } void diff --git a/include/grub/acpi.h b/include/grub/acpi.h index f6e6a11c5..8a8110241 100644 --- a/include/grub/acpi.h +++ b/include/grub/acpi.h @@ -67,10 +67,14 @@ struct grub_acpi_fadt grub_uint32_t dsdt_addr; grub_uint8_t somefields1[20]; grub_uint32_t pm1a; - grub_uint8_t somefields2[64]; + grub_uint8_t somefields2[8]; + grub_uint32_t pmtimer; + grub_uint8_t somefields3[32]; + grub_uint32_t flags; + grub_uint8_t somefields4[16]; grub_uint64_t facs_xaddr; grub_uint64_t dsdt_xaddr; - grub_uint8_t somefields3[96]; + grub_uint8_t somefields5[96]; } GRUB_PACKED; #define GRUB_ACPI_MADT_SIGNATURE "APIC" @@ -176,9 +180,9 @@ enum #ifndef GRUB_DSDT_TEST struct grub_acpi_rsdp_v10 *grub_acpi_get_rsdpv1 (void); struct grub_acpi_rsdp_v20 *grub_acpi_get_rsdpv2 (void); -struct grub_acpi_rsdp_v10 *grub_machine_acpi_get_rsdpv1 (void); -struct grub_acpi_rsdp_v20 *grub_machine_acpi_get_rsdpv2 (void); -grub_uint8_t grub_byte_checksum (void *base, grub_size_t size); +struct grub_acpi_rsdp_v10 *EXPORT_FUNC(grub_machine_acpi_get_rsdpv1) (void); +struct grub_acpi_rsdp_v20 *EXPORT_FUNC(grub_machine_acpi_get_rsdpv2) (void); +grub_uint8_t EXPORT_FUNC(grub_byte_checksum) (void *base, grub_size_t size); grub_err_t grub_acpi_create_ebda (void); @@ -234,4 +238,7 @@ enum GRUB_ACPI_EXTOPCODE_BANK_FIELD_OP = 0x87, }; +struct grub_acpi_fadt * +grub_acpi_find_fadt (void); + #endif /* ! GRUB_ACPI_HEADER */ diff --git a/include/grub/arm64/fdtload.h b/include/grub/arm64/fdtload.h new file mode 100644 index 000000000..7b9ddba91 --- /dev/null +++ b/include/grub/arm64/fdtload.h @@ -0,0 +1,35 @@ +/* + * GRUB -- GRand Unified Bootloader + * Copyright (C) 2013-2015 Free Software Foundation, Inc. + * + * GRUB is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 3 of the License, or + * (at your option) any later version. + * + * GRUB is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with GRUB. If not, see . + */ + +#ifndef GRUB_FDTLOAD_CPU_HEADER +#define GRUB_FDTLOAD_CPU_HEADER 1 + +#include +#include + +void * +grub_fdt_load (grub_size_t additional_size); +void +grub_fdt_unload (void); +grub_err_t +grub_fdt_install (void); + +#define GRUB_EFI_PAGE_SHIFT 12 +#define GRUB_EFI_BYTES_TO_PAGES(bytes) (((bytes) + 0xfff) >> GRUB_EFI_PAGE_SHIFT) + +#endif diff --git a/include/grub/arm64/linux.h b/include/grub/arm64/linux.h index 65796d907..1ea23696e 100644 --- a/include/grub/arm64/linux.h +++ b/include/grub/arm64/linux.h @@ -23,8 +23,6 @@ #define GRUB_ARM64_LINUX_MAGIC 0x644d5241 /* 'ARM\x64' */ -#define GRUB_EFI_PAGE_SHIFT 12 -#define BYTES_TO_PAGES(bytes) (((bytes) + 0xfff) >> GRUB_EFI_PAGE_SHIFT) #define GRUB_EFI_PE_MAGIC 0x5A4D /* From linux/Documentation/arm64/booting.txt */ @@ -42,8 +40,6 @@ struct grub_arm64_linux_kernel_header grub_uint32_t hdr_offset; /* Offset of PE/COFF header */ }; -/* Declare the functions for getting dtb and checking/booting image */ -void *grub_linux_get_fdt (void); grub_err_t grub_arm64_uefi_check_image (struct grub_arm64_linux_kernel_header *lh); grub_err_t grub_arm64_uefi_boot_image (grub_addr_t addr, grub_size_t size, diff --git a/include/grub/cryptodisk.h b/include/grub/cryptodisk.h index f2ad2a79a..32f564ae0 100644 --- a/include/grub/cryptodisk.h +++ b/include/grub/cryptodisk.h @@ -97,6 +97,7 @@ struct grub_cryptodisk grub_uint8_t rekey_key[64]; grub_uint64_t last_rekey; int rekey_derived_size; + grub_disk_addr_t partition_start; }; typedef struct grub_cryptodisk *grub_cryptodisk_t; diff --git a/include/grub/efi/api.h b/include/grub/efi/api.h index 1a5e38c1e..c7c9f0e1d 100644 --- a/include/grub/efi/api.h +++ b/include/grub/efi/api.h @@ -49,6 +49,9 @@ #define GRUB_EFI_MEMORY_WP 0x0000000000001000LL #define GRUB_EFI_MEMORY_RP 0x0000000000002000LL #define GRUB_EFI_MEMORY_XP 0x0000000000004000LL +#define GRUB_EFI_MEMORY_NV 0x0000000000008000LL +#define GRUB_EFI_MEMORY_MORE_RELIABLE 0x0000000000010000LL +#define GRUB_EFI_MEMORY_RO 0x0000000000020000LL #define GRUB_EFI_MEMORY_RUNTIME 0x8000000000000000LL #define GRUB_EFI_OPEN_PROTOCOL_BY_HANDLE_PROTOCOL 0x00000001 @@ -111,7 +114,7 @@ { 0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b } \ } -#define EFI_SIMPLE_TEXT_INPUT_EX_PROTOCOL_GUID \ +#define GRUB_EFI_SIMPLE_TEXT_INPUT_EX_PROTOCOL_GUID \ { 0xdd9e7534, 0x7762, 0x4698, \ { 0x8c, 0x14, 0xf5, 0x85, 0x17, 0xa6, 0x25, 0xaa } \ } @@ -246,6 +249,51 @@ { 0x8E, 0x8B, 0xBB, 0xA2, 0x0B, 0x1B, 0x5B, 0x75 } \ } +#define GRUB_EFI_TIANO_CUSTOM_DECOMPRESS_GUID \ + { 0xa31280ad, 0x481e, 0x41b6, \ + { 0x95, 0xe8, 0x12, 0x7f, 0x4c, 0x98, 0x47, 0x79 } \ + } + +#define GRUB_EFI_CRC32_GUIDED_SECTION_EXTRACTION_GUID \ + { 0xfc1bcdb0, 0x7d31, 0x49aa, \ + { 0x93, 0x6a, 0xa4, 0x60, 0x0d, 0x9d, 0xd0, 0x83 } \ + } + +#define GRUB_EFI_LZMA_CUSTOM_DECOMPRESS_GUID \ + { 0xee4e5898, 0x3914, 0x4259, \ + { 0x9d, 0x6e, 0xdc, 0x7b, 0xd7, 0x94, 0x03, 0xcf } \ + } + +#define GRUB_EFI_TSC_FREQUENCY_GUID \ + { 0xdba6a7e3, 0xbb57, 0x4be7, \ + { 0x8a, 0xf8, 0xd5, 0x78, 0xdb, 0x7e, 0x56, 0x87 } \ + } + +#define GRUB_EFI_SYSTEM_RESOURCE_TABLE_GUID \ + { 0xb122a263, 0x3661, 0x4f68, \ + { 0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80 } \ + } + +#define GRUB_EFI_DXE_SERVICES_TABLE_GUID \ + { 0x05ad34ba, 0x6f02, 0x4214, \ + { 0x95, 0x2e, 0x4d, 0xa0, 0x39, 0x8e, 0x2b, 0xb9 } \ + } + +#define GRUB_EFI_HOB_LIST_GUID \ + { 0x7739f24c, 0x93d7, 0x11d4, \ + { 0x9a, 0x3a, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d } \ + } + +#define GRUB_EFI_MEMORY_TYPE_INFORMATION_GUID \ + { 0x4c19049f, 0x4137, 0x4dd3, \ + { 0x9c, 0x10, 0x8b, 0x97, 0xa8, 0x3f, 0xfd, 0xfa } \ + } + +#define GRUB_EFI_DEBUG_IMAGE_INFO_TABLE_GUID \ + { 0x49152e77, 0x1ada, 0x4764, \ + { 0xb7, 0xa2, 0x7a, 0xfe, 0xfe, 0xd9, 0x5e, 0x8b } \ + } + #define GRUB_EFI_MPS_TABLE_GUID \ { 0xeb9d2d2f, 0x2d88, 0x11d3, \ { 0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d } \ @@ -431,6 +479,7 @@ enum grub_efi_memory_type GRUB_EFI_MEMORY_MAPPED_IO, GRUB_EFI_MEMORY_MAPPED_IO_PORT_SPACE, GRUB_EFI_PAL_CODE, + GRUB_EFI_PERSISTENT_MEMORY, GRUB_EFI_MAX_MEMORY_TYPE }; typedef enum grub_efi_memory_type grub_efi_memory_type_t; @@ -952,6 +1001,32 @@ struct grub_efi_input_key }; typedef struct grub_efi_input_key grub_efi_input_key_t; +typedef grub_efi_uint8_t grub_efi_key_toggle_state_t; +struct grub_efi_key_state +{ + grub_efi_uint32_t key_shift_state; + grub_efi_key_toggle_state_t key_toggle_state; +}; +typedef struct grub_efi_key_state grub_efi_key_state_t; + +#define GRUB_EFI_SHIFT_STATE_VALID 0x80000000 +#define GRUB_EFI_RIGHT_SHIFT_PRESSED 0x00000001 +#define GRUB_EFI_LEFT_SHIFT_PRESSED 0x00000002 +#define GRUB_EFI_RIGHT_CONTROL_PRESSED 0x00000004 +#define GRUB_EFI_LEFT_CONTROL_PRESSED 0x00000008 +#define GRUB_EFI_RIGHT_ALT_PRESSED 0x00000010 +#define GRUB_EFI_LEFT_ALT_PRESSED 0x00000020 +#define GRUB_EFI_RIGHT_LOGO_PRESSED 0x00000040 +#define GRUB_EFI_LEFT_LOGO_PRESSED 0x00000080 +#define GRUB_EFI_MENU_KEY_PRESSED 0x00000100 +#define GRUB_EFI_SYS_REQ_PRESSED 0x00000200 + +#define GRUB_EFI_TOGGLE_STATE_VALID 0x80 +#define GRUB_EFI_KEY_STATE_EXPOSED 0x40 +#define GRUB_EFI_SCROLL_LOCK_ACTIVE 0x01 +#define GRUB_EFI_NUM_LOCK_ACTIVE 0x02 +#define GRUB_EFI_CAPS_LOCK_ACTIVE 0x04 + struct grub_efi_simple_text_output_mode { grub_efi_int32_t max_mode; @@ -1294,6 +1369,43 @@ struct grub_efi_simple_input_interface }; typedef struct grub_efi_simple_input_interface grub_efi_simple_input_interface_t; +struct grub_efi_key_data { + grub_efi_input_key_t key; + grub_efi_key_state_t key_state; +}; +typedef struct grub_efi_key_data grub_efi_key_data_t; + +typedef grub_efi_status_t (*grub_efi_key_notify_function_t) ( + grub_efi_key_data_t *key_data + ); + +struct grub_efi_simple_text_input_ex_interface +{ + grub_efi_status_t + (*reset) (struct grub_efi_simple_text_input_ex_interface *this, + grub_efi_boolean_t extended_verification); + + grub_efi_status_t + (*read_key_stroke) (struct grub_efi_simple_text_input_ex_interface *this, + grub_efi_key_data_t *key_data); + + grub_efi_event_t wait_for_key; + + grub_efi_status_t + (*set_state) (struct grub_efi_simple_text_input_ex_interface *this, + grub_efi_key_toggle_state_t *key_toggle_state); + + grub_efi_status_t + (*register_key_notify) (struct grub_efi_simple_text_input_ex_interface *this, + grub_efi_key_data_t *key_data, + grub_efi_key_notify_function_t key_notification_function); + + grub_efi_status_t + (*unregister_key_notify) (struct grub_efi_simple_text_input_ex_interface *this, + void *notification_handle); +}; +typedef struct grub_efi_simple_text_input_ex_interface grub_efi_simple_text_input_ex_interface_t; + struct grub_efi_simple_text_output_interface { grub_efi_status_t diff --git a/include/grub/i386/tsc.h b/include/grub/i386/tsc.h index 71b32e6b8..71fa7ca2f 100644 --- a/include/grub/i386/tsc.h +++ b/include/grub/i386/tsc.h @@ -20,9 +20,35 @@ #define KERNEL_CPU_TSC_HEADER 1 #include +#include void grub_tsc_init (void); /* In ms per 2^32 ticks. */ extern grub_uint32_t EXPORT_VAR(grub_tsc_rate); +int +grub_tsc_calibrate_from_xen (void); +int +grub_tsc_calibrate_from_efi (void); +int +grub_tsc_calibrate_from_pmtimer (void); +int +grub_tsc_calibrate_from_pit (void); + +/* Read the TSC value, which increments with each CPU clock cycle. */ +static __inline grub_uint64_t +grub_get_tsc (void) +{ + grub_uint32_t lo, hi; + grub_uint32_t a,b,c,d; + + /* The CPUID instruction is a 'serializing' instruction, and + avoids out-of-order execution of the RDTSC instruction. */ + grub_cpuid (0,a,b,c,d); + /* Read TSC value. We cannot use "=A", since this would use + %rax on x86_64. */ + __asm__ __volatile__ ("rdtsc":"=a" (lo), "=d" (hi)); + + return (((grub_uint64_t) hi) << 32) | lo; +} #endif /* ! KERNEL_CPU_TSC_HEADER */ diff --git a/include/grub/memory.h b/include/grub/memory.h index 083cfb680..6da114a1b 100644 --- a/include/grub/memory.h +++ b/include/grub/memory.h @@ -30,6 +30,8 @@ typedef enum grub_memory_type GRUB_MEMORY_ACPI = 3, GRUB_MEMORY_NVS = 4, GRUB_MEMORY_BADRAM = 5, + GRUB_MEMORY_PERSISTENT = 7, + GRUB_MEMORY_PERSISTENT_LEGACY = 12, GRUB_MEMORY_COREBOOT_TABLES = 16, GRUB_MEMORY_CODE = 20, /* This one is special: it's used internally but is never reported diff --git a/include/grub/mips/asm.h b/include/grub/mips/asm.h new file mode 100644 index 000000000..4c397f4a0 --- /dev/null +++ b/include/grub/mips/asm.h @@ -0,0 +1,18 @@ +#ifndef GRUB_MIPS_ASM_HEADER +#define GRUB_MIPS_ASM_HEADER 1 + +#if defined(_MIPS_SIM) && defined(_ABIN32) && _MIPS_SIM == _ABIN32 +#define GRUB_ASM_T4 $a4 +#define GRUB_ASM_T5 $a5 +#define GRUB_ASM_SZREG 8 +#define GRUB_ASM_REG_S sd +#define GRUB_ASM_REG_L ld +#else +#define GRUB_ASM_T4 $t4 +#define GRUB_ASM_T5 $t5 +#define GRUB_ASM_SZREG 4 +#define GRUB_ASM_REG_S sw +#define GRUB_ASM_REG_L lw +#endif + +#endif diff --git a/include/grub/mips/setjmp.h b/include/grub/mips/setjmp.h index a99dde9ef..f8f6517ac 100644 --- a/include/grub/mips/setjmp.h +++ b/include/grub/mips/setjmp.h @@ -19,7 +19,7 @@ #ifndef GRUB_SETJMP_CPU_HEADER #define GRUB_SETJMP_CPU_HEADER 1 -typedef unsigned long grub_jmp_buf[12]; +typedef grub_uint64_t grub_jmp_buf[12]; int grub_setjmp (grub_jmp_buf env) RETURNS_TWICE; void grub_longjmp (grub_jmp_buf env, int val) __attribute__ ((noreturn)); diff --git a/include/grub/util/install.h b/include/grub/util/install.h index aedcd29f9..5ca4811cd 100644 --- a/include/grub/util/install.h +++ b/include/grub/util/install.h @@ -39,7 +39,7 @@ { "locales", GRUB_INSTALL_OPTIONS_INSTALL_LOCALES, N_("LOCALES"),\ 0, N_("install only LOCALES [default=all]"), 1 }, \ { "compress", GRUB_INSTALL_OPTIONS_INSTALL_COMPRESS, \ - "no,xz,gz,lzo", OPTION_ARG_OPTIONAL, \ + "no|xz|gz|lzo", 0, \ N_("compress GRUB files [optional]"), 1 }, \ {"core-compress", GRUB_INSTALL_OPTIONS_INSTALL_CORE_COMPRESS, \ "xz|none|auto", \ diff --git a/include/grub/xen.h b/include/grub/xen.h index 9ba3b8e6b..c31cc10c7 100644 --- a/include/grub/xen.h +++ b/include/grub/xen.h @@ -33,7 +33,12 @@ #include #ifndef GRUB_SYMBOL_GENERATOR -#include +typedef grub_int8_t int8_t; +typedef grub_int16_t int16_t; +typedef grub_uint8_t uint8_t; +typedef grub_uint16_t uint16_t; +typedef grub_uint32_t uint32_t; +typedef grub_uint64_t uint64_t; #include #include diff --git a/include/xen/arch-x86/xen-x86_32.h b/include/xen/arch-x86/xen-x86_32.h new file mode 100644 index 000000000..15041911e --- /dev/null +++ b/include/xen/arch-x86/xen-x86_32.h @@ -0,0 +1,171 @@ +/****************************************************************************** + * xen-x86_32.h + * + * Guest OS interface to x86 32-bit Xen. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2004-2007, K A Fraser + */ + +#ifndef __XEN_PUBLIC_ARCH_X86_XEN_X86_32_H__ +#define __XEN_PUBLIC_ARCH_X86_XEN_X86_32_H__ + +/* + * Hypercall interface: + * Input: %ebx, %ecx, %edx, %esi, %edi, %ebp (arguments 1-6) + * Output: %eax + * Access is via hypercall page (set up by guest loader or via a Xen MSR): + * call hypercall_page + hypercall-number * 32 + * Clobbered: Argument registers (e.g., 2-arg hypercall clobbers %ebx,%ecx) + */ + +/* + * These flat segments are in the Xen-private section of every GDT. Since these + * are also present in the initial GDT, many OSes will be able to avoid + * installing their own GDT. + */ +#define FLAT_RING1_CS 0xe019 /* GDT index 259 */ +#define FLAT_RING1_DS 0xe021 /* GDT index 260 */ +#define FLAT_RING1_SS 0xe021 /* GDT index 260 */ +#define FLAT_RING3_CS 0xe02b /* GDT index 261 */ +#define FLAT_RING3_DS 0xe033 /* GDT index 262 */ +#define FLAT_RING3_SS 0xe033 /* GDT index 262 */ + +#define FLAT_KERNEL_CS FLAT_RING1_CS +#define FLAT_KERNEL_DS FLAT_RING1_DS +#define FLAT_KERNEL_SS FLAT_RING1_SS +#define FLAT_USER_CS FLAT_RING3_CS +#define FLAT_USER_DS FLAT_RING3_DS +#define FLAT_USER_SS FLAT_RING3_SS + +#define __HYPERVISOR_VIRT_START_PAE 0xF5800000 +#define __MACH2PHYS_VIRT_START_PAE 0xF5800000 +#define __MACH2PHYS_VIRT_END_PAE 0xF6800000 +#define HYPERVISOR_VIRT_START_PAE \ + mk_unsigned_long(__HYPERVISOR_VIRT_START_PAE) +#define MACH2PHYS_VIRT_START_PAE \ + mk_unsigned_long(__MACH2PHYS_VIRT_START_PAE) +#define MACH2PHYS_VIRT_END_PAE \ + mk_unsigned_long(__MACH2PHYS_VIRT_END_PAE) + +/* Non-PAE bounds are obsolete. */ +#define __HYPERVISOR_VIRT_START_NONPAE 0xFC000000 +#define __MACH2PHYS_VIRT_START_NONPAE 0xFC000000 +#define __MACH2PHYS_VIRT_END_NONPAE 0xFC400000 +#define HYPERVISOR_VIRT_START_NONPAE \ + mk_unsigned_long(__HYPERVISOR_VIRT_START_NONPAE) +#define MACH2PHYS_VIRT_START_NONPAE \ + mk_unsigned_long(__MACH2PHYS_VIRT_START_NONPAE) +#define MACH2PHYS_VIRT_END_NONPAE \ + mk_unsigned_long(__MACH2PHYS_VIRT_END_NONPAE) + +#define __HYPERVISOR_VIRT_START __HYPERVISOR_VIRT_START_PAE +#define __MACH2PHYS_VIRT_START __MACH2PHYS_VIRT_START_PAE +#define __MACH2PHYS_VIRT_END __MACH2PHYS_VIRT_END_PAE + +#ifndef HYPERVISOR_VIRT_START +#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START) +#endif + +#define MACH2PHYS_VIRT_START mk_unsigned_long(__MACH2PHYS_VIRT_START) +#define MACH2PHYS_VIRT_END mk_unsigned_long(__MACH2PHYS_VIRT_END) +#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>2) +#ifndef machine_to_phys_mapping +#define machine_to_phys_mapping ((unsigned long *)MACH2PHYS_VIRT_START) +#endif + +/* 32-/64-bit invariability for control interfaces (domctl/sysctl). */ +#if defined(__XEN__) || defined(__XEN_TOOLS__) +#undef ___DEFINE_XEN_GUEST_HANDLE +#define ___DEFINE_XEN_GUEST_HANDLE(name, type) \ + typedef struct { type *p; } \ + __guest_handle_ ## name; \ + typedef struct { union { type *p; uint64_aligned_t q; }; } \ + __guest_handle_64_ ## name +#undef set_xen_guest_handle_raw +#define set_xen_guest_handle_raw(hnd, val) \ + do { if ( sizeof(hnd) == 8 ) *(uint64_t *)&(hnd) = 0; \ + (hnd).p = val; \ + } while ( 0 ) +#define uint64_aligned_t uint64_t __attribute__((aligned(8))) +#define __XEN_GUEST_HANDLE_64(name) __guest_handle_64_ ## name +#define XEN_GUEST_HANDLE_64(name) __XEN_GUEST_HANDLE_64(name) +#endif + +#ifndef __ASSEMBLY__ + +struct cpu_user_regs { + uint32_t ebx; + uint32_t ecx; + uint32_t edx; + uint32_t esi; + uint32_t edi; + uint32_t ebp; + uint32_t eax; + uint16_t error_code; /* private */ + uint16_t entry_vector; /* private */ + uint32_t eip; + uint16_t cs; + uint8_t saved_upcall_mask; + uint8_t _pad0; + uint32_t eflags; /* eflags.IF == !saved_upcall_mask */ + uint32_t esp; + uint16_t ss, _pad1; + uint16_t es, _pad2; + uint16_t ds, _pad3; + uint16_t fs, _pad4; + uint16_t gs, _pad5; +}; +typedef struct cpu_user_regs cpu_user_regs_t; +DEFINE_XEN_GUEST_HANDLE(cpu_user_regs_t); + +/* + * Page-directory addresses above 4GB do not fit into architectural %cr3. + * When accessing %cr3, or equivalent field in vcpu_guest_context, guests + * must use the following accessor macros to pack/unpack valid MFNs. + */ +#define xen_pfn_to_cr3(pfn) (((unsigned)(pfn) << 12) | ((unsigned)(pfn) >> 20)) +#define xen_cr3_to_pfn(cr3) (((unsigned)(cr3) >> 12) | ((unsigned)(cr3) << 20)) + +struct arch_vcpu_info { + unsigned long cr2; + unsigned long pad[5]; /* sizeof(vcpu_info_t) == 64 */ +}; +typedef struct arch_vcpu_info arch_vcpu_info_t; + +struct xen_callback { + unsigned long cs; + unsigned long eip; +}; +typedef struct xen_callback xen_callback_t; + +#endif /* !__ASSEMBLY__ */ + +#endif /* __XEN_PUBLIC_ARCH_X86_XEN_X86_32_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/arch-x86/xen-x86_64.h b/include/xen/arch-x86/xen-x86_64.h new file mode 100644 index 000000000..1c4e1590f --- /dev/null +++ b/include/xen/arch-x86/xen-x86_64.h @@ -0,0 +1,202 @@ +/****************************************************************************** + * xen-x86_64.h + * + * Guest OS interface to x86 64-bit Xen. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2004-2006, K A Fraser + */ + +#ifndef __XEN_PUBLIC_ARCH_X86_XEN_X86_64_H__ +#define __XEN_PUBLIC_ARCH_X86_XEN_X86_64_H__ + +/* + * Hypercall interface: + * Input: %rdi, %rsi, %rdx, %r10, %r8, %r9 (arguments 1-6) + * Output: %rax + * Access is via hypercall page (set up by guest loader or via a Xen MSR): + * call hypercall_page + hypercall-number * 32 + * Clobbered: argument registers (e.g., 2-arg hypercall clobbers %rdi,%rsi) + */ + +/* + * 64-bit segment selectors + * These flat segments are in the Xen-private section of every GDT. Since these + * are also present in the initial GDT, many OSes will be able to avoid + * installing their own GDT. + */ + +#define FLAT_RING3_CS32 0xe023 /* GDT index 260 */ +#define FLAT_RING3_CS64 0xe033 /* GDT index 261 */ +#define FLAT_RING3_DS32 0xe02b /* GDT index 262 */ +#define FLAT_RING3_DS64 0x0000 /* NULL selector */ +#define FLAT_RING3_SS32 0xe02b /* GDT index 262 */ +#define FLAT_RING3_SS64 0xe02b /* GDT index 262 */ + +#define FLAT_KERNEL_DS64 FLAT_RING3_DS64 +#define FLAT_KERNEL_DS32 FLAT_RING3_DS32 +#define FLAT_KERNEL_DS FLAT_KERNEL_DS64 +#define FLAT_KERNEL_CS64 FLAT_RING3_CS64 +#define FLAT_KERNEL_CS32 FLAT_RING3_CS32 +#define FLAT_KERNEL_CS FLAT_KERNEL_CS64 +#define FLAT_KERNEL_SS64 FLAT_RING3_SS64 +#define FLAT_KERNEL_SS32 FLAT_RING3_SS32 +#define FLAT_KERNEL_SS FLAT_KERNEL_SS64 + +#define FLAT_USER_DS64 FLAT_RING3_DS64 +#define FLAT_USER_DS32 FLAT_RING3_DS32 +#define FLAT_USER_DS FLAT_USER_DS64 +#define FLAT_USER_CS64 FLAT_RING3_CS64 +#define FLAT_USER_CS32 FLAT_RING3_CS32 +#define FLAT_USER_CS FLAT_USER_CS64 +#define FLAT_USER_SS64 FLAT_RING3_SS64 +#define FLAT_USER_SS32 FLAT_RING3_SS32 +#define FLAT_USER_SS FLAT_USER_SS64 + +#define __HYPERVISOR_VIRT_START 0xFFFF800000000000 +#define __HYPERVISOR_VIRT_END 0xFFFF880000000000 +#define __MACH2PHYS_VIRT_START 0xFFFF800000000000 +#define __MACH2PHYS_VIRT_END 0xFFFF804000000000 + +#ifndef HYPERVISOR_VIRT_START +#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START) +#define HYPERVISOR_VIRT_END mk_unsigned_long(__HYPERVISOR_VIRT_END) +#endif + +#define MACH2PHYS_VIRT_START mk_unsigned_long(__MACH2PHYS_VIRT_START) +#define MACH2PHYS_VIRT_END mk_unsigned_long(__MACH2PHYS_VIRT_END) +#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3) +#ifndef machine_to_phys_mapping +#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START) +#endif + +/* + * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base) + * @which == SEGBASE_* ; @base == 64-bit base address + * Returns 0 on success. + */ +#define SEGBASE_FS 0 +#define SEGBASE_GS_USER 1 +#define SEGBASE_GS_KERNEL 2 +#define SEGBASE_GS_USER_SEL 3 /* Set user %gs specified in base[15:0] */ + +/* + * int HYPERVISOR_iret(void) + * All arguments are on the kernel stack, in the following format. + * Never returns if successful. Current kernel context is lost. + * The saved CS is mapped as follows: + * RING0 -> RING3 kernel mode. + * RING1 -> RING3 kernel mode. + * RING2 -> RING3 kernel mode. + * RING3 -> RING3 user mode. + * However RING0 indicates that the guest kernel should return to iteself + * directly with + * orb $3,1*8(%rsp) + * iretq + * If flags contains VGCF_in_syscall: + * Restore RAX, RIP, RFLAGS, RSP. + * Discard R11, RCX, CS, SS. + * Otherwise: + * Restore RAX, R11, RCX, CS:RIP, RFLAGS, SS:RSP. + * All other registers are saved on hypercall entry and restored to user. + */ +/* Guest exited in SYSCALL context? Return to guest with SYSRET? */ +#define _VGCF_in_syscall 8 +#define VGCF_in_syscall (1<<_VGCF_in_syscall) +#define VGCF_IN_SYSCALL VGCF_in_syscall + +#ifndef __ASSEMBLY__ + +struct iret_context { + /* Top of stack (%rsp at point of hypercall). */ + uint64_t rax, r11, rcx, flags, rip, cs, rflags, rsp, ss; + /* Bottom of iret stack frame. */ +}; + +#if defined(__GNUC__) && !defined(__STRICT_ANSI__) +/* Anonymous union includes both 32- and 64-bit names (e.g., eax/rax). */ +#define __DECL_REG(name) union { \ + uint64_t r ## name, e ## name; \ + uint32_t _e ## name; \ +} +#else +/* Non-gcc sources must always use the proper 64-bit name (e.g., rax). */ +#define __DECL_REG(name) uint64_t r ## name +#endif + +struct cpu_user_regs { + uint64_t r15; + uint64_t r14; + uint64_t r13; + uint64_t r12; + __DECL_REG(bp); + __DECL_REG(bx); + uint64_t r11; + uint64_t r10; + uint64_t r9; + uint64_t r8; + __DECL_REG(ax); + __DECL_REG(cx); + __DECL_REG(dx); + __DECL_REG(si); + __DECL_REG(di); + uint32_t error_code; /* private */ + uint32_t entry_vector; /* private */ + __DECL_REG(ip); + uint16_t cs, _pad0[1]; + uint8_t saved_upcall_mask; + uint8_t _pad1[3]; + __DECL_REG(flags); /* rflags.IF == !saved_upcall_mask */ + __DECL_REG(sp); + uint16_t ss, _pad2[3]; + uint16_t es, _pad3[3]; + uint16_t ds, _pad4[3]; + uint16_t fs, _pad5[3]; /* Non-zero => takes precedence over fs_base. */ + uint16_t gs, _pad6[3]; /* Non-zero => takes precedence over gs_base_usr. */ +}; +typedef struct cpu_user_regs cpu_user_regs_t; +DEFINE_XEN_GUEST_HANDLE(cpu_user_regs_t); + +#undef __DECL_REG + +#define xen_pfn_to_cr3(pfn) ((unsigned long)(pfn) << 12) +#define xen_cr3_to_pfn(cr3) ((unsigned long)(cr3) >> 12) + +struct arch_vcpu_info { + unsigned long cr2; + unsigned long pad; /* sizeof(vcpu_info_t) == 64 */ +}; +typedef struct arch_vcpu_info arch_vcpu_info_t; + +typedef unsigned long xen_callback_t; + +#endif /* !__ASSEMBLY__ */ + +#endif /* __XEN_PUBLIC_ARCH_X86_XEN_X86_64_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/arch-x86/xen.h b/include/xen/arch-x86/xen.h new file mode 100644 index 000000000..f35804b88 --- /dev/null +++ b/include/xen/arch-x86/xen.h @@ -0,0 +1,273 @@ +/****************************************************************************** + * arch-x86/xen.h + * + * Guest OS interface to x86 Xen. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2004-2006, K A Fraser + */ + +#include "../xen.h" + +#ifndef __XEN_PUBLIC_ARCH_X86_XEN_H__ +#define __XEN_PUBLIC_ARCH_X86_XEN_H__ + +/* Structural guest handles introduced in 0x00030201. */ +#if __XEN_INTERFACE_VERSION__ >= 0x00030201 +#define ___DEFINE_XEN_GUEST_HANDLE(name, type) \ + typedef struct { type *p; } __guest_handle_ ## name +#else +#define ___DEFINE_XEN_GUEST_HANDLE(name, type) \ + typedef type * __guest_handle_ ## name +#endif + +/* + * XEN_GUEST_HANDLE represents a guest pointer, when passed as a field + * in a struct in memory. + * XEN_GUEST_HANDLE_PARAM represent a guest pointer, when passed as an + * hypercall argument. + * XEN_GUEST_HANDLE_PARAM and XEN_GUEST_HANDLE are the same on X86 but + * they might not be on other architectures. + */ +#define __DEFINE_XEN_GUEST_HANDLE(name, type) \ + ___DEFINE_XEN_GUEST_HANDLE(name, type); \ + ___DEFINE_XEN_GUEST_HANDLE(const_##name, const type) +#define DEFINE_XEN_GUEST_HANDLE(name) __DEFINE_XEN_GUEST_HANDLE(name, name) +#define __XEN_GUEST_HANDLE(name) __guest_handle_ ## name +#define XEN_GUEST_HANDLE(name) __XEN_GUEST_HANDLE(name) +#define XEN_GUEST_HANDLE_PARAM(name) XEN_GUEST_HANDLE(name) +#define set_xen_guest_handle_raw(hnd, val) do { (hnd).p = val; } while (0) +#ifdef __XEN_TOOLS__ +#define get_xen_guest_handle(val, hnd) do { val = (hnd).p; } while (0) +#endif +#define set_xen_guest_handle(hnd, val) set_xen_guest_handle_raw(hnd, val) + +#if defined(__i386__) +#include "xen-x86_32.h" +#elif defined(__x86_64__) +#include "xen-x86_64.h" +#endif + +#ifndef __ASSEMBLY__ +typedef unsigned long xen_pfn_t; +#define PRI_xen_pfn "lx" +#endif + +#define XEN_HAVE_PV_GUEST_ENTRY 1 + +#define XEN_HAVE_PV_UPCALL_MASK 1 + +/* + * `incontents 200 segdesc Segment Descriptor Tables + */ +/* + * ` enum neg_errnoval + * ` HYPERVISOR_set_gdt(const xen_pfn_t frames[], unsigned int entries); + * ` + */ +/* + * A number of GDT entries are reserved by Xen. These are not situated at the + * start of the GDT because some stupid OSes export hard-coded selector values + * in their ABI. These hard-coded values are always near the start of the GDT, + * so Xen places itself out of the way, at the far end of the GDT. + * + * NB The LDT is set using the MMUEXT_SET_LDT op of HYPERVISOR_mmuext_op + */ +#define FIRST_RESERVED_GDT_PAGE 14 +#define FIRST_RESERVED_GDT_BYTE (FIRST_RESERVED_GDT_PAGE * 4096) +#define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8) + + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_update_descriptor(u64 pa, u64 desc); + * ` + * ` @pa The machine physical address of the descriptor to + * ` update. Must be either a descriptor page or writable. + * ` @desc The descriptor value to update, in the same format as a + * ` native descriptor table entry. + */ + +/* Maximum number of virtual CPUs in legacy multi-processor guests. */ +#define XEN_LEGACY_MAX_VCPUS 32 + +#ifndef __ASSEMBLY__ + +typedef unsigned long xen_ulong_t; +#define PRI_xen_ulong "lx" + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_stack_switch(unsigned long ss, unsigned long esp); + * ` + * Sets the stack segment and pointer for the current vcpu. + */ + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_set_trap_table(const struct trap_info traps[]); + * ` + */ +/* + * Send an array of these to HYPERVISOR_set_trap_table(). + * Terminate the array with a sentinel entry, with traps[].address==0. + * The privilege level specifies which modes may enter a trap via a software + * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate + * privilege levels as follows: + * Level == 0: Noone may enter + * Level == 1: Kernel may enter + * Level == 2: Kernel may enter + * Level == 3: Everyone may enter + */ +#define TI_GET_DPL(_ti) ((_ti)->flags & 3) +#define TI_GET_IF(_ti) ((_ti)->flags & 4) +#define TI_SET_DPL(_ti,_dpl) ((_ti)->flags |= (_dpl)) +#define TI_SET_IF(_ti,_if) ((_ti)->flags |= ((!!(_if))<<2)) +struct trap_info { + uint8_t vector; /* exception vector */ + uint8_t flags; /* 0-3: privilege level; 4: clear event enable? */ + uint16_t cs; /* code selector */ + unsigned long address; /* code offset */ +}; +typedef struct trap_info trap_info_t; +DEFINE_XEN_GUEST_HANDLE(trap_info_t); + +typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */ + +/* + * The following is all CPU context. Note that the fpu_ctxt block is filled + * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used. + * + * Also note that when calling DOMCTL_setvcpucontext and VCPU_initialise + * for HVM and PVH guests, not all information in this structure is updated: + * + * - For HVM guests, the structures read include: fpu_ctxt (if + * VGCT_I387_VALID is set), flags, user_regs, debugreg[*] + * + * - PVH guests are the same as HVM guests, but additionally use ctrlreg[3] to + * set cr3. All other fields not used should be set to 0. + */ +struct vcpu_guest_context { + /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */ + struct { char x[512]; } fpu_ctxt; /* User-level FPU registers */ +#define VGCF_I387_VALID (1<<0) +#define VGCF_IN_KERNEL (1<<2) +#define _VGCF_i387_valid 0 +#define VGCF_i387_valid (1<<_VGCF_i387_valid) +#define _VGCF_in_kernel 2 +#define VGCF_in_kernel (1<<_VGCF_in_kernel) +#define _VGCF_failsafe_disables_events 3 +#define VGCF_failsafe_disables_events (1<<_VGCF_failsafe_disables_events) +#define _VGCF_syscall_disables_events 4 +#define VGCF_syscall_disables_events (1<<_VGCF_syscall_disables_events) +#define _VGCF_online 5 +#define VGCF_online (1<<_VGCF_online) + unsigned long flags; /* VGCF_* flags */ + struct cpu_user_regs user_regs; /* User-level CPU registers */ + struct trap_info trap_ctxt[256]; /* Virtual IDT */ + unsigned long ldt_base, ldt_ents; /* LDT (linear address, # ents) */ + unsigned long gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */ + unsigned long kernel_ss, kernel_sp; /* Virtual TSS (only SS1/SP1) */ + /* NB. User pagetable on x86/64 is placed in ctrlreg[1]. */ + unsigned long ctrlreg[8]; /* CR0-CR7 (control registers) */ + unsigned long debugreg[8]; /* DB0-DB7 (debug registers) */ +#ifdef __i386__ + unsigned long event_callback_cs; /* CS:EIP of event callback */ + unsigned long event_callback_eip; + unsigned long failsafe_callback_cs; /* CS:EIP of failsafe callback */ + unsigned long failsafe_callback_eip; +#else + unsigned long event_callback_eip; + unsigned long failsafe_callback_eip; +#ifdef __XEN__ + union { + unsigned long syscall_callback_eip; + struct { + unsigned int event_callback_cs; /* compat CS of event cb */ + unsigned int failsafe_callback_cs; /* compat CS of failsafe cb */ + }; + }; +#else + unsigned long syscall_callback_eip; +#endif +#endif + unsigned long vm_assist; /* VMASST_TYPE_* bitmap */ +#ifdef __x86_64__ + /* Segment base addresses. */ + uint64_t fs_base; + uint64_t gs_base_kernel; + uint64_t gs_base_user; +#endif +}; +typedef struct vcpu_guest_context vcpu_guest_context_t; +DEFINE_XEN_GUEST_HANDLE(vcpu_guest_context_t); + +struct arch_shared_info { + unsigned long max_pfn; /* max pfn that appears in table */ + /* Frame containing list of mfns containing list of mfns containing p2m. */ + xen_pfn_t pfn_to_mfn_frame_list_list; + unsigned long nmi_reason; + uint64_t pad[32]; +}; +typedef struct arch_shared_info arch_shared_info_t; + +#endif /* !__ASSEMBLY__ */ + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_fpu_taskswitch(int set); + * ` + * Sets (if set!=0) or clears (if set==0) CR0.TS. + */ + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_set_debugreg(int regno, unsigned long value); + * + * ` unsigned long + * ` HYPERVISOR_get_debugreg(int regno); + * For 0<=reg<=7, returns the debug register value. + * For other values of reg, returns ((unsigned long)-EINVAL). + * (Unfortunately, this interface is defective.) + */ + +/* + * Prefix forces emulation of some non-trapping instructions. + * Currently only CPUID. + */ +#ifdef __ASSEMBLY__ +#define XEN_EMULATE_PREFIX .byte 0x0f,0x0b,0x78,0x65,0x6e ; +#define XEN_CPUID XEN_EMULATE_PREFIX cpuid +#else +#define XEN_EMULATE_PREFIX ".byte 0x0f,0x0b,0x78,0x65,0x6e ; " +#define XEN_CPUID XEN_EMULATE_PREFIX "cpuid" +#endif + +#endif /* __XEN_PUBLIC_ARCH_X86_XEN_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/event_channel.h b/include/xen/event_channel.h new file mode 100644 index 000000000..49ac8cca5 --- /dev/null +++ b/include/xen/event_channel.h @@ -0,0 +1,381 @@ +/****************************************************************************** + * event_channel.h + * + * Event channels between domains. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2003-2004, K A Fraser. + */ + +#ifndef __XEN_PUBLIC_EVENT_CHANNEL_H__ +#define __XEN_PUBLIC_EVENT_CHANNEL_H__ + +#include "xen.h" + +/* + * `incontents 150 evtchn Event Channels + * + * Event channels are the basic primitive provided by Xen for event + * notifications. An event is the Xen equivalent of a hardware + * interrupt. They essentially store one bit of information, the event + * of interest is signalled by transitioning this bit from 0 to 1. + * + * Notifications are received by a guest via an upcall from Xen, + * indicating when an event arrives (setting the bit). Further + * notifications are masked until the bit is cleared again (therefore, + * guests must check the value of the bit after re-enabling event + * delivery to ensure no missed notifications). + * + * Event notifications can be masked by setting a flag; this is + * equivalent to disabling interrupts and can be used to ensure + * atomicity of certain operations in the guest kernel. + * + * Event channels are represented by the evtchn_* fields in + * struct shared_info and struct vcpu_info. + */ + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_event_channel_op(enum event_channel_op cmd, void *args) + * ` + * @cmd == EVTCHNOP_* (event-channel operation). + * @args == struct evtchn_* Operation-specific extra arguments (NULL if none). + */ + +/* ` enum event_channel_op { // EVTCHNOP_* => struct evtchn_* */ +#define EVTCHNOP_bind_interdomain 0 +#define EVTCHNOP_bind_virq 1 +#define EVTCHNOP_bind_pirq 2 +#define EVTCHNOP_close 3 +#define EVTCHNOP_send 4 +#define EVTCHNOP_status 5 +#define EVTCHNOP_alloc_unbound 6 +#define EVTCHNOP_bind_ipi 7 +#define EVTCHNOP_bind_vcpu 8 +#define EVTCHNOP_unmask 9 +#define EVTCHNOP_reset 10 +#define EVTCHNOP_init_control 11 +#define EVTCHNOP_expand_array 12 +#define EVTCHNOP_set_priority 13 +/* ` } */ + +typedef uint32_t evtchn_port_t; +DEFINE_XEN_GUEST_HANDLE(evtchn_port_t); + +/* + * EVTCHNOP_alloc_unbound: Allocate a port in domain and mark as + * accepting interdomain bindings from domain . A fresh port + * is allocated in and returned as . + * NOTES: + * 1. If the caller is unprivileged then must be DOMID_SELF. + * 2. may be DOMID_SELF, allowing loopback connections. + */ +struct evtchn_alloc_unbound { + /* IN parameters */ + domid_t dom, remote_dom; + /* OUT parameters */ + evtchn_port_t port; +}; +typedef struct evtchn_alloc_unbound evtchn_alloc_unbound_t; + +/* + * EVTCHNOP_bind_interdomain: Construct an interdomain event channel between + * the calling domain and . must identify + * a port that is unbound and marked as accepting bindings from the calling + * domain. A fresh port is allocated in the calling domain and returned as + * . + * + * In case the peer domain has already tried to set our event channel + * pending, before it was bound, EVTCHNOP_bind_interdomain always sets + * the local event channel pending. + * + * The usual pattern of use, in the guest's upcall (or subsequent + * handler) is as follows: (Re-enable the event channel for subsequent + * signalling and then) check for the existence of whatever condition + * is being waited for by other means, and take whatever action is + * needed (if any). + * + * NOTES: + * 1. may be DOMID_SELF, allowing loopback connections. + */ +struct evtchn_bind_interdomain { + /* IN parameters. */ + domid_t remote_dom; + evtchn_port_t remote_port; + /* OUT parameters. */ + evtchn_port_t local_port; +}; +typedef struct evtchn_bind_interdomain evtchn_bind_interdomain_t; + +/* + * EVTCHNOP_bind_virq: Bind a local event channel to VIRQ on specified + * vcpu. + * NOTES: + * 1. Virtual IRQs are classified as per-vcpu or global. See the VIRQ list + * in xen.h for the classification of each VIRQ. + * 2. Global VIRQs must be allocated on VCPU0 but can subsequently be + * re-bound via EVTCHNOP_bind_vcpu. + * 3. Per-vcpu VIRQs may be bound to at most one event channel per vcpu. + * The allocated event channel is bound to the specified vcpu and the + * binding cannot be changed. + */ +struct evtchn_bind_virq { + /* IN parameters. */ + uint32_t virq; /* enum virq */ + uint32_t vcpu; + /* OUT parameters. */ + evtchn_port_t port; +}; +typedef struct evtchn_bind_virq evtchn_bind_virq_t; + +/* + * EVTCHNOP_bind_pirq: Bind a local event channel to a real IRQ (PIRQ ). + * NOTES: + * 1. A physical IRQ may be bound to at most one event channel per domain. + * 2. Only a sufficiently-privileged domain may bind to a physical IRQ. + */ +struct evtchn_bind_pirq { + /* IN parameters. */ + uint32_t pirq; +#define BIND_PIRQ__WILL_SHARE 1 + uint32_t flags; /* BIND_PIRQ__* */ + /* OUT parameters. */ + evtchn_port_t port; +}; +typedef struct evtchn_bind_pirq evtchn_bind_pirq_t; + +/* + * EVTCHNOP_bind_ipi: Bind a local event channel to receive events. + * NOTES: + * 1. The allocated event channel is bound to the specified vcpu. The binding + * may not be changed. + */ +struct evtchn_bind_ipi { + uint32_t vcpu; + /* OUT parameters. */ + evtchn_port_t port; +}; +typedef struct evtchn_bind_ipi evtchn_bind_ipi_t; + +/* + * EVTCHNOP_close: Close a local event channel . If the channel is + * interdomain then the remote end is placed in the unbound state + * (EVTCHNSTAT_unbound), awaiting a new connection. + */ +struct evtchn_close { + /* IN parameters. */ + evtchn_port_t port; +}; +typedef struct evtchn_close evtchn_close_t; + +/* + * EVTCHNOP_send: Send an event to the remote end of the channel whose local + * endpoint is . + */ +struct evtchn_send { + /* IN parameters. */ + evtchn_port_t port; +}; +typedef struct evtchn_send evtchn_send_t; + +/* + * EVTCHNOP_status: Get the current status of the communication channel which + * has an endpoint at . + * NOTES: + * 1. may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may obtain the status of an event + * channel for which is not DOMID_SELF. + */ +struct evtchn_status { + /* IN parameters */ + domid_t dom; + evtchn_port_t port; + /* OUT parameters */ +#define EVTCHNSTAT_closed 0 /* Channel is not in use. */ +#define EVTCHNSTAT_unbound 1 /* Channel is waiting interdom connection.*/ +#define EVTCHNSTAT_interdomain 2 /* Channel is connected to remote domain. */ +#define EVTCHNSTAT_pirq 3 /* Channel is bound to a phys IRQ line. */ +#define EVTCHNSTAT_virq 4 /* Channel is bound to a virtual IRQ line */ +#define EVTCHNSTAT_ipi 5 /* Channel is bound to a virtual IPI line */ + uint32_t status; + uint32_t vcpu; /* VCPU to which this channel is bound. */ + union { + struct { + domid_t dom; + } unbound; /* EVTCHNSTAT_unbound */ + struct { + domid_t dom; + evtchn_port_t port; + } interdomain; /* EVTCHNSTAT_interdomain */ + uint32_t pirq; /* EVTCHNSTAT_pirq */ + uint32_t virq; /* EVTCHNSTAT_virq */ + } u; +}; +typedef struct evtchn_status evtchn_status_t; + +/* + * EVTCHNOP_bind_vcpu: Specify which vcpu a channel should notify when an + * event is pending. + * NOTES: + * 1. IPI-bound channels always notify the vcpu specified at bind time. + * This binding cannot be changed. + * 2. Per-VCPU VIRQ channels always notify the vcpu specified at bind time. + * This binding cannot be changed. + * 3. All other channels notify vcpu0 by default. This default is set when + * the channel is allocated (a port that is freed and subsequently reused + * has its binding reset to vcpu0). + */ +struct evtchn_bind_vcpu { + /* IN parameters. */ + evtchn_port_t port; + uint32_t vcpu; +}; +typedef struct evtchn_bind_vcpu evtchn_bind_vcpu_t; + +/* + * EVTCHNOP_unmask: Unmask the specified local event-channel port and deliver + * a notification to the appropriate VCPU if an event is pending. + */ +struct evtchn_unmask { + /* IN parameters. */ + evtchn_port_t port; +}; +typedef struct evtchn_unmask evtchn_unmask_t; + +/* + * EVTCHNOP_reset: Close all event channels associated with specified domain. + * NOTES: + * 1. may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may specify other than DOMID_SELF. + */ +struct evtchn_reset { + /* IN parameters. */ + domid_t dom; +}; +typedef struct evtchn_reset evtchn_reset_t; + +/* + * EVTCHNOP_init_control: initialize the control block for the FIFO ABI. + * + * Note: any events that are currently pending will not be resent and + * will be lost. Guests should call this before binding any event to + * avoid losing any events. + */ +struct evtchn_init_control { + /* IN parameters. */ + uint64_t control_gfn; + uint32_t offset; + uint32_t vcpu; + /* OUT parameters. */ + uint8_t link_bits; + uint8_t _pad[7]; +}; +typedef struct evtchn_init_control evtchn_init_control_t; + +/* + * EVTCHNOP_expand_array: add an additional page to the event array. + */ +struct evtchn_expand_array { + /* IN parameters. */ + uint64_t array_gfn; +}; +typedef struct evtchn_expand_array evtchn_expand_array_t; + +/* + * EVTCHNOP_set_priority: set the priority for an event channel. + */ +struct evtchn_set_priority { + /* IN parameters. */ + uint32_t port; + uint32_t priority; +}; +typedef struct evtchn_set_priority evtchn_set_priority_t; + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_event_channel_op_compat(struct evtchn_op *op) + * ` + * Superceded by new event_channel_op() hypercall since 0x00030202. + */ +struct evtchn_op { + uint32_t cmd; /* enum event_channel_op */ + union { + struct evtchn_alloc_unbound alloc_unbound; + struct evtchn_bind_interdomain bind_interdomain; + struct evtchn_bind_virq bind_virq; + struct evtchn_bind_pirq bind_pirq; + struct evtchn_bind_ipi bind_ipi; + struct evtchn_close close; + struct evtchn_send send; + struct evtchn_status status; + struct evtchn_bind_vcpu bind_vcpu; + struct evtchn_unmask unmask; + } u; +}; +typedef struct evtchn_op evtchn_op_t; +DEFINE_XEN_GUEST_HANDLE(evtchn_op_t); + +/* + * 2-level ABI + */ + +#define EVTCHN_2L_NR_CHANNELS (sizeof(xen_ulong_t) * sizeof(xen_ulong_t) * 64) + +/* + * FIFO ABI + */ + +/* Events may have priorities from 0 (highest) to 15 (lowest). */ +#define EVTCHN_FIFO_PRIORITY_MAX 0 +#define EVTCHN_FIFO_PRIORITY_DEFAULT 7 +#define EVTCHN_FIFO_PRIORITY_MIN 15 + +#define EVTCHN_FIFO_MAX_QUEUES (EVTCHN_FIFO_PRIORITY_MIN + 1) + +typedef uint32_t event_word_t; + +#define EVTCHN_FIFO_PENDING 31 +#define EVTCHN_FIFO_MASKED 30 +#define EVTCHN_FIFO_LINKED 29 +#define EVTCHN_FIFO_BUSY 28 + +#define EVTCHN_FIFO_LINK_BITS 17 +#define EVTCHN_FIFO_LINK_MASK ((1 << EVTCHN_FIFO_LINK_BITS) - 1) + +#define EVTCHN_FIFO_NR_CHANNELS (1 << EVTCHN_FIFO_LINK_BITS) + +struct evtchn_fifo_control_block { + uint32_t ready; + uint32_t _rsvd; + uint32_t head[EVTCHN_FIFO_MAX_QUEUES]; +}; +typedef struct evtchn_fifo_control_block evtchn_fifo_control_block_t; + +#endif /* __XEN_PUBLIC_EVENT_CHANNEL_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h new file mode 100644 index 000000000..b8a3d6ceb --- /dev/null +++ b/include/xen/grant_table.h @@ -0,0 +1,662 @@ +/****************************************************************************** + * grant_table.h + * + * Interface for granting foreign access to page frames, and receiving + * page-ownership transfers. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2004, K A Fraser + */ + +#ifndef __XEN_PUBLIC_GRANT_TABLE_H__ +#define __XEN_PUBLIC_GRANT_TABLE_H__ + +#include "xen.h" + +/* + * `incontents 150 gnttab Grant Tables + * + * Xen's grant tables provide a generic mechanism to memory sharing + * between domains. This shared memory interface underpins the split + * device drivers for block and network IO. + * + * Each domain has its own grant table. This is a data structure that + * is shared with Xen; it allows the domain to tell Xen what kind of + * permissions other domains have on its pages. Entries in the grant + * table are identified by grant references. A grant reference is an + * integer, which indexes into the grant table. It acts as a + * capability which the grantee can use to perform operations on the + * granter’s memory. + * + * This capability-based system allows shared-memory communications + * between unprivileged domains. A grant reference also encapsulates + * the details of a shared page, removing the need for a domain to + * know the real machine address of a page it is sharing. This makes + * it possible to share memory correctly with domains running in + * fully virtualised memory. + */ + +/*********************************** + * GRANT TABLE REPRESENTATION + */ + +/* Some rough guidelines on accessing and updating grant-table entries + * in a concurrency-safe manner. For more information, Linux contains a + * reference implementation for guest OSes (drivers/xen/grant_table.c, see + * http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git;a=blob;f=drivers/xen/grant-table.c;hb=HEAD + * + * NB. WMB is a no-op on current-generation x86 processors. However, a + * compiler barrier will still be required. + * + * Introducing a valid entry into the grant table: + * 1. Write ent->domid. + * 2. Write ent->frame: + * GTF_permit_access: Frame to which access is permitted. + * GTF_accept_transfer: Pseudo-phys frame slot being filled by new + * frame, or zero if none. + * 3. Write memory barrier (WMB). + * 4. Write ent->flags, inc. valid type. + * + * Invalidating an unused GTF_permit_access entry: + * 1. flags = ent->flags. + * 2. Observe that !(flags & (GTF_reading|GTF_writing)). + * 3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0). + * NB. No need for WMB as reuse of entry is control-dependent on success of + * step 3, and all architectures guarantee ordering of ctrl-dep writes. + * + * Invalidating an in-use GTF_permit_access entry: + * This cannot be done directly. Request assistance from the domain controller + * which can set a timeout on the use of a grant entry and take necessary + * action. (NB. This is not yet implemented!). + * + * Invalidating an unused GTF_accept_transfer entry: + * 1. flags = ent->flags. + * 2. Observe that !(flags & GTF_transfer_committed). [*] + * 3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0). + * NB. No need for WMB as reuse of entry is control-dependent on success of + * step 3, and all architectures guarantee ordering of ctrl-dep writes. + * [*] If GTF_transfer_committed is set then the grant entry is 'committed'. + * The guest must /not/ modify the grant entry until the address of the + * transferred frame is written. It is safe for the guest to spin waiting + * for this to occur (detect by observing GTF_transfer_completed in + * ent->flags). + * + * Invalidating a committed GTF_accept_transfer entry: + * 1. Wait for (ent->flags & GTF_transfer_completed). + * + * Changing a GTF_permit_access from writable to read-only: + * Use SMP-safe CMPXCHG to set GTF_readonly, while checking !GTF_writing. + * + * Changing a GTF_permit_access from read-only to writable: + * Use SMP-safe bit-setting instruction. + */ + +/* + * Reference to a grant entry in a specified domain's grant table. + */ +typedef uint32_t grant_ref_t; + +/* + * A grant table comprises a packed array of grant entries in one or more + * page frames shared between Xen and a guest. + * [XEN]: This field is written by Xen and read by the sharing guest. + * [GST]: This field is written by the guest and read by Xen. + */ + +/* + * Version 1 of the grant table entry structure is maintained purely + * for backwards compatibility. New guests should use version 2. + */ +#if __XEN_INTERFACE_VERSION__ < 0x0003020a +#define grant_entry_v1 grant_entry +#define grant_entry_v1_t grant_entry_t +#endif +struct grant_entry_v1 { + /* GTF_xxx: various type and flag information. [XEN,GST] */ + uint16_t flags; + /* The domain being granted foreign privileges. [GST] */ + domid_t domid; + /* + * GTF_permit_access: Frame that @domid is allowed to map and access. [GST] + * GTF_accept_transfer: Frame whose ownership transferred by @domid. [XEN] + */ + uint32_t frame; +}; +typedef struct grant_entry_v1 grant_entry_v1_t; + +/* The first few grant table entries will be preserved across grant table + * version changes and may be pre-populated at domain creation by tools. + */ +#define GNTTAB_NR_RESERVED_ENTRIES 8 +#define GNTTAB_RESERVED_CONSOLE 0 +#define GNTTAB_RESERVED_XENSTORE 1 + +/* + * Type of grant entry. + * GTF_invalid: This grant entry grants no privileges. + * GTF_permit_access: Allow @domid to map/access @frame. + * GTF_accept_transfer: Allow @domid to transfer ownership of one page frame + * to this guest. Xen writes the page number to @frame. + * GTF_transitive: Allow @domid to transitively access a subrange of + * @trans_grant in @trans_domid. No mappings are allowed. + */ +#define GTF_invalid (0U<<0) +#define GTF_permit_access (1U<<0) +#define GTF_accept_transfer (2U<<0) +#define GTF_transitive (3U<<0) +#define GTF_type_mask (3U<<0) + +/* + * Subflags for GTF_permit_access. + * GTF_readonly: Restrict @domid to read-only mappings and accesses. [GST] + * GTF_reading: Grant entry is currently mapped for reading by @domid. [XEN] + * GTF_writing: Grant entry is currently mapped for writing by @domid. [XEN] + * GTF_PAT, GTF_PWT, GTF_PCD: (x86) cache attribute flags for the grant [GST] + * GTF_sub_page: Grant access to only a subrange of the page. @domid + * will only be allowed to copy from the grant, and not + * map it. [GST] + */ +#define _GTF_readonly (2) +#define GTF_readonly (1U<<_GTF_readonly) +#define _GTF_reading (3) +#define GTF_reading (1U<<_GTF_reading) +#define _GTF_writing (4) +#define GTF_writing (1U<<_GTF_writing) +#define _GTF_PWT (5) +#define GTF_PWT (1U<<_GTF_PWT) +#define _GTF_PCD (6) +#define GTF_PCD (1U<<_GTF_PCD) +#define _GTF_PAT (7) +#define GTF_PAT (1U<<_GTF_PAT) +#define _GTF_sub_page (8) +#define GTF_sub_page (1U<<_GTF_sub_page) + +/* + * Subflags for GTF_accept_transfer: + * GTF_transfer_committed: Xen sets this flag to indicate that it is committed + * to transferring ownership of a page frame. When a guest sees this flag + * it must /not/ modify the grant entry until GTF_transfer_completed is + * set by Xen. + * GTF_transfer_completed: It is safe for the guest to spin-wait on this flag + * after reading GTF_transfer_committed. Xen will always write the frame + * address, followed by ORing this flag, in a timely manner. + */ +#define _GTF_transfer_committed (2) +#define GTF_transfer_committed (1U<<_GTF_transfer_committed) +#define _GTF_transfer_completed (3) +#define GTF_transfer_completed (1U<<_GTF_transfer_completed) + +/* + * Version 2 grant table entries. These fulfil the same role as + * version 1 entries, but can represent more complicated operations. + * Any given domain will have either a version 1 or a version 2 table, + * and every entry in the table will be the same version. + * + * The interface by which domains use grant references does not depend + * on the grant table version in use by the other domain. + */ +#if __XEN_INTERFACE_VERSION__ >= 0x0003020a +/* + * Version 1 and version 2 grant entries share a common prefix. The + * fields of the prefix are documented as part of struct + * grant_entry_v1. + */ +struct grant_entry_header { + uint16_t flags; + domid_t domid; +}; +typedef struct grant_entry_header grant_entry_header_t; + +/* + * Version 2 of the grant entry structure. + */ +union grant_entry_v2 { + grant_entry_header_t hdr; + + /* + * This member is used for V1-style full page grants, where either: + * + * -- hdr.type is GTF_accept_transfer, or + * -- hdr.type is GTF_permit_access and GTF_sub_page is not set. + * + * In that case, the frame field has the same semantics as the + * field of the same name in the V1 entry structure. + */ + struct { + grant_entry_header_t hdr; + uint32_t pad0; + uint64_t frame; + } full_page; + + /* + * If the grant type is GTF_grant_access and GTF_sub_page is set, + * @domid is allowed to access bytes [@page_off,@page_off+@length) + * in frame @frame. + */ + struct { + grant_entry_header_t hdr; + uint16_t page_off; + uint16_t length; + uint64_t frame; + } sub_page; + + /* + * If the grant is GTF_transitive, @domid is allowed to use the + * grant @gref in domain @trans_domid, as if it was the local + * domain. Obviously, the transitive access must be compatible + * with the original grant. + * + * The current version of Xen does not allow transitive grants + * to be mapped. + */ + struct { + grant_entry_header_t hdr; + domid_t trans_domid; + uint16_t pad0; + grant_ref_t gref; + } transitive; + + uint32_t __spacer[4]; /* Pad to a power of two */ +}; +typedef union grant_entry_v2 grant_entry_v2_t; + +typedef uint16_t grant_status_t; + +#endif /* __XEN_INTERFACE_VERSION__ */ + +/*********************************** + * GRANT TABLE QUERIES AND USES + */ + +/* ` enum neg_errnoval + * ` HYPERVISOR_grant_table_op(enum grant_table_op cmd, + * ` void *args, + * ` unsigned int count) + * ` + * + * @args points to an array of a per-command data structure. The array + * has @count members + */ + +/* ` enum grant_table_op { // GNTTABOP_* => struct gnttab_* */ +#define GNTTABOP_map_grant_ref 0 +#define GNTTABOP_unmap_grant_ref 1 +#define GNTTABOP_setup_table 2 +#define GNTTABOP_dump_table 3 +#define GNTTABOP_transfer 4 +#define GNTTABOP_copy 5 +#define GNTTABOP_query_size 6 +#define GNTTABOP_unmap_and_replace 7 +#if __XEN_INTERFACE_VERSION__ >= 0x0003020a +#define GNTTABOP_set_version 8 +#define GNTTABOP_get_status_frames 9 +#define GNTTABOP_get_version 10 +#define GNTTABOP_swap_grant_ref 11 +#endif /* __XEN_INTERFACE_VERSION__ */ +/* ` } */ + +/* + * Handle to track a mapping created via a grant reference. + */ +typedef uint32_t grant_handle_t; + +/* + * GNTTABOP_map_grant_ref: Map the grant entry (,) for access + * by devices and/or host CPUs. If successful, is a tracking number + * that must be presented later to destroy the mapping(s). On error, + * is a negative status code. + * NOTES: + * 1. If GNTMAP_device_map is specified then is the address + * via which I/O devices may access the granted frame. + * 2. If GNTMAP_host_map is specified then a mapping will be added at + * either a host virtual address in the current address space, or at + * a PTE at the specified machine address. The type of mapping to + * perform is selected through the GNTMAP_contains_pte flag, and the + * address is specified in . + * 3. Mappings should only be destroyed via GNTTABOP_unmap_grant_ref. If a + * host mapping is destroyed by other means then it is *NOT* guaranteed + * to be accounted to the correct grant reference! + */ +struct gnttab_map_grant_ref { + /* IN parameters. */ + uint64_t host_addr; + uint32_t flags; /* GNTMAP_* */ + grant_ref_t ref; + domid_t dom; + /* OUT parameters. */ + int16_t status; /* => enum grant_status */ + grant_handle_t handle; + uint64_t dev_bus_addr; +}; +typedef struct gnttab_map_grant_ref gnttab_map_grant_ref_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_map_grant_ref_t); + +/* + * GNTTABOP_unmap_grant_ref: Destroy one or more grant-reference mappings + * tracked by . If or is zero, that + * field is ignored. If non-zero, they must refer to a device/host mapping + * that is tracked by + * NOTES: + * 1. The call may fail in an undefined manner if either mapping is not + * tracked by . + * 3. After executing a batch of unmaps, it is guaranteed that no stale + * mappings will remain in the device or host TLBs. + */ +struct gnttab_unmap_grant_ref { + /* IN parameters. */ + uint64_t host_addr; + uint64_t dev_bus_addr; + grant_handle_t handle; + /* OUT parameters. */ + int16_t status; /* => enum grant_status */ +}; +typedef struct gnttab_unmap_grant_ref gnttab_unmap_grant_ref_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_unmap_grant_ref_t); + +/* + * GNTTABOP_setup_table: Set up a grant table for comprising at least + * pages. The frame addresses are written to the . + * Only addresses are written, even if the table is larger. + * NOTES: + * 1. may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may specify != DOMID_SELF. + * 3. Xen may not support more than a single grant-table page per domain. + */ +struct gnttab_setup_table { + /* IN parameters. */ + domid_t dom; + uint32_t nr_frames; + /* OUT parameters. */ + int16_t status; /* => enum grant_status */ +#if __XEN_INTERFACE_VERSION__ < 0x00040300 + XEN_GUEST_HANDLE(ulong) frame_list; +#else + XEN_GUEST_HANDLE(xen_pfn_t) frame_list; +#endif +}; +typedef struct gnttab_setup_table gnttab_setup_table_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_setup_table_t); + +/* + * GNTTABOP_dump_table: Dump the contents of the grant table to the + * xen console. Debugging use only. + */ +struct gnttab_dump_table { + /* IN parameters. */ + domid_t dom; + /* OUT parameters. */ + int16_t status; /* => enum grant_status */ +}; +typedef struct gnttab_dump_table gnttab_dump_table_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_dump_table_t); + +/* + * GNTTABOP_transfer_grant_ref: Transfer to a foreign domain. The + * foreign domain has previously registered its interest in the transfer via + * . + * + * Note that, even if the transfer fails, the specified page no longer belongs + * to the calling domain *unless* the error is GNTST_bad_page. + */ +struct gnttab_transfer { + /* IN parameters. */ + xen_pfn_t mfn; + domid_t domid; + grant_ref_t ref; + /* OUT parameters. */ + int16_t status; +}; +typedef struct gnttab_transfer gnttab_transfer_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_transfer_t); + + +/* + * GNTTABOP_copy: Hypervisor based copy + * source and destinations can be eithers MFNs or, for foreign domains, + * grant references. the foreign domain has to grant read/write access + * in its grant table. + * + * The flags specify what type source and destinations are (either MFN + * or grant reference). + * + * Note that this can also be used to copy data between two domains + * via a third party if the source and destination domains had previously + * grant appropriate access to their pages to the third party. + * + * source_offset specifies an offset in the source frame, dest_offset + * the offset in the target frame and len specifies the number of + * bytes to be copied. + */ + +#define _GNTCOPY_source_gref (0) +#define GNTCOPY_source_gref (1<<_GNTCOPY_source_gref) +#define _GNTCOPY_dest_gref (1) +#define GNTCOPY_dest_gref (1<<_GNTCOPY_dest_gref) + +struct gnttab_copy { + /* IN parameters. */ + struct { + union { + grant_ref_t ref; + xen_pfn_t gmfn; + } u; + domid_t domid; + uint16_t offset; + } source, dest; + uint16_t len; + uint16_t flags; /* GNTCOPY_* */ + /* OUT parameters. */ + int16_t status; +}; +typedef struct gnttab_copy gnttab_copy_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_copy_t); + +/* + * GNTTABOP_query_size: Query the current and maximum sizes of the shared + * grant table. + * NOTES: + * 1. may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may specify != DOMID_SELF. + */ +struct gnttab_query_size { + /* IN parameters. */ + domid_t dom; + /* OUT parameters. */ + uint32_t nr_frames; + uint32_t max_nr_frames; + int16_t status; /* => enum grant_status */ +}; +typedef struct gnttab_query_size gnttab_query_size_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_query_size_t); + +/* + * GNTTABOP_unmap_and_replace: Destroy one or more grant-reference mappings + * tracked by but atomically replace the page table entry with one + * pointing to the machine address under . will be + * redirected to the null entry. + * NOTES: + * 1. The call may fail in an undefined manner if either mapping is not + * tracked by . + * 2. After executing a batch of unmaps, it is guaranteed that no stale + * mappings will remain in the device or host TLBs. + */ +struct gnttab_unmap_and_replace { + /* IN parameters. */ + uint64_t host_addr; + uint64_t new_addr; + grant_handle_t handle; + /* OUT parameters. */ + int16_t status; /* => enum grant_status */ +}; +typedef struct gnttab_unmap_and_replace gnttab_unmap_and_replace_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_unmap_and_replace_t); + +#if __XEN_INTERFACE_VERSION__ >= 0x0003020a +/* + * GNTTABOP_set_version: Request a particular version of the grant + * table shared table structure. This operation can only be performed + * once in any given domain. It must be performed before any grants + * are activated; otherwise, the domain will be stuck with version 1. + * The only defined versions are 1 and 2. + */ +struct gnttab_set_version { + /* IN/OUT parameters */ + uint32_t version; +}; +typedef struct gnttab_set_version gnttab_set_version_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_set_version_t); + + +/* + * GNTTABOP_get_status_frames: Get the list of frames used to store grant + * status for . In grant format version 2, the status is separated + * from the other shared grant fields to allow more efficient synchronization + * using barriers instead of atomic cmpexch operations. + * specify the size of vector . + * The frame addresses are returned in the . + * Only addresses are returned, even if the table is larger. + * NOTES: + * 1. may be specified as DOMID_SELF. + * 2. Only a sufficiently-privileged domain may specify != DOMID_SELF. + */ +struct gnttab_get_status_frames { + /* IN parameters. */ + uint32_t nr_frames; + domid_t dom; + /* OUT parameters. */ + int16_t status; /* => enum grant_status */ + XEN_GUEST_HANDLE(uint64_t) frame_list; +}; +typedef struct gnttab_get_status_frames gnttab_get_status_frames_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_get_status_frames_t); + +/* + * GNTTABOP_get_version: Get the grant table version which is in + * effect for domain . + */ +struct gnttab_get_version { + /* IN parameters */ + domid_t dom; + uint16_t pad; + /* OUT parameters */ + uint32_t version; +}; +typedef struct gnttab_get_version gnttab_get_version_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_get_version_t); + +/* + * GNTTABOP_swap_grant_ref: Swap the contents of two grant entries. + */ +struct gnttab_swap_grant_ref { + /* IN parameters */ + grant_ref_t ref_a; + grant_ref_t ref_b; + /* OUT parameters */ + int16_t status; /* => enum grant_status */ +}; +typedef struct gnttab_swap_grant_ref gnttab_swap_grant_ref_t; +DEFINE_XEN_GUEST_HANDLE(gnttab_swap_grant_ref_t); + +#endif /* __XEN_INTERFACE_VERSION__ */ + +/* + * Bitfield values for gnttab_map_grant_ref.flags. + */ + /* Map the grant entry for access by I/O devices. */ +#define _GNTMAP_device_map (0) +#define GNTMAP_device_map (1<<_GNTMAP_device_map) + /* Map the grant entry for access by host CPUs. */ +#define _GNTMAP_host_map (1) +#define GNTMAP_host_map (1<<_GNTMAP_host_map) + /* Accesses to the granted frame will be restricted to read-only access. */ +#define _GNTMAP_readonly (2) +#define GNTMAP_readonly (1<<_GNTMAP_readonly) + /* + * GNTMAP_host_map subflag: + * 0 => The host mapping is usable only by the guest OS. + * 1 => The host mapping is usable by guest OS + current application. + */ +#define _GNTMAP_application_map (3) +#define GNTMAP_application_map (1<<_GNTMAP_application_map) + + /* + * GNTMAP_contains_pte subflag: + * 0 => This map request contains a host virtual address. + * 1 => This map request contains the machine addess of the PTE to update. + */ +#define _GNTMAP_contains_pte (4) +#define GNTMAP_contains_pte (1<<_GNTMAP_contains_pte) + +#define _GNTMAP_can_fail (5) +#define GNTMAP_can_fail (1<<_GNTMAP_can_fail) + +/* + * Bits to be placed in guest kernel available PTE bits (architecture + * dependent; only supported when XENFEAT_gnttab_map_avail_bits is set). + */ +#define _GNTMAP_guest_avail0 (16) +#define GNTMAP_guest_avail_mask ((uint32_t)~0 << _GNTMAP_guest_avail0) + +/* + * Values for error status returns. All errors are -ve. + */ +/* ` enum grant_status { */ +#define GNTST_okay (0) /* Normal return. */ +#define GNTST_general_error (-1) /* General undefined error. */ +#define GNTST_bad_domain (-2) /* Unrecognsed domain id. */ +#define GNTST_bad_gntref (-3) /* Unrecognised or inappropriate gntref. */ +#define GNTST_bad_handle (-4) /* Unrecognised or inappropriate handle. */ +#define GNTST_bad_virt_addr (-5) /* Inappropriate virtual address to map. */ +#define GNTST_bad_dev_addr (-6) /* Inappropriate device address to unmap.*/ +#define GNTST_no_device_space (-7) /* Out of space in I/O MMU. */ +#define GNTST_permission_denied (-8) /* Not enough privilege for operation. */ +#define GNTST_bad_page (-9) /* Specified page was invalid for op. */ +#define GNTST_bad_copy_arg (-10) /* copy arguments cross page boundary. */ +#define GNTST_address_too_big (-11) /* transfer page address too large. */ +#define GNTST_eagain (-12) /* Operation not done; try again. */ +/* ` } */ + +#define GNTTABOP_error_msgs { \ + "okay", \ + "undefined error", \ + "unrecognised domain id", \ + "invalid grant reference", \ + "invalid mapping handle", \ + "invalid virtual address", \ + "invalid device address", \ + "no spare translation slot in the I/O MMU", \ + "permission denied", \ + "bad page", \ + "copy arguments cross page boundary", \ + "page address size too large", \ + "operation not done; try again" \ +} + +#endif /* __XEN_PUBLIC_GRANT_TABLE_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/io/blkif.h b/include/xen/io/blkif.h new file mode 100644 index 000000000..c3e169ce2 --- /dev/null +++ b/include/xen/io/blkif.h @@ -0,0 +1,608 @@ +/****************************************************************************** + * blkif.h + * + * Unified block-device I/O interface for Xen guest OSes. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2003-2004, Keir Fraser + * Copyright (c) 2012, Spectra Logic Corporation + */ + +#ifndef __XEN_PUBLIC_IO_BLKIF_H__ +#define __XEN_PUBLIC_IO_BLKIF_H__ + +#include "ring.h" +#include "../grant_table.h" + +/* + * Front->back notifications: When enqueuing a new request, sending a + * notification can be made conditional on req_event (i.e., the generic + * hold-off mechanism provided by the ring macros). Backends must set + * req_event appropriately (e.g., using RING_FINAL_CHECK_FOR_REQUESTS()). + * + * Back->front notifications: When enqueuing a new response, sending a + * notification can be made conditional on rsp_event (i.e., the generic + * hold-off mechanism provided by the ring macros). Frontends must set + * rsp_event appropriately (e.g., using RING_FINAL_CHECK_FOR_RESPONSES()). + */ + +#ifndef blkif_vdev_t +#define blkif_vdev_t uint16_t +#endif +#define blkif_sector_t uint64_t + +/* + * Feature and Parameter Negotiation + * ================================= + * The two halves of a Xen block driver utilize nodes within the XenStore to + * communicate capabilities and to negotiate operating parameters. This + * section enumerates these nodes which reside in the respective front and + * backend portions of the XenStore, following the XenBus convention. + * + * All data in the XenStore is stored as strings. Nodes specifying numeric + * values are encoded in decimal. Integer value ranges listed below are + * expressed as fixed sized integer types capable of storing the conversion + * of a properly formated node string, without loss of information. + * + * Any specified default value is in effect if the corresponding XenBus node + * is not present in the XenStore. + * + * XenStore nodes in sections marked "PRIVATE" are solely for use by the + * driver side whose XenBus tree contains them. + * + * XenStore nodes marked "DEPRECATED" in their notes section should only be + * used to provide interoperability with legacy implementations. + * + * See the XenBus state transition diagram below for details on when XenBus + * nodes must be published and when they can be queried. + * + ***************************************************************************** + * Backend XenBus Nodes + ***************************************************************************** + * + *------------------ Backend Device Identification (PRIVATE) ------------------ + * + * mode + * Values: "r" (read only), "w" (writable) + * + * The read or write access permissions to the backing store to be + * granted to the frontend. + * + * params + * Values: string + * + * A free formatted string providing sufficient information for the + * backend driver to open the backing device. (e.g. the path to the + * file or block device representing the backing store.) + * + * type + * Values: "file", "phy", "tap" + * + * The type of the backing device/object. + * + *--------------------------------- Features --------------------------------- + * + * feature-barrier + * Values: 0/1 (boolean) + * Default Value: 0 + * + * A value of "1" indicates that the backend can process requests + * containing the BLKIF_OP_WRITE_BARRIER request opcode. Requests + * of this type may still be returned at any time with the + * BLKIF_RSP_EOPNOTSUPP result code. + * + * feature-flush-cache + * Values: 0/1 (boolean) + * Default Value: 0 + * + * A value of "1" indicates that the backend can process requests + * containing the BLKIF_OP_FLUSH_DISKCACHE request opcode. Requests + * of this type may still be returned at any time with the + * BLKIF_RSP_EOPNOTSUPP result code. + * + * feature-discard + * Values: 0/1 (boolean) + * Default Value: 0 + * + * A value of "1" indicates that the backend can process requests + * containing the BLKIF_OP_DISCARD request opcode. Requests + * of this type may still be returned at any time with the + * BLKIF_RSP_EOPNOTSUPP result code. + * + * feature-persistent + * Values: 0/1 (boolean) + * Default Value: 0 + * Notes: 7 + * + * A value of "1" indicates that the backend can keep the grants used + * by the frontend driver mapped, so the same set of grants should be + * used in all transactions. The maximum number of grants the backend + * can map persistently depends on the implementation, but ideally it + * should be RING_SIZE * BLKIF_MAX_SEGMENTS_PER_REQUEST. Using this + * feature the backend doesn't need to unmap each grant, preventing + * costly TLB flushes. The backend driver should only map grants + * persistently if the frontend supports it. If a backend driver chooses + * to use the persistent protocol when the frontend doesn't support it, + * it will probably hit the maximum number of persistently mapped grants + * (due to the fact that the frontend won't be reusing the same grants), + * and fall back to non-persistent mode. Backend implementations may + * shrink or expand the number of persistently mapped grants without + * notifying the frontend depending on memory constraints (this might + * cause a performance degradation). + * + * If a backend driver wants to limit the maximum number of persistently + * mapped grants to a value less than RING_SIZE * + * BLKIF_MAX_SEGMENTS_PER_REQUEST a LRU strategy should be used to + * discard the grants that are less commonly used. Using a LRU in the + * backend driver paired with a LIFO queue in the frontend will + * allow us to have better performance in this scenario. + * + *----------------------- Request Transport Parameters ------------------------ + * + * max-ring-page-order + * Values: + * Default Value: 0 + * Notes: 1, 3 + * + * The maximum supported size of the request ring buffer in units of + * lb(machine pages). (e.g. 0 == 1 page, 1 = 2 pages, 2 == 4 pages, + * etc.). + * + * max-ring-pages + * Values: + * Default Value: 1 + * Notes: DEPRECATED, 2, 3 + * + * The maximum supported size of the request ring buffer in units of + * machine pages. The value must be a power of 2. + * + *------------------------- Backend Device Properties ------------------------- + * + * discard-alignment + * Values: + * Default Value: 0 + * Notes: 4, 5 + * + * The offset, in bytes from the beginning of the virtual block device, + * to the first, addressable, discard extent on the underlying device. + * + * discard-granularity + * Values: + * Default Value: <"sector-size"> + * Notes: 4 + * + * The size, in bytes, of the individually addressable discard extents + * of the underlying device. + * + * discard-secure + * Values: 0/1 (boolean) + * Default Value: 0 + * Notes: 10 + * + * A value of "1" indicates that the backend can process BLKIF_OP_DISCARD + * requests with the BLKIF_DISCARD_SECURE flag set. + * + * info + * Values: (bitmap) + * + * A collection of bit flags describing attributes of the backing + * device. The VDISK_* macros define the meaning of each bit + * location. + * + * sector-size + * Values: + * + * The logical sector size, in bytes, of the backend device. + * + * physical-sector-size + * Values: + * + * The physical sector size, in bytes, of the backend device. + * + * sectors + * Values: + * + * The size of the backend device, expressed in units of its logical + * sector size ("sector-size"). + * + ***************************************************************************** + * Frontend XenBus Nodes + ***************************************************************************** + * + *----------------------- Request Transport Parameters ----------------------- + * + * event-channel + * Values: + * + * The identifier of the Xen event channel used to signal activity + * in the ring buffer. + * + * ring-ref + * Values: + * Notes: 6 + * + * The Xen grant reference granting permission for the backend to map + * the sole page in a single page sized ring buffer. + * + * ring-ref%u + * Values: + * Notes: 6 + * + * For a frontend providing a multi-page ring, a "number of ring pages" + * sized list of nodes, each containing a Xen grant reference granting + * permission for the backend to map the page of the ring located + * at page index "%u". Page indexes are zero based. + * + * protocol + * Values: string (XEN_IO_PROTO_ABI_*) + * Default Value: XEN_IO_PROTO_ABI_NATIVE + * + * The machine ABI rules governing the format of all ring request and + * response structures. + * + * ring-page-order + * Values: + * Default Value: 0 + * Maximum Value: MAX(ffs(max-ring-pages) - 1, max-ring-page-order) + * Notes: 1, 3 + * + * The size of the frontend allocated request ring buffer in units + * of lb(machine pages). (e.g. 0 == 1 page, 1 = 2 pages, 2 == 4 pages, + * etc.). + * + * num-ring-pages + * Values: + * Default Value: 1 + * Maximum Value: MAX(max-ring-pages,(0x1 << max-ring-page-order)) + * Notes: DEPRECATED, 2, 3 + * + * The size of the frontend allocated request ring buffer in units of + * machine pages. The value must be a power of 2. + * + * feature-persistent + * Values: 0/1 (boolean) + * Default Value: 0 + * Notes: 7, 8, 9 + * + * A value of "1" indicates that the frontend will reuse the same grants + * for all transactions, allowing the backend to map them with write + * access (even when it should be read-only). If the frontend hits the + * maximum number of allowed persistently mapped grants, it can fallback + * to non persistent mode. This will cause a performance degradation, + * since the the backend driver will still try to map those grants + * persistently. Since the persistent grants protocol is compatible with + * the previous protocol, a frontend driver can choose to work in + * persistent mode even when the backend doesn't support it. + * + * It is recommended that the frontend driver stores the persistently + * mapped grants in a LIFO queue, so a subset of all persistently mapped + * grants gets used commonly. This is done in case the backend driver + * decides to limit the maximum number of persistently mapped grants + * to a value less than RING_SIZE * BLKIF_MAX_SEGMENTS_PER_REQUEST. + * + *------------------------- Virtual Device Properties ------------------------- + * + * device-type + * Values: "disk", "cdrom", "floppy", etc. + * + * virtual-device + * Values: + * + * A value indicating the physical device to virtualize within the + * frontend's domain. (e.g. "The first ATA disk", "The third SCSI + * disk", etc.) + * + * See docs/misc/vbd-interface.txt for details on the format of this + * value. + * + * Notes + * ----- + * (1) Multi-page ring buffer scheme first developed in the Citrix XenServer + * PV drivers. + * (2) Multi-page ring buffer scheme first used in some RedHat distributions + * including a distribution deployed on certain nodes of the Amazon + * EC2 cluster. + * (3) Support for multi-page ring buffers was implemented independently, + * in slightly different forms, by both Citrix and RedHat/Amazon. + * For full interoperability, block front and backends should publish + * identical ring parameters, adjusted for unit differences, to the + * XenStore nodes used in both schemes. + * (4) Devices that support discard functionality may internally allocate space + * (discardable extents) in units that are larger than the exported logical + * block size. If the backing device has such discardable extents the + * backend should provide both discard-granularity and discard-alignment. + * Providing just one of the two may be considered an error by the frontend. + * Backends supporting discard should include discard-granularity and + * discard-alignment even if it supports discarding individual sectors. + * Frontends should assume discard-alignment == 0 and discard-granularity + * == sector size if these keys are missing. + * (5) The discard-alignment parameter allows a physical device to be + * partitioned into virtual devices that do not necessarily begin or + * end on a discardable extent boundary. + * (6) When there is only a single page allocated to the request ring, + * 'ring-ref' is used to communicate the grant reference for this + * page to the backend. When using a multi-page ring, the 'ring-ref' + * node is not created. Instead 'ring-ref0' - 'ring-refN' are used. + * (7) When using persistent grants data has to be copied from/to the page + * where the grant is currently mapped. The overhead of doing this copy + * however doesn't suppress the speed improvement of not having to unmap + * the grants. + * (8) The frontend driver has to allow the backend driver to map all grants + * with write access, even when they should be mapped read-only, since + * further requests may reuse these grants and require write permissions. + * (9) Linux implementation doesn't have a limit on the maximum number of + * grants that can be persistently mapped in the frontend driver, but + * due to the frontent driver implementation it should never be bigger + * than RING_SIZE * BLKIF_MAX_SEGMENTS_PER_REQUEST. + *(10) The discard-secure property may be present and will be set to 1 if the + * backing device supports secure discard. + */ + +/* + * STATE DIAGRAMS + * + ***************************************************************************** + * Startup * + ***************************************************************************** + * + * Tool stack creates front and back nodes with state XenbusStateInitialising. + * + * Front Back + * ================================= ===================================== + * XenbusStateInitialising XenbusStateInitialising + * o Query virtual device o Query backend device identification + * properties. data. + * o Setup OS device instance. o Open and validate backend device. + * o Publish backend features and + * transport parameters. + * | + * | + * V + * XenbusStateInitWait + * + * o Query backend features and + * transport parameters. + * o Allocate and initialize the + * request ring. + * o Publish transport parameters + * that will be in effect during + * this connection. + * | + * | + * V + * XenbusStateInitialised + * + * o Query frontend transport parameters. + * o Connect to the request ring and + * event channel. + * o Publish backend device properties. + * | + * | + * V + * XenbusStateConnected + * + * o Query backend device properties. + * o Finalize OS virtual device + * instance. + * | + * | + * V + * XenbusStateConnected + * + * Note: Drivers that do not support any optional features, or the negotiation + * of transport parameters, can skip certain states in the state machine: + * + * o A frontend may transition to XenbusStateInitialised without + * waiting for the backend to enter XenbusStateInitWait. In this + * case, default transport parameters are in effect and any + * transport parameters published by the frontend must contain + * their default values. + * + * o A backend may transition to XenbusStateInitialised, bypassing + * XenbusStateInitWait, without waiting for the frontend to first + * enter the XenbusStateInitialised state. In this case, default + * transport parameters are in effect and any transport parameters + * published by the backend must contain their default values. + * + * Drivers that support optional features and/or transport parameter + * negotiation must tolerate these additional state transition paths. + * In general this means performing the work of any skipped state + * transition, if it has not already been performed, in addition to the + * work associated with entry into the current state. + */ + +/* + * REQUEST CODES. + */ +#define BLKIF_OP_READ 0 +#define BLKIF_OP_WRITE 1 +/* + * All writes issued prior to a request with the BLKIF_OP_WRITE_BARRIER + * operation code ("barrier request") must be completed prior to the + * execution of the barrier request. All writes issued after the barrier + * request must not execute until after the completion of the barrier request. + * + * Optional. See "feature-barrier" XenBus node documentation above. + */ +#define BLKIF_OP_WRITE_BARRIER 2 +/* + * Commit any uncommitted contents of the backing device's volatile cache + * to stable storage. + * + * Optional. See "feature-flush-cache" XenBus node documentation above. + */ +#define BLKIF_OP_FLUSH_DISKCACHE 3 +/* + * Used in SLES sources for device specific command packet + * contained within the request. Reserved for that purpose. + */ +#define BLKIF_OP_RESERVED_1 4 +/* + * Indicate to the backend device that a region of storage is no longer in + * use, and may be discarded at any time without impact to the client. If + * the BLKIF_DISCARD_SECURE flag is set on the request, all copies of the + * discarded region on the device must be rendered unrecoverable before the + * command returns. + * + * This operation is analogous to performing a trim (ATA) or unamp (SCSI), + * command on a native device. + * + * More information about trim/unmap operations can be found at: + * http://t13.org/Documents/UploadedDocuments/docs2008/ + * e07154r6-Data_Set_Management_Proposal_for_ATA-ACS2.doc + * http://www.seagate.com/staticfiles/support/disc/manuals/ + * Interface%20manuals/100293068c.pdf + * + * Optional. See "feature-discard", "discard-alignment", + * "discard-granularity", and "discard-secure" in the XenBus node + * documentation above. + */ +#define BLKIF_OP_DISCARD 5 + +/* + * Recognized if "feature-max-indirect-segments" in present in the backend + * xenbus info. The "feature-max-indirect-segments" node contains the maximum + * number of segments allowed by the backend per request. If the node is + * present, the frontend might use blkif_request_indirect structs in order to + * issue requests with more than BLKIF_MAX_SEGMENTS_PER_REQUEST (11). The + * maximum number of indirect segments is fixed by the backend, but the + * frontend can issue requests with any number of indirect segments as long as + * it's less than the number provided by the backend. The indirect_grefs field + * in blkif_request_indirect should be filled by the frontend with the + * grant references of the pages that are holding the indirect segments. + * These pages are filled with an array of blkif_request_segment that hold the + * information about the segments. The number of indirect pages to use is + * determined by the number of segments an indirect request contains. Every + * indirect page can contain a maximum of + * (PAGE_SIZE / sizeof(struct blkif_request_segment)) segments, so to + * calculate the number of indirect pages to use we have to do + * ceil(indirect_segments / (PAGE_SIZE / sizeof(struct blkif_request_segment))). + * + * If a backend does not recognize BLKIF_OP_INDIRECT, it should *not* + * create the "feature-max-indirect-segments" node! + */ +#define BLKIF_OP_INDIRECT 6 + +/* + * Maximum scatter/gather segments per request. + * This is carefully chosen so that sizeof(blkif_ring_t) <= PAGE_SIZE. + * NB. This could be 12 if the ring indexes weren't stored in the same page. + */ +#define BLKIF_MAX_SEGMENTS_PER_REQUEST 11 + +/* + * Maximum number of indirect pages to use per request. + */ +#define BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST 8 + +/* + * NB. first_sect and last_sect in blkif_request_segment, as well as + * sector_number in blkif_request, are always expressed in 512-byte units. + * However they must be properly aligned to the real sector size of the + * physical disk, which is reported in the "physical-sector-size" node in + * the backend xenbus info. Also the xenbus "sectors" node is expressed in + * 512-byte units. + */ +struct blkif_request_segment { + grant_ref_t gref; /* reference to I/O buffer frame */ + /* @first_sect: first sector in frame to transfer (inclusive). */ + /* @last_sect: last sector in frame to transfer (inclusive). */ + uint8_t first_sect, last_sect; +}; + +/* + * Starting ring element for any I/O request. + */ +struct blkif_request { + uint8_t operation; /* BLKIF_OP_??? */ + uint8_t nr_segments; /* number of segments */ + blkif_vdev_t handle; /* only for read/write requests */ + uint64_t id; /* private guest value, echoed in resp */ + blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ + struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST]; +}; +typedef struct blkif_request blkif_request_t; + +/* + * Cast to this structure when blkif_request.operation == BLKIF_OP_DISCARD + * sizeof(struct blkif_request_discard) <= sizeof(struct blkif_request) + */ +struct blkif_request_discard { + uint8_t operation; /* BLKIF_OP_DISCARD */ + uint8_t flag; /* BLKIF_DISCARD_SECURE or zero */ +#define BLKIF_DISCARD_SECURE (1<<0) /* ignored if discard-secure=0 */ + blkif_vdev_t handle; /* same as for read/write requests */ + uint64_t id; /* private guest value, echoed in resp */ + blkif_sector_t sector_number;/* start sector idx on disk */ + uint64_t nr_sectors; /* number of contiguous sectors to discard*/ +}; +typedef struct blkif_request_discard blkif_request_discard_t; + +struct blkif_request_indirect { + uint8_t operation; /* BLKIF_OP_INDIRECT */ + uint8_t indirect_op; /* BLKIF_OP_{READ/WRITE} */ + uint16_t nr_segments; /* number of segments */ + uint64_t id; /* private guest value, echoed in resp */ + blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */ + blkif_vdev_t handle; /* same as for read/write requests */ + grant_ref_t indirect_grefs[BLKIF_MAX_INDIRECT_PAGES_PER_REQUEST]; +#ifdef __i386__ + uint64_t pad; /* Make it 64 byte aligned on i386 */ +#endif +}; +typedef struct blkif_request_indirect blkif_request_indirect_t; + +struct blkif_response { + uint64_t id; /* copied from request */ + uint8_t operation; /* copied from request */ + int16_t status; /* BLKIF_RSP_??? */ +}; +typedef struct blkif_response blkif_response_t; + +/* + * STATUS RETURN CODES. + */ + /* Operation not supported (only happens on barrier writes). */ +#define BLKIF_RSP_EOPNOTSUPP -2 + /* Operation failed for some unspecified reason (-EIO). */ +#define BLKIF_RSP_ERROR -1 + /* Operation completed successfully. */ +#define BLKIF_RSP_OKAY 0 + +/* + * Generate blkif ring structures and types. + */ +DEFINE_RING_TYPES(blkif, struct blkif_request, struct blkif_response); + +#define VDISK_CDROM 0x1 +#define VDISK_REMOVABLE 0x2 +#define VDISK_READONLY 0x4 + +#endif /* __XEN_PUBLIC_IO_BLKIF_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/io/console.h b/include/xen/io/console.h new file mode 100644 index 000000000..e2cd97f77 --- /dev/null +++ b/include/xen/io/console.h @@ -0,0 +1,51 @@ +/****************************************************************************** + * console.h + * + * Console I/O interface for Xen guest OSes. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2005, Keir Fraser + */ + +#ifndef __XEN_PUBLIC_IO_CONSOLE_H__ +#define __XEN_PUBLIC_IO_CONSOLE_H__ + +typedef uint32_t XENCONS_RING_IDX; + +#define MASK_XENCONS_IDX(idx, ring) ((idx) & (sizeof(ring)-1)) + +struct xencons_interface { + char in[1024]; + char out[2048]; + XENCONS_RING_IDX in_cons, in_prod; + XENCONS_RING_IDX out_cons, out_prod; +}; + +#endif /* __XEN_PUBLIC_IO_CONSOLE_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/io/protocols.h b/include/xen/io/protocols.h new file mode 100644 index 000000000..80b196bc3 --- /dev/null +++ b/include/xen/io/protocols.h @@ -0,0 +1,40 @@ +/****************************************************************************** + * protocols.h + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + */ + +#ifndef __XEN_PROTOCOLS_H__ +#define __XEN_PROTOCOLS_H__ + +#define XEN_IO_PROTO_ABI_X86_32 "x86_32-abi" +#define XEN_IO_PROTO_ABI_X86_64 "x86_64-abi" +#define XEN_IO_PROTO_ABI_ARM "arm-abi" + +#if defined(__i386__) +# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_32 +#elif defined(__x86_64__) +# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_X86_64 +#elif defined(__arm__) || defined(__aarch64__) +# define XEN_IO_PROTO_ABI_NATIVE XEN_IO_PROTO_ABI_ARM +#else +# error arch fixup needed here +#endif + +#endif diff --git a/include/xen/io/ring.h b/include/xen/io/ring.h new file mode 100644 index 000000000..73e13d7ae --- /dev/null +++ b/include/xen/io/ring.h @@ -0,0 +1,312 @@ +/****************************************************************************** + * ring.h + * + * Shared producer-consumer ring macros. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Tim Deegan and Andrew Warfield November 2004. + */ + +#ifndef __XEN_PUBLIC_IO_RING_H__ +#define __XEN_PUBLIC_IO_RING_H__ + +#include "../xen-compat.h" + +#if __XEN_INTERFACE_VERSION__ < 0x00030208 +#define xen_mb() mb() +#define xen_rmb() rmb() +#define xen_wmb() wmb() +#endif + +typedef unsigned int RING_IDX; + +/* Round a 32-bit unsigned constant down to the nearest power of two. */ +#define __RD2(_x) (((_x) & 0x00000002) ? 0x2 : ((_x) & 0x1)) +#define __RD4(_x) (((_x) & 0x0000000c) ? __RD2((_x)>>2)<<2 : __RD2(_x)) +#define __RD8(_x) (((_x) & 0x000000f0) ? __RD4((_x)>>4)<<4 : __RD4(_x)) +#define __RD16(_x) (((_x) & 0x0000ff00) ? __RD8((_x)>>8)<<8 : __RD8(_x)) +#define __RD32(_x) (((_x) & 0xffff0000) ? __RD16((_x)>>16)<<16 : __RD16(_x)) + +/* + * Calculate size of a shared ring, given the total available space for the + * ring and indexes (_sz), and the name tag of the request/response structure. + * A ring contains as many entries as will fit, rounded down to the nearest + * power of two (so we can mask with (size-1) to loop around). + */ +#define __CONST_RING_SIZE(_s, _sz) \ + (__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \ + sizeof(((struct _s##_sring *)0)->ring[0]))) +/* + * The same for passing in an actual pointer instead of a name tag. + */ +#define __RING_SIZE(_s, _sz) \ + (__RD32(((_sz) - (long)(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0]))) + +/* + * Macros to make the correct C datatypes for a new kind of ring. + * + * To make a new ring datatype, you need to have two message structures, + * let's say request_t, and response_t already defined. + * + * In a header where you want the ring datatype declared, you then do: + * + * DEFINE_RING_TYPES(mytag, request_t, response_t); + * + * These expand out to give you a set of types, as you can see below. + * The most important of these are: + * + * mytag_sring_t - The shared ring. + * mytag_front_ring_t - The 'front' half of the ring. + * mytag_back_ring_t - The 'back' half of the ring. + * + * To initialize a ring in your code you need to know the location and size + * of the shared memory area (PAGE_SIZE, for instance). To initialise + * the front half: + * + * mytag_front_ring_t front_ring; + * SHARED_RING_INIT((mytag_sring_t *)shared_page); + * FRONT_RING_INIT(&front_ring, (mytag_sring_t *)shared_page, PAGE_SIZE); + * + * Initializing the back follows similarly (note that only the front + * initializes the shared ring): + * + * mytag_back_ring_t back_ring; + * BACK_RING_INIT(&back_ring, (mytag_sring_t *)shared_page, PAGE_SIZE); + */ + +#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t) \ + \ +/* Shared ring entry */ \ +union __name##_sring_entry { \ + __req_t req; \ + __rsp_t rsp; \ +}; \ + \ +/* Shared ring page */ \ +struct __name##_sring { \ + RING_IDX req_prod, req_event; \ + RING_IDX rsp_prod, rsp_event; \ + union { \ + struct { \ + uint8_t smartpoll_active; \ + } netif; \ + struct { \ + uint8_t msg; \ + } tapif_user; \ + uint8_t pvt_pad[4]; \ + } private; \ + uint8_t __pad[44]; \ + union __name##_sring_entry ring[1]; /* variable-length */ \ +}; \ + \ +/* "Front" end's private variables */ \ +struct __name##_front_ring { \ + RING_IDX req_prod_pvt; \ + RING_IDX rsp_cons; \ + unsigned int nr_ents; \ + struct __name##_sring *sring; \ +}; \ + \ +/* "Back" end's private variables */ \ +struct __name##_back_ring { \ + RING_IDX rsp_prod_pvt; \ + RING_IDX req_cons; \ + unsigned int nr_ents; \ + struct __name##_sring *sring; \ +}; \ + \ +/* Syntactic sugar */ \ +typedef struct __name##_sring __name##_sring_t; \ +typedef struct __name##_front_ring __name##_front_ring_t; \ +typedef struct __name##_back_ring __name##_back_ring_t + +/* + * Macros for manipulating rings. + * + * FRONT_RING_whatever works on the "front end" of a ring: here + * requests are pushed on to the ring and responses taken off it. + * + * BACK_RING_whatever works on the "back end" of a ring: here + * requests are taken off the ring and responses put on. + * + * N.B. these macros do NO INTERLOCKS OR FLOW CONTROL. + * This is OK in 1-for-1 request-response situations where the + * requestor (front end) never has more than RING_SIZE()-1 + * outstanding requests. + */ + +/* Initialising empty rings */ +#define SHARED_RING_INIT(_s) do { \ + (_s)->req_prod = (_s)->rsp_prod = 0; \ + (_s)->req_event = (_s)->rsp_event = 1; \ + (void)memset((_s)->private.pvt_pad, 0, sizeof((_s)->private.pvt_pad)); \ + (void)memset((_s)->__pad, 0, sizeof((_s)->__pad)); \ +} while(0) + +#define FRONT_RING_INIT(_r, _s, __size) do { \ + (_r)->req_prod_pvt = 0; \ + (_r)->rsp_cons = 0; \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ + (_r)->sring = (_s); \ +} while (0) + +#define BACK_RING_INIT(_r, _s, __size) do { \ + (_r)->rsp_prod_pvt = 0; \ + (_r)->req_cons = 0; \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ + (_r)->sring = (_s); \ +} while (0) + +/* How big is this ring? */ +#define RING_SIZE(_r) \ + ((_r)->nr_ents) + +/* Number of free requests (for use on front side only). */ +#define RING_FREE_REQUESTS(_r) \ + (RING_SIZE(_r) - ((_r)->req_prod_pvt - (_r)->rsp_cons)) + +/* Test if there is an empty slot available on the front ring. + * (This is only meaningful from the front. ) + */ +#define RING_FULL(_r) \ + (RING_FREE_REQUESTS(_r) == 0) + +/* Test if there are outstanding messages to be processed on a ring. */ +#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ + ((_r)->sring->rsp_prod - (_r)->rsp_cons) + +#ifdef __GNUC__ +#define RING_HAS_UNCONSUMED_REQUESTS(_r) ({ \ + unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \ + unsigned int rsp = RING_SIZE(_r) - \ + ((_r)->req_cons - (_r)->rsp_prod_pvt); \ + req < rsp ? req : rsp; \ +}) +#else +/* Same as above, but without the nice GCC ({ ... }) syntax. */ +#define RING_HAS_UNCONSUMED_REQUESTS(_r) \ + ((((_r)->sring->req_prod - (_r)->req_cons) < \ + (RING_SIZE(_r) - ((_r)->req_cons - (_r)->rsp_prod_pvt))) ? \ + ((_r)->sring->req_prod - (_r)->req_cons) : \ + (RING_SIZE(_r) - ((_r)->req_cons - (_r)->rsp_prod_pvt))) +#endif + +/* Direct access to individual ring elements, by index. */ +#define RING_GET_REQUEST(_r, _idx) \ + (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req)) + +#define RING_GET_RESPONSE(_r, _idx) \ + (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp)) + +/* Loop termination condition: Would the specified index overflow the ring? */ +#define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \ + (((_cons) - (_r)->rsp_prod_pvt) >= RING_SIZE(_r)) + +/* Ill-behaved frontend determination: Can there be this many requests? */ +#define RING_REQUEST_PROD_OVERFLOW(_r, _prod) \ + (((_prod) - (_r)->rsp_prod_pvt) > RING_SIZE(_r)) + +#define RING_PUSH_REQUESTS(_r) do { \ + xen_wmb(); /* back sees requests /before/ updated producer index */ \ + (_r)->sring->req_prod = (_r)->req_prod_pvt; \ +} while (0) + +#define RING_PUSH_RESPONSES(_r) do { \ + xen_wmb(); /* front sees resps /before/ updated producer index */ \ + (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt; \ +} while (0) + +/* + * Notification hold-off (req_event and rsp_event): + * + * When queueing requests or responses on a shared ring, it may not always be + * necessary to notify the remote end. For example, if requests are in flight + * in a backend, the front may be able to queue further requests without + * notifying the back (if the back checks for new requests when it queues + * responses). + * + * When enqueuing requests or responses: + * + * Use RING_PUSH_{REQUESTS,RESPONSES}_AND_CHECK_NOTIFY(). The second argument + * is a boolean return value. True indicates that the receiver requires an + * asynchronous notification. + * + * After dequeuing requests or responses (before sleeping the connection): + * + * Use RING_FINAL_CHECK_FOR_REQUESTS() or RING_FINAL_CHECK_FOR_RESPONSES(). + * The second argument is a boolean return value. True indicates that there + * are pending messages on the ring (i.e., the connection should not be put + * to sleep). + * + * These macros will set the req_event/rsp_event field to trigger a + * notification on the very next message that is enqueued. If you want to + * create batches of work (i.e., only receive a notification after several + * messages have been enqueued) then you will need to create a customised + * version of the FINAL_CHECK macro in your own code, which sets the event + * field appropriately. + */ + +#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do { \ + RING_IDX __old = (_r)->sring->req_prod; \ + RING_IDX __new = (_r)->req_prod_pvt; \ + xen_wmb(); /* back sees requests /before/ updated producer index */ \ + (_r)->sring->req_prod = __new; \ + xen_mb(); /* back sees new requests /before/ we check req_event */ \ + (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) < \ + (RING_IDX)(__new - __old)); \ +} while (0) + +#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do { \ + RING_IDX __old = (_r)->sring->rsp_prod; \ + RING_IDX __new = (_r)->rsp_prod_pvt; \ + xen_wmb(); /* front sees resps /before/ updated producer index */ \ + (_r)->sring->rsp_prod = __new; \ + xen_mb(); /* front sees new resps /before/ we check rsp_event */ \ + (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) < \ + (RING_IDX)(__new - __old)); \ +} while (0) + +#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do { \ + (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ + if (_work_to_do) break; \ + (_r)->sring->req_event = (_r)->req_cons + 1; \ + xen_mb(); \ + (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ +} while (0) + +#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do { \ + (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ + if (_work_to_do) break; \ + (_r)->sring->rsp_event = (_r)->rsp_cons + 1; \ + xen_mb(); \ + (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ +} while (0) + +#endif /* __XEN_PUBLIC_IO_RING_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/io/xenbus.h b/include/xen/io/xenbus.h new file mode 100644 index 000000000..927f9db55 --- /dev/null +++ b/include/xen/io/xenbus.h @@ -0,0 +1,80 @@ +/***************************************************************************** + * xenbus.h + * + * Xenbus protocol details. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (C) 2005 XenSource Ltd. + */ + +#ifndef _XEN_PUBLIC_IO_XENBUS_H +#define _XEN_PUBLIC_IO_XENBUS_H + +/* + * The state of either end of the Xenbus, i.e. the current communication + * status of initialisation across the bus. States here imply nothing about + * the state of the connection between the driver and the kernel's device + * layers. + */ +enum xenbus_state { + XenbusStateUnknown = 0, + + XenbusStateInitialising = 1, + + /* + * InitWait: Finished early initialisation but waiting for information + * from the peer or hotplug scripts. + */ + XenbusStateInitWait = 2, + + /* + * Initialised: Waiting for a connection from the peer. + */ + XenbusStateInitialised = 3, + + XenbusStateConnected = 4, + + /* + * Closing: The device is being closed due to an error or an unplug event. + */ + XenbusStateClosing = 5, + + XenbusStateClosed = 6, + + /* + * Reconfiguring: The device is being reconfigured. + */ + XenbusStateReconfiguring = 7, + + XenbusStateReconfigured = 8 +}; +typedef enum xenbus_state XenbusState; + +#endif /* _XEN_PUBLIC_IO_XENBUS_H */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/io/xs_wire.h b/include/xen/io/xs_wire.h new file mode 100644 index 000000000..585f0c8f5 --- /dev/null +++ b/include/xen/io/xs_wire.h @@ -0,0 +1,138 @@ +/* + * Details of the "wire" protocol between Xen Store Daemon and client + * library or guest kernel. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (C) 2005 Rusty Russell IBM Corporation + */ + +#ifndef _XS_WIRE_H +#define _XS_WIRE_H + +enum xsd_sockmsg_type +{ + XS_DEBUG, + XS_DIRECTORY, + XS_READ, + XS_GET_PERMS, + XS_WATCH, + XS_UNWATCH, + XS_TRANSACTION_START, + XS_TRANSACTION_END, + XS_INTRODUCE, + XS_RELEASE, + XS_GET_DOMAIN_PATH, + XS_WRITE, + XS_MKDIR, + XS_RM, + XS_SET_PERMS, + XS_WATCH_EVENT, + XS_ERROR, + XS_IS_DOMAIN_INTRODUCED, + XS_RESUME, + XS_SET_TARGET, + XS_RESTRICT, + XS_RESET_WATCHES +}; + +#define XS_WRITE_NONE "NONE" +#define XS_WRITE_CREATE "CREATE" +#define XS_WRITE_CREATE_EXCL "CREATE|EXCL" + +/* We hand errors as strings, for portability. */ +struct xsd_errors +{ + int errnum; + const char *errstring; +}; +#ifdef EINVAL +#define XSD_ERROR(x) { x, #x } +/* LINTED: static unused */ +static struct xsd_errors xsd_errors[] +#if defined(__GNUC__) +__attribute__((unused)) +#endif + = { + XSD_ERROR(EINVAL), + XSD_ERROR(EACCES), + XSD_ERROR(EEXIST), + XSD_ERROR(EISDIR), + XSD_ERROR(ENOENT), + XSD_ERROR(ENOMEM), + XSD_ERROR(ENOSPC), + XSD_ERROR(EIO), + XSD_ERROR(ENOTEMPTY), + XSD_ERROR(ENOSYS), + XSD_ERROR(EROFS), + XSD_ERROR(EBUSY), + XSD_ERROR(EAGAIN), + XSD_ERROR(EISCONN), + XSD_ERROR(E2BIG) +}; +#endif + +struct xsd_sockmsg +{ + uint32_t type; /* XS_??? */ + uint32_t req_id;/* Request identifier, echoed in daemon's response. */ + uint32_t tx_id; /* Transaction id (0 if not related to a transaction). */ + uint32_t len; /* Length of data following this. */ + + /* Generally followed by nul-terminated string(s). */ +}; + +enum xs_watch_type +{ + XS_WATCH_PATH = 0, + XS_WATCH_TOKEN +}; + +/* + * `incontents 150 xenstore_struct XenStore wire protocol. + * + * Inter-domain shared memory communications. */ +#define XENSTORE_RING_SIZE 1024 +typedef uint32_t XENSTORE_RING_IDX; +#define MASK_XENSTORE_IDX(idx) ((idx) & (XENSTORE_RING_SIZE-1)) +struct xenstore_domain_interface { + char req[XENSTORE_RING_SIZE]; /* Requests to xenstore daemon. */ + char rsp[XENSTORE_RING_SIZE]; /* Replies and async watch events. */ + XENSTORE_RING_IDX req_cons, req_prod; + XENSTORE_RING_IDX rsp_cons, rsp_prod; +}; + +/* Violating this is very bad. See docs/misc/xenstore.txt. */ +#define XENSTORE_PAYLOAD_MAX 4096 + +/* Violating these just gets you an error back */ +#define XENSTORE_ABS_PATH_MAX 3072 +#define XENSTORE_REL_PATH_MAX 2048 + +#endif /* _XS_WIRE_H */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/sched.h b/include/xen/sched.h new file mode 100644 index 000000000..a30b11d96 --- /dev/null +++ b/include/xen/sched.h @@ -0,0 +1,174 @@ +/****************************************************************************** + * sched.h + * + * Scheduler state interactions + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2005, Keir Fraser + */ + +#ifndef __XEN_PUBLIC_SCHED_H__ +#define __XEN_PUBLIC_SCHED_H__ + +#include "event_channel.h" + +/* + * `incontents 150 sched Guest Scheduler Operations + * + * The SCHEDOP interface provides mechanisms for a guest to interact + * with the scheduler, including yield, blocking and shutting itself + * down. + */ + +/* + * The prototype for this hypercall is: + * ` long HYPERVISOR_sched_op(enum sched_op cmd, void *arg, ...) + * + * @cmd == SCHEDOP_??? (scheduler operation). + * @arg == Operation-specific extra argument(s), as described below. + * ... == Additional Operation-specific extra arguments, described below. + * + * Versions of Xen prior to 3.0.2 provided only the following legacy version + * of this hypercall, supporting only the commands yield, block and shutdown: + * long sched_op(int cmd, unsigned long arg) + * @cmd == SCHEDOP_??? (scheduler operation). + * @arg == 0 (SCHEDOP_yield and SCHEDOP_block) + * == SHUTDOWN_* code (SCHEDOP_shutdown) + * + * This legacy version is available to new guests as: + * ` long HYPERVISOR_sched_op_compat(enum sched_op cmd, unsigned long arg) + */ + +/* ` enum sched_op { // SCHEDOP_* => struct sched_* */ +/* + * Voluntarily yield the CPU. + * @arg == NULL. + */ +#define SCHEDOP_yield 0 + +/* + * Block execution of this VCPU until an event is received for processing. + * If called with event upcalls masked, this operation will atomically + * reenable event delivery and check for pending events before blocking the + * VCPU. This avoids a "wakeup waiting" race. + * @arg == NULL. + */ +#define SCHEDOP_block 1 + +/* + * Halt execution of this domain (all VCPUs) and notify the system controller. + * @arg == pointer to sched_shutdown_t structure. + * + * If the sched_shutdown_t reason is SHUTDOWN_suspend then this + * hypercall takes an additional extra argument which should be the + * MFN of the guest's start_info_t. + * + * In addition, which reason is SHUTDOWN_suspend this hypercall + * returns 1 if suspend was cancelled or the domain was merely + * checkpointed, and 0 if it is resuming in a new domain. + */ +#define SCHEDOP_shutdown 2 + +/* + * Poll a set of event-channel ports. Return when one or more are pending. An + * optional timeout may be specified. + * @arg == pointer to sched_poll_t structure. + */ +#define SCHEDOP_poll 3 + +/* + * Declare a shutdown for another domain. The main use of this function is + * in interpreting shutdown requests and reasons for fully-virtualized + * domains. A para-virtualized domain may use SCHEDOP_shutdown directly. + * @arg == pointer to sched_remote_shutdown_t structure. + */ +#define SCHEDOP_remote_shutdown 4 + +/* + * Latch a shutdown code, so that when the domain later shuts down it + * reports this code to the control tools. + * @arg == sched_shutdown_t, as for SCHEDOP_shutdown. + */ +#define SCHEDOP_shutdown_code 5 + +/* + * Setup, poke and destroy a domain watchdog timer. + * @arg == pointer to sched_watchdog_t structure. + * With id == 0, setup a domain watchdog timer to cause domain shutdown + * after timeout, returns watchdog id. + * With id != 0 and timeout == 0, destroy domain watchdog timer. + * With id != 0 and timeout != 0, poke watchdog timer and set new timeout. + */ +#define SCHEDOP_watchdog 6 +/* ` } */ + +struct sched_shutdown { + unsigned int reason; /* SHUTDOWN_* => enum sched_shutdown_reason */ +}; +typedef struct sched_shutdown sched_shutdown_t; +DEFINE_XEN_GUEST_HANDLE(sched_shutdown_t); + +struct sched_poll { + XEN_GUEST_HANDLE(evtchn_port_t) ports; + unsigned int nr_ports; + uint64_t timeout; +}; +typedef struct sched_poll sched_poll_t; +DEFINE_XEN_GUEST_HANDLE(sched_poll_t); + +struct sched_remote_shutdown { + domid_t domain_id; /* Remote domain ID */ + unsigned int reason; /* SHUTDOWN_* => enum sched_shutdown_reason */ +}; +typedef struct sched_remote_shutdown sched_remote_shutdown_t; +DEFINE_XEN_GUEST_HANDLE(sched_remote_shutdown_t); + +struct sched_watchdog { + uint32_t id; /* watchdog ID */ + uint32_t timeout; /* timeout */ +}; +typedef struct sched_watchdog sched_watchdog_t; +DEFINE_XEN_GUEST_HANDLE(sched_watchdog_t); + +/* + * Reason codes for SCHEDOP_shutdown. These may be interpreted by control + * software to determine the appropriate action. For the most part, Xen does + * not care about the shutdown code. + */ +/* ` enum sched_shutdown_reason { */ +#define SHUTDOWN_poweroff 0 /* Domain exited normally. Clean up and kill. */ +#define SHUTDOWN_reboot 1 /* Clean up, kill, and then restart. */ +#define SHUTDOWN_suspend 2 /* Clean up, save suspend info, kill. */ +#define SHUTDOWN_crash 3 /* Tell controller we've crashed. */ +#define SHUTDOWN_watchdog 4 /* Restart because watchdog time expired. */ +#define SHUTDOWN_MAX 4 /* Maximum valid shutdown reason. */ +/* ` } */ + +#endif /* __XEN_PUBLIC_SCHED_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/include/xen/xen-compat.h b/include/xen/xen-compat.h new file mode 100644 index 000000000..3eb80a02d --- /dev/null +++ b/include/xen/xen-compat.h @@ -0,0 +1,44 @@ +/****************************************************************************** + * xen-compat.h + * + * Guest OS interface to Xen. Compatibility layer. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2006, Christian Limpach + */ + +#ifndef __XEN_PUBLIC_XEN_COMPAT_H__ +#define __XEN_PUBLIC_XEN_COMPAT_H__ + +#define __XEN_LATEST_INTERFACE_VERSION__ 0x00040400 + +#if defined(__XEN__) || defined(__XEN_TOOLS__) +/* Xen is built with matching headers and implements the latest interface. */ +#define __XEN_INTERFACE_VERSION__ __XEN_LATEST_INTERFACE_VERSION__ +#elif !defined(__XEN_INTERFACE_VERSION__) +/* Guests which do not specify a version get the legacy interface. */ +#define __XEN_INTERFACE_VERSION__ 0x00000000 +#endif + +#if __XEN_INTERFACE_VERSION__ > __XEN_LATEST_INTERFACE_VERSION__ +#error "These header files do not support the requested interface version." +#endif + +#endif /* __XEN_PUBLIC_XEN_COMPAT_H__ */ diff --git a/include/xen/xen.h b/include/xen/xen.h new file mode 100644 index 000000000..a6a20926a --- /dev/null +++ b/include/xen/xen.h @@ -0,0 +1,899 @@ +/****************************************************************************** + * xen.h + * + * Guest OS interface to Xen. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2004, K A Fraser + */ + +#ifndef __XEN_PUBLIC_XEN_H__ +#define __XEN_PUBLIC_XEN_H__ + +#include "xen-compat.h" + +#if defined(__i386__) || defined(__x86_64__) +#include "arch-x86/xen.h" +#elif defined(__arm__) || defined (__aarch64__) +#include "arch-arm.h" +#else +#error "Unsupported architecture" +#endif + +#ifndef __ASSEMBLY__ +/* Guest handles for primitive C types. */ +DEFINE_XEN_GUEST_HANDLE(char); +__DEFINE_XEN_GUEST_HANDLE(uchar, unsigned char); +DEFINE_XEN_GUEST_HANDLE(int); +__DEFINE_XEN_GUEST_HANDLE(uint, unsigned int); +#if __XEN_INTERFACE_VERSION__ < 0x00040300 +DEFINE_XEN_GUEST_HANDLE(long); +__DEFINE_XEN_GUEST_HANDLE(ulong, unsigned long); +#endif +DEFINE_XEN_GUEST_HANDLE(void); + +DEFINE_XEN_GUEST_HANDLE(uint64_t); +DEFINE_XEN_GUEST_HANDLE(xen_pfn_t); +DEFINE_XEN_GUEST_HANDLE(xen_ulong_t); +#endif + +/* + * HYPERCALLS + */ + +/* `incontents 100 hcalls List of hypercalls + * ` enum hypercall_num { // __HYPERVISOR_* => HYPERVISOR_*() + */ + +#define __HYPERVISOR_set_trap_table 0 +#define __HYPERVISOR_mmu_update 1 +#define __HYPERVISOR_set_gdt 2 +#define __HYPERVISOR_stack_switch 3 +#define __HYPERVISOR_set_callbacks 4 +#define __HYPERVISOR_fpu_taskswitch 5 +#define __HYPERVISOR_sched_op_compat 6 /* compat since 0x00030101 */ +#define __HYPERVISOR_platform_op 7 +#define __HYPERVISOR_set_debugreg 8 +#define __HYPERVISOR_get_debugreg 9 +#define __HYPERVISOR_update_descriptor 10 +#define __HYPERVISOR_memory_op 12 +#define __HYPERVISOR_multicall 13 +#define __HYPERVISOR_update_va_mapping 14 +#define __HYPERVISOR_set_timer_op 15 +#define __HYPERVISOR_event_channel_op_compat 16 /* compat since 0x00030202 */ +#define __HYPERVISOR_xen_version 17 +#define __HYPERVISOR_console_io 18 +#define __HYPERVISOR_physdev_op_compat 19 /* compat since 0x00030202 */ +#define __HYPERVISOR_grant_table_op 20 +#define __HYPERVISOR_vm_assist 21 +#define __HYPERVISOR_update_va_mapping_otherdomain 22 +#define __HYPERVISOR_iret 23 /* x86 only */ +#define __HYPERVISOR_vcpu_op 24 +#define __HYPERVISOR_set_segment_base 25 /* x86/64 only */ +#define __HYPERVISOR_mmuext_op 26 +#define __HYPERVISOR_xsm_op 27 +#define __HYPERVISOR_nmi_op 28 +#define __HYPERVISOR_sched_op 29 +#define __HYPERVISOR_callback_op 30 +#define __HYPERVISOR_xenoprof_op 31 +#define __HYPERVISOR_event_channel_op 32 +#define __HYPERVISOR_physdev_op 33 +#define __HYPERVISOR_hvm_op 34 +#define __HYPERVISOR_sysctl 35 +#define __HYPERVISOR_domctl 36 +#define __HYPERVISOR_kexec_op 37 +#define __HYPERVISOR_tmem_op 38 +#define __HYPERVISOR_xc_reserved_op 39 /* reserved for XenClient */ + +/* Architecture-specific hypercall definitions. */ +#define __HYPERVISOR_arch_0 48 +#define __HYPERVISOR_arch_1 49 +#define __HYPERVISOR_arch_2 50 +#define __HYPERVISOR_arch_3 51 +#define __HYPERVISOR_arch_4 52 +#define __HYPERVISOR_arch_5 53 +#define __HYPERVISOR_arch_6 54 +#define __HYPERVISOR_arch_7 55 + +/* ` } */ + +/* + * HYPERCALL COMPATIBILITY. + */ + +/* New sched_op hypercall introduced in 0x00030101. */ +#if __XEN_INTERFACE_VERSION__ < 0x00030101 +#undef __HYPERVISOR_sched_op +#define __HYPERVISOR_sched_op __HYPERVISOR_sched_op_compat +#endif + +/* New event-channel and physdev hypercalls introduced in 0x00030202. */ +#if __XEN_INTERFACE_VERSION__ < 0x00030202 +#undef __HYPERVISOR_event_channel_op +#define __HYPERVISOR_event_channel_op __HYPERVISOR_event_channel_op_compat +#undef __HYPERVISOR_physdev_op +#define __HYPERVISOR_physdev_op __HYPERVISOR_physdev_op_compat +#endif + +/* New platform_op hypercall introduced in 0x00030204. */ +#if __XEN_INTERFACE_VERSION__ < 0x00030204 +#define __HYPERVISOR_dom0_op __HYPERVISOR_platform_op +#endif + +/* + * VIRTUAL INTERRUPTS + * + * Virtual interrupts that a guest OS may receive from Xen. + * + * In the side comments, 'V.' denotes a per-VCPU VIRQ while 'G.' denotes a + * global VIRQ. The former can be bound once per VCPU and cannot be re-bound. + * The latter can be allocated only once per guest: they must initially be + * allocated to VCPU0 but can subsequently be re-bound. + */ +/* ` enum virq { */ +#define VIRQ_TIMER 0 /* V. Timebase update, and/or requested timeout. */ +#define VIRQ_DEBUG 1 /* V. Request guest to dump debug info. */ +#define VIRQ_CONSOLE 2 /* G. (DOM0) Bytes received on emergency console. */ +#define VIRQ_DOM_EXC 3 /* G. (DOM0) Exceptional event for some domain. */ +#define VIRQ_TBUF 4 /* G. (DOM0) Trace buffer has records available. */ +#define VIRQ_DEBUGGER 6 /* G. (DOM0) A domain has paused for debugging. */ +#define VIRQ_XENOPROF 7 /* V. XenOprofile interrupt: new sample available */ +#define VIRQ_CON_RING 8 /* G. (DOM0) Bytes received on console */ +#define VIRQ_PCPU_STATE 9 /* G. (DOM0) PCPU state changed */ +#define VIRQ_MEM_EVENT 10 /* G. (DOM0) A memory event has occured */ +#define VIRQ_XC_RESERVED 11 /* G. Reserved for XenClient */ +#define VIRQ_ENOMEM 12 /* G. (DOM0) Low on heap memory */ + +/* Architecture-specific VIRQ definitions. */ +#define VIRQ_ARCH_0 16 +#define VIRQ_ARCH_1 17 +#define VIRQ_ARCH_2 18 +#define VIRQ_ARCH_3 19 +#define VIRQ_ARCH_4 20 +#define VIRQ_ARCH_5 21 +#define VIRQ_ARCH_6 22 +#define VIRQ_ARCH_7 23 +/* ` } */ + +#define NR_VIRQS 24 + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_mmu_update(const struct mmu_update reqs[], + * ` unsigned count, unsigned *done_out, + * ` unsigned foreigndom) + * ` + * @reqs is an array of mmu_update_t structures ((ptr, val) pairs). + * @count is the length of the above array. + * @pdone is an output parameter indicating number of completed operations + * @foreigndom[15:0]: FD, the expected owner of data pages referenced in this + * hypercall invocation. Can be DOMID_SELF. + * @foreigndom[31:16]: PFD, the expected owner of pagetable pages referenced + * in this hypercall invocation. The value of this field + * (x) encodes the PFD as follows: + * x == 0 => PFD == DOMID_SELF + * x != 0 => PFD == x - 1 + * + * Sub-commands: ptr[1:0] specifies the appropriate MMU_* command. + * ------------- + * ptr[1:0] == MMU_NORMAL_PT_UPDATE: + * Updates an entry in a page table belonging to PFD. If updating an L1 table, + * and the new table entry is valid/present, the mapped frame must belong to + * FD. If attempting to map an I/O page then the caller assumes the privilege + * of the FD. + * FD == DOMID_IO: Permit /only/ I/O mappings, at the priv level of the caller. + * FD == DOMID_XEN: Map restricted areas of Xen's heap space. + * ptr[:2] -- Machine address of the page-table entry to modify. + * val -- Value to write. + * + * There also certain implicit requirements when using this hypercall. The + * pages that make up a pagetable must be mapped read-only in the guest. + * This prevents uncontrolled guest updates to the pagetable. Xen strictly + * enforces this, and will disallow any pagetable update which will end up + * mapping pagetable page RW, and will disallow using any writable page as a + * pagetable. In practice it means that when constructing a page table for a + * process, thread, etc, we MUST be very dilligient in following these rules: + * 1). Start with top-level page (PGD or in Xen language: L4). Fill out + * the entries. + * 2). Keep on going, filling out the upper (PUD or L3), and middle (PMD + * or L2). + * 3). Start filling out the PTE table (L1) with the PTE entries. Once + * done, make sure to set each of those entries to RO (so writeable bit + * is unset). Once that has been completed, set the PMD (L2) for this + * PTE table as RO. + * 4). When completed with all of the PMD (L2) entries, and all of them have + * been set to RO, make sure to set RO the PUD (L3). Do the same + * operation on PGD (L4) pagetable entries that have a PUD (L3) entry. + * 5). Now before you can use those pages (so setting the cr3), you MUST also + * pin them so that the hypervisor can verify the entries. This is done + * via the HYPERVISOR_mmuext_op(MMUEXT_PIN_L4_TABLE, guest physical frame + * number of the PGD (L4)). And this point the HYPERVISOR_mmuext_op( + * MMUEXT_NEW_BASEPTR, guest physical frame number of the PGD (L4)) can be + * issued. + * For 32-bit guests, the L4 is not used (as there is less pagetables), so + * instead use L3. + * At this point the pagetables can be modified using the MMU_NORMAL_PT_UPDATE + * hypercall. Also if so desired the OS can also try to write to the PTE + * and be trapped by the hypervisor (as the PTE entry is RO). + * + * To deallocate the pages, the operations are the reverse of the steps + * mentioned above. The argument is MMUEXT_UNPIN_TABLE for all levels and the + * pagetable MUST not be in use (meaning that the cr3 is not set to it). + * + * ptr[1:0] == MMU_MACHPHYS_UPDATE: + * Updates an entry in the machine->pseudo-physical mapping table. + * ptr[:2] -- Machine address within the frame whose mapping to modify. + * The frame must belong to the FD, if one is specified. + * val -- Value to write into the mapping entry. + * + * ptr[1:0] == MMU_PT_UPDATE_PRESERVE_AD: + * As MMU_NORMAL_PT_UPDATE above, but A/D bits currently in the PTE are ORed + * with those in @val. + * + * @val is usually the machine frame number along with some attributes. + * The attributes by default follow the architecture defined bits. Meaning that + * if this is a X86_64 machine and four page table layout is used, the layout + * of val is: + * - 63 if set means No execute (NX) + * - 46-13 the machine frame number + * - 12 available for guest + * - 11 available for guest + * - 10 available for guest + * - 9 available for guest + * - 8 global + * - 7 PAT (PSE is disabled, must use hypercall to make 4MB or 2MB pages) + * - 6 dirty + * - 5 accessed + * - 4 page cached disabled + * - 3 page write through + * - 2 userspace accessible + * - 1 writeable + * - 0 present + * + * The one bits that does not fit with the default layout is the PAGE_PSE + * also called PAGE_PAT). The MMUEXT_[UN]MARK_SUPER arguments to the + * HYPERVISOR_mmuext_op serve as mechanism to set a pagetable to be 4MB + * (or 2MB) instead of using the PAGE_PSE bit. + * + * The reason that the PAGE_PSE (bit 7) is not being utilized is due to Xen + * using it as the Page Attribute Table (PAT) bit - for details on it please + * refer to Intel SDM 10.12. The PAT allows to set the caching attributes of + * pages instead of using MTRRs. + * + * The PAT MSR is as follows (it is a 64-bit value, each entry is 8 bits): + * PAT4 PAT0 + * +-----+-----+----+----+----+-----+----+----+ + * | UC | UC- | WC | WB | UC | UC- | WC | WB | <= Linux + * +-----+-----+----+----+----+-----+----+----+ + * | UC | UC- | WT | WB | UC | UC- | WT | WB | <= BIOS (default when machine boots) + * +-----+-----+----+----+----+-----+----+----+ + * | rsv | rsv | WP | WC | UC | UC- | WT | WB | <= Xen + * +-----+-----+----+----+----+-----+----+----+ + * + * The lookup of this index table translates to looking up + * Bit 7, Bit 4, and Bit 3 of val entry: + * + * PAT/PSE (bit 7) ... PCD (bit 4) .. PWT (bit 3). + * + * If all bits are off, then we are using PAT0. If bit 3 turned on, + * then we are using PAT1, if bit 3 and bit 4, then PAT2.. + * + * As you can see, the Linux PAT1 translates to PAT4 under Xen. Which means + * that if a guest that follows Linux's PAT setup and would like to set Write + * Combined on pages it MUST use PAT4 entry. Meaning that Bit 7 (PAGE_PAT) is + * set. For example, under Linux it only uses PAT0, PAT1, and PAT2 for the + * caching as: + * + * WB = none (so PAT0) + * WC = PWT (bit 3 on) + * UC = PWT | PCD (bit 3 and 4 are on). + * + * To make it work with Xen, it needs to translate the WC bit as so: + * + * PWT (so bit 3 on) --> PAT (so bit 7 is on) and clear bit 3 + * + * And to translate back it would: + * + * PAT (bit 7 on) --> PWT (bit 3 on) and clear bit 7. + */ +#define MMU_NORMAL_PT_UPDATE 0 /* checked '*ptr = val'. ptr is MA. */ +#define MMU_MACHPHYS_UPDATE 1 /* ptr = MA of frame to modify entry for */ +#define MMU_PT_UPDATE_PRESERVE_AD 2 /* atomically: *ptr = val | (*ptr&(A|D)) */ + +/* + * MMU EXTENDED OPERATIONS + * + * ` enum neg_errnoval + * ` HYPERVISOR_mmuext_op(mmuext_op_t uops[], + * ` unsigned int count, + * ` unsigned int *pdone, + * ` unsigned int foreigndom) + */ +/* HYPERVISOR_mmuext_op() accepts a list of mmuext_op structures. + * A foreigndom (FD) can be specified (or DOMID_SELF for none). + * Where the FD has some effect, it is described below. + * + * cmd: MMUEXT_(UN)PIN_*_TABLE + * mfn: Machine frame number to be (un)pinned as a p.t. page. + * The frame must belong to the FD, if one is specified. + * + * cmd: MMUEXT_NEW_BASEPTR + * mfn: Machine frame number of new page-table base to install in MMU. + * + * cmd: MMUEXT_NEW_USER_BASEPTR [x86/64 only] + * mfn: Machine frame number of new page-table base to install in MMU + * when in user space. + * + * cmd: MMUEXT_TLB_FLUSH_LOCAL + * No additional arguments. Flushes local TLB. + * + * cmd: MMUEXT_INVLPG_LOCAL + * linear_addr: Linear address to be flushed from the local TLB. + * + * cmd: MMUEXT_TLB_FLUSH_MULTI + * vcpumask: Pointer to bitmap of VCPUs to be flushed. + * + * cmd: MMUEXT_INVLPG_MULTI + * linear_addr: Linear address to be flushed. + * vcpumask: Pointer to bitmap of VCPUs to be flushed. + * + * cmd: MMUEXT_TLB_FLUSH_ALL + * No additional arguments. Flushes all VCPUs' TLBs. + * + * cmd: MMUEXT_INVLPG_ALL + * linear_addr: Linear address to be flushed from all VCPUs' TLBs. + * + * cmd: MMUEXT_FLUSH_CACHE + * No additional arguments. Writes back and flushes cache contents. + * + * cmd: MMUEXT_FLUSH_CACHE_GLOBAL + * No additional arguments. Writes back and flushes cache contents + * on all CPUs in the system. + * + * cmd: MMUEXT_SET_LDT + * linear_addr: Linear address of LDT base (NB. must be page-aligned). + * nr_ents: Number of entries in LDT. + * + * cmd: MMUEXT_CLEAR_PAGE + * mfn: Machine frame number to be cleared. + * + * cmd: MMUEXT_COPY_PAGE + * mfn: Machine frame number of the destination page. + * src_mfn: Machine frame number of the source page. + * + * cmd: MMUEXT_[UN]MARK_SUPER + * mfn: Machine frame number of head of superpage to be [un]marked. + */ +/* ` enum mmuext_cmd { */ +#define MMUEXT_PIN_L1_TABLE 0 +#define MMUEXT_PIN_L2_TABLE 1 +#define MMUEXT_PIN_L3_TABLE 2 +#define MMUEXT_PIN_L4_TABLE 3 +#define MMUEXT_UNPIN_TABLE 4 +#define MMUEXT_NEW_BASEPTR 5 +#define MMUEXT_TLB_FLUSH_LOCAL 6 +#define MMUEXT_INVLPG_LOCAL 7 +#define MMUEXT_TLB_FLUSH_MULTI 8 +#define MMUEXT_INVLPG_MULTI 9 +#define MMUEXT_TLB_FLUSH_ALL 10 +#define MMUEXT_INVLPG_ALL 11 +#define MMUEXT_FLUSH_CACHE 12 +#define MMUEXT_SET_LDT 13 +#define MMUEXT_NEW_USER_BASEPTR 15 +#define MMUEXT_CLEAR_PAGE 16 +#define MMUEXT_COPY_PAGE 17 +#define MMUEXT_FLUSH_CACHE_GLOBAL 18 +#define MMUEXT_MARK_SUPER 19 +#define MMUEXT_UNMARK_SUPER 20 +/* ` } */ + +#ifndef __ASSEMBLY__ +struct mmuext_op { + unsigned int cmd; /* => enum mmuext_cmd */ + union { + /* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR + * CLEAR_PAGE, COPY_PAGE, [UN]MARK_SUPER */ + xen_pfn_t mfn; + /* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */ + unsigned long linear_addr; + } arg1; + union { + /* SET_LDT */ + unsigned int nr_ents; + /* TLB_FLUSH_MULTI, INVLPG_MULTI */ +#if __XEN_INTERFACE_VERSION__ >= 0x00030205 + XEN_GUEST_HANDLE(const_void) vcpumask; +#else + const void *vcpumask; +#endif + /* COPY_PAGE */ + xen_pfn_t src_mfn; + } arg2; +}; +typedef struct mmuext_op mmuext_op_t; +DEFINE_XEN_GUEST_HANDLE(mmuext_op_t); +#endif + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_update_va_mapping(unsigned long va, u64 val, + * ` enum uvm_flags flags) + * ` + * ` enum neg_errnoval + * ` HYPERVISOR_update_va_mapping_otherdomain(unsigned long va, u64 val, + * ` enum uvm_flags flags, + * ` domid_t domid) + * ` + * ` @va: The virtual address whose mapping we want to change + * ` @val: The new page table entry, must contain a machine address + * ` @flags: Control TLB flushes + */ +/* These are passed as 'flags' to update_va_mapping. They can be ORed. */ +/* When specifying UVMF_MULTI, also OR in a pointer to a CPU bitmap. */ +/* UVMF_LOCAL is merely UVMF_MULTI with a NULL bitmap pointer. */ +/* ` enum uvm_flags { */ +#define UVMF_NONE (0UL<<0) /* No flushing at all. */ +#define UVMF_TLB_FLUSH (1UL<<0) /* Flush entire TLB(s). */ +#define UVMF_INVLPG (2UL<<0) /* Flush only one entry. */ +#define UVMF_FLUSHTYPE_MASK (3UL<<0) +#define UVMF_MULTI (0UL<<2) /* Flush subset of TLBs. */ +#define UVMF_LOCAL (0UL<<2) /* Flush local TLB. */ +#define UVMF_ALL (1UL<<2) /* Flush all TLBs. */ +/* ` } */ + +/* + * Commands to HYPERVISOR_console_io(). + */ +#define CONSOLEIO_write 0 +#define CONSOLEIO_read 1 + +/* + * Commands to HYPERVISOR_vm_assist(). + */ +#define VMASST_CMD_enable 0 +#define VMASST_CMD_disable 1 + +/* x86/32 guests: simulate full 4GB segment limits. */ +#define VMASST_TYPE_4gb_segments 0 + +/* x86/32 guests: trap (vector 15) whenever above vmassist is used. */ +#define VMASST_TYPE_4gb_segments_notify 1 + +/* + * x86 guests: support writes to bottom-level PTEs. + * NB1. Page-directory entries cannot be written. + * NB2. Guest must continue to remove all writable mappings of PTEs. + */ +#define VMASST_TYPE_writable_pagetables 2 + +/* x86/PAE guests: support PDPTs above 4GB. */ +#define VMASST_TYPE_pae_extended_cr3 3 + +#define MAX_VMASST_TYPE 3 + +#ifndef __ASSEMBLY__ + +typedef uint16_t domid_t; + +/* Domain ids >= DOMID_FIRST_RESERVED cannot be used for ordinary domains. */ +#define DOMID_FIRST_RESERVED (0x7FF0U) + +/* DOMID_SELF is used in certain contexts to refer to oneself. */ +#define DOMID_SELF (0x7FF0U) + +/* + * DOMID_IO is used to restrict page-table updates to mapping I/O memory. + * Although no Foreign Domain need be specified to map I/O pages, DOMID_IO + * is useful to ensure that no mappings to the OS's own heap are accidentally + * installed. (e.g., in Linux this could cause havoc as reference counts + * aren't adjusted on the I/O-mapping code path). + * This only makes sense in MMUEXT_SET_FOREIGNDOM, but in that context can + * be specified by any calling domain. + */ +#define DOMID_IO (0x7FF1U) + +/* + * DOMID_XEN is used to allow privileged domains to map restricted parts of + * Xen's heap space (e.g., the machine_to_phys table). + * This only makes sense in MMUEXT_SET_FOREIGNDOM, and is only permitted if + * the caller is privileged. + */ +#define DOMID_XEN (0x7FF2U) + +/* + * DOMID_COW is used as the owner of sharable pages */ +#define DOMID_COW (0x7FF3U) + +/* DOMID_INVALID is used to identify pages with unknown owner. */ +#define DOMID_INVALID (0x7FF4U) + +/* Idle domain. */ +#define DOMID_IDLE (0x7FFFU) + +/* + * Send an array of these to HYPERVISOR_mmu_update(). + * NB. The fields are natural pointer/address size for this architecture. + */ +struct mmu_update { + uint64_t ptr; /* Machine address of PTE. */ + uint64_t val; /* New contents of PTE. */ +}; +typedef struct mmu_update mmu_update_t; +DEFINE_XEN_GUEST_HANDLE(mmu_update_t); + +/* + * ` enum neg_errnoval + * ` HYPERVISOR_multicall(multicall_entry_t call_list[], + * ` uint32_t nr_calls); + * + * NB. The fields are logically the natural register size for this + * architecture. In cases where xen_ulong_t is larger than this then + * any unused bits in the upper portion must be zero. + */ +struct multicall_entry { + xen_ulong_t op, result; + xen_ulong_t args[6]; +}; +typedef struct multicall_entry multicall_entry_t; +DEFINE_XEN_GUEST_HANDLE(multicall_entry_t); + +#if __XEN_INTERFACE_VERSION__ < 0x00040400 +/* + * Event channel endpoints per domain (when using the 2-level ABI): + * 1024 if a long is 32 bits; 4096 if a long is 64 bits. + */ +#define NR_EVENT_CHANNELS EVTCHN_2L_NR_CHANNELS +#endif + +struct vcpu_time_info { + /* + * Updates to the following values are preceded and followed by an + * increment of 'version'. The guest can therefore detect updates by + * looking for changes to 'version'. If the least-significant bit of + * the version number is set then an update is in progress and the guest + * must wait to read a consistent set of values. + * The correct way to interact with the version number is similar to + * Linux's seqlock: see the implementations of read_seqbegin/read_seqretry. + */ + uint32_t version; + uint32_t pad0; + uint64_t tsc_timestamp; /* TSC at last update of time vals. */ + uint64_t system_time; /* Time, in nanosecs, since boot. */ + /* + * Current system time: + * system_time + + * ((((tsc - tsc_timestamp) << tsc_shift) * tsc_to_system_mul) >> 32) + * CPU frequency (Hz): + * ((10^9 << 32) / tsc_to_system_mul) >> tsc_shift + */ + uint32_t tsc_to_system_mul; + int8_t tsc_shift; + int8_t pad1[3]; +}; /* 32 bytes */ +typedef struct vcpu_time_info vcpu_time_info_t; + +struct vcpu_info { + /* + * 'evtchn_upcall_pending' is written non-zero by Xen to indicate + * a pending notification for a particular VCPU. It is then cleared + * by the guest OS /before/ checking for pending work, thus avoiding + * a set-and-check race. Note that the mask is only accessed by Xen + * on the CPU that is currently hosting the VCPU. This means that the + * pending and mask flags can be updated by the guest without special + * synchronisation (i.e., no need for the x86 LOCK prefix). + * This may seem suboptimal because if the pending flag is set by + * a different CPU then an IPI may be scheduled even when the mask + * is set. However, note: + * 1. The task of 'interrupt holdoff' is covered by the per-event- + * channel mask bits. A 'noisy' event that is continually being + * triggered can be masked at source at this very precise + * granularity. + * 2. The main purpose of the per-VCPU mask is therefore to restrict + * reentrant execution: whether for concurrency control, or to + * prevent unbounded stack usage. Whatever the purpose, we expect + * that the mask will be asserted only for short periods at a time, + * and so the likelihood of a 'spurious' IPI is suitably small. + * The mask is read before making an event upcall to the guest: a + * non-zero mask therefore guarantees that the VCPU will not receive + * an upcall activation. The mask is cleared when the VCPU requests + * to block: this avoids wakeup-waiting races. + */ + uint8_t evtchn_upcall_pending; +#ifdef XEN_HAVE_PV_UPCALL_MASK + uint8_t evtchn_upcall_mask; +#else /* XEN_HAVE_PV_UPCALL_MASK */ + uint8_t pad0; +#endif /* XEN_HAVE_PV_UPCALL_MASK */ + xen_ulong_t evtchn_pending_sel; + struct arch_vcpu_info arch; + struct vcpu_time_info time; +}; /* 64 bytes (x86) */ +#ifndef __XEN__ +typedef struct vcpu_info vcpu_info_t; +#endif + +/* + * `incontents 200 startofday_shared Start-of-day shared data structure + * Xen/kernel shared data -- pointer provided in start_info. + * + * This structure is defined to be both smaller than a page, and the + * only data on the shared page, but may vary in actual size even within + * compatible Xen versions; guests should not rely on the size + * of this structure remaining constant. + */ +struct shared_info { + struct vcpu_info vcpu_info[XEN_LEGACY_MAX_VCPUS]; + + /* + * A domain can create "event channels" on which it can send and receive + * asynchronous event notifications. There are three classes of event that + * are delivered by this mechanism: + * 1. Bi-directional inter- and intra-domain connections. Domains must + * arrange out-of-band to set up a connection (usually by allocating + * an unbound 'listener' port and avertising that via a storage service + * such as xenstore). + * 2. Physical interrupts. A domain with suitable hardware-access + * privileges can bind an event-channel port to a physical interrupt + * source. + * 3. Virtual interrupts ('events'). A domain can bind an event-channel + * port to a virtual interrupt source, such as the virtual-timer + * device or the emergency console. + * + * Event channels are addressed by a "port index". Each channel is + * associated with two bits of information: + * 1. PENDING -- notifies the domain that there is a pending notification + * to be processed. This bit is cleared by the guest. + * 2. MASK -- if this bit is clear then a 0->1 transition of PENDING + * will cause an asynchronous upcall to be scheduled. This bit is only + * updated by the guest. It is read-only within Xen. If a channel + * becomes pending while the channel is masked then the 'edge' is lost + * (i.e., when the channel is unmasked, the guest must manually handle + * pending notifications as no upcall will be scheduled by Xen). + * + * To expedite scanning of pending notifications, any 0->1 pending + * transition on an unmasked channel causes a corresponding bit in a + * per-vcpu selector word to be set. Each bit in the selector covers a + * 'C long' in the PENDING bitfield array. + */ + xen_ulong_t evtchn_pending[sizeof(xen_ulong_t) * 8]; + xen_ulong_t evtchn_mask[sizeof(xen_ulong_t) * 8]; + + /* + * Wallclock time: updated only by control software. Guests should base + * their gettimeofday() syscall on this wallclock-base value. + */ + uint32_t wc_version; /* Version counter: see vcpu_time_info_t. */ + uint32_t wc_sec; /* Secs 00:00:00 UTC, Jan 1, 1970. */ + uint32_t wc_nsec; /* Nsecs 00:00:00 UTC, Jan 1, 1970. */ + + struct arch_shared_info arch; + +}; +#ifndef __XEN__ +typedef struct shared_info shared_info_t; +#endif + +/* + * `incontents 200 startofday Start-of-day memory layout + * + * 1. The domain is started within contiguous virtual-memory region. + * 2. The contiguous region ends on an aligned 4MB boundary. + * 3. This the order of bootstrap elements in the initial virtual region: + * a. relocated kernel image + * b. initial ram disk [mod_start, mod_len] + * c. list of allocated page frames [mfn_list, nr_pages] + * (unless relocated due to XEN_ELFNOTE_INIT_P2M) + * d. start_info_t structure [register ESI (x86)] + * e. bootstrap page tables [pt_base and CR3 (x86)] + * f. bootstrap stack [register ESP (x86)] + * 4. Bootstrap elements are packed together, but each is 4kB-aligned. + * 5. The initial ram disk may be omitted. + * 6. The list of page frames forms a contiguous 'pseudo-physical' memory + * layout for the domain. In particular, the bootstrap virtual-memory + * region is a 1:1 mapping to the first section of the pseudo-physical map. + * 7. All bootstrap elements are mapped read-writable for the guest OS. The + * only exception is the bootstrap page table, which is mapped read-only. + * 8. There is guaranteed to be at least 512kB padding after the final + * bootstrap element. If necessary, the bootstrap virtual region is + * extended by an extra 4MB to ensure this. + * + * Note: Prior to 25833:bb85bbccb1c9. ("x86/32-on-64 adjust Dom0 initial page + * table layout") a bug caused the pt_base (3.e above) and cr3 to not point + * to the start of the guest page tables (it was offset by two pages). + * This only manifested itself on 32-on-64 dom0 kernels and not 32-on-64 domU + * or 64-bit kernels of any colour. The page tables for a 32-on-64 dom0 got + * allocated in the order: 'first L1','first L2', 'first L3', so the offset + * to the page table base is by two pages back. The initial domain if it is + * 32-bit and runs under a 64-bit hypervisor should _NOT_ use two of the + * pages preceding pt_base and mark them as reserved/unused. + */ +#ifdef XEN_HAVE_PV_GUEST_ENTRY +struct start_info { + /* THE FOLLOWING ARE FILLED IN BOTH ON INITIAL BOOT AND ON RESUME. */ + char magic[32]; /* "xen--". */ + unsigned long nr_pages; /* Total pages allocated to this domain. */ + unsigned long shared_info; /* MACHINE address of shared info struct. */ + uint32_t flags; /* SIF_xxx flags. */ + xen_pfn_t store_mfn; /* MACHINE page number of shared page. */ + uint32_t store_evtchn; /* Event channel for store communication. */ + union { + struct { + xen_pfn_t mfn; /* MACHINE page number of console page. */ + uint32_t evtchn; /* Event channel for console page. */ + } domU; + struct { + uint32_t info_off; /* Offset of console_info struct. */ + uint32_t info_size; /* Size of console_info struct from start.*/ + } dom0; + } console; + /* THE FOLLOWING ARE ONLY FILLED IN ON INITIAL BOOT (NOT RESUME). */ + unsigned long pt_base; /* VIRTUAL address of page directory. */ + unsigned long nr_pt_frames; /* Number of bootstrap p.t. frames. */ + unsigned long mfn_list; /* VIRTUAL address of page-frame list. */ + unsigned long mod_start; /* VIRTUAL address of pre-loaded module */ + /* (PFN of pre-loaded module if */ + /* SIF_MOD_START_PFN set in flags). */ + unsigned long mod_len; /* Size (bytes) of pre-loaded module. */ +#define MAX_GUEST_CMDLINE 1024 + int8_t cmd_line[MAX_GUEST_CMDLINE]; + /* The pfn range here covers both page table and p->m table frames. */ + unsigned long first_p2m_pfn;/* 1st pfn forming initial P->M table. */ + unsigned long nr_p2m_frames;/* # of pfns forming initial P->M table. */ +}; +typedef struct start_info start_info_t; + +/* New console union for dom0 introduced in 0x00030203. */ +#if __XEN_INTERFACE_VERSION__ < 0x00030203 +#define console_mfn console.domU.mfn +#define console_evtchn console.domU.evtchn +#endif +#endif /* XEN_HAVE_PV_GUEST_ENTRY */ + +/* These flags are passed in the 'flags' field of start_info_t. */ +#define SIF_PRIVILEGED (1<<0) /* Is the domain privileged? */ +#define SIF_INITDOMAIN (1<<1) /* Is this the initial control domain? */ +#define SIF_MULTIBOOT_MOD (1<<2) /* Is mod_start a multiboot module? */ +#define SIF_MOD_START_PFN (1<<3) /* Is mod_start a PFN? */ +#define SIF_PM_MASK (0xFF<<8) /* reserve 1 byte for xen-pm options */ + +/* + * A multiboot module is a package containing modules very similar to a + * multiboot module array. The only differences are: + * - the array of module descriptors is by convention simply at the beginning + * of the multiboot module, + * - addresses in the module descriptors are based on the beginning of the + * multiboot module, + * - the number of modules is determined by a termination descriptor that has + * mod_start == 0. + * + * This permits to both build it statically and reference it in a configuration + * file, and let the PV guest easily rebase the addresses to virtual addresses + * and at the same time count the number of modules. + */ +struct xen_multiboot_mod_list +{ + /* Address of first byte of the module */ + uint32_t mod_start; + /* Address of last byte of the module (inclusive) */ + uint32_t mod_end; + /* Address of zero-terminated command line */ + uint32_t cmdline; + /* Unused, must be zero */ + uint32_t pad; +}; +/* + * `incontents 200 startofday_dom0_console Dom0_console + * + * The console structure in start_info.console.dom0 + * + * This structure includes a variety of information required to + * have a working VGA/VESA console. + */ +typedef struct dom0_vga_console_info { + uint8_t video_type; /* DOM0_VGA_CONSOLE_??? */ +#define XEN_VGATYPE_TEXT_MODE_3 0x03 +#define XEN_VGATYPE_VESA_LFB 0x23 +#define XEN_VGATYPE_EFI_LFB 0x70 + + union { + struct { + /* Font height, in pixels. */ + uint16_t font_height; + /* Cursor location (column, row). */ + uint16_t cursor_x, cursor_y; + /* Number of rows and columns (dimensions in characters). */ + uint16_t rows, columns; + } text_mode_3; + + struct { + /* Width and height, in pixels. */ + uint16_t width, height; + /* Bytes per scan line. */ + uint16_t bytes_per_line; + /* Bits per pixel. */ + uint16_t bits_per_pixel; + /* LFB physical address, and size (in units of 64kB). */ + uint32_t lfb_base; + uint32_t lfb_size; + /* RGB mask offsets and sizes, as defined by VBE 1.2+ */ + uint8_t red_pos, red_size; + uint8_t green_pos, green_size; + uint8_t blue_pos, blue_size; + uint8_t rsvd_pos, rsvd_size; +#if __XEN_INTERFACE_VERSION__ >= 0x00030206 + /* VESA capabilities (offset 0xa, VESA command 0x4f00). */ + uint32_t gbl_caps; + /* Mode attributes (offset 0x0, VESA command 0x4f01). */ + uint16_t mode_attrs; +#endif + } vesa_lfb; + } u; +} dom0_vga_console_info_t; +#define xen_vga_console_info dom0_vga_console_info +#define xen_vga_console_info_t dom0_vga_console_info_t + +typedef uint8_t xen_domain_handle_t[16]; + +/* Turn a plain number into a C unsigned long constant. */ +#define __mk_unsigned_long(x) x ## UL +#define mk_unsigned_long(x) __mk_unsigned_long(x) + +__DEFINE_XEN_GUEST_HANDLE(uint8, uint8_t); +__DEFINE_XEN_GUEST_HANDLE(uint16, uint16_t); +__DEFINE_XEN_GUEST_HANDLE(uint32, uint32_t); +__DEFINE_XEN_GUEST_HANDLE(uint64, uint64_t); + +#else /* __ASSEMBLY__ */ + +/* In assembly code we cannot use C numeric constant suffixes. */ +#define mk_unsigned_long(x) x + +#endif /* !__ASSEMBLY__ */ + +/* Default definitions for macros used by domctl/sysctl. */ +#if defined(__XEN__) || defined(__XEN_TOOLS__) + +#ifndef uint64_aligned_t +#define uint64_aligned_t uint64_t +#endif +#ifndef XEN_GUEST_HANDLE_64 +#define XEN_GUEST_HANDLE_64(name) XEN_GUEST_HANDLE(name) +#endif + +#ifndef __ASSEMBLY__ +struct xenctl_bitmap { + XEN_GUEST_HANDLE_64(uint8) bitmap; + uint32_t nr_bits; +}; +#endif + +#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */ + +#endif /* __XEN_PUBLIC_XEN_H__ */ + +/* + * Local variables: + * mode: C + * c-file-style: "BSD" + * c-basic-offset: 4 + * tab-width: 4 + * indent-tabs-mode: nil + * End: + */ diff --git a/linguas.sh b/linguas.sh index 1de42ba2d..e57f50dc6 100755 --- a/linguas.sh +++ b/linguas.sh @@ -6,7 +6,7 @@ autogenerated="en@quot en@hebrew de@hebrew en@cyrillic en@greek en@arabic en@pig for x in $autogenerated; do - rm "po/$x.po"; + rm -f "po/$x.po"; done diff --git a/po/Rules-swiss b/po/Rules-swiss index d192f4911..b5fbda92b 100644 --- a/po/Rules-swiss +++ b/po/Rules-swiss @@ -3,5 +3,5 @@ DISTFILES.common.extra2 = swiss.sed Rules-swiss de_CH.po-create: de.po swiss.sed - LC_ALL=en_US.UTF-8 $(MSGFILTER) -i $< -o $(srcdir)/de_CH.po sed -f $(srcdir)/swiss.sed + LC_ALL=C.UTF-8 $(MSGFILTER) -i $< -o $(srcdir)/de_CH.po sed -f $(srcdir)/swiss.sed diff --git a/po/Rules-translit b/po/Rules-translit index 2962163bc..ab84a5f1f 100644 --- a/po/Rules-translit +++ b/po/Rules-translit @@ -1,16 +1,16 @@ DISTFILES.common.extra4 = hebrew.sed cyrillic.sed greek.sed arabic.sed Rules-translit de@hebrew.po-create: de.po hebrew.sed - LC_ALL=en_US.UTF-8 $(MSGFILTER) -i $< -o $(srcdir)/de@hebrew.po sed -f $(srcdir)/hebrew.sed + LC_ALL=C $(MSGFILTER) -i $< -o $(srcdir)/de@hebrew.po sed -f $(srcdir)/hebrew.sed en@hebrew.po-create: $(DOMAIN).pot hebrew.sed - LC_ALL=en_US.UTF-8 $(MSGINIT) -i $(srcdir)/$(DOMAIN).pot --no-translator -l en@hebrew -o - 2>/dev/null | LC_ALL=en_US.UTF-8 $(MSGCONV) -t UTF-8 | LC_ALL=en_US.UTF-8 $(MSGFILTER) -o $(srcdir)/en@hebrew.po -i - sed -f $(srcdir)/hebrew.sed + LC_ALL=C $(MSGINIT) -i $(srcdir)/$(DOMAIN).pot --no-translator -l en@hebrew -o - 2>/dev/null | LC_ALL=C $(MSGCONV) -t UTF-8 | LC_ALL=C $(MSGFILTER) -o $(srcdir)/en@hebrew.po -i - sed -f $(srcdir)/hebrew.sed en@cyrillic.po-create: $(DOMAIN).pot cyrillic.sed - LC_ALL=en_US.UTF-8 $(MSGINIT) -i $(srcdir)/$(DOMAIN).pot --no-translator -l en@cyrillic -o - 2>/dev/null | LC_ALL=en_US.UTF-8 $(MSGCONV) -t UTF-8 | LC_ALL=en_US.UTF-8 $(MSGFILTER) -o $(srcdir)/en@cyrillic.po -i - sed -f $(srcdir)/cyrillic.sed + LC_ALL=C $(MSGINIT) -i $(srcdir)/$(DOMAIN).pot --no-translator -l en@cyrillic -o - 2>/dev/null | LC_ALL=C $(MSGCONV) -t UTF-8 | LC_ALL=C $(MSGFILTER) -o $(srcdir)/en@cyrillic.po -i - sed -f $(srcdir)/cyrillic.sed en@greek.po-create: $(DOMAIN).pot greek.sed - LC_ALL=en_US.UTF-8 $(MSGINIT) -i $(srcdir)/$(DOMAIN).pot --no-translator -l en@greek -o - 2>/dev/null | LC_ALL=en_US.UTF-8 $(MSGCONV) -t UTF-8 | LC_ALL=en_US.UTF-8 $(MSGFILTER) -o $(srcdir)/en@greek.po -i - sed -f $(srcdir)/greek.sed + LC_ALL=C $(MSGINIT) -i $(srcdir)/$(DOMAIN).pot --no-translator -l en@greek -o - 2>/dev/null | LC_ALL=C $(MSGCONV) -t UTF-8 | LC_ALL=C $(MSGFILTER) -o $(srcdir)/en@greek.po -i - sed -f $(srcdir)/greek.sed en@arabic.po-create: $(DOMAIN).pot arabic.sed - LC_ALL=en_US.UTF-8 $(MSGINIT) -i $(srcdir)/$(DOMAIN).pot --no-translator -l en@arabic -o - 2>/dev/null | LC_ALL=en_US.UTF-8 $(MSGCONV) -t UTF-8 | LC_ALL=en_US.UTF-8 $(MSGFILTER) -o $(srcdir)/en@arabic.po -i - sed -f $(srcdir)/arabic.sed + LC_ALL=C $(MSGINIT) -i $(srcdir)/$(DOMAIN).pot --no-translator -l en@arabic -o - 2>/dev/null | LC_ALL=C $(MSGCONV) -t UTF-8 | LC_ALL=C $(MSGFILTER) -o $(srcdir)/en@arabic.po -i - sed -f $(srcdir)/arabic.sed diff --git a/po/cyrillic.sed b/po/cyrillic.sed index 46ddaec6e..ffad0ed8c 100644 --- a/po/cyrillic.sed +++ b/po/cyrillic.sed @@ -10,8 +10,84 @@ /^Content-Transfer-Encoding:/ b /^Plural-Forms:/ b -y,abcdefghijklmnopqrstuvwxyz,абцдефгхийклмнопќрстувўѯѝз, -y,ABCDEFGHIJKLMNOPQRSTUVWXYZ,АБЦДЕФГХИЙКЛМНОПЌРСТУВЎѮЍЗ, +s,a,а,g +s,b,б,g +s,c,ц,g +s,d,д,g +s,e,е,g +s,f,ф,g +s,g,г,g +s,h,х,g +s,i,и,g +s,j,й,g +s,k,к,g +s,l,л,g +s,m,м,g +s,n,н,g +s,o,о,g +s,p,п,g +s,q,ќ,g +s,r,р,g +s,s,с,g +s,t,т,g +s,u,у,g +s,v,в,g +s,w,ў,g +s,x,ѯ,g +s,y,ѝ,g +s,z,з,g +s,A,А,g +s,B,Б,g +s,C,Ц,g +s,D,Д,g +s,E,Е,g +s,F,Ф,g +s,G,Г,g +s,H,Х,g +s,I,И,g +s,J,Й,g +s,K,К,g +s,L,Л,g +s,M,М,g +s,N,Н,g +s,O,О,g +s,P,П,g +s,Q,Ќ,g +s,R,Р,g +s,S,С,g +s,T,Т,g +s,U,У,g +s,V,В,g +s,W,Ў,g +s,X,Ѯ,g +s,Y,Ѝ,g +s,Z,З,g +s,А,А,g +s,Б,Б,g +s,Ц,Ц,g +s,Д,Д,g +s,Е,Е,g +s,Ф,Ф,g +s,Г,Г,g +s,Х,Х,g +s,И,И,g +s,Й,Й,g +s,К,К,g +s,Л,Л,g +s,М,М,g +s,Н,Н,g +s,О,О,g +s,П,П,g +s,Ќ,Ќ,g +s,Р,Р,g +s,С,С,g +s,Т,Т,g +s,У,У,g +s,В,В,g +s,Ў,Ў,g +s,Ѯ,Ѯ,g +s,Ѝ,Ѝ,g +s,З,З,g s,%\([0-9]*\)Ц,%\1C,g s,%\([0-9]*\)ц,%\1c,g diff --git a/po/greek.sed b/po/greek.sed index 17e4b0468..93556c386 100644 --- a/po/greek.sed +++ b/po/greek.sed @@ -12,8 +12,84 @@ s,%\([0-9]*\)C,%\1#,g -y,abcdefghijklmnopqrstuvwxyz,αϭϲδεφγχιϊκλμνοπϗρστυβωξϋζ, -y,ABCDEFGHIJKLMNOPQRSTUVWXYZ,ΑϬϲΔΕΦΓΧΙΪΚΛΜΝΟΠϏΡΣΤΥΒΩΞΫΖ, +s,a,α,g +s,b,ϭ,g +s,c,ϲ,g +s,d,δ,g +s,e,ε,g +s,f,φ,g +s,g,γ,g +s,h,χ,g +s,i,ι,g +s,j,ϊ,g +s,k,κ,g +s,l,λ,g +s,m,μ,g +s,n,ν,g +s,o,ο,g +s,p,π,g +s,q,ϗ,g +s,r,ρ,g +s,s,σ,g +s,t,τ,g +s,u,υ,g +s,v,β,g +s,w,ω,g +s,x,ξ,g +s,y,ϋ,g +s,z,ζ,g +s,A,Α,g +s,B,Ϭ,g +s,C,ϲ,g +s,D,Δ,g +s,E,Ε,g +s,F,Φ,g +s,G,Γ,g +s,H,Χ,g +s,I,Ι,g +s,J,Ϊ,g +s,K,Κ,g +s,L,Λ,g +s,M,Μ,g +s,N,Ν,g +s,O,Ο,g +s,P,Π,g +s,Q,Ϗ,g +s,R,Ρ,g +s,S,Σ,g +s,T,Τ,g +s,U,Υ,g +s,V,Β,g +s,W,Ω,g +s,X,Ξ,g +s,Y,Ϋ,g +s,Z,Ζ,g +s,А,А,g +s,Б,Б,g +s,Ц,Ц,g +s,Д,Д,g +s,Е,Е,g +s,Ф,Ф,g +s,Г,Г,g +s,Х,Х,g +s,И,И,g +s,Й,Й,g +s,К,К,g +s,Л,Л,g +s,М,М,g +s,Н,Н,g +s,О,О,g +s,П,П,g +s,Ќ,Ќ,g +s,Р,Р,g +s,С,С,g +s,Т,Т,g +s,У,У,g +s,В,В,g +s,Ў,Ў,g +s,Ѯ,Ѯ,g +s,Ѝ,Ѝ,g +s,З,З,g s,%\([0-9]*\)#,%\1C,g s,%\([0-9]*\)ϲ,%\1c,g diff --git a/tests/partmap_test.in b/tests/partmap_test.in index 7786ccfbc..4230ba228 100644 --- a/tests/partmap_test.in +++ b/tests/partmap_test.in @@ -92,6 +92,12 @@ case "${grub_modinfo_target_cpu}-${grub_modinfo_platform}" in disk=hd0 ;; esac + +if ! which parted >/dev/null 2>&1; then + echo "parted not installed; cannot test partmap" + exit 77 +fi + imgfile="`mktemp "${TMPDIR:-/tmp}/tmp.XXXXXXXXXX"`" || exit 1 outfile="`mktemp "${TMPDIR:-/tmp}/tmp.XXXXXXXXXX"`" || exit 1 diff --git a/tests/util/grub-fs-tester.in b/tests/util/grub-fs-tester.in index ff5dc8558..fe7e97427 100644 --- a/tests/util/grub-fs-tester.in +++ b/tests/util/grub-fs-tester.in @@ -10,7 +10,7 @@ tempdir=`mktemp -d "${TMPDIR:-/tmp}/tmp.XXXXXXXXXX"` || exit 1 # This wrapper is to ease insertion of valgrind or time statistics run_it () { - "$GRUBFSTEST" "$@" + LC_ALL=C "$GRUBFSTEST" "$@" } run_grubfstest () { diff --git a/util/grub-install.c b/util/grub-install.c index df5c7e520..eabd6de4d 100644 --- a/util/grub-install.c +++ b/util/grub-install.c @@ -1698,7 +1698,7 @@ main (int argc, char *argv[]) /* Now perform the installation. */ if (install_bootsector) grub_util_sparc_setup (platdir, "boot.img", "core.img", - install_device, force, + install_drive, force, fs_probe, allow_floppy, 0 /* unused */ ); break; diff --git a/util/grub-mkimagexx.c b/util/grub-mkimagexx.c index 3c76d0708..a1ddc6269 100644 --- a/util/grub-mkimagexx.c +++ b/util/grub-mkimagexx.c @@ -101,7 +101,7 @@ SUFFIX (generate_elf) (const struct grub_install_image_target_desc *image_target program_size = ALIGN_ADDR (*core_size); elf_img = xmalloc (program_size + header_size + footer_size); - memset (elf_img, 0, program_size + header_size); + memset (elf_img, 0, program_size + header_size + footer_size); memcpy (elf_img + header_size, *core_img, *core_size); ehdr = (void *) elf_img; phdr = (void *) (elf_img + sizeof (*ehdr)); @@ -1587,6 +1587,7 @@ SUFFIX (load_image) (const char *kernel_path, size_t *exec_size, } out_img = xmalloc (*kernel_sz + total_module_size); + memset (out_img, 0, *kernel_sz + total_module_size); if (image_target->id == IMAGE_EFI) { diff --git a/util/mkimage.c b/util/mkimage.c index 35df99871..dc4046185 100644 --- a/util/mkimage.c +++ b/util/mkimage.c @@ -992,7 +992,7 @@ grub_install_generate_image (const char *dir, const char *prefix, { char *kernel_img, *core_img; size_t kernel_size, total_module_size, core_size, exec_size; - size_t memdisk_size = 0, config_size = 0, config_size_pure = 0; + size_t memdisk_size = 0, config_size = 0; size_t prefix_size = 0; char *kernel_path; size_t offset; @@ -1043,8 +1043,7 @@ grub_install_generate_image (const char *dir, const char *prefix, if (config_path) { - config_size_pure = grub_util_get_image_size (config_path) + 1; - config_size = ALIGN_ADDR (config_size_pure); + config_size = ALIGN_ADDR (grub_util_get_image_size (config_path) + 1); grub_util_info ("the size of config file is 0x%" GRUB_HOST_PRIxLONG_LONG, (unsigned long long) config_size); total_module_size += config_size + sizeof (struct grub_module_header); @@ -1080,7 +1079,10 @@ grub_install_generate_image (const char *dir, const char *prefix, = grub_host_to_target32 (total_module_size); if (image_target->flags & PLATFORM_FLAGS_MODULES_BEFORE_KERNEL) - memmove (kernel_img + total_module_size, kernel_img, kernel_size); + { + memmove (kernel_img + total_module_size, kernel_img, kernel_size); + memset (kernel_img, 0, total_module_size); + } if (image_target->voidp_sizeof == 8) { @@ -1090,7 +1092,6 @@ grub_install_generate_image (const char *dir, const char *prefix, modinfo = (struct grub_module_info64 *) kernel_img; else modinfo = (struct grub_module_info64 *) (kernel_img + kernel_size); - memset (modinfo, 0, sizeof (struct grub_module_info64)); modinfo->magic = grub_host_to_target32 (GRUB_MODULE_MAGIC); modinfo->offset = grub_host_to_target_addr (sizeof (struct grub_module_info64)); modinfo->size = grub_host_to_target_addr (total_module_size); @@ -1107,7 +1108,6 @@ grub_install_generate_image (const char *dir, const char *prefix, modinfo = (struct grub_module_info32 *) kernel_img; else modinfo = (struct grub_module_info32 *) (kernel_img + kernel_size); - memset (modinfo, 0, sizeof (struct grub_module_info32)); modinfo->magic = grub_host_to_target32 (GRUB_MODULE_MAGIC); modinfo->offset = grub_host_to_target_addr (sizeof (struct grub_module_info32)); modinfo->size = grub_host_to_target_addr (total_module_size); @@ -1120,17 +1120,14 @@ grub_install_generate_image (const char *dir, const char *prefix, for (p = path_list; p; p = p->next) { struct grub_module_header *header; - size_t mod_size, orig_size; + size_t mod_size; - orig_size = grub_util_get_image_size (p->name); - mod_size = ALIGN_ADDR (orig_size); + mod_size = ALIGN_ADDR (grub_util_get_image_size (p->name)); header = (struct grub_module_header *) (kernel_img + offset); - memset (header, 0, sizeof (struct grub_module_header)); header->type = grub_host_to_target32 (OBJ_TYPE_ELF); header->size = grub_host_to_target32 (mod_size + sizeof (*header)); offset += sizeof (*header); - memset (kernel_img + offset + orig_size, 0, mod_size - orig_size); grub_util_load_image (p->name, kernel_img + offset); offset += mod_size; @@ -1146,7 +1143,6 @@ grub_install_generate_image (const char *dir, const char *prefix, curs = grub_util_get_image_size (pubkey_paths[i]); header = (struct grub_module_header *) (kernel_img + offset); - memset (header, 0, sizeof (struct grub_module_header)); header->type = grub_host_to_target32 (OBJ_TYPE_PUBKEY); header->size = grub_host_to_target32 (curs + sizeof (*header)); offset += sizeof (*header); @@ -1161,7 +1157,6 @@ grub_install_generate_image (const char *dir, const char *prefix, struct grub_module_header *header; header = (struct grub_module_header *) (kernel_img + offset); - memset (header, 0, sizeof (struct grub_module_header)); header->type = grub_host_to_target32 (OBJ_TYPE_MEMDISK); header->size = grub_host_to_target32 (memdisk_size + sizeof (*header)); offset += sizeof (*header); @@ -1175,13 +1170,11 @@ grub_install_generate_image (const char *dir, const char *prefix, struct grub_module_header *header; header = (struct grub_module_header *) (kernel_img + offset); - memset (header, 0, sizeof (struct grub_module_header)); header->type = grub_host_to_target32 (OBJ_TYPE_CONFIG); header->size = grub_host_to_target32 (config_size + sizeof (*header)); offset += sizeof (*header); grub_util_load_image (config_path, kernel_img + offset); - *(kernel_img + offset + config_size_pure - 1) = 0; offset += config_size; } @@ -1190,12 +1183,10 @@ grub_install_generate_image (const char *dir, const char *prefix, struct grub_module_header *header; header = (struct grub_module_header *) (kernel_img + offset); - memset (header, 0, sizeof (struct grub_module_header)); header->type = grub_host_to_target32 (OBJ_TYPE_PREFIX); header->size = grub_host_to_target32 (prefix_size + sizeof (*header)); offset += sizeof (*header); - grub_memset (kernel_img + offset, 0, prefix_size); grub_strcpy (kernel_img + offset, prefix); offset += prefix_size; } @@ -1269,15 +1260,11 @@ grub_install_generate_image (const char *dir, const char *prefix, full_size = core_size + decompress_size; full_img = xmalloc (full_size); - memset (full_img, 0, full_size); memcpy (full_img, decompress_img, decompress_size); memcpy (full_img + decompress_size, core_img, core_size); - memset (full_img + decompress_size + core_size, 0, - full_size - (decompress_size + core_size)); - free (core_img); core_img = full_img; core_size = full_size; @@ -1428,6 +1415,7 @@ grub_install_generate_image (const char *dir, const char *prefix, pe_img = xmalloc (reloc_addr + reloc_size); memset (pe_img, 0, header_size); memcpy ((char *) pe_img + header_size, core_img, core_size); + memset ((char *) pe_img + header_size + core_size, 0, reloc_addr - (header_size + core_size)); memcpy ((char *) pe_img + reloc_addr, rel_section, reloc_size); header = pe_img;