Hi; here's this week's arm pullreq. Mostly this is my work on FEAT_MOPS and FEAT_HBC, but there are some other bits and pieces in there too, including a recent set of elf2dmp patches. thanks -- PMM The following changes since commit 55394dcbec8f0c29c30e792c102a0edd50a52bf4: Merge tag 'pull-loongarch-20230920' of https://gitlab.com/gaosong/qemu into staging (2023-09-20 13:56:18 -0400) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20230921 for you to fetch changes up to 231f6a7d66254a58bedbee458591b780e0a507b1: elf2dmp: rework PDB_STREAM_INDEXES::segments obtaining (2023-09-21 16:13:54 +0100) ---------------------------------------------------------------- target-arm queue: * target/m68k: Add URL to semihosting spec * docs/devel/loads-stores: Fix git grep regexes * hw/arm/boot: Set SCR_EL3.FGTEn when booting kernel * linux-user: Correct SME feature names reported in cpuinfo * linux-user: Add missing arm32 hwcaps * Don't skip MTE checks for LDRT/STRT at EL0 * Implement FEAT_HBC * Implement FEAT_MOPS * audio/jackaudio: Avoid dynamic stack allocation * sbsa-ref: add non-secure EL2 virtual timer * elf2dmp: improve Win2022, Win11 and large dumps ---------------------------------------------------------------- Fabian Vogt (1): hw/arm/boot: Set SCR_EL3.FGTEn when booting kernel Marcin Juszkiewicz (1): sbsa-ref: add non-secure EL2 virtual timer Peter Maydell (23): target/m68k: Add URL to semihosting spec docs/devel/loads-stores: Fix git grep regexes linux-user/elfload.c: Correct SME feature names reported in cpuinfo linux-user/elfload.c: Add missing arm and arm64 hwcap values linux-user/elfload.c: Report previously missing arm32 hwcaps target/arm: Update AArch64 ID register field definitions target/arm: Update user-mode ID reg mask values target/arm: Implement FEAT_HBC target/arm: Remove unused allocation_tag_mem() argument target/arm: Don't skip MTE checks for LDRT/STRT at EL0 target/arm: Implement FEAT_MOPS enable bits target/arm: Pass unpriv bool to get_a64_user_mem_index() target/arm: Define syndrome function for MOPS exceptions target/arm: New function allocation_tag_mem_probe() target/arm: Implement MTE tag-checking functions for FEAT_MOPS target/arm: Implement the SET* instructions target/arm: Define new TB flag for ATA0 target/arm: Implement the SETG* instructions target/arm: Implement MTE tag-checking functions for FEAT_MOPS copies target/arm: Implement the CPY* instructions target/arm: Enable FEAT_MOPS for CPU 'max' audio/jackaudio: Avoid dynamic stack allocation in qjack_client_init audio/jackaudio: Avoid dynamic stack allocation in qjack_process() Viktor Prutyanov (5): elf2dmp: replace PE export name check with PDB name check elf2dmp: introduce physical block alignment elf2dmp: introduce merging of physical memory runs elf2dmp: use Linux mmap with MAP_NORESERVE when possible elf2dmp: rework PDB_STREAM_INDEXES::segments obtaining docs/devel/loads-stores.rst | 40 +- docs/system/arm/emulation.rst | 2 + contrib/elf2dmp/addrspace.h | 1 + contrib/elf2dmp/pdb.h | 2 +- contrib/elf2dmp/qemu_elf.h | 2 + target/arm/cpu.h | 35 ++ target/arm/internals.h | 55 +++ target/arm/syndrome.h | 12 + target/arm/tcg/helper-a64.h | 14 + target/arm/tcg/translate.h | 4 +- target/arm/tcg/a64.decode | 38 +- audio/jackaudio.c | 21 +- contrib/elf2dmp/addrspace.c | 31 +- contrib/elf2dmp/main.c | 154 ++++---- contrib/elf2dmp/pdb.c | 15 +- contrib/elf2dmp/qemu_elf.c | 68 +++- hw/arm/boot.c | 4 + hw/arm/sbsa-ref.c | 2 + linux-user/elfload.c | 72 +++- target/arm/helper.c | 39 +- target/arm/tcg/cpu64.c | 5 + target/arm/tcg/helper-a64.c | 878 +++++++++++++++++++++++++++++++++++++++++ target/arm/tcg/hflags.c | 21 + target/arm/tcg/mte_helper.c | 281 +++++++++++-- target/arm/tcg/translate-a64.c | 164 +++++++- target/m68k/m68k-semi.c | 4 + tests/tcg/aarch64/sysregs.c | 4 +- 27 files changed, 1768 insertions(+), 200 deletions(-) The spec for m68k semihosting is documented in the libgloss sources. Add a comment with the URL for it, as we already have for nios2 semihosting. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230801154451.3505492-1-peter.maydell@linaro.org --- target/m68k/m68k-semi.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/target/m68k/m68k-semi.c b/target/m68k/m68k-semi.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/m68k-semi.c +++ b/target/m68k/m68k-semi.c @@ -XXX,XX +XXX,XX @@ * * You should have received a copy of the GNU General Public License * along with this program; if not, see <http://www.gnu.org/licenses/>. + * + * The semihosting protocol implemented here is described in the + * libgloss sources: + * https://sourceware.org/git/?p=newlib-cygwin.git;a=blob;f=libgloss/m68k/m68k-semi.txt;hb=HEAD */ #include "qemu/osdep.h" -- 2.34.1 The loads-and-stores documentation includes git grep regexes to find occurrences of the various functions. Some of these regexes have errors, typically failing to escape the '?', '(' and ')' when they should be metacharacters (since these are POSIX basic REs). We also weren't consistent about whether to have a ':' on the end of the line introducing the list of regexes in each section. Fix the errors. The following shell rune will complain about any REs in the file which don't have any matches in the codebase: for re in $(sed -ne 's/ - ``\(\\<.*\)``/\1/p' docs/devel/loads-stores.rst); do git grep -q "$re" || echo "no matches for re $re"; done Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230904161703.3996734-1-peter.maydell@linaro.org --- docs/devel/loads-stores.rst | 40 ++++++++++++++++++------------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/docs/devel/loads-stores.rst b/docs/devel/loads-stores.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/loads-stores.rst +++ b/docs/devel/loads-stores.rst @@ -XXX,XX +XXX,XX @@ which stores ``val`` to ``ptr`` as an ``{endian}`` order value of size ``sz`` bytes. -Regexes for git grep +Regexes for git grep: - ``\<ld[us]\?[bwlq]\(_[hbl]e\)\?_p\>`` - ``\<st[bwlq]\(_[hbl]e\)\?_p\>`` - ``\<st24\(_[hbl]e\)\?_p\>`` - - ``\<ldn_\([hbl]e\)?_p\>`` - - ``\<stn_\([hbl]e\)?_p\>`` + - ``\<ldn_\([hbl]e\)\?_p\>`` + - ``\<stn_\([hbl]e\)\?_p\>`` ``cpu_{ld,st}*_mmu`` ~~~~~~~~~~~~~~~~~~~~ @@ -XXX,XX +XXX,XX @@ store: ``cpu_st{size}{end}_mmu(env, ptr, val, oi, retaddr)`` - ``_le`` : little endian Regexes for git grep: - - ``\<cpu_ld[bwlq](_[bl]e)\?_mmu\>`` - - ``\<cpu_st[bwlq](_[bl]e)\?_mmu\>`` + - ``\<cpu_ld[bwlq]\(_[bl]e\)\?_mmu\>`` + - ``\<cpu_st[bwlq]\(_[bl]e\)\?_mmu\>`` ``cpu_{ld,st}*_mmuidx_ra`` @@ -XXX,XX +XXX,XX @@ store: ``cpu_st{size}{end}_mmuidx_ra(env, ptr, val, mmuidx, retaddr)`` - ``_le`` : little endian Regexes for git grep: - - ``\<cpu_ld[us]\?[bwlq](_[bl]e)\?_mmuidx_ra\>`` - - ``\<cpu_st[bwlq](_[bl]e)\?_mmuidx_ra\>`` + - ``\<cpu_ld[us]\?[bwlq]\(_[bl]e\)\?_mmuidx_ra\>`` + - ``\<cpu_st[bwlq]\(_[bl]e\)\?_mmuidx_ra\>`` ``cpu_{ld,st}*_data_ra`` ~~~~~~~~~~~~~~~~~~~~~~~~ @@ -XXX,XX +XXX,XX @@ store: ``cpu_st{size}{end}_data_ra(env, ptr, val, ra)`` - ``_le`` : little endian Regexes for git grep: - - ``\<cpu_ld[us]\?[bwlq](_[bl]e)\?_data_ra\>`` - - ``\<cpu_st[bwlq](_[bl]e)\?_data_ra\>`` + - ``\<cpu_ld[us]\?[bwlq]\(_[bl]e\)\?_data_ra\>`` + - ``\<cpu_st[bwlq]\(_[bl]e\)\?_data_ra\>`` ``cpu_{ld,st}*_data`` ~~~~~~~~~~~~~~~~~~~~~ @@ -XXX,XX +XXX,XX @@ store: ``cpu_st{size}{end}_data(env, ptr, val)`` - ``_be`` : big endian - ``_le`` : little endian -Regexes for git grep - - ``\<cpu_ld[us]\?[bwlq](_[bl]e)\?_data\>`` - - ``\<cpu_st[bwlq](_[bl]e)\?_data\+\>`` +Regexes for git grep: + - ``\<cpu_ld[us]\?[bwlq]\(_[bl]e\)\?_data\>`` + - ``\<cpu_st[bwlq]\(_[bl]e\)\?_data\+\>`` ``cpu_ld*_code`` ~~~~~~~~~~~~~~~~ @@ -XXX,XX +XXX,XX @@ swap: ``translator_ld{sign}{size}_swap(env, ptr, swap)`` - ``l`` : 32 bits - ``q`` : 64 bits -Regexes for git grep +Regexes for git grep: - ``\<translator_ld[us]\?[bwlq]\(_swap\)\?\>`` ``helper_{ld,st}*_mmu`` @@ -XXX,XX +XXX,XX @@ store: ``helper_{size}_mmu(env, addr, val, opindex, retaddr)`` - ``l`` : 32 bits - ``q`` : 64 bits -Regexes for git grep +Regexes for git grep: - ``\<helper_ld[us]\?[bwlq]_mmu\>`` - ``\<helper_st[bwlq]_mmu\>`` @@ -XXX,XX +XXX,XX @@ succeeded using a MemTxResult return code. The ``_{endian}`` suffix is omitted for byte accesses. -Regexes for git grep +Regexes for git grep: - ``\<address_space_\(read\|write\|rw\)\>`` - ``\<address_space_ldu\?[bwql]\(_[lb]e\)\?\>`` - ``\<address_space_st[bwql]\(_[lb]e\)\?\>`` @@ -XXX,XX +XXX,XX @@ Note that portions of the write which attempt to write data to a device will be silently ignored -- only real RAM and ROM will be written to. -Regexes for git grep +Regexes for git grep: - ``address_space_write_rom`` ``{ld,st}*_phys`` @@ -XXX,XX +XXX,XX @@ device doing the access has no way to report such an error. The ``_{endian}_`` infix is omitted for byte accesses. -Regexes for git grep +Regexes for git grep: - ``\<ldu\?[bwlq]\(_[bl]e\)\?_phys\>`` - ``\<st[bwlq]\(_[bl]e\)\?_phys\>`` @@ -XXX,XX +XXX,XX @@ For new code they are better avoided: ``cpu_physical_memory_rw`` -Regexes for git grep +Regexes for git grep: - ``\<cpu_physical_memory_\(read\|write\|rw\)\>`` ``cpu_memory_rw_debug`` @@ -XXX,XX +XXX,XX @@ make sure our existing code is doing things correctly. ``dma_memory_rw`` -Regexes for git grep +Regexes for git grep: - ``\<dma_memory_\(read\|write\|rw\)\>`` - ``\<ldu\?[bwlq]\(_[bl]e\)\?_dma\>`` - ``\<st[bwlq]\(_[bl]e\)\?_dma\>`` @@ -XXX,XX +XXX,XX @@ correct address space for that device. The ``_{endian}_`` infix is omitted for byte accesses. -Regexes for git grep +Regexes for git grep: - ``\<pci_dma_\(read\|write\|rw\)\>`` - ``\<ldu\?[bwlq]\(_[bl]e\)\?_pci_dma\>`` - ``\<st[bwlq]\(_[bl]e\)\?_pci_dma\>`` -- 2.34.1 From: Fabian Vogt <fvogt@suse.de> Just like d7ef5e16a17c sets SCR_EL3.HXEn for FEAT_HCX, this commit handles SCR_EL3.FGTEn for FEAT_FGT: When we direct boot a kernel on a CPU which emulates EL3, we need to set up the EL3 system registers as the Linux kernel documentation specifies: https://www.kernel.org/doc/Documentation/arm64/booting.rst > For CPUs with the Fine Grained Traps (FEAT_FGT) extension present: > - If EL3 is present and the kernel is entered at EL2: > - SCR_EL3.FGTEn (bit 27) must be initialised to 0b1. Cc: qemu-stable@nongnu.org Signed-off-by: Fabian Vogt <fvogt@suse.de> Message-id: 4831384.GXAFRqVoOG@linux-e202.suse.de Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/boot.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ static void do_cpu_reset(void *opaque) if (cpu_isar_feature(aa64_hcx, cpu)) { env->cp15.scr_el3 |= SCR_HXEN; } + if (cpu_isar_feature(aa64_fgt, cpu)) { + env->cp15.scr_el3 |= SCR_FGTEN; + } + /* AArch64 kernels never boot in secure mode */ assert(!info->secure_boot); /* This hook is only supported for AArch32 currently: -- 2.34.1 Some of the names we use for CPU features in linux-user's dummy /proc/cpuinfo don't match the strings in the real kernel in arch/arm64/kernel/cpuinfo.c. Specifically, the SME related features have an underscore in the HWCAP_FOO define name, but (like the SVE ones) they do not have an underscore in the string in cpuinfo. Correct the errors. Fixes: a55b9e7226708 ("linux-user: Emulate /proc/cpuinfo on aarch64 and arm") Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- linux-user/elfload.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ const char *elf_hwcap2_str(uint32_t bit) [__builtin_ctz(ARM_HWCAP2_A64_RPRES )] = "rpres", [__builtin_ctz(ARM_HWCAP2_A64_MTE3 )] = "mte3", [__builtin_ctz(ARM_HWCAP2_A64_SME )] = "sme", - [__builtin_ctz(ARM_HWCAP2_A64_SME_I16I64 )] = "sme_i16i64", - [__builtin_ctz(ARM_HWCAP2_A64_SME_F64F64 )] = "sme_f64f64", - [__builtin_ctz(ARM_HWCAP2_A64_SME_I8I32 )] = "sme_i8i32", - [__builtin_ctz(ARM_HWCAP2_A64_SME_F16F32 )] = "sme_f16f32", - [__builtin_ctz(ARM_HWCAP2_A64_SME_B16F32 )] = "sme_b16f32", - [__builtin_ctz(ARM_HWCAP2_A64_SME_F32F32 )] = "sme_f32f32", - [__builtin_ctz(ARM_HWCAP2_A64_SME_FA64 )] = "sme_fa64", + [__builtin_ctz(ARM_HWCAP2_A64_SME_I16I64 )] = "smei16i64", + [__builtin_ctz(ARM_HWCAP2_A64_SME_F64F64 )] = "smef64f64", + [__builtin_ctz(ARM_HWCAP2_A64_SME_I8I32 )] = "smei8i32", + [__builtin_ctz(ARM_HWCAP2_A64_SME_F16F32 )] = "smef16f32", + [__builtin_ctz(ARM_HWCAP2_A64_SME_B16F32 )] = "smeb16f32", + [__builtin_ctz(ARM_HWCAP2_A64_SME_F32F32 )] = "smef32f32", + [__builtin_ctz(ARM_HWCAP2_A64_SME_FA64 )] = "smefa64", }; return bit < ARRAY_SIZE(hwcap_str) ? hwcap_str[bit] : NULL; -- 2.34.1 Our lists of Arm 32 and 64 bit hwcap values have lagged behind the Linux kernel. Update them to include all the bits defined as of upstream Linux git commit a48fa7efaf1161c1 (in the middle of the kernel 6.6 dev cycle). For 64-bit, we don't yet implement any of the features reported via these hwcap bits. For 32-bit we do in fact already implement them all; we'll add the code to set them in a subsequent commit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- linux-user/elfload.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ enum ARM_HWCAP_ARM_VFPD32 = 1 << 19, ARM_HWCAP_ARM_LPAE = 1 << 20, ARM_HWCAP_ARM_EVTSTRM = 1 << 21, + ARM_HWCAP_ARM_FPHP = 1 << 22, + ARM_HWCAP_ARM_ASIMDHP = 1 << 23, + ARM_HWCAP_ARM_ASIMDDP = 1 << 24, + ARM_HWCAP_ARM_ASIMDFHM = 1 << 25, + ARM_HWCAP_ARM_ASIMDBF16 = 1 << 26, + ARM_HWCAP_ARM_I8MM = 1 << 27, }; enum { @@ -XXX,XX +XXX,XX @@ enum { ARM_HWCAP2_ARM_SHA1 = 1 << 2, ARM_HWCAP2_ARM_SHA2 = 1 << 3, ARM_HWCAP2_ARM_CRC32 = 1 << 4, + ARM_HWCAP2_ARM_SB = 1 << 5, + ARM_HWCAP2_ARM_SSBS = 1 << 6, }; /* The commpage only exists for 32 bit kernels */ @@ -XXX,XX +XXX,XX @@ const char *elf_hwcap_str(uint32_t bit) [__builtin_ctz(ARM_HWCAP_ARM_VFPD32 )] = "vfpd32", [__builtin_ctz(ARM_HWCAP_ARM_LPAE )] = "lpae", [__builtin_ctz(ARM_HWCAP_ARM_EVTSTRM )] = "evtstrm", + [__builtin_ctz(ARM_HWCAP_ARM_FPHP )] = "fphp", + [__builtin_ctz(ARM_HWCAP_ARM_ASIMDHP )] = "asimdhp", + [__builtin_ctz(ARM_HWCAP_ARM_ASIMDDP )] = "asimddp", + [__builtin_ctz(ARM_HWCAP_ARM_ASIMDFHM )] = "asimdfhm", + [__builtin_ctz(ARM_HWCAP_ARM_ASIMDBF16)] = "asimdbf16", + [__builtin_ctz(ARM_HWCAP_ARM_I8MM )] = "i8mm", }; return bit < ARRAY_SIZE(hwcap_str) ? hwcap_str[bit] : NULL; @@ -XXX,XX +XXX,XX @@ const char *elf_hwcap2_str(uint32_t bit) [__builtin_ctz(ARM_HWCAP2_ARM_SHA1 )] = "sha1", [__builtin_ctz(ARM_HWCAP2_ARM_SHA2 )] = "sha2", [__builtin_ctz(ARM_HWCAP2_ARM_CRC32)] = "crc32", + [__builtin_ctz(ARM_HWCAP2_ARM_SB )] = "sb", + [__builtin_ctz(ARM_HWCAP2_ARM_SSBS )] = "ssbs", }; return bit < ARRAY_SIZE(hwcap_str) ? hwcap_str[bit] : NULL; @@ -XXX,XX +XXX,XX @@ enum { ARM_HWCAP2_A64_SME_B16F32 = 1 << 28, ARM_HWCAP2_A64_SME_F32F32 = 1 << 29, ARM_HWCAP2_A64_SME_FA64 = 1 << 30, + ARM_HWCAP2_A64_WFXT = 1ULL << 31, + ARM_HWCAP2_A64_EBF16 = 1ULL << 32, + ARM_HWCAP2_A64_SVE_EBF16 = 1ULL << 33, + ARM_HWCAP2_A64_CSSC = 1ULL << 34, + ARM_HWCAP2_A64_RPRFM = 1ULL << 35, + ARM_HWCAP2_A64_SVE2P1 = 1ULL << 36, + ARM_HWCAP2_A64_SME2 = 1ULL << 37, + ARM_HWCAP2_A64_SME2P1 = 1ULL << 38, + ARM_HWCAP2_A64_SME_I16I32 = 1ULL << 39, + ARM_HWCAP2_A64_SME_BI32I32 = 1ULL << 40, + ARM_HWCAP2_A64_SME_B16B16 = 1ULL << 41, + ARM_HWCAP2_A64_SME_F16F16 = 1ULL << 42, + ARM_HWCAP2_A64_MOPS = 1ULL << 43, + ARM_HWCAP2_A64_HBC = 1ULL << 44, }; #define ELF_HWCAP get_elf_hwcap() @@ -XXX,XX +XXX,XX @@ const char *elf_hwcap2_str(uint32_t bit) [__builtin_ctz(ARM_HWCAP2_A64_SME_B16F32 )] = "smeb16f32", [__builtin_ctz(ARM_HWCAP2_A64_SME_F32F32 )] = "smef32f32", [__builtin_ctz(ARM_HWCAP2_A64_SME_FA64 )] = "smefa64", + [__builtin_ctz(ARM_HWCAP2_A64_WFXT )] = "wfxt", + [__builtin_ctzll(ARM_HWCAP2_A64_EBF16 )] = "ebf16", + [__builtin_ctzll(ARM_HWCAP2_A64_SVE_EBF16 )] = "sveebf16", + [__builtin_ctzll(ARM_HWCAP2_A64_CSSC )] = "cssc", + [__builtin_ctzll(ARM_HWCAP2_A64_RPRFM )] = "rprfm", + [__builtin_ctzll(ARM_HWCAP2_A64_SVE2P1 )] = "sve2p1", + [__builtin_ctzll(ARM_HWCAP2_A64_SME2 )] = "sme2", + [__builtin_ctzll(ARM_HWCAP2_A64_SME2P1 )] = "sme2p1", + [__builtin_ctzll(ARM_HWCAP2_A64_SME_I16I32 )] = "smei16i32", + [__builtin_ctzll(ARM_HWCAP2_A64_SME_BI32I32)] = "smebi32i32", + [__builtin_ctzll(ARM_HWCAP2_A64_SME_B16B16 )] = "smeb16b16", + [__builtin_ctzll(ARM_HWCAP2_A64_SME_F16F16 )] = "smef16f16", + [__builtin_ctzll(ARM_HWCAP2_A64_MOPS )] = "mops", + [__builtin_ctzll(ARM_HWCAP2_A64_HBC )] = "hbc", }; return bit < ARRAY_SIZE(hwcap_str) ? hwcap_str[bit] : NULL; -- 2.34.1 Add the code to report the arm32 hwcaps we were previously missing: ss, ssbs, fphp, asimdhp, asimddp, asimdfhm, asimdbf16, i8mm Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- linux-user/elfload.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ uint32_t get_elf_hwcap(void) } } GET_FEATURE_ID(aa32_simdfmac, ARM_HWCAP_ARM_VFPv4); + /* + * MVFR1.FPHP and .SIMDHP must be in sync, and QEMU uses the same + * isar_feature function for both. The kernel reports them as two hwcaps. + */ + GET_FEATURE_ID(aa32_fp16_arith, ARM_HWCAP_ARM_FPHP); + GET_FEATURE_ID(aa32_fp16_arith, ARM_HWCAP_ARM_ASIMDHP); + GET_FEATURE_ID(aa32_dp, ARM_HWCAP_ARM_ASIMDDP); + GET_FEATURE_ID(aa32_fhm, ARM_HWCAP_ARM_ASIMDFHM); + GET_FEATURE_ID(aa32_bf16, ARM_HWCAP_ARM_ASIMDBF16); + GET_FEATURE_ID(aa32_i8mm, ARM_HWCAP_ARM_I8MM); return hwcaps; } @@ -XXX,XX +XXX,XX @@ uint32_t get_elf_hwcap2(void) GET_FEATURE_ID(aa32_sha1, ARM_HWCAP2_ARM_SHA1); GET_FEATURE_ID(aa32_sha2, ARM_HWCAP2_ARM_SHA2); GET_FEATURE_ID(aa32_crc32, ARM_HWCAP2_ARM_CRC32); + GET_FEATURE_ID(aa32_sb, ARM_HWCAP2_ARM_SB); + GET_FEATURE_ID(aa32_ssbs, ARM_HWCAP2_ARM_SSBS); return hwcaps; } -- 2.34.1 Update our AArch64 ID register field definitions from the 2023-06 system register XML release: https://developer.arm.com/documentation/ddi0601/2023-06/ Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/cpu.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64ISAR0, SHA1, 8, 4) FIELD(ID_AA64ISAR0, SHA2, 12, 4) FIELD(ID_AA64ISAR0, CRC32, 16, 4) FIELD(ID_AA64ISAR0, ATOMIC, 20, 4) +FIELD(ID_AA64ISAR0, TME, 24, 4) FIELD(ID_AA64ISAR0, RDM, 28, 4) FIELD(ID_AA64ISAR0, SHA3, 32, 4) FIELD(ID_AA64ISAR0, SM3, 36, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64ISAR2, APA3, 12, 4) FIELD(ID_AA64ISAR2, MOPS, 16, 4) FIELD(ID_AA64ISAR2, BC, 20, 4) FIELD(ID_AA64ISAR2, PAC_FRAC, 24, 4) +FIELD(ID_AA64ISAR2, CLRBHB, 28, 4) +FIELD(ID_AA64ISAR2, SYSREG_128, 32, 4) +FIELD(ID_AA64ISAR2, SYSINSTR_128, 36, 4) +FIELD(ID_AA64ISAR2, PRFMSLC, 40, 4) +FIELD(ID_AA64ISAR2, RPRFM, 48, 4) +FIELD(ID_AA64ISAR2, CSSC, 52, 4) +FIELD(ID_AA64ISAR2, ATS1A, 60, 4) FIELD(ID_AA64PFR0, EL0, 0, 4) FIELD(ID_AA64PFR0, EL1, 4, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64PFR1, SME, 24, 4) FIELD(ID_AA64PFR1, RNDR_TRAP, 28, 4) FIELD(ID_AA64PFR1, CSV2_FRAC, 32, 4) FIELD(ID_AA64PFR1, NMI, 36, 4) +FIELD(ID_AA64PFR1, MTE_FRAC, 40, 4) +FIELD(ID_AA64PFR1, GCS, 44, 4) +FIELD(ID_AA64PFR1, THE, 48, 4) +FIELD(ID_AA64PFR1, MTEX, 52, 4) +FIELD(ID_AA64PFR1, DF2, 56, 4) +FIELD(ID_AA64PFR1, PFAR, 60, 4) FIELD(ID_AA64MMFR0, PARANGE, 0, 4) FIELD(ID_AA64MMFR0, ASIDBITS, 4, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64MMFR1, AFP, 44, 4) FIELD(ID_AA64MMFR1, NTLBPA, 48, 4) FIELD(ID_AA64MMFR1, TIDCP1, 52, 4) FIELD(ID_AA64MMFR1, CMOW, 56, 4) +FIELD(ID_AA64MMFR1, ECBHB, 60, 4) FIELD(ID_AA64MMFR2, CNP, 0, 4) FIELD(ID_AA64MMFR2, UAO, 4, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64DFR0, DEBUGVER, 0, 4) FIELD(ID_AA64DFR0, TRACEVER, 4, 4) FIELD(ID_AA64DFR0, PMUVER, 8, 4) FIELD(ID_AA64DFR0, BRPS, 12, 4) +FIELD(ID_AA64DFR0, PMSS, 16, 4) FIELD(ID_AA64DFR0, WRPS, 20, 4) +FIELD(ID_AA64DFR0, SEBEP, 24, 4) FIELD(ID_AA64DFR0, CTX_CMPS, 28, 4) FIELD(ID_AA64DFR0, PMSVER, 32, 4) FIELD(ID_AA64DFR0, DOUBLELOCK, 36, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64DFR0, TRACEFILT, 40, 4) FIELD(ID_AA64DFR0, TRACEBUFFER, 44, 4) FIELD(ID_AA64DFR0, MTPMU, 48, 4) FIELD(ID_AA64DFR0, BRBE, 52, 4) +FIELD(ID_AA64DFR0, EXTTRCBUFF, 56, 4) FIELD(ID_AA64DFR0, HPMN0, 60, 4) FIELD(ID_AA64ZFR0, SVEVER, 0, 4) FIELD(ID_AA64ZFR0, AES, 4, 4) FIELD(ID_AA64ZFR0, BITPERM, 16, 4) FIELD(ID_AA64ZFR0, BFLOAT16, 20, 4) +FIELD(ID_AA64ZFR0, B16B16, 24, 4) FIELD(ID_AA64ZFR0, SHA3, 32, 4) FIELD(ID_AA64ZFR0, SM4, 40, 4) FIELD(ID_AA64ZFR0, I8MM, 44, 4) @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64ZFR0, F32MM, 52, 4) FIELD(ID_AA64ZFR0, F64MM, 56, 4) FIELD(ID_AA64SMFR0, F32F32, 32, 1) +FIELD(ID_AA64SMFR0, BI32I32, 33, 1) FIELD(ID_AA64SMFR0, B16F32, 34, 1) FIELD(ID_AA64SMFR0, F16F32, 35, 1) FIELD(ID_AA64SMFR0, I8I32, 36, 4) +FIELD(ID_AA64SMFR0, F16F16, 42, 1) +FIELD(ID_AA64SMFR0, B16B16, 43, 1) +FIELD(ID_AA64SMFR0, I16I32, 44, 4) FIELD(ID_AA64SMFR0, F64F64, 48, 1) FIELD(ID_AA64SMFR0, I16I64, 52, 4) FIELD(ID_AA64SMFR0, SMEVER, 56, 4) -- 2.34.1 For user-only mode we reveal a subset of the AArch64 ID registers to the guest, to emulate the kernel's trap-and-emulate-ID-regs handling. Update the feature bit masks to match upstream kernel commit a48fa7efaf1161c1c. None of these features are yet implemented by QEMU, so this doesn't yet have a behavioural change, but implementation of FEAT_MOPS and FEAT_HBC is imminent. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper.c | 11 ++++++++++- tests/tcg/aarch64/sysregs.c | 4 ++-- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) R_ID_AA64ZFR0_F64MM_MASK }, { .name = "ID_AA64SMFR0_EL1", .exported_bits = R_ID_AA64SMFR0_F32F32_MASK | + R_ID_AA64SMFR0_BI32I32_MASK | R_ID_AA64SMFR0_B16F32_MASK | R_ID_AA64SMFR0_F16F32_MASK | R_ID_AA64SMFR0_I8I32_MASK | + R_ID_AA64SMFR0_F16F16_MASK | + R_ID_AA64SMFR0_B16B16_MASK | + R_ID_AA64SMFR0_I16I32_MASK | R_ID_AA64SMFR0_F64F64_MASK | R_ID_AA64SMFR0_I16I64_MASK | + R_ID_AA64SMFR0_SMEVER_MASK | R_ID_AA64SMFR0_FA64_MASK }, { .name = "ID_AA64MMFR0_EL1", .exported_bits = R_ID_AA64MMFR0_ECV_MASK, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) .exported_bits = R_ID_AA64ISAR2_WFXT_MASK | R_ID_AA64ISAR2_RPRES_MASK | R_ID_AA64ISAR2_GPA3_MASK | - R_ID_AA64ISAR2_APA3_MASK }, + R_ID_AA64ISAR2_APA3_MASK | + R_ID_AA64ISAR2_MOPS_MASK | + R_ID_AA64ISAR2_BC_MASK | + R_ID_AA64ISAR2_RPRFM_MASK | + R_ID_AA64ISAR2_CSSC_MASK }, { .name = "ID_AA64ISAR*_EL1_RESERVED", .is_glob = true }, }; diff --git a/tests/tcg/aarch64/sysregs.c b/tests/tcg/aarch64/sysregs.c index XXXXXXX..XXXXXXX 100644 --- a/tests/tcg/aarch64/sysregs.c +++ b/tests/tcg/aarch64/sysregs.c @@ -XXX,XX +XXX,XX @@ int main(void) */ get_cpu_reg_check_mask(id_aa64isar0_el1, _m(f0ff,ffff,f0ff,fff0)); get_cpu_reg_check_mask(id_aa64isar1_el1, _m(00ff,f0ff,ffff,ffff)); - get_cpu_reg_check_mask(SYS_ID_AA64ISAR2_EL1, _m(0000,0000,0000,ffff)); + get_cpu_reg_check_mask(SYS_ID_AA64ISAR2_EL1, _m(00ff,0000,00ff,ffff)); /* TGran4 & TGran64 as pegged to -1 */ get_cpu_reg_check_mask(id_aa64mmfr0_el1, _m(f000,0000,ff00,0000)); get_cpu_reg_check_mask(id_aa64mmfr1_el1, _m(0000,f000,0000,0000)); @@ -XXX,XX +XXX,XX @@ int main(void) get_cpu_reg_check_mask(id_aa64dfr0_el1, _m(0000,0000,0000,0006)); get_cpu_reg_check_zero(id_aa64dfr1_el1); get_cpu_reg_check_mask(SYS_ID_AA64ZFR0_EL1, _m(0ff0,ff0f,00ff,00ff)); - get_cpu_reg_check_mask(SYS_ID_AA64SMFR0_EL1, _m(80f1,00fd,0000,0000)); + get_cpu_reg_check_mask(SYS_ID_AA64SMFR0_EL1, _m(8ff1,fcff,0000,0000)); get_cpu_reg_check_zero(id_aa64afr0_el1); get_cpu_reg_check_zero(id_aa64afr1_el1); -- 2.34.1 FEAT_HBC (Hinted conditional branches) provides a new instruction BC.cond, which behaves exactly like the existing B.cond except that it provides a hint to the branch predictor about the likely behaviour of the branch. Since QEMU does not implement branch prediction, we can treat this identically to B.cond. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/cpu.h | 5 +++++ target/arm/tcg/a64.decode | 3 ++- linux-user/elfload.c | 1 + target/arm/tcg/cpu64.c | 4 ++++ target/arm/tcg/translate-a64.c | 4 ++++ 6 files changed, 17 insertions(+), 1 deletion(-) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_FlagM2 (Enhancements to flag manipulation instructions) - FEAT_GTG (Guest translation granule size) - FEAT_HAFDBS (Hardware management of the access flag and dirty bit state) +- FEAT_HBC (Hinted conditional branches) - FEAT_HCX (Support for the HCRX_EL2 register) - FEAT_HPDS (Hierarchical permission disables) - FEAT_HPDS2 (Translation table page-based hardware attributes) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_i8mm(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 0; } +static inline bool isar_feature_aa64_hbc(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, BC) != 0; +} + static inline bool isar_feature_aa64_tgran4_lpa2(const ARMISARegisters *id) { return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 1; diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ CBZ sf:1 011010 nz:1 ................... rt:5 &cbz imm=%imm19 TBZ . 011011 nz:1 ..... .............. rt:5 &tbz imm=%imm14 bitpos=%imm31_19 -B_cond 0101010 0 ................... 0 cond:4 imm=%imm19 +# B.cond and BC.cond +B_cond 0101010 0 ................... c:1 cond:4 imm=%imm19 BR 1101011 0000 11111 000000 rn:5 00000 &r BLR 1101011 0001 11111 000000 rn:5 00000 &r diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ uint32_t get_elf_hwcap2(void) GET_FEATURE_ID(aa64_sme_f64f64, ARM_HWCAP2_A64_SME_F64F64); GET_FEATURE_ID(aa64_sme_i16i64, ARM_HWCAP2_A64_SME_I16I64); GET_FEATURE_ID(aa64_sme_fa64, ARM_HWCAP2_A64_SME_FA64); + GET_FEATURE_ID(aa64_hbc, ARM_HWCAP2_A64_HBC); return hwcaps; } diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64ISAR1, I8MM, 1); /* FEAT_I8MM */ cpu->isar.id_aa64isar1 = t; + t = cpu->isar.id_aa64isar2; + t = FIELD_DP64(t, ID_AA64ISAR2, BC, 1); /* FEAT_HBC */ + cpu->isar.id_aa64isar2 = t; + t = cpu->isar.id_aa64pfr0; t = FIELD_DP64(t, ID_AA64PFR0, FP, 1); /* FEAT_FP16 */ t = FIELD_DP64(t, ID_AA64PFR0, ADVSIMD, 1); /* FEAT_FP16 */ diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_TBZ(DisasContext *s, arg_tbz *a) static bool trans_B_cond(DisasContext *s, arg_B_cond *a) { + /* BC.cond is only present with FEAT_HBC */ + if (a->c && !dc_isar_feature(aa64_hbc, s)) { + return false; + } reset_btype(s); if (a->cond < 0x0e) { /* genuinely conditional branches */ -- 2.34.1 The allocation_tag_mem() function takes an argument tag_size, but it never uses it. Remove the argument. In mte_probe_int() in particular this also lets us delete the code computing the value we were passing in. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> --- target/arm/tcg/mte_helper.c | 42 +++++++++++++------------------------ 1 file changed, 14 insertions(+), 28 deletions(-) diff --git a/target/arm/tcg/mte_helper.c b/target/arm/tcg/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mte_helper.c +++ b/target/arm/tcg/mte_helper.c @@ -XXX,XX +XXX,XX @@ static int choose_nonexcluded_tag(int tag, int offset, uint16_t exclude) * @ptr_access: the access to use for the virtual address * @ptr_size: the number of bytes in the normal memory access * @tag_access: the access to use for the tag memory - * @tag_size: the number of bytes in the tag memory access * @ra: the return address for exception handling * * Our tag memory is formatted as a sequence of little-endian nibbles. @@ -XXX,XX +XXX,XX @@ static int choose_nonexcluded_tag(int tag, int offset, uint16_t exclude) * a pointer to the corresponding tag byte. Exit with exception if the * virtual address is not accessible for @ptr_access. * - * The @ptr_size and @tag_size values may not have an obvious relation - * due to the alignment of @ptr, and the number of tag checks required. - * * If there is no tag storage corresponding to @ptr, return NULL. */ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, uint64_t ptr, MMUAccessType ptr_access, int ptr_size, MMUAccessType tag_access, - int tag_size, uintptr_t ra) + uintptr_t ra) { #ifdef CONFIG_USER_ONLY uint64_t clean_ptr = useronly_clean_ptr(ptr); @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(ldg)(CPUARMState *env, uint64_t ptr, uint64_t xt) /* Trap if accessing an invalid page. */ mem = allocation_tag_mem(env, mmu_idx, ptr, MMU_DATA_LOAD, 1, - MMU_DATA_LOAD, 1, GETPC()); + MMU_DATA_LOAD, GETPC()); /* Load if page supports tags. */ if (mem) { @@ -XXX,XX +XXX,XX @@ static inline void do_stg(CPUARMState *env, uint64_t ptr, uint64_t xt, /* Trap if accessing an invalid page. */ mem = allocation_tag_mem(env, mmu_idx, ptr, MMU_DATA_STORE, TAG_GRANULE, - MMU_DATA_STORE, 1, ra); + MMU_DATA_STORE, ra); /* Store if page supports tags. */ if (mem) { @@ -XXX,XX +XXX,XX @@ static inline void do_st2g(CPUARMState *env, uint64_t ptr, uint64_t xt, if (ptr & TAG_GRANULE) { /* Two stores unaligned mod TAG_GRANULE*2 -- modify two bytes. */ mem1 = allocation_tag_mem(env, mmu_idx, ptr, MMU_DATA_STORE, - TAG_GRANULE, MMU_DATA_STORE, 1, ra); + TAG_GRANULE, MMU_DATA_STORE, ra); mem2 = allocation_tag_mem(env, mmu_idx, ptr + TAG_GRANULE, MMU_DATA_STORE, TAG_GRANULE, - MMU_DATA_STORE, 1, ra); + MMU_DATA_STORE, ra); /* Store if page(s) support tags. */ if (mem1) { @@ -XXX,XX +XXX,XX @@ static inline void do_st2g(CPUARMState *env, uint64_t ptr, uint64_t xt, } else { /* Two stores aligned mod TAG_GRANULE*2 -- modify one byte. */ mem1 = allocation_tag_mem(env, mmu_idx, ptr, MMU_DATA_STORE, - 2 * TAG_GRANULE, MMU_DATA_STORE, 1, ra); + 2 * TAG_GRANULE, MMU_DATA_STORE, ra); if (mem1) { tag |= tag << 4; qatomic_set(mem1, tag); @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(ldgm)(CPUARMState *env, uint64_t ptr) /* Trap if accessing an invalid page. */ tag_mem = allocation_tag_mem(env, mmu_idx, ptr, MMU_DATA_LOAD, - gm_bs_bytes, MMU_DATA_LOAD, - gm_bs_bytes / (2 * TAG_GRANULE), ra); + gm_bs_bytes, MMU_DATA_LOAD, ra); /* The tag is squashed to zero if the page does not support tags. */ if (!tag_mem) { @@ -XXX,XX +XXX,XX @@ void HELPER(stgm)(CPUARMState *env, uint64_t ptr, uint64_t val) /* Trap if accessing an invalid page. */ tag_mem = allocation_tag_mem(env, mmu_idx, ptr, MMU_DATA_STORE, - gm_bs_bytes, MMU_DATA_LOAD, - gm_bs_bytes / (2 * TAG_GRANULE), ra); + gm_bs_bytes, MMU_DATA_LOAD, ra); /* * Tag store only happens if the page support tags, @@ -XXX,XX +XXX,XX @@ void HELPER(stzgm_tags)(CPUARMState *env, uint64_t ptr, uint64_t val) ptr &= -dcz_bytes; mem = allocation_tag_mem(env, mmu_idx, ptr, MMU_DATA_STORE, dcz_bytes, - MMU_DATA_STORE, tag_bytes, ra); + MMU_DATA_STORE, ra); if (mem) { int tag_pair = (val & 0xf) * 0x11; memset(mem, tag_pair, tag_bytes); @@ -XXX,XX +XXX,XX @@ static int mte_probe_int(CPUARMState *env, uint32_t desc, uint64_t ptr, int mmu_idx, ptr_tag, bit55; uint64_t ptr_last, prev_page, next_page; uint64_t tag_first, tag_last; - uint64_t tag_byte_first, tag_byte_last; - uint32_t sizem1, tag_count, tag_size, n, c; + uint32_t sizem1, tag_count, n, c; uint8_t *mem1, *mem2; MMUAccessType type; @@ -XXX,XX +XXX,XX @@ static int mte_probe_int(CPUARMState *env, uint32_t desc, uint64_t ptr, tag_last = QEMU_ALIGN_DOWN(ptr_last, TAG_GRANULE); tag_count = ((tag_last - tag_first) / TAG_GRANULE) + 1; - /* Round the bounds to twice the tag granule, and compute the bytes. */ - tag_byte_first = QEMU_ALIGN_DOWN(ptr, 2 * TAG_GRANULE); - tag_byte_last = QEMU_ALIGN_DOWN(ptr_last, 2 * TAG_GRANULE); - /* Locate the page boundaries. */ prev_page = ptr & TARGET_PAGE_MASK; next_page = prev_page + TARGET_PAGE_SIZE; if (likely(tag_last - prev_page < TARGET_PAGE_SIZE)) { /* Memory access stays on one page. */ - tag_size = ((tag_byte_last - tag_byte_first) / (2 * TAG_GRANULE)) + 1; mem1 = allocation_tag_mem(env, mmu_idx, ptr, type, sizem1 + 1, - MMU_DATA_LOAD, tag_size, ra); + MMU_DATA_LOAD, ra); if (!mem1) { return 1; } @@ -XXX,XX +XXX,XX @@ static int mte_probe_int(CPUARMState *env, uint32_t desc, uint64_t ptr, n = checkN(mem1, ptr & TAG_GRANULE, ptr_tag, tag_count); } else { /* Memory access crosses to next page. */ - tag_size = (next_page - tag_byte_first) / (2 * TAG_GRANULE); mem1 = allocation_tag_mem(env, mmu_idx, ptr, type, next_page - ptr, - MMU_DATA_LOAD, tag_size, ra); + MMU_DATA_LOAD, ra); - tag_size = ((tag_byte_last - next_page) / (2 * TAG_GRANULE)) + 1; mem2 = allocation_tag_mem(env, mmu_idx, next_page, type, ptr_last - next_page + 1, - MMU_DATA_LOAD, tag_size, ra); + MMU_DATA_LOAD, ra); /* * Perform all of the comparisons. @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mte_check_zva)(CPUARMState *env, uint32_t desc, uint64_t ptr) mmu_idx = FIELD_EX32(desc, MTEDESC, MIDX); (void) probe_write(env, ptr, 1, mmu_idx, ra); mem = allocation_tag_mem(env, mmu_idx, align_ptr, MMU_DATA_STORE, - dcz_bytes, MMU_DATA_LOAD, tag_bytes, ra); + dcz_bytes, MMU_DATA_LOAD, ra); if (!mem) { goto done; } -- 2.34.1 The LDRT/STRT "unprivileged load/store" instructions behave like normal ones if executed at EL0. We handle this correctly for the load/store semantics, but get the MTE checking wrong. We always look at s->mte_active[is_unpriv] to see whether we should be doing MTE checks, but in hflags.c when we set the TB flags that will be used to fill the mte_active[] array we only set the MTE0_ACTIVE bit if UNPRIV is true (i.e. we are not at EL0). This means that a LDRT at EL0 will see s->mte_active[1] as 0, and will not do MTE checks even when MTE is enabled. To avoid the translate-time code having to do an explicit check on s->unpriv to see if it is OK to index into the mte_active[] array, duplicate MTE_ACTIVE into MTE0_ACTIVE when UNPRIV is false. (This isn't a very serious bug because generally nobody executes LDRT/STRT at EL0, because they have no use there.) Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230912140434.1333369-2-peter.maydell@linaro.org --- target/arm/tcg/hflags.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/hflags.c +++ b/target/arm/tcg/hflags.c @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, && !(env->pstate & PSTATE_TCO) && (sctlr & (el == 0 ? SCTLR_TCF0 : SCTLR_TCF))) { DP_TBFLAG_A64(flags, MTE_ACTIVE, 1); + if (!EX_TBFLAG_A64(flags, UNPRIV)) { + /* + * In non-unpriv contexts (eg EL0), unpriv load/stores + * act like normal ones; duplicate the MTE info to + * avoid translate-a64.c having to check UNPRIV to see + * whether it is OK to index into MTE_ACTIVE[]. + */ + DP_TBFLAG_A64(flags, MTE0_ACTIVE, 1); + } } } /* And again for unprivileged accesses, if required. */ -- 2.34.1 FEAT_MOPS defines a handful of new enable bits: * HCRX_EL2.MSCEn, SCTLR_EL1.MSCEn, SCTLR_EL2.MSCen: define whether the new insns should UNDEF or not * HCRX_EL2.MCE2: defines whether memops exceptions from EL1 should be taken to EL1 or EL2 Since we don't sanitise what bits can be written for the SCTLR registers, we only need to handle the new bits in HCRX_EL2, and define SCTLR_MSCEN for the new SCTLR bit value. The precedence of "HCRX bits acts as 0 if SCR_EL3.HXEn is 0" versus "bit acts as 1 if EL2 disabled" is not clear from the register definition text, but it is clear in the CheckMOPSEnabled() pseudocode(), so we follow that. We'll have to check whether other bits we need to implement in future follow the same logic or not. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230912140434.1333369-3-peter.maydell@linaro.org --- target/arm/cpu.h | 6 ++++++ target/arm/helper.c | 28 +++++++++++++++++++++------- 2 files changed, 27 insertions(+), 7 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define SCTLR_EnIB (1U << 30) /* v8.3, AArch64 only */ #define SCTLR_EnIA (1U << 31) /* v8.3, AArch64 only */ #define SCTLR_DSSBS_32 (1U << 31) /* v8.5, AArch32 only */ +#define SCTLR_MSCEN (1ULL << 33) /* FEAT_MOPS */ #define SCTLR_BT0 (1ULL << 35) /* v8.5-BTI */ #define SCTLR_BT1 (1ULL << 36) /* v8.5-BTI */ #define SCTLR_ITFSB (1ULL << 37) /* v8.5-MemTag */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_doublelock(const ARMISARegisters *id) return FIELD_SEX64(id->id_aa64dfr0, ID_AA64DFR0, DOUBLELOCK) >= 0; } +static inline bool isar_feature_aa64_mops(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, MOPS); +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void hcrx_write(CPUARMState *env, const ARMCPRegInfo *ri, { uint64_t valid_mask = 0; - /* No features adding bits to HCRX are implemented. */ + /* FEAT_MOPS adds MSCEn and MCE2 */ + if (cpu_isar_feature(aa64_mops, env_archcpu(env))) { + valid_mask |= HCRX_MSCEN | HCRX_MCE2; + } /* Clear RES0 bits. */ env->cp15.hcrx_el2 = value & valid_mask; @@ -XXX,XX +XXX,XX @@ uint64_t arm_hcrx_el2_eff(CPUARMState *env) { /* * The bits in this register behave as 0 for all purposes other than - * direct reads of the register if: - * - EL2 is not enabled in the current security state, - * - SCR_EL3.HXEn is 0. + * direct reads of the register if SCR_EL3.HXEn is 0. + * If EL2 is not enabled in the current security state, then the + * bit may behave as if 0, or as if 1, depending on the bit. + * For the moment, we treat the EL2-disabled case as taking + * priority over the HXEn-disabled case. This is true for the only + * bit for a feature which we implement where the answer is different + * for the two cases (MSCEn for FEAT_MOPS). + * This may need to be revisited for future bits. */ - if (!arm_is_el2_enabled(env) - || (arm_feature(env, ARM_FEATURE_EL3) - && !(env->cp15.scr_el3 & SCR_HXEN))) { + if (!arm_is_el2_enabled(env)) { + uint64_t hcrx = 0; + if (cpu_isar_feature(aa64_mops, env_archcpu(env))) { + /* MSCEn behaves as 1 if EL2 is not enabled */ + hcrx |= HCRX_MSCEN; + } + return hcrx; + } + if (arm_feature(env, ARM_FEATURE_EL3) && !(env->cp15.scr_el3 & SCR_HXEN)) { return 0; } return env->cp15.hcrx_el2; -- 2.34.1 In every place that we call the get_a64_user_mem_index() function we do it like this: memidx = a->unpriv ? get_a64_user_mem_index(s) : get_mem_index(s); Refactor so the caller passes in the bool that says whether they want the 'unpriv' or 'normal' mem_index rather than having to do the ?: themselves. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20230912140434.1333369-4-peter.maydell@linaro.org --- target/arm/tcg/translate-a64.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ void a64_translate_init(void) } /* - * Return the core mmu_idx to use for A64 "unprivileged load/store" insns + * Return the core mmu_idx to use for A64 load/store insns which + * have a "unprivileged load/store" variant. Those insns access + * EL0 if executed from an EL which has control over EL0 (usually + * EL1) but behave like normal loads and stores if executed from + * elsewhere (eg EL3). + * + * @unpriv : true for the unprivileged encoding; false for the + * normal encoding (in which case we will return the same + * thing as get_mem_index(). */ -static int get_a64_user_mem_index(DisasContext *s) +static int get_a64_user_mem_index(DisasContext *s, bool unpriv) { /* * If AccType_UNPRIV is not used, the insn uses AccType_NORMAL, @@ -XXX,XX +XXX,XX @@ static int get_a64_user_mem_index(DisasContext *s) */ ARMMMUIdx useridx = s->mmu_idx; - if (s->unpriv) { + if (unpriv && s->unpriv) { /* * We have pre-computed the condition for AccType_UNPRIV. * Therefore we should never get here with a mmu_idx for @@ -XXX,XX +XXX,XX @@ static void op_addr_ldst_imm_pre(DisasContext *s, arg_ldst_imm *a, if (!a->p) { tcg_gen_addi_i64(*dirty_addr, *dirty_addr, offset); } - memidx = a->unpriv ? get_a64_user_mem_index(s) : get_mem_index(s); + memidx = get_a64_user_mem_index(s, a->unpriv); *clean_addr = gen_mte_check1_mmuidx(s, *dirty_addr, is_store, a->w || a->rn != 31, mop, a->unpriv, memidx); @@ -XXX,XX +XXX,XX @@ static bool trans_STR_i(DisasContext *s, arg_ldst_imm *a) { bool iss_sf, iss_valid = !a->w; TCGv_i64 clean_addr, dirty_addr, tcg_rt; - int memidx = a->unpriv ? get_a64_user_mem_index(s) : get_mem_index(s); + int memidx = get_a64_user_mem_index(s, a->unpriv); MemOp mop = finalize_memop(s, a->sz + a->sign * MO_SIGN); op_addr_ldst_imm_pre(s, a, &clean_addr, &dirty_addr, a->imm, true, mop); @@ -XXX,XX +XXX,XX @@ static bool trans_LDR_i(DisasContext *s, arg_ldst_imm *a) { bool iss_sf, iss_valid = !a->w; TCGv_i64 clean_addr, dirty_addr, tcg_rt; - int memidx = a->unpriv ? get_a64_user_mem_index(s) : get_mem_index(s); + int memidx = get_a64_user_mem_index(s, a->unpriv); MemOp mop = finalize_memop(s, a->sz + a->sign * MO_SIGN); op_addr_ldst_imm_pre(s, a, &clean_addr, &dirty_addr, a->imm, false, mop); -- 2.34.1 The FEAT_MOPS memory operations can raise a Memory Copy or Memory Set exception if a copy or set instruction is executed when the CPU register state is not correct for that instruction. Define the usual syn_* function that constructs the syndrome register value for these exceptions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230912140434.1333369-5-peter.maydell@linaro.org --- target/arm/syndrome.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ enum arm_exception_class { EC_DATAABORT = 0x24, EC_DATAABORT_SAME_EL = 0x25, EC_SPALIGNMENT = 0x26, + EC_MOP = 0x27, EC_AA32_FPTRAP = 0x28, EC_AA64_FPTRAP = 0x2c, EC_SERROR = 0x2f, @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_serror(uint32_t extra) return (EC_SERROR << ARM_EL_EC_SHIFT) | ARM_EL_IL | extra; } +static inline uint32_t syn_mop(bool is_set, bool is_setg, int options, + bool epilogue, bool wrong_option, bool option_a, + int destreg, int srcreg, int sizereg) +{ + return (EC_MOP << ARM_EL_EC_SHIFT) | ARM_EL_IL | + (is_set << 24) | (is_setg << 23) | (options << 19) | + (epilogue << 18) | (wrong_option << 17) | (option_a << 16) | + (destreg << 10) | (srcreg << 5) | sizereg; +} + + #endif /* TARGET_ARM_SYNDROME_H */ -- 2.34.1 For the FEAT_MOPS operations, the existing allocation_tag_mem() function almost does what we want, but it will take a watchpoint exception even for an ra == 0 probe request, and it requires that the caller guarantee that the memory is accessible. For FEAT_MOPS we want a function that will not take any kind of exception, and will return NULL for the not-accessible case. Rename allocation_tag_mem() to allocation_tag_mem_probe() and add an extra 'probe' argument that lets us distinguish these cases; allocation_tag_mem() is now a wrapper that always passes 'false'. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230912140434.1333369-6-peter.maydell@linaro.org --- target/arm/tcg/mte_helper.c | 48 ++++++++++++++++++++++++++++--------- 1 file changed, 37 insertions(+), 11 deletions(-) diff --git a/target/arm/tcg/mte_helper.c b/target/arm/tcg/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mte_helper.c +++ b/target/arm/tcg/mte_helper.c @@ -XXX,XX +XXX,XX @@ static int choose_nonexcluded_tag(int tag, int offset, uint16_t exclude) } /** - * allocation_tag_mem: + * allocation_tag_mem_probe: * @env: the cpu environment * @ptr_mmu_idx: the addressing regime to use for the virtual address * @ptr: the virtual address for which to look up tag memory * @ptr_access: the access to use for the virtual address * @ptr_size: the number of bytes in the normal memory access * @tag_access: the access to use for the tag memory + * @probe: true to merely probe, never taking an exception * @ra: the return address for exception handling * * Our tag memory is formatted as a sequence of little-endian nibbles. @@ -XXX,XX +XXX,XX @@ static int choose_nonexcluded_tag(int tag, int offset, uint16_t exclude) * for the higher addr. * * Here, resolve the physical address from the virtual address, and return - * a pointer to the corresponding tag byte. Exit with exception if the - * virtual address is not accessible for @ptr_access. + * a pointer to the corresponding tag byte. * * If there is no tag storage corresponding to @ptr, return NULL. + * + * If the page is inaccessible for @ptr_access, or has a watchpoint, there are + * three options: + * (1) probe = true, ra = 0 : pure probe -- we return NULL if the page is not + * accessible, and do not take watchpoint traps. The calling code must + * handle those cases in the right priority compared to MTE traps. + * (2) probe = false, ra = 0 : probe, no fault expected -- the caller guarantees + * that the page is going to be accessible. We will take watchpoint traps. + * (3) probe = false, ra != 0 : non-probe -- we will take both memory access + * traps and watchpoint traps. + * (probe = true, ra != 0 is invalid and will assert.) */ -static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, - uint64_t ptr, MMUAccessType ptr_access, - int ptr_size, MMUAccessType tag_access, - uintptr_t ra) +static uint8_t *allocation_tag_mem_probe(CPUARMState *env, int ptr_mmu_idx, + uint64_t ptr, MMUAccessType ptr_access, + int ptr_size, MMUAccessType tag_access, + bool probe, uintptr_t ra) { #ifdef CONFIG_USER_ONLY uint64_t clean_ptr = useronly_clean_ptr(ptr); @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, uint8_t *tags; uintptr_t index; + assert(!(probe && ra)); + if (!(flags & (ptr_access == MMU_DATA_STORE ? PAGE_WRITE_ORG : PAGE_READ))) { cpu_loop_exit_sigsegv(env_cpu(env), ptr, ptr_access, !(flags & PAGE_VALID), ra); @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, * exception for inaccessible pages, and resolves the virtual address * into the softmmu tlb. * - * When RA == 0, this is for mte_probe. The page is expected to be - * valid. Indicate to probe_access_flags no-fault, then assert that - * we received a valid page. + * When RA == 0, this is either a pure probe or a no-fault-expected probe. + * Indicate to probe_access_flags no-fault, then either return NULL + * for the pure probe, or assert that we received a valid page for the + * no-fault-expected probe. */ flags = probe_access_full(env, ptr, 0, ptr_access, ptr_mmu_idx, ra == 0, &host, &full, ra); + if (probe && (flags & TLB_INVALID_MASK)) { + return NULL; + } assert(!(flags & TLB_INVALID_MASK)); /* If the virtual page MemAttr != Tagged, access unchecked. */ @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, } /* Any debug exception has priority over a tag check exception. */ - if (unlikely(flags & TLB_WATCHPOINT)) { + if (!probe && unlikely(flags & TLB_WATCHPOINT)) { int wp = ptr_access == MMU_DATA_LOAD ? BP_MEM_READ : BP_MEM_WRITE; assert(ra != 0); cpu_check_watchpoint(env_cpu(env), ptr, ptr_size, attrs, wp, ra); @@ -XXX,XX +XXX,XX @@ static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, #endif } +static uint8_t *allocation_tag_mem(CPUARMState *env, int ptr_mmu_idx, + uint64_t ptr, MMUAccessType ptr_access, + int ptr_size, MMUAccessType tag_access, + uintptr_t ra) +{ + return allocation_tag_mem_probe(env, ptr_mmu_idx, ptr, ptr_access, + ptr_size, tag_access, false, ra); +} + uint64_t HELPER(irg)(CPUARMState *env, uint64_t rn, uint64_t rm) { uint16_t exclude = extract32(rm | env->cp15.gcr_el1, 0, 16); -- 2.34.1 The FEAT_MOPS instructions need a couple of helper routines that check for MTE tag failures: * mte_mops_probe() checks whether there is going to be a tag error in the next up-to-a-page worth of data * mte_check_fail() is an existing function to record the fact of a tag failure, which we need to make global so we can call it from helper-a64.c Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230912140434.1333369-7-peter.maydell@linaro.org --- target/arm/internals.h | 28 +++++++++++++++++++ target/arm/tcg/mte_helper.c | 54 +++++++++++++++++++++++++++++++++++-- 2 files changed, 80 insertions(+), 2 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ FIELD(MTEDESC, SIZEM1, 12, SIMD_DATA_BITS - 12) /* size - 1 */ bool mte_probe(CPUARMState *env, uint32_t desc, uint64_t ptr); uint64_t mte_check(CPUARMState *env, uint32_t desc, uint64_t ptr, uintptr_t ra); +/** + * mte_mops_probe: Check where the next MTE failure is for a FEAT_MOPS operation + * @env: CPU env + * @ptr: start address of memory region (dirty pointer) + * @size: length of region (guaranteed not to cross a page boundary) + * @desc: MTEDESC descriptor word (0 means no MTE checks) + * Returns: the size of the region that can be copied without hitting + * an MTE tag failure + * + * Note that we assume that the caller has already checked the TBI + * and TCMA bits with mte_checks_needed() and an MTE check is definitely + * required. + */ +uint64_t mte_mops_probe(CPUARMState *env, uint64_t ptr, uint64_t size, + uint32_t desc); + +/** + * mte_check_fail: Record an MTE tag check failure + * @env: CPU env + * @desc: MTEDESC descriptor word + * @dirty_ptr: Failing dirty address + * @ra: TCG retaddr + * + * This may never return (if the MTE tag checks are configured to fault). + */ +void mte_check_fail(CPUARMState *env, uint32_t desc, + uint64_t dirty_ptr, uintptr_t ra); + static inline int allocation_tag_from_addr(uint64_t ptr) { return extract64(ptr, 56, 4); diff --git a/target/arm/tcg/mte_helper.c b/target/arm/tcg/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mte_helper.c +++ b/target/arm/tcg/mte_helper.c @@ -XXX,XX +XXX,XX @@ static void mte_async_check_fail(CPUARMState *env, uint64_t dirty_ptr, } /* Record a tag check failure. */ -static void mte_check_fail(CPUARMState *env, uint32_t desc, - uint64_t dirty_ptr, uintptr_t ra) +void mte_check_fail(CPUARMState *env, uint32_t desc, + uint64_t dirty_ptr, uintptr_t ra) { int mmu_idx = FIELD_EX32(desc, MTEDESC, MIDX); ARMMMUIdx arm_mmu_idx = core_to_aa64_mmu_idx(mmu_idx); @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mte_check_zva)(CPUARMState *env, uint32_t desc, uint64_t ptr) done: return useronly_clean_ptr(ptr); } + +uint64_t mte_mops_probe(CPUARMState *env, uint64_t ptr, uint64_t size, + uint32_t desc) +{ + int mmu_idx, tag_count; + uint64_t ptr_tag, tag_first, tag_last; + void *mem; + bool w = FIELD_EX32(desc, MTEDESC, WRITE); + uint32_t n; + + mmu_idx = FIELD_EX32(desc, MTEDESC, MIDX); + /* True probe; this will never fault */ + mem = allocation_tag_mem_probe(env, mmu_idx, ptr, + w ? MMU_DATA_STORE : MMU_DATA_LOAD, + size, MMU_DATA_LOAD, true, 0); + if (!mem) { + return size; + } + + /* + * TODO: checkN() is not designed for checks of the size we expect + * for FEAT_MOPS operations, so we should implement this differently. + * Maybe we should do something like + * if (region start and size are aligned nicely) { + * do direct loads of 64 tag bits at a time; + * } else { + * call checkN() + * } + */ + /* Round the bounds to the tag granule, and compute the number of tags. */ + ptr_tag = allocation_tag_from_addr(ptr); + tag_first = QEMU_ALIGN_DOWN(ptr, TAG_GRANULE); + tag_last = QEMU_ALIGN_DOWN(ptr + size - 1, TAG_GRANULE); + tag_count = ((tag_last - tag_first) / TAG_GRANULE) + 1; + n = checkN(mem, ptr & TAG_GRANULE, ptr_tag, tag_count); + if (likely(n == tag_count)) { + return size; + } + + /* + * Failure; for the first granule, it's at @ptr. Otherwise + * it's at the first byte of the nth granule. Calculate how + * many bytes we can access without hitting that failure. + */ + if (n == 0) { + return 0; + } else { + return n * TAG_GRANULE - (ptr - tag_first); + } +} -- 2.34.1 Implement the SET* instructions which collectively implement a "memset" operation. These come in a set of three, eg SETP (prologue), SETM (main), SETE (epilogue), and each of those has different flavours to indicate whether memory accesses should be unpriv or non-temporal. This commit does not include the "memset with tag setting" SETG* instructions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230912140434.1333369-8-peter.maydell@linaro.org --- target/arm/tcg/helper-a64.h | 4 + target/arm/tcg/a64.decode | 16 ++ target/arm/tcg/helper-a64.c | 344 +++++++++++++++++++++++++++++++++ target/arm/tcg/translate-a64.c | 49 +++++ 4 files changed, 413 insertions(+) diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(stzgm_tags, TCG_CALL_NO_WG, void, env, i64, i64) DEF_HELPER_FLAGS_4(unaligned_access, TCG_CALL_NO_WG, noreturn, env, i64, i32, i32) + +DEF_HELPER_3(setp, void, env, i32, i32) +DEF_HELPER_3(setm, void, env, i32, i32) +DEF_HELPER_3(sete, void, env, i32, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ LDGM 11011001 11 1 ......... 00 ..... ..... @ldst_tag_mult p=0 w=0 STZ2G 11011001 11 1 ......... 01 ..... ..... @ldst_tag p=1 w=1 STZ2G 11011001 11 1 ......... 10 ..... ..... @ldst_tag p=0 w=0 STZ2G 11011001 11 1 ......... 11 ..... ..... @ldst_tag p=0 w=1 + +# Memory operations (memset, memcpy, memmove) +# Each of these comes in a set of three, eg SETP (prologue), SETM (main), +# SETE (epilogue), and each of those has different flavours to +# indicate whether memory accesses should be unpriv or non-temporal. +# We don't distinguish temporal and non-temporal accesses, but we +# do need to report it in syndrome register values. + +# Memset +&set rs rn rd unpriv nontemp +# op2 bit 1 is nontemporal bit +@set .. ......... rs:5 .. nontemp:1 unpriv:1 .. rn:5 rd:5 &set + +SETP 00 011001110 ..... 00 . . 01 ..... ..... @set +SETM 00 011001110 ..... 01 . . 01 ..... ..... @set +SETE 00 011001110 ..... 10 . . 01 ..... ..... @set diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -XXX,XX +XXX,XX @@ void HELPER(unaligned_access)(CPUARMState *env, uint64_t addr, arm_cpu_do_unaligned_access(env_cpu(env), addr, access_type, mmu_idx, GETPC()); } + +/* Memory operations (memset, memmove, memcpy) */ + +/* + * Return true if the CPY* and SET* insns can execute; compare + * pseudocode CheckMOPSEnabled(), though we refactor it a little. + */ +static bool mops_enabled(CPUARMState *env) +{ + int el = arm_current_el(env); + + if (el < 2 && + (arm_hcr_el2_eff(env) & (HCR_E2H | HCR_TGE)) != (HCR_E2H | HCR_TGE) && + !(arm_hcrx_el2_eff(env) & HCRX_MSCEN)) { + return false; + } + + if (el == 0) { + if (!el_is_in_host(env, 0)) { + return env->cp15.sctlr_el[1] & SCTLR_MSCEN; + } else { + return env->cp15.sctlr_el[2] & SCTLR_MSCEN; + } + } + return true; +} + +static void check_mops_enabled(CPUARMState *env, uintptr_t ra) +{ + if (!mops_enabled(env)) { + raise_exception_ra(env, EXCP_UDEF, syn_uncategorized(), + exception_target_el(env), ra); + } +} + +/* + * Return the target exception level for an exception due + * to mismatched arguments in a FEAT_MOPS copy or set. + * Compare pseudocode MismatchedCpySetTargetEL() + */ +static int mops_mismatch_exception_target_el(CPUARMState *env) +{ + int el = arm_current_el(env); + + if (el > 1) { + return el; + } + if (el == 0 && (arm_hcr_el2_eff(env) & HCR_TGE)) { + return 2; + } + if (el == 1 && (arm_hcrx_el2_eff(env) & HCRX_MCE2)) { + return 2; + } + return 1; +} + +/* + * Check whether an M or E instruction was executed with a CF value + * indicating the wrong option for this implementation. + * Assumes we are always Option A. + */ +static void check_mops_wrong_option(CPUARMState *env, uint32_t syndrome, + uintptr_t ra) +{ + if (env->CF != 0) { + syndrome |= 1 << 17; /* Set the wrong-option bit */ + raise_exception_ra(env, EXCP_UDEF, syndrome, + mops_mismatch_exception_target_el(env), ra); + } +} + +/* + * Return the maximum number of bytes we can transfer starting at addr + * without crossing a page boundary. + */ +static uint64_t page_limit(uint64_t addr) +{ + return TARGET_PAGE_ALIGN(addr + 1) - addr; +} + +/* + * Perform part of a memory set on an area of guest memory starting at + * toaddr (a dirty address) and extending for setsize bytes. + * + * Returns the number of bytes actually set, which might be less than + * setsize; the caller should loop until the whole set has been done. + * The caller should ensure that the guest registers are correct + * for the possibility that the first byte of the set encounters + * an exception or watchpoint. We guarantee not to take any faults + * for bytes other than the first. + */ +static uint64_t set_step(CPUARMState *env, uint64_t toaddr, + uint64_t setsize, uint32_t data, int memidx, + uint32_t *mtedesc, uintptr_t ra) +{ + void *mem; + + setsize = MIN(setsize, page_limit(toaddr)); + if (*mtedesc) { + uint64_t mtesize = mte_mops_probe(env, toaddr, setsize, *mtedesc); + if (mtesize == 0) { + /* Trap, or not. All CPU state is up to date */ + mte_check_fail(env, *mtedesc, toaddr, ra); + /* Continue, with no further MTE checks required */ + *mtedesc = 0; + } else { + /* Advance to the end, or to the tag mismatch */ + setsize = MIN(setsize, mtesize); + } + } + + toaddr = useronly_clean_ptr(toaddr); + /* + * Trapless lookup: returns NULL for invalid page, I/O, + * watchpoints, clean pages, etc. + */ + mem = tlb_vaddr_to_host(env, toaddr, MMU_DATA_STORE, memidx); + +#ifndef CONFIG_USER_ONLY + if (unlikely(!mem)) { + /* + * Slow-path: just do one byte write. This will handle the + * watchpoint, invalid page, etc handling correctly. + * For clean code pages, the next iteration will see + * the page dirty and will use the fast path. + */ + cpu_stb_mmuidx_ra(env, toaddr, data, memidx, ra); + return 1; + } +#endif + /* Easy case: just memset the host memory */ + memset(mem, data, setsize); + return setsize; +} + +typedef uint64_t StepFn(CPUARMState *env, uint64_t toaddr, + uint64_t setsize, uint32_t data, + int memidx, uint32_t *mtedesc, uintptr_t ra); + +/* Extract register numbers from a MOPS exception syndrome value */ +static int mops_destreg(uint32_t syndrome) +{ + return extract32(syndrome, 10, 5); +} + +static int mops_srcreg(uint32_t syndrome) +{ + return extract32(syndrome, 5, 5); +} + +static int mops_sizereg(uint32_t syndrome) +{ + return extract32(syndrome, 0, 5); +} + +/* + * Return true if TCMA and TBI bits mean we need to do MTE checks. + * We only need to do this once per MOPS insn, not for every page. + */ +static bool mte_checks_needed(uint64_t ptr, uint32_t desc) +{ + int bit55 = extract64(ptr, 55, 1); + + /* + * Note that tbi_check() returns true for "access checked" but + * tcma_check() returns true for "access unchecked". + */ + if (!tbi_check(desc, bit55)) { + return false; + } + return !tcma_check(desc, bit55, allocation_tag_from_addr(ptr)); +} + +/* + * For the Memory Set operation, our implementation chooses + * always to use "option A", where we update Xd to the final + * address in the SETP insn, and set Xn to be -(bytes remaining). + * On SETM and SETE insns we only need update Xn. + * + * @env: CPU + * @syndrome: syndrome value for mismatch exceptions + * (also contains the register numbers we need to use) + * @mtedesc: MTE descriptor word + * @stepfn: function which does a single part of the set operation + * @is_setg: true if this is the tag-setting SETG variant + */ +static void do_setp(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc, + StepFn *stepfn, bool is_setg, uintptr_t ra) +{ + /* Prologue: we choose to do up to the next page boundary */ + int rd = mops_destreg(syndrome); + int rs = mops_srcreg(syndrome); + int rn = mops_sizereg(syndrome); + uint8_t data = env->xregs[rs]; + uint32_t memidx = FIELD_EX32(mtedesc, MTEDESC, MIDX); + uint64_t toaddr = env->xregs[rd]; + uint64_t setsize = env->xregs[rn]; + uint64_t stagesetsize, step; + + check_mops_enabled(env, ra); + + if (setsize > INT64_MAX) { + setsize = INT64_MAX; + } + + if (!mte_checks_needed(toaddr, mtedesc)) { + mtedesc = 0; + } + + stagesetsize = MIN(setsize, page_limit(toaddr)); + while (stagesetsize) { + env->xregs[rd] = toaddr; + env->xregs[rn] = setsize; + step = stepfn(env, toaddr, stagesetsize, data, memidx, &mtedesc, ra); + toaddr += step; + setsize -= step; + stagesetsize -= step; + } + /* Insn completed, so update registers to the Option A format */ + env->xregs[rd] = toaddr + setsize; + env->xregs[rn] = -setsize; + + /* Set NZCV = 0000 to indicate we are an Option A implementation */ + env->NF = 0; + env->ZF = 1; /* our env->ZF encoding is inverted */ + env->CF = 0; + env->VF = 0; + return; +} + +void HELPER(setp)(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc) +{ + do_setp(env, syndrome, mtedesc, set_step, false, GETPC()); +} + +static void do_setm(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc, + StepFn *stepfn, bool is_setg, uintptr_t ra) +{ + /* Main: we choose to do all the full-page chunks */ + CPUState *cs = env_cpu(env); + int rd = mops_destreg(syndrome); + int rs = mops_srcreg(syndrome); + int rn = mops_sizereg(syndrome); + uint8_t data = env->xregs[rs]; + uint64_t toaddr = env->xregs[rd] + env->xregs[rn]; + uint64_t setsize = -env->xregs[rn]; + uint32_t memidx = FIELD_EX32(mtedesc, MTEDESC, MIDX); + uint64_t step, stagesetsize; + + check_mops_enabled(env, ra); + + /* + * We're allowed to NOP out "no data to copy" before the consistency + * checks; we choose to do so. + */ + if (env->xregs[rn] == 0) { + return; + } + + check_mops_wrong_option(env, syndrome, ra); + + /* + * Our implementation will work fine even if we have an unaligned + * destination address, and because we update Xn every time around + * the loop below and the return value from stepfn() may be less + * than requested, we might find toaddr is unaligned. So we don't + * have an IMPDEF check for alignment here. + */ + + if (!mte_checks_needed(toaddr, mtedesc)) { + mtedesc = 0; + } + + /* Do the actual memset: we leave the last partial page to SETE */ + stagesetsize = setsize & TARGET_PAGE_MASK; + while (stagesetsize > 0) { + step = stepfn(env, toaddr, setsize, data, memidx, &mtedesc, ra); + toaddr += step; + setsize -= step; + stagesetsize -= step; + env->xregs[rn] = -setsize; + if (stagesetsize > 0 && unlikely(cpu_loop_exit_requested(cs))) { + cpu_loop_exit_restore(cs, ra); + } + } +} + +void HELPER(setm)(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc) +{ + do_setm(env, syndrome, mtedesc, set_step, false, GETPC()); +} + +static void do_sete(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc, + StepFn *stepfn, bool is_setg, uintptr_t ra) +{ + /* Epilogue: do the last partial page */ + int rd = mops_destreg(syndrome); + int rs = mops_srcreg(syndrome); + int rn = mops_sizereg(syndrome); + uint8_t data = env->xregs[rs]; + uint64_t toaddr = env->xregs[rd] + env->xregs[rn]; + uint64_t setsize = -env->xregs[rn]; + uint32_t memidx = FIELD_EX32(mtedesc, MTEDESC, MIDX); + uint64_t step; + + check_mops_enabled(env, ra); + + /* + * We're allowed to NOP out "no data to copy" before the consistency + * checks; we choose to do so. + */ + if (setsize == 0) { + return; + } + + check_mops_wrong_option(env, syndrome, ra); + + /* + * Our implementation has no address alignment requirements, but + * we do want to enforce the "less than a page" size requirement, + * so we don't need to have the "check for interrupts" here. + */ + if (setsize >= TARGET_PAGE_SIZE) { + raise_exception_ra(env, EXCP_UDEF, syndrome, + mops_mismatch_exception_target_el(env), ra); + } + + if (!mte_checks_needed(toaddr, mtedesc)) { + mtedesc = 0; + } + + /* Do the actual memset */ + while (setsize > 0) { + step = stepfn(env, toaddr, setsize, data, memidx, &mtedesc, ra); + toaddr += step; + setsize -= step; + env->xregs[rn] = -setsize; + } +} + +void HELPER(sete)(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc) +{ + do_sete(env, syndrome, mtedesc, set_step, false, GETPC()); +} diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(STZG, aa64_mte_insn_reg, do_STG, a, true, false) TRANS_FEAT(ST2G, aa64_mte_insn_reg, do_STG, a, false, true) TRANS_FEAT(STZ2G, aa64_mte_insn_reg, do_STG, a, true, true) +typedef void SetFn(TCGv_env, TCGv_i32, TCGv_i32); + +static bool do_SET(DisasContext *s, arg_set *a, bool is_epilogue, SetFn fn) +{ + int memidx; + uint32_t syndrome, desc = 0; + + /* + * UNPREDICTABLE cases: we choose to UNDEF, which allows + * us to pull this check before the CheckMOPSEnabled() test + * (which we do in the helper function) + */ + if (a->rs == a->rn || a->rs == a->rd || a->rn == a->rd || + a->rd == 31 || a->rn == 31) { + return false; + } + + memidx = get_a64_user_mem_index(s, a->unpriv); + + /* + * We pass option_a == true, matching our implementation; + * we pass wrong_option == false: helper function may set that bit. + */ + syndrome = syn_mop(true, false, (a->nontemp << 1) | a->unpriv, + is_epilogue, false, true, a->rd, a->rs, a->rn); + + if (s->mte_active[a->unpriv]) { + /* We may need to do MTE tag checking, so assemble the descriptor */ + desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); + desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); + desc = FIELD_DP32(desc, MTEDESC, WRITE, true); + /* SIZEM1 and ALIGN we leave 0 (byte write) */ + } + /* The helper function always needs the memidx even with MTE disabled */ + desc = FIELD_DP32(desc, MTEDESC, MIDX, memidx); + + /* + * The helper needs the register numbers, but since they're in + * the syndrome anyway, we let it extract them from there rather + * than passing in an extra three integer arguments. + */ + fn(cpu_env, tcg_constant_i32(syndrome), tcg_constant_i32(desc)); + return true; +} + +TRANS_FEAT(SETP, aa64_mops, do_SET, a, false, gen_helper_setp) +TRANS_FEAT(SETM, aa64_mops, do_SET, a, false, gen_helper_setm) +TRANS_FEAT(SETE, aa64_mops, do_SET, a, true, gen_helper_sete) + typedef void ArithTwoOp(TCGv_i64, TCGv_i64, TCGv_i64); static bool gen_rri(DisasContext *s, arg_rri_sf *a, -- 2.34.1 Currently the only tag-setting instructions always do so in the context of the current EL, and so we only need one ATA bit in the TB flags. The FEAT_MOPS SETG instructions include ones which set tags for a non-privileged access, so we now also need the equivalent "are tags enabled?" information for EL0. Add the new TB flag, and convert the existing 'bool ata' field in DisasContext to a 'bool ata[2]' that can be indexed by the is_unpriv bit in an instruction, similarly to mte[2]. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230912140434.1333369-9-peter.maydell@linaro.org --- target/arm/cpu.h | 1 + target/arm/tcg/translate.h | 4 ++-- target/arm/tcg/hflags.c | 12 ++++++++++++ target/arm/tcg/translate-a64.c | 23 ++++++++++++----------- 4 files changed, 27 insertions(+), 13 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, SVL, 24, 4) FIELD(TBFLAG_A64, SME_TRAP_NONSTREAMING, 28, 1) FIELD(TBFLAG_A64, FGT_ERET, 29, 1) FIELD(TBFLAG_A64, NAA, 30, 1) +FIELD(TBFLAG_A64, ATA0, 31, 1) /* * Helpers for using the above. diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { bool unpriv; /* True if v8.3-PAuth is active. */ bool pauth_active; - /* True if v8.5-MTE access to tags is enabled. */ - bool ata; + /* True if v8.5-MTE access to tags is enabled; index with is_unpriv. */ + bool ata[2]; /* True if v8.5-MTE tag checks affect the PE; index with is_unpriv. */ bool mte_active[2]; /* True with v8.5-BTI and SCTLR_ELx.BT* set. */ diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/hflags.c +++ b/target/arm/tcg/hflags.c @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, && allocation_tag_access_enabled(env, 0, sctlr)) { DP_TBFLAG_A64(flags, MTE0_ACTIVE, 1); } + /* + * For unpriv tag-setting accesses we alse need ATA0. Again, in + * contexts where unpriv and normal insns are the same we + * duplicate the ATA bit to save effort for translate-a64.c. + */ + if (EX_TBFLAG_A64(flags, UNPRIV)) { + if (allocation_tag_access_enabled(env, 0, sctlr)) { + DP_TBFLAG_A64(flags, ATA0, 1); + } + } else { + DP_TBFLAG_A64(flags, ATA0, EX_TBFLAG_A64(flags, ATA)); + } /* Cache TCMA as well as TBI. */ DP_TBFLAG_A64(flags, TCMA, aa64_va_parameter_tcma(tcr, mmu_idx)); } diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, bool isread, clean_addr = clean_data_tbi(s, tcg_rt); gen_probe_access(s, clean_addr, MMU_DATA_STORE, MO_8); - if (s->ata) { + if (s->ata[0]) { /* Extract the tag from the register to match STZGM. */ tag = tcg_temp_new_i64(); tcg_gen_shri_i64(tag, tcg_rt, 56); @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, bool isread, clean_addr = clean_data_tbi(s, tcg_rt); gen_helper_dc_zva(cpu_env, clean_addr); - if (s->ata) { + if (s->ata[0]) { /* Extract the tag from the register to match STZGM. */ tag = tcg_temp_new_i64(); tcg_gen_shri_i64(tag, tcg_rt, 56); @@ -XXX,XX +XXX,XX @@ static bool trans_STGP(DisasContext *s, arg_ldstpair *a) tcg_gen_qemu_st_i128(tmp, clean_addr, get_mem_index(s), mop); /* Perform the tag store, if tag access enabled. */ - if (s->ata) { + if (s->ata[0]) { if (tb_cflags(s->base.tb) & CF_PARALLEL) { gen_helper_stg_parallel(cpu_env, dirty_addr, dirty_addr); } else { @@ -XXX,XX +XXX,XX @@ static bool trans_STZGM(DisasContext *s, arg_ldst_tag *a) tcg_gen_addi_i64(addr, addr, a->imm); tcg_rt = cpu_reg(s, a->rt); - if (s->ata) { + if (s->ata[0]) { gen_helper_stzgm_tags(cpu_env, addr, tcg_rt); } /* @@ -XXX,XX +XXX,XX @@ static bool trans_STGM(DisasContext *s, arg_ldst_tag *a) tcg_gen_addi_i64(addr, addr, a->imm); tcg_rt = cpu_reg(s, a->rt); - if (s->ata) { + if (s->ata[0]) { gen_helper_stgm(cpu_env, addr, tcg_rt); } else { MMUAccessType acc = MMU_DATA_STORE; @@ -XXX,XX +XXX,XX @@ static bool trans_LDGM(DisasContext *s, arg_ldst_tag *a) tcg_gen_addi_i64(addr, addr, a->imm); tcg_rt = cpu_reg(s, a->rt); - if (s->ata) { + if (s->ata[0]) { gen_helper_ldgm(tcg_rt, cpu_env, addr); } else { MMUAccessType acc = MMU_DATA_LOAD; @@ -XXX,XX +XXX,XX @@ static bool trans_LDG(DisasContext *s, arg_ldst_tag *a) tcg_gen_andi_i64(addr, addr, -TAG_GRANULE); tcg_rt = cpu_reg(s, a->rt); - if (s->ata) { + if (s->ata[0]) { gen_helper_ldg(tcg_rt, cpu_env, addr, tcg_rt); } else { /* @@ -XXX,XX +XXX,XX @@ static bool do_STG(DisasContext *s, arg_ldst_tag *a, bool is_zero, bool is_pair) tcg_gen_addi_i64(addr, addr, a->imm); } tcg_rt = cpu_reg_sp(s, a->rt); - if (!s->ata) { + if (!s->ata[0]) { /* * For STG and ST2G, we need to check alignment and probe memory. * TODO: For STZG and STZ2G, we could rely on the stores below, @@ -XXX,XX +XXX,XX @@ static bool gen_add_sub_imm_with_tags(DisasContext *s, arg_rri_tag *a, tcg_rn = cpu_reg_sp(s, a->rn); tcg_rd = cpu_reg_sp(s, a->rd); - if (s->ata) { + if (s->ata[0]) { gen_helper_addsubg(tcg_rd, cpu_env, tcg_rn, tcg_constant_i32(imm), tcg_constant_i32(a->uimm4)); @@ -XXX,XX +XXX,XX @@ static void disas_data_proc_2src(DisasContext *s, uint32_t insn) if (sf == 0 || !dc_isar_feature(aa64_mte_insn_reg, s)) { goto do_unallocated; } - if (s->ata) { + if (s->ata[0]) { gen_helper_irg(cpu_reg_sp(s, rd), cpu_env, cpu_reg_sp(s, rn), cpu_reg(s, rm)); } else { @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->bt = EX_TBFLAG_A64(tb_flags, BT); dc->btype = EX_TBFLAG_A64(tb_flags, BTYPE); dc->unpriv = EX_TBFLAG_A64(tb_flags, UNPRIV); - dc->ata = EX_TBFLAG_A64(tb_flags, ATA); + dc->ata[0] = EX_TBFLAG_A64(tb_flags, ATA); + dc->ata[1] = EX_TBFLAG_A64(tb_flags, ATA0); dc->mte_active[0] = EX_TBFLAG_A64(tb_flags, MTE_ACTIVE); dc->mte_active[1] = EX_TBFLAG_A64(tb_flags, MTE0_ACTIVE); dc->pstate_sm = EX_TBFLAG_A64(tb_flags, PSTATE_SM); -- 2.34.1 The FEAT_MOPS SETG* instructions are very similar to the SET* instructions, but as well as setting memory contents they also set the MTE tags. They are architecturally required to operate on tag-granule aligned regions only. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230912140434.1333369-10-peter.maydell@linaro.org --- target/arm/internals.h | 10 ++++ target/arm/tcg/helper-a64.h | 3 ++ target/arm/tcg/a64.decode | 5 ++ target/arm/tcg/helper-a64.c | 86 ++++++++++++++++++++++++++++++++-- target/arm/tcg/mte_helper.c | 40 ++++++++++++++++ target/arm/tcg/translate-a64.c | 20 +++++--- 6 files changed, 155 insertions(+), 9 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ uint64_t mte_mops_probe(CPUARMState *env, uint64_t ptr, uint64_t size, void mte_check_fail(CPUARMState *env, uint32_t desc, uint64_t dirty_ptr, uintptr_t ra); +/** + * mte_mops_set_tags: Set MTE tags for a portion of a FEAT_MOPS operation + * @env: CPU env + * @dirty_ptr: Start address of memory region (dirty pointer) + * @size: length of region (guaranteed not to cross page boundary) + * @desc: MTEDESC descriptor word + */ +void mte_mops_set_tags(CPUARMState *env, uint64_t dirty_ptr, uint64_t size, + uint32_t desc); + static inline int allocation_tag_from_addr(uint64_t ptr) { return extract64(ptr, 56, 4); diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(unaligned_access, TCG_CALL_NO_WG, DEF_HELPER_3(setp, void, env, i32, i32) DEF_HELPER_3(setm, void, env, i32, i32) DEF_HELPER_3(sete, void, env, i32, i32) +DEF_HELPER_3(setgp, void, env, i32, i32) +DEF_HELPER_3(setgm, void, env, i32, i32) +DEF_HELPER_3(setge, void, env, i32, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ STZ2G 11011001 11 1 ......... 11 ..... ..... @ldst_tag p=0 w=1 SETP 00 011001110 ..... 00 . . 01 ..... ..... @set SETM 00 011001110 ..... 01 . . 01 ..... ..... @set SETE 00 011001110 ..... 10 . . 01 ..... ..... @set + +# Like SET, but also setting MTE tags +SETGP 00 011101110 ..... 00 . . 01 ..... ..... @set +SETGM 00 011101110 ..... 01 . . 01 ..... ..... @set +SETGE 00 011101110 ..... 10 . . 01 ..... ..... @set diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -XXX,XX +XXX,XX @@ static uint64_t set_step(CPUARMState *env, uint64_t toaddr, return setsize; } +/* + * Similar, but setting tags. The architecture requires us to do this + * in 16-byte chunks. SETP accesses are not tag checked; they set + * the tags. + */ +static uint64_t set_step_tags(CPUARMState *env, uint64_t toaddr, + uint64_t setsize, uint32_t data, int memidx, + uint32_t *mtedesc, uintptr_t ra) +{ + void *mem; + uint64_t cleanaddr; + + setsize = MIN(setsize, page_limit(toaddr)); + + cleanaddr = useronly_clean_ptr(toaddr); + /* + * Trapless lookup: returns NULL for invalid page, I/O, + * watchpoints, clean pages, etc. + */ + mem = tlb_vaddr_to_host(env, cleanaddr, MMU_DATA_STORE, memidx); + +#ifndef CONFIG_USER_ONLY + if (unlikely(!mem)) { + /* + * Slow-path: just do one write. This will handle the + * watchpoint, invalid page, etc handling correctly. + * The architecture requires that we do 16 bytes at a time, + * and we know both ptr and size are 16 byte aligned. + * For clean code pages, the next iteration will see + * the page dirty and will use the fast path. + */ + uint64_t repldata = data * 0x0101010101010101ULL; + MemOpIdx oi16 = make_memop_idx(MO_TE | MO_128, memidx); + cpu_st16_mmu(env, toaddr, int128_make128(repldata, repldata), oi16, ra); + mte_mops_set_tags(env, toaddr, 16, *mtedesc); + return 16; + } +#endif + /* Easy case: just memset the host memory */ + memset(mem, data, setsize); + mte_mops_set_tags(env, toaddr, setsize, *mtedesc); + return setsize; +} + typedef uint64_t StepFn(CPUARMState *env, uint64_t toaddr, uint64_t setsize, uint32_t data, int memidx, uint32_t *mtedesc, uintptr_t ra); @@ -XXX,XX +XXX,XX @@ static bool mte_checks_needed(uint64_t ptr, uint32_t desc) return !tcma_check(desc, bit55, allocation_tag_from_addr(ptr)); } +/* Take an exception if the SETG addr/size are not granule aligned */ +static void check_setg_alignment(CPUARMState *env, uint64_t ptr, uint64_t size, + uint32_t memidx, uintptr_t ra) +{ + if ((size != 0 && !QEMU_IS_ALIGNED(ptr, TAG_GRANULE)) || + !QEMU_IS_ALIGNED(size, TAG_GRANULE)) { + arm_cpu_do_unaligned_access(env_cpu(env), ptr, MMU_DATA_STORE, + memidx, ra); + + } +} + /* * For the Memory Set operation, our implementation chooses * always to use "option A", where we update Xd to the final @@ -XXX,XX +XXX,XX @@ static void do_setp(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc, if (setsize > INT64_MAX) { setsize = INT64_MAX; + if (is_setg) { + setsize &= ~0xf; + } } - if (!mte_checks_needed(toaddr, mtedesc)) { + if (unlikely(is_setg)) { + check_setg_alignment(env, toaddr, setsize, memidx, ra); + } else if (!mte_checks_needed(toaddr, mtedesc)) { mtedesc = 0; } @@ -XXX,XX +XXX,XX @@ void HELPER(setp)(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc) do_setp(env, syndrome, mtedesc, set_step, false, GETPC()); } +void HELPER(setgp)(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc) +{ + do_setp(env, syndrome, mtedesc, set_step_tags, true, GETPC()); +} + static void do_setm(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc, StepFn *stepfn, bool is_setg, uintptr_t ra) { @@ -XXX,XX +XXX,XX @@ static void do_setm(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc, * have an IMPDEF check for alignment here. */ - if (!mte_checks_needed(toaddr, mtedesc)) { + if (unlikely(is_setg)) { + check_setg_alignment(env, toaddr, setsize, memidx, ra); + } else if (!mte_checks_needed(toaddr, mtedesc)) { mtedesc = 0; } @@ -XXX,XX +XXX,XX @@ void HELPER(setm)(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc) do_setm(env, syndrome, mtedesc, set_step, false, GETPC()); } +void HELPER(setgm)(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc) +{ + do_setm(env, syndrome, mtedesc, set_step_tags, true, GETPC()); +} + static void do_sete(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc, StepFn *stepfn, bool is_setg, uintptr_t ra) { @@ -XXX,XX +XXX,XX @@ static void do_sete(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc, mops_mismatch_exception_target_el(env), ra); } - if (!mte_checks_needed(toaddr, mtedesc)) { + if (unlikely(is_setg)) { + check_setg_alignment(env, toaddr, setsize, memidx, ra); + } else if (!mte_checks_needed(toaddr, mtedesc)) { mtedesc = 0; } @@ -XXX,XX +XXX,XX @@ void HELPER(sete)(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc) { do_sete(env, syndrome, mtedesc, set_step, false, GETPC()); } + +void HELPER(setge)(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc) +{ + do_sete(env, syndrome, mtedesc, set_step_tags, true, GETPC()); +} diff --git a/target/arm/tcg/mte_helper.c b/target/arm/tcg/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mte_helper.c +++ b/target/arm/tcg/mte_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t mte_mops_probe(CPUARMState *env, uint64_t ptr, uint64_t size, return n * TAG_GRANULE - (ptr - tag_first); } } + +void mte_mops_set_tags(CPUARMState *env, uint64_t ptr, uint64_t size, + uint32_t desc) +{ + int mmu_idx, tag_count; + uint64_t ptr_tag; + void *mem; + + if (!desc) { + /* Tags not actually enabled */ + return; + } + + mmu_idx = FIELD_EX32(desc, MTEDESC, MIDX); + /* True probe: this will never fault */ + mem = allocation_tag_mem_probe(env, mmu_idx, ptr, MMU_DATA_STORE, size, + MMU_DATA_STORE, true, 0); + if (!mem) { + return; + } + + /* + * We know that ptr and size are both TAG_GRANULE aligned; store + * the tag from the pointer value into the tag memory. + */ + ptr_tag = allocation_tag_from_addr(ptr); + tag_count = size / TAG_GRANULE; + if (ptr & TAG_GRANULE) { + /* Not 2*TAG_GRANULE-aligned: store tag to first nibble */ + store_tag1_parallel(TAG_GRANULE, mem, ptr_tag); + mem++; + tag_count--; + } + memset(mem, ptr_tag | (ptr_tag << 4), tag_count / 2); + if (tag_count & 1) { + /* Final trailing unaligned nibble */ + mem += tag_count / 2; + store_tag1_parallel(0, mem, ptr_tag); + } +} diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(STZ2G, aa64_mte_insn_reg, do_STG, a, true, true) typedef void SetFn(TCGv_env, TCGv_i32, TCGv_i32); -static bool do_SET(DisasContext *s, arg_set *a, bool is_epilogue, SetFn fn) +static bool do_SET(DisasContext *s, arg_set *a, bool is_epilogue, + bool is_setg, SetFn fn) { int memidx; uint32_t syndrome, desc = 0; + if (is_setg && !dc_isar_feature(aa64_mte, s)) { + return false; + } + /* * UNPREDICTABLE cases: we choose to UNDEF, which allows * us to pull this check before the CheckMOPSEnabled() test @@ -XXX,XX +XXX,XX @@ static bool do_SET(DisasContext *s, arg_set *a, bool is_epilogue, SetFn fn) * We pass option_a == true, matching our implementation; * we pass wrong_option == false: helper function may set that bit. */ - syndrome = syn_mop(true, false, (a->nontemp << 1) | a->unpriv, + syndrome = syn_mop(true, is_setg, (a->nontemp << 1) | a->unpriv, is_epilogue, false, true, a->rd, a->rs, a->rn); - if (s->mte_active[a->unpriv]) { + if (is_setg ? s->ata[a->unpriv] : s->mte_active[a->unpriv]) { /* We may need to do MTE tag checking, so assemble the descriptor */ desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); @@ -XXX,XX +XXX,XX @@ static bool do_SET(DisasContext *s, arg_set *a, bool is_epilogue, SetFn fn) return true; } -TRANS_FEAT(SETP, aa64_mops, do_SET, a, false, gen_helper_setp) -TRANS_FEAT(SETM, aa64_mops, do_SET, a, false, gen_helper_setm) -TRANS_FEAT(SETE, aa64_mops, do_SET, a, true, gen_helper_sete) +TRANS_FEAT(SETP, aa64_mops, do_SET, a, false, false, gen_helper_setp) +TRANS_FEAT(SETM, aa64_mops, do_SET, a, false, false, gen_helper_setm) +TRANS_FEAT(SETE, aa64_mops, do_SET, a, true, false, gen_helper_sete) +TRANS_FEAT(SETGP, aa64_mops, do_SET, a, false, true, gen_helper_setgp) +TRANS_FEAT(SETGM, aa64_mops, do_SET, a, false, true, gen_helper_setgm) +TRANS_FEAT(SETGE, aa64_mops, do_SET, a, true, true, gen_helper_setge) typedef void ArithTwoOp(TCGv_i64, TCGv_i64, TCGv_i64); -- 2.34.1 The FEAT_MOPS memory copy operations need an extra helper routine for checking for MTE tag checking failures beyond the ones we already added for memory set operations: * mte_mops_probe_rev() does the same job as mte_mops_probe(), but it checks tags starting at the provided address and working backwards, rather than forwards Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230912140434.1333369-11-peter.maydell@linaro.org --- target/arm/internals.h | 17 +++++++ target/arm/tcg/mte_helper.c | 99 +++++++++++++++++++++++++++++++++++++ 2 files changed, 116 insertions(+) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ uint64_t mte_check(CPUARMState *env, uint32_t desc, uint64_t ptr, uintptr_t ra); uint64_t mte_mops_probe(CPUARMState *env, uint64_t ptr, uint64_t size, uint32_t desc); +/** + * mte_mops_probe_rev: Check where the next MTE failure is for a FEAT_MOPS + * operation going in the reverse direction + * @env: CPU env + * @ptr: *end* address of memory region (dirty pointer) + * @size: length of region (guaranteed not to cross a page boundary) + * @desc: MTEDESC descriptor word (0 means no MTE checks) + * Returns: the size of the region that can be copied without hitting + * an MTE tag failure + * + * Note that we assume that the caller has already checked the TBI + * and TCMA bits with mte_checks_needed() and an MTE check is definitely + * required. + */ +uint64_t mte_mops_probe_rev(CPUARMState *env, uint64_t ptr, uint64_t size, + uint32_t desc); + /** * mte_check_fail: Record an MTE tag check failure * @env: CPU env diff --git a/target/arm/tcg/mte_helper.c b/target/arm/tcg/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mte_helper.c +++ b/target/arm/tcg/mte_helper.c @@ -XXX,XX +XXX,XX @@ static int checkN(uint8_t *mem, int odd, int cmp, int count) return n; } +/** + * checkNrev: + * @tag: tag memory to test + * @odd: true to begin testing at tags at odd nibble + * @cmp: the tag to compare against + * @count: number of tags to test + * + * Return the number of successful tests. + * Thus a return value < @count indicates a failure. + * + * This is like checkN, but it runs backwards, checking the + * tags starting with @tag and then the tags preceding it. + * This is needed by the backwards-memory-copying operations. + */ +static int checkNrev(uint8_t *mem, int odd, int cmp, int count) +{ + int n = 0, diff; + + /* Replicate the test tag and compare. */ + cmp *= 0x11; + diff = *mem-- ^ cmp; + + if (!odd) { + goto start_even; + } + + while (1) { + /* Test odd tag. */ + if (unlikely((diff) & 0xf0)) { + break; + } + if (++n == count) { + break; + } + + start_even: + /* Test even tag. */ + if (unlikely((diff) & 0x0f)) { + break; + } + if (++n == count) { + break; + } + + diff = *mem-- ^ cmp; + } + return n; +} + /** * mte_probe_int() - helper for mte_probe and mte_check * @env: CPU environment @@ -XXX,XX +XXX,XX @@ uint64_t mte_mops_probe(CPUARMState *env, uint64_t ptr, uint64_t size, } } +uint64_t mte_mops_probe_rev(CPUARMState *env, uint64_t ptr, uint64_t size, + uint32_t desc) +{ + int mmu_idx, tag_count; + uint64_t ptr_tag, tag_first, tag_last; + void *mem; + bool w = FIELD_EX32(desc, MTEDESC, WRITE); + uint32_t n; + + mmu_idx = FIELD_EX32(desc, MTEDESC, MIDX); + /* True probe; this will never fault */ + mem = allocation_tag_mem_probe(env, mmu_idx, ptr, + w ? MMU_DATA_STORE : MMU_DATA_LOAD, + size, MMU_DATA_LOAD, true, 0); + if (!mem) { + return size; + } + + /* + * TODO: checkNrev() is not designed for checks of the size we expect + * for FEAT_MOPS operations, so we should implement this differently. + * Maybe we should do something like + * if (region start and size are aligned nicely) { + * do direct loads of 64 tag bits at a time; + * } else { + * call checkN() + * } + */ + /* Round the bounds to the tag granule, and compute the number of tags. */ + ptr_tag = allocation_tag_from_addr(ptr); + tag_first = QEMU_ALIGN_DOWN(ptr - (size - 1), TAG_GRANULE); + tag_last = QEMU_ALIGN_DOWN(ptr, TAG_GRANULE); + tag_count = ((tag_last - tag_first) / TAG_GRANULE) + 1; + n = checkNrev(mem, ptr & TAG_GRANULE, ptr_tag, tag_count); + if (likely(n == tag_count)) { + return size; + } + + /* + * Failure; for the first granule, it's at @ptr. Otherwise + * it's at the last byte of the nth granule. Calculate how + * many bytes we can access without hitting that failure. + */ + if (n == 0) { + return 0; + } else { + return (n - 1) * TAG_GRANULE + ((ptr + 1) - tag_last); + } +} + void mte_mops_set_tags(CPUARMState *env, uint64_t ptr, uint64_t size, uint32_t desc) { -- 2.34.1 The FEAT_MOPS CPY* instructions implement memory copies. These come in both "always forwards" (memcpy-style) and "overlap OK" (memmove-style) flavours. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230912140434.1333369-12-peter.maydell@linaro.org --- target/arm/tcg/helper-a64.h | 7 + target/arm/tcg/a64.decode | 14 + target/arm/tcg/helper-a64.c | 454 +++++++++++++++++++++++++++++++++ target/arm/tcg/translate-a64.c | 60 +++++ 4 files changed, 535 insertions(+) diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(sete, void, env, i32, i32) DEF_HELPER_3(setgp, void, env, i32, i32) DEF_HELPER_3(setgm, void, env, i32, i32) DEF_HELPER_3(setge, void, env, i32, i32) + +DEF_HELPER_4(cpyp, void, env, i32, i32, i32) +DEF_HELPER_4(cpym, void, env, i32, i32, i32) +DEF_HELPER_4(cpye, void, env, i32, i32, i32) +DEF_HELPER_4(cpyfp, void, env, i32, i32, i32) +DEF_HELPER_4(cpyfm, void, env, i32, i32, i32) +DEF_HELPER_4(cpyfe, void, env, i32, i32, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SETE 00 011001110 ..... 10 . . 01 ..... ..... @set SETGP 00 011101110 ..... 00 . . 01 ..... ..... @set SETGM 00 011101110 ..... 01 . . 01 ..... ..... @set SETGE 00 011101110 ..... 10 . . 01 ..... ..... @set + +# Memmove/Memcopy: the CPY insns allow overlapping src/dest and +# copy in the correct direction; the CPYF insns always copy forwards. +# +# options has the nontemporal and unpriv bits for src and dest +&cpy rs rn rd options +@cpy .. ... . ..... rs:5 options:4 .. rn:5 rd:5 &cpy + +CPYFP 00 011 0 01000 ..... .... 01 ..... ..... @cpy +CPYFM 00 011 0 01010 ..... .... 01 ..... ..... @cpy +CPYFE 00 011 0 01100 ..... .... 01 ..... ..... @cpy +CPYP 00 011 1 01000 ..... .... 01 ..... ..... @cpy +CPYM 00 011 1 01010 ..... .... 01 ..... ..... @cpy +CPYE 00 011 1 01100 ..... .... 01 ..... ..... @cpy diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -XXX,XX +XXX,XX @@ static uint64_t page_limit(uint64_t addr) return TARGET_PAGE_ALIGN(addr + 1) - addr; } +/* + * Return the number of bytes we can copy starting from addr and working + * backwards without crossing a page boundary. + */ +static uint64_t page_limit_rev(uint64_t addr) +{ + return (addr & ~TARGET_PAGE_MASK) + 1; +} + /* * Perform part of a memory set on an area of guest memory starting at * toaddr (a dirty address) and extending for setsize bytes. @@ -XXX,XX +XXX,XX @@ void HELPER(setge)(CPUARMState *env, uint32_t syndrome, uint32_t mtedesc) { do_sete(env, syndrome, mtedesc, set_step_tags, true, GETPC()); } + +/* + * Perform part of a memory copy from the guest memory at fromaddr + * and extending for copysize bytes, to the guest memory at + * toaddr. Both addreses are dirty. + * + * Returns the number of bytes actually set, which might be less than + * copysize; the caller should loop until the whole copy has been done. + * The caller should ensure that the guest registers are correct + * for the possibility that the first byte of the copy encounters + * an exception or watchpoint. We guarantee not to take any faults + * for bytes other than the first. + */ +static uint64_t copy_step(CPUARMState *env, uint64_t toaddr, uint64_t fromaddr, + uint64_t copysize, int wmemidx, int rmemidx, + uint32_t *wdesc, uint32_t *rdesc, uintptr_t ra) +{ + void *rmem; + void *wmem; + + /* Don't cross a page boundary on either source or destination */ + copysize = MIN(copysize, page_limit(toaddr)); + copysize = MIN(copysize, page_limit(fromaddr)); + /* + * Handle MTE tag checks: either handle the tag mismatch for byte 0, + * or else copy up to but not including the byte with the mismatch. + */ + if (*rdesc) { + uint64_t mtesize = mte_mops_probe(env, fromaddr, copysize, *rdesc); + if (mtesize == 0) { + mte_check_fail(env, *rdesc, fromaddr, ra); + *rdesc = 0; + } else { + copysize = MIN(copysize, mtesize); + } + } + if (*wdesc) { + uint64_t mtesize = mte_mops_probe(env, toaddr, copysize, *wdesc); + if (mtesize == 0) { + mte_check_fail(env, *wdesc, toaddr, ra); + *wdesc = 0; + } else { + copysize = MIN(copysize, mtesize); + } + } + + toaddr = useronly_clean_ptr(toaddr); + fromaddr = useronly_clean_ptr(fromaddr); + /* Trapless lookup of whether we can get a host memory pointer */ + wmem = tlb_vaddr_to_host(env, toaddr, MMU_DATA_STORE, wmemidx); + rmem = tlb_vaddr_to_host(env, fromaddr, MMU_DATA_LOAD, rmemidx); + +#ifndef CONFIG_USER_ONLY + /* + * If we don't have host memory for both source and dest then just + * do a single byte copy. This will handle watchpoints, invalid pages, + * etc correctly. For clean code pages, the next iteration will see + * the page dirty and will use the fast path. + */ + if (unlikely(!rmem || !wmem)) { + uint8_t byte; + if (rmem) { + byte = *(uint8_t *)rmem; + } else { + byte = cpu_ldub_mmuidx_ra(env, fromaddr, rmemidx, ra); + } + if (wmem) { + *(uint8_t *)wmem = byte; + } else { + cpu_stb_mmuidx_ra(env, toaddr, byte, wmemidx, ra); + } + return 1; + } +#endif + /* Easy case: just memmove the host memory */ + memmove(wmem, rmem, copysize); + return copysize; +} + +/* + * Do part of a backwards memory copy. Here toaddr and fromaddr point + * to the *last* byte to be copied. + */ +static uint64_t copy_step_rev(CPUARMState *env, uint64_t toaddr, + uint64_t fromaddr, + uint64_t copysize, int wmemidx, int rmemidx, + uint32_t *wdesc, uint32_t *rdesc, uintptr_t ra) +{ + void *rmem; + void *wmem; + + /* Don't cross a page boundary on either source or destination */ + copysize = MIN(copysize, page_limit_rev(toaddr)); + copysize = MIN(copysize, page_limit_rev(fromaddr)); + + /* + * Handle MTE tag checks: either handle the tag mismatch for byte 0, + * or else copy up to but not including the byte with the mismatch. + */ + if (*rdesc) { + uint64_t mtesize = mte_mops_probe_rev(env, fromaddr, copysize, *rdesc); + if (mtesize == 0) { + mte_check_fail(env, *rdesc, fromaddr, ra); + *rdesc = 0; + } else { + copysize = MIN(copysize, mtesize); + } + } + if (*wdesc) { + uint64_t mtesize = mte_mops_probe_rev(env, toaddr, copysize, *wdesc); + if (mtesize == 0) { + mte_check_fail(env, *wdesc, toaddr, ra); + *wdesc = 0; + } else { + copysize = MIN(copysize, mtesize); + } + } + + toaddr = useronly_clean_ptr(toaddr); + fromaddr = useronly_clean_ptr(fromaddr); + /* Trapless lookup of whether we can get a host memory pointer */ + wmem = tlb_vaddr_to_host(env, toaddr, MMU_DATA_STORE, wmemidx); + rmem = tlb_vaddr_to_host(env, fromaddr, MMU_DATA_LOAD, rmemidx); + +#ifndef CONFIG_USER_ONLY + /* + * If we don't have host memory for both source and dest then just + * do a single byte copy. This will handle watchpoints, invalid pages, + * etc correctly. For clean code pages, the next iteration will see + * the page dirty and will use the fast path. + */ + if (unlikely(!rmem || !wmem)) { + uint8_t byte; + if (rmem) { + byte = *(uint8_t *)rmem; + } else { + byte = cpu_ldub_mmuidx_ra(env, fromaddr, rmemidx, ra); + } + if (wmem) { + *(uint8_t *)wmem = byte; + } else { + cpu_stb_mmuidx_ra(env, toaddr, byte, wmemidx, ra); + } + return 1; + } +#endif + /* + * Easy case: just memmove the host memory. Note that wmem and + * rmem here point to the *last* byte to copy. + */ + memmove(wmem - (copysize - 1), rmem - (copysize - 1), copysize); + return copysize; +} + +/* + * for the Memory Copy operation, our implementation chooses always + * to use "option A", where we update Xd and Xs to the final addresses + * in the CPYP insn, and then in CPYM and CPYE only need to update Xn. + * + * @env: CPU + * @syndrome: syndrome value for mismatch exceptions + * (also contains the register numbers we need to use) + * @wdesc: MTE descriptor for the writes (destination) + * @rdesc: MTE descriptor for the reads (source) + * @move: true if this is CPY (memmove), false for CPYF (memcpy forwards) + */ +static void do_cpyp(CPUARMState *env, uint32_t syndrome, uint32_t wdesc, + uint32_t rdesc, uint32_t move, uintptr_t ra) +{ + int rd = mops_destreg(syndrome); + int rs = mops_srcreg(syndrome); + int rn = mops_sizereg(syndrome); + uint32_t rmemidx = FIELD_EX32(rdesc, MTEDESC, MIDX); + uint32_t wmemidx = FIELD_EX32(wdesc, MTEDESC, MIDX); + bool forwards = true; + uint64_t toaddr = env->xregs[rd]; + uint64_t fromaddr = env->xregs[rs]; + uint64_t copysize = env->xregs[rn]; + uint64_t stagecopysize, step; + + check_mops_enabled(env, ra); + + + if (move) { + /* + * Copy backwards if necessary. The direction for a non-overlapping + * copy is IMPDEF; we choose forwards. + */ + if (copysize > 0x007FFFFFFFFFFFFFULL) { + copysize = 0x007FFFFFFFFFFFFFULL; + } + uint64_t fs = extract64(fromaddr, 0, 56); + uint64_t ts = extract64(toaddr, 0, 56); + uint64_t fe = extract64(fromaddr + copysize, 0, 56); + + if (fs < ts && fe > ts) { + forwards = false; + } + } else { + if (copysize > INT64_MAX) { + copysize = INT64_MAX; + } + } + + if (!mte_checks_needed(fromaddr, rdesc)) { + rdesc = 0; + } + if (!mte_checks_needed(toaddr, wdesc)) { + wdesc = 0; + } + + if (forwards) { + stagecopysize = MIN(copysize, page_limit(toaddr)); + stagecopysize = MIN(stagecopysize, page_limit(fromaddr)); + while (stagecopysize) { + env->xregs[rd] = toaddr; + env->xregs[rs] = fromaddr; + env->xregs[rn] = copysize; + step = copy_step(env, toaddr, fromaddr, stagecopysize, + wmemidx, rmemidx, &wdesc, &rdesc, ra); + toaddr += step; + fromaddr += step; + copysize -= step; + stagecopysize -= step; + } + /* Insn completed, so update registers to the Option A format */ + env->xregs[rd] = toaddr + copysize; + env->xregs[rs] = fromaddr + copysize; + env->xregs[rn] = -copysize; + } else { + /* + * In a reverse copy the to and from addrs in Xs and Xd are the start + * of the range, but it's more convenient for us to work with pointers + * to the last byte being copied. + */ + toaddr += copysize - 1; + fromaddr += copysize - 1; + stagecopysize = MIN(copysize, page_limit_rev(toaddr)); + stagecopysize = MIN(stagecopysize, page_limit_rev(fromaddr)); + while (stagecopysize) { + env->xregs[rn] = copysize; + step = copy_step_rev(env, toaddr, fromaddr, stagecopysize, + wmemidx, rmemidx, &wdesc, &rdesc, ra); + copysize -= step; + stagecopysize -= step; + toaddr -= step; + fromaddr -= step; + } + /* + * Insn completed, so update registers to the Option A format. + * For a reverse copy this is no different to the CPYP input format. + */ + env->xregs[rn] = copysize; + } + + /* Set NZCV = 0000 to indicate we are an Option A implementation */ + env->NF = 0; + env->ZF = 1; /* our env->ZF encoding is inverted */ + env->CF = 0; + env->VF = 0; + return; +} + +void HELPER(cpyp)(CPUARMState *env, uint32_t syndrome, uint32_t wdesc, + uint32_t rdesc) +{ + do_cpyp(env, syndrome, wdesc, rdesc, true, GETPC()); +} + +void HELPER(cpyfp)(CPUARMState *env, uint32_t syndrome, uint32_t wdesc, + uint32_t rdesc) +{ + do_cpyp(env, syndrome, wdesc, rdesc, false, GETPC()); +} + +static void do_cpym(CPUARMState *env, uint32_t syndrome, uint32_t wdesc, + uint32_t rdesc, uint32_t move, uintptr_t ra) +{ + /* Main: we choose to copy until less than a page remaining */ + CPUState *cs = env_cpu(env); + int rd = mops_destreg(syndrome); + int rs = mops_srcreg(syndrome); + int rn = mops_sizereg(syndrome); + uint32_t rmemidx = FIELD_EX32(rdesc, MTEDESC, MIDX); + uint32_t wmemidx = FIELD_EX32(wdesc, MTEDESC, MIDX); + bool forwards = true; + uint64_t toaddr, fromaddr, copysize, step; + + check_mops_enabled(env, ra); + + /* We choose to NOP out "no data to copy" before consistency checks */ + if (env->xregs[rn] == 0) { + return; + } + + check_mops_wrong_option(env, syndrome, ra); + + if (move) { + forwards = (int64_t)env->xregs[rn] < 0; + } + + if (forwards) { + toaddr = env->xregs[rd] + env->xregs[rn]; + fromaddr = env->xregs[rs] + env->xregs[rn]; + copysize = -env->xregs[rn]; + } else { + copysize = env->xregs[rn]; + /* This toaddr and fromaddr point to the *last* byte to copy */ + toaddr = env->xregs[rd] + copysize - 1; + fromaddr = env->xregs[rs] + copysize - 1; + } + + if (!mte_checks_needed(fromaddr, rdesc)) { + rdesc = 0; + } + if (!mte_checks_needed(toaddr, wdesc)) { + wdesc = 0; + } + + /* Our implementation has no particular parameter requirements for CPYM */ + + /* Do the actual memmove */ + if (forwards) { + while (copysize >= TARGET_PAGE_SIZE) { + step = copy_step(env, toaddr, fromaddr, copysize, + wmemidx, rmemidx, &wdesc, &rdesc, ra); + toaddr += step; + fromaddr += step; + copysize -= step; + env->xregs[rn] = -copysize; + if (copysize >= TARGET_PAGE_SIZE && + unlikely(cpu_loop_exit_requested(cs))) { + cpu_loop_exit_restore(cs, ra); + } + } + } else { + while (copysize >= TARGET_PAGE_SIZE) { + step = copy_step_rev(env, toaddr, fromaddr, copysize, + wmemidx, rmemidx, &wdesc, &rdesc, ra); + toaddr -= step; + fromaddr -= step; + copysize -= step; + env->xregs[rn] = copysize; + if (copysize >= TARGET_PAGE_SIZE && + unlikely(cpu_loop_exit_requested(cs))) { + cpu_loop_exit_restore(cs, ra); + } + } + } +} + +void HELPER(cpym)(CPUARMState *env, uint32_t syndrome, uint32_t wdesc, + uint32_t rdesc) +{ + do_cpym(env, syndrome, wdesc, rdesc, true, GETPC()); +} + +void HELPER(cpyfm)(CPUARMState *env, uint32_t syndrome, uint32_t wdesc, + uint32_t rdesc) +{ + do_cpym(env, syndrome, wdesc, rdesc, false, GETPC()); +} + +static void do_cpye(CPUARMState *env, uint32_t syndrome, uint32_t wdesc, + uint32_t rdesc, uint32_t move, uintptr_t ra) +{ + /* Epilogue: do the last partial page */ + int rd = mops_destreg(syndrome); + int rs = mops_srcreg(syndrome); + int rn = mops_sizereg(syndrome); + uint32_t rmemidx = FIELD_EX32(rdesc, MTEDESC, MIDX); + uint32_t wmemidx = FIELD_EX32(wdesc, MTEDESC, MIDX); + bool forwards = true; + uint64_t toaddr, fromaddr, copysize, step; + + check_mops_enabled(env, ra); + + /* We choose to NOP out "no data to copy" before consistency checks */ + if (env->xregs[rn] == 0) { + return; + } + + check_mops_wrong_option(env, syndrome, ra); + + if (move) { + forwards = (int64_t)env->xregs[rn] < 0; + } + + if (forwards) { + toaddr = env->xregs[rd] + env->xregs[rn]; + fromaddr = env->xregs[rs] + env->xregs[rn]; + copysize = -env->xregs[rn]; + } else { + copysize = env->xregs[rn]; + /* This toaddr and fromaddr point to the *last* byte to copy */ + toaddr = env->xregs[rd] + copysize - 1; + fromaddr = env->xregs[rs] + copysize - 1; + } + + if (!mte_checks_needed(fromaddr, rdesc)) { + rdesc = 0; + } + if (!mte_checks_needed(toaddr, wdesc)) { + wdesc = 0; + } + + /* Check the size; we don't want to have do a check-for-interrupts */ + if (copysize >= TARGET_PAGE_SIZE) { + raise_exception_ra(env, EXCP_UDEF, syndrome, + mops_mismatch_exception_target_el(env), ra); + } + + /* Do the actual memmove */ + if (forwards) { + while (copysize > 0) { + step = copy_step(env, toaddr, fromaddr, copysize, + wmemidx, rmemidx, &wdesc, &rdesc, ra); + toaddr += step; + fromaddr += step; + copysize -= step; + env->xregs[rn] = -copysize; + } + } else { + while (copysize > 0) { + step = copy_step_rev(env, toaddr, fromaddr, copysize, + wmemidx, rmemidx, &wdesc, &rdesc, ra); + toaddr -= step; + fromaddr -= step; + copysize -= step; + env->xregs[rn] = copysize; + } + } +} + +void HELPER(cpye)(CPUARMState *env, uint32_t syndrome, uint32_t wdesc, + uint32_t rdesc) +{ + do_cpye(env, syndrome, wdesc, rdesc, true, GETPC()); +} + +void HELPER(cpyfe)(CPUARMState *env, uint32_t syndrome, uint32_t wdesc, + uint32_t rdesc) +{ + do_cpye(env, syndrome, wdesc, rdesc, false, GETPC()); +} diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SETGP, aa64_mops, do_SET, a, false, true, gen_helper_setgp) TRANS_FEAT(SETGM, aa64_mops, do_SET, a, false, true, gen_helper_setgm) TRANS_FEAT(SETGE, aa64_mops, do_SET, a, true, true, gen_helper_setge) +typedef void CpyFn(TCGv_env, TCGv_i32, TCGv_i32, TCGv_i32); + +static bool do_CPY(DisasContext *s, arg_cpy *a, bool is_epilogue, CpyFn fn) +{ + int rmemidx, wmemidx; + uint32_t syndrome, rdesc = 0, wdesc = 0; + bool wunpriv = extract32(a->options, 0, 1); + bool runpriv = extract32(a->options, 1, 1); + + /* + * UNPREDICTABLE cases: we choose to UNDEF, which allows + * us to pull this check before the CheckMOPSEnabled() test + * (which we do in the helper function) + */ + if (a->rs == a->rn || a->rs == a->rd || a->rn == a->rd || + a->rd == 31 || a->rs == 31 || a->rn == 31) { + return false; + } + + rmemidx = get_a64_user_mem_index(s, runpriv); + wmemidx = get_a64_user_mem_index(s, wunpriv); + + /* + * We pass option_a == true, matching our implementation; + * we pass wrong_option == false: helper function may set that bit. + */ + syndrome = syn_mop(false, false, a->options, is_epilogue, + false, true, a->rd, a->rs, a->rn); + + /* If we need to do MTE tag checking, assemble the descriptors */ + if (s->mte_active[runpriv]) { + rdesc = FIELD_DP32(rdesc, MTEDESC, TBI, s->tbid); + rdesc = FIELD_DP32(rdesc, MTEDESC, TCMA, s->tcma); + } + if (s->mte_active[wunpriv]) { + wdesc = FIELD_DP32(wdesc, MTEDESC, TBI, s->tbid); + wdesc = FIELD_DP32(wdesc, MTEDESC, TCMA, s->tcma); + wdesc = FIELD_DP32(wdesc, MTEDESC, WRITE, true); + } + /* The helper function needs these parts of the descriptor regardless */ + rdesc = FIELD_DP32(rdesc, MTEDESC, MIDX, rmemidx); + wdesc = FIELD_DP32(wdesc, MTEDESC, MIDX, wmemidx); + + /* + * The helper needs the register numbers, but since they're in + * the syndrome anyway, we let it extract them from there rather + * than passing in an extra three integer arguments. + */ + fn(cpu_env, tcg_constant_i32(syndrome), tcg_constant_i32(wdesc), + tcg_constant_i32(rdesc)); + return true; +} + +TRANS_FEAT(CPYP, aa64_mops, do_CPY, a, false, gen_helper_cpyp) +TRANS_FEAT(CPYM, aa64_mops, do_CPY, a, false, gen_helper_cpym) +TRANS_FEAT(CPYE, aa64_mops, do_CPY, a, true, gen_helper_cpye) +TRANS_FEAT(CPYFP, aa64_mops, do_CPY, a, false, gen_helper_cpyfp) +TRANS_FEAT(CPYFM, aa64_mops, do_CPY, a, false, gen_helper_cpyfm) +TRANS_FEAT(CPYFE, aa64_mops, do_CPY, a, true, gen_helper_cpyfe) + typedef void ArithTwoOp(TCGv_i64, TCGv_i64, TCGv_i64); static bool gen_rri(DisasContext *s, arg_rri_sf *a, -- 2.34.1 Enable FEAT_MOPS on the AArch64 'max' CPU, and add it to the list of features we implement. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230912140434.1333369-13-peter.maydell@linaro.org --- docs/system/arm/emulation.rst | 1 + linux-user/elfload.c | 1 + target/arm/tcg/cpu64.c | 1 + 3 files changed, 3 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_LSE (Large System Extensions) - FEAT_LSE2 (Large System Extensions v2) - FEAT_LVA (Large Virtual Address space) +- FEAT_MOPS (Standardization of memory operations) - FEAT_MTE (Memory Tagging Extension) - FEAT_MTE2 (Memory Tagging Extension) - FEAT_MTE3 (MTE Asymmetric Fault Handling) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ uint32_t get_elf_hwcap2(void) GET_FEATURE_ID(aa64_sme_i16i64, ARM_HWCAP2_A64_SME_I16I64); GET_FEATURE_ID(aa64_sme_fa64, ARM_HWCAP2_A64_SME_FA64); GET_FEATURE_ID(aa64_hbc, ARM_HWCAP2_A64_HBC); + GET_FEATURE_ID(aa64_mops, ARM_HWCAP2_A64_MOPS); return hwcaps; } diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) cpu->isar.id_aa64isar1 = t; t = cpu->isar.id_aa64isar2; + t = FIELD_DP64(t, ID_AA64ISAR2, MOPS, 1); /* FEAT_MOPS */ t = FIELD_DP64(t, ID_AA64ISAR2, BC, 1); /* FEAT_HBC */ cpu->isar.id_aa64isar2 = t; -- 2.34.1 Avoid a dynamic stack allocation in qjack_client_init(), by using a g_autofree heap allocation instead. (We stick with allocate + snprintf() because the JACK API requires the name to be no more than its maximum size, so g_strdup_printf() would require an extra truncation step.) The codebase has very few VLAs, and if we can get rid of them all we can make the compiler error on new additions. This is a defensive measure against security bugs where an on-stack dynamic allocation isn't correctly size-checked (e.g. CVE-2021-3527). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Reviewed-by: Christian Schoenebeck <qemu_oss@crudebyte.com> Message-id: 20230818155846.1651287-2-peter.maydell@linaro.org --- audio/jackaudio.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/audio/jackaudio.c b/audio/jackaudio.c index XXXXXXX..XXXXXXX 100644 --- a/audio/jackaudio.c +++ b/audio/jackaudio.c @@ -XXX,XX +XXX,XX @@ static void qjack_client_connect_ports(QJackClient *c) static int qjack_client_init(QJackClient *c) { jack_status_t status; - char client_name[jack_client_name_size()]; + int client_name_len = jack_client_name_size(); /* includes NUL */ + g_autofree char *client_name = g_new(char, client_name_len); jack_options_t options = JackNullOption; if (c->state == QJACK_STATE_RUNNING) { @@ -XXX,XX +XXX,XX @@ static int qjack_client_init(QJackClient *c) c->connect_ports = true; - snprintf(client_name, sizeof(client_name), "%s-%s", + snprintf(client_name, client_name_len, "%s-%s", c->out ? "out" : "in", c->opt->client_name ? c->opt->client_name : audio_application_name()); -- 2.34.1 Avoid a dynamic stack allocation in qjack_process(). Since this function is a JACK process callback, we are not permitted to malloc() here, so we allocate a working buffer in qjack_client_init() instead. The codebase has very few VLAs, and if we can get rid of them all we can make the compiler error on new additions. This is a defensive measure against security bugs where an on-stack dynamic allocation isn't correctly size-checked (e.g. CVE-2021-3527). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Reviewed-by: Christian Schoenebeck <qemu_oss@crudebyte.com> Message-id: 20230818155846.1651287-3-peter.maydell@linaro.org --- audio/jackaudio.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/audio/jackaudio.c b/audio/jackaudio.c index XXXXXXX..XXXXXXX 100644 --- a/audio/jackaudio.c +++ b/audio/jackaudio.c @@ -XXX,XX +XXX,XX @@ typedef struct QJackClient { int buffersize; jack_port_t **port; QJackBuffer fifo; + + /* Used as workspace by qjack_process() */ + float **process_buffers; } QJackClient; @@ -XXX,XX +XXX,XX @@ static int qjack_process(jack_nframes_t nframes, void *arg) } /* get the buffers for the ports */ - float *buffers[c->nchannels]; for (int i = 0; i < c->nchannels; ++i) { - buffers[i] = jack_port_get_buffer(c->port[i], nframes); + c->process_buffers[i] = jack_port_get_buffer(c->port[i], nframes); } if (c->out) { if (likely(c->enabled)) { - qjack_buffer_read_l(&c->fifo, buffers, nframes); + qjack_buffer_read_l(&c->fifo, c->process_buffers, nframes); } else { for (int i = 0; i < c->nchannels; ++i) { - memset(buffers[i], 0, nframes * sizeof(float)); + memset(c->process_buffers[i], 0, nframes * sizeof(float)); } } } else { if (likely(c->enabled)) { - qjack_buffer_write_l(&c->fifo, buffers, nframes); + qjack_buffer_write_l(&c->fifo, c->process_buffers, nframes); } } @@ -XXX,XX +XXX,XX @@ static int qjack_client_init(QJackClient *c) jack_get_client_name(c->client)); } + /* Allocate working buffer for process callback */ + c->process_buffers = g_new(float *, c->nchannels); + jack_set_process_callback(c->client, qjack_process , c); jack_set_port_registration_callback(c->client, qjack_port_registration, c); jack_set_xrun_callback(c->client, qjack_xrun, c); @@ -XXX,XX +XXX,XX @@ static void qjack_client_fini_locked(QJackClient *c) qjack_buffer_free(&c->fifo); g_free(c->port); + g_free(c->process_buffers); c->state = QJACK_STATE_DISCONNECTED; /* fallthrough */ -- 2.34.1 From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Armv8.1+ cpus have Virtual Host Extension (VHE) which added non-secure EL2 virtual timer. This change adds it to fullfil Arm BSA (Base System Architecture) requirements. Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Message-id: 20230913140610.214893-2-marcin.juszkiewicz@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ #define ARCH_TIMER_S_EL1_IRQ 13 #define ARCH_TIMER_NS_EL1_IRQ 14 #define ARCH_TIMER_NS_EL2_IRQ 10 +#define ARCH_TIMER_NS_EL2_VIRT_IRQ 12 enum { SBSA_FLASH, @@ -XXX,XX +XXX,XX @@ static void create_gic(SBSAMachineState *sms, MemoryRegion *mem) [GTIMER_VIRT] = ARCH_TIMER_VIRT_IRQ, [GTIMER_HYP] = ARCH_TIMER_NS_EL2_IRQ, [GTIMER_SEC] = ARCH_TIMER_S_EL1_IRQ, + [GTIMER_HYPVIRT] = ARCH_TIMER_NS_EL2_VIRT_IRQ, }; for (irq = 0; irq < ARRAY_SIZE(timer_irq); irq++) { -- 2.34.1 From: Viktor Prutyanov <viktor@daynix.com> PE export name check introduced in d399d6b179 isn't reliable enough, because a page with the export directory may be not present for some reason. On the other hand, elf2dmp retrieves the PDB name in any case. It can be also used to check that a PE image is the kernel image. So, check PDB name when searching for Windows kernel image. Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2165917 Signed-off-by: Viktor Prutyanov <viktor@daynix.com> Reviewed-by: Akihiko Odaki <akihiko.odaki@daynix.com> Message-id: 20230915170153.10959-2-viktor@daynix.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- contrib/elf2dmp/main.c | 93 +++++++++++++++--------------------------- 1 file changed, 33 insertions(+), 60 deletions(-) diff --git a/contrib/elf2dmp/main.c b/contrib/elf2dmp/main.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/elf2dmp/main.c +++ b/contrib/elf2dmp/main.c @@ -XXX,XX +XXX,XX @@ static int write_dump(struct pa_space *ps, return fclose(dmp_file); } -static bool pe_check_export_name(uint64_t base, void *start_addr, - struct va_space *vs) -{ - IMAGE_EXPORT_DIRECTORY export_dir; - const char *pe_name; - - if (pe_get_data_dir_entry(base, start_addr, IMAGE_FILE_EXPORT_DIRECTORY, - &export_dir, sizeof(export_dir), vs)) { - return false; - } - - pe_name = va_space_resolve(vs, base + export_dir.Name); - if (!pe_name) { - return false; - } - - return !strcmp(pe_name, PE_NAME); -} - -static int pe_get_pdb_symstore_hash(uint64_t base, void *start_addr, - char *hash, struct va_space *vs) +static bool pe_check_pdb_name(uint64_t base, void *start_addr, + struct va_space *vs, OMFSignatureRSDS *rsds) { const char sign_rsds[4] = "RSDS"; IMAGE_DEBUG_DIRECTORY debug_dir; - OMFSignatureRSDS rsds; - char *pdb_name; - size_t pdb_name_sz; - size_t i; + char pdb_name[sizeof(PDB_NAME)]; if (pe_get_data_dir_entry(base, start_addr, IMAGE_FILE_DEBUG_DIRECTORY, &debug_dir, sizeof(debug_dir), vs)) { eprintf("Failed to get Debug Directory\n"); - return 1; + return false; } if (debug_dir.Type != IMAGE_DEBUG_TYPE_CODEVIEW) { - return 1; + eprintf("Debug Directory type is not CodeView\n"); + return false; } if (va_space_rw(vs, base + debug_dir.AddressOfRawData, - &rsds, sizeof(rsds), 0)) { - return 1; + rsds, sizeof(*rsds), 0)) { + eprintf("Failed to resolve OMFSignatureRSDS\n"); + return false; } - printf("CodeView signature is \'%.4s\'\n", rsds.Signature); - - if (memcmp(&rsds.Signature, sign_rsds, sizeof(sign_rsds))) { - return 1; + if (memcmp(&rsds->Signature, sign_rsds, sizeof(sign_rsds))) { + eprintf("CodeView signature is \'%.4s\', \'%s\' expected\n", + rsds->Signature, sign_rsds); + return false; } - pdb_name_sz = debug_dir.SizeOfData - sizeof(rsds); - pdb_name = malloc(pdb_name_sz); - if (!pdb_name) { - return 1; + if (debug_dir.SizeOfData - sizeof(*rsds) != sizeof(PDB_NAME)) { + eprintf("PDB name size doesn't match\n"); + return false; } if (va_space_rw(vs, base + debug_dir.AddressOfRawData + - offsetof(OMFSignatureRSDS, name), pdb_name, pdb_name_sz, 0)) { - free(pdb_name); - return 1; + offsetof(OMFSignatureRSDS, name), pdb_name, sizeof(PDB_NAME), + 0)) { + eprintf("Failed to resolve PDB name\n"); + return false; } printf("PDB name is \'%s\', \'%s\' expected\n", pdb_name, PDB_NAME); - if (strcmp(pdb_name, PDB_NAME)) { - eprintf("Unexpected PDB name, it seems the kernel isn't found\n"); - free(pdb_name); - return 1; - } + return !strcmp(pdb_name, PDB_NAME); +} - free(pdb_name); - - sprintf(hash, "%.08x%.04x%.04x%.02x%.02x", rsds.guid.a, rsds.guid.b, - rsds.guid.c, rsds.guid.d[0], rsds.guid.d[1]); +static void pe_get_pdb_symstore_hash(OMFSignatureRSDS *rsds, char *hash) +{ + sprintf(hash, "%.08x%.04x%.04x%.02x%.02x", rsds->guid.a, rsds->guid.b, + rsds->guid.c, rsds->guid.d[0], rsds->guid.d[1]); hash += 20; - for (i = 0; i < 6; i++, hash += 2) { - sprintf(hash, "%.02x", rsds.guid.e[i]); + for (unsigned int i = 0; i < 6; i++, hash += 2) { + sprintf(hash, "%.02x", rsds->guid.e[i]); } - sprintf(hash, "%.01x", rsds.age); - - return 0; + sprintf(hash, "%.01x", rsds->age); } int main(int argc, char *argv[]) @@ -XXX,XX +XXX,XX @@ int main(int argc, char *argv[]) KDDEBUGGER_DATA64 *kdbg; uint64_t KdVersionBlock; bool kernel_found = false; + OMFSignatureRSDS rsds; if (argc != 3) { eprintf("usage:\n\t%s elf_file dmp_file\n", argv[0]); @@ -XXX,XX +XXX,XX @@ int main(int argc, char *argv[]) } if (*(uint16_t *)nt_start_addr == 0x5a4d) { /* MZ */ - if (pe_check_export_name(KernBase, nt_start_addr, &vs)) { + printf("Checking candidate KernBase = 0x%016"PRIx64"\n", KernBase); + if (pe_check_pdb_name(KernBase, nt_start_addr, &vs, &rsds)) { kernel_found = true; break; } @@ -XXX,XX +XXX,XX @@ int main(int argc, char *argv[]) printf("KernBase = 0x%016"PRIx64", signature is \'%.2s\'\n", KernBase, (char *)nt_start_addr); - if (pe_get_pdb_symstore_hash(KernBase, nt_start_addr, pdb_hash, &vs)) { - eprintf("Failed to get PDB symbol store hash\n"); - err = 1; - goto out_ps; - } + pe_get_pdb_symstore_hash(&rsds, pdb_hash); sprintf(pdb_url, "%s%s/%s/%s", SYM_URL_BASE, PDB_NAME, pdb_hash, PDB_NAME); printf("PDB URL is %s\n", pdb_url); -- 2.34.1 From: Viktor Prutyanov <viktor@daynix.com> Physical memory ranges may not be aligned to page size in QEMU ELF, but DMP can only contain page-aligned runs. So, align them. Signed-off-by: Viktor Prutyanov <viktor@daynix.com> Reviewed-by: Akihiko Odaki <akihiko.odaki@daynix.com> Message-id: 20230915170153.10959-3-viktor@daynix.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- contrib/elf2dmp/addrspace.h | 1 + contrib/elf2dmp/addrspace.c | 31 +++++++++++++++++++++++++++++-- contrib/elf2dmp/main.c | 5 +++-- 3 files changed, 33 insertions(+), 4 deletions(-) diff --git a/contrib/elf2dmp/addrspace.h b/contrib/elf2dmp/addrspace.h index XXXXXXX..XXXXXXX 100644 --- a/contrib/elf2dmp/addrspace.h +++ b/contrib/elf2dmp/addrspace.h @@ -XXX,XX +XXX,XX @@ #define ELF2DMP_PAGE_BITS 12 #define ELF2DMP_PAGE_SIZE (1ULL << ELF2DMP_PAGE_BITS) +#define ELF2DMP_PAGE_MASK (ELF2DMP_PAGE_SIZE - 1) #define ELF2DMP_PFN_MASK (~(ELF2DMP_PAGE_SIZE - 1)) #define INVALID_PA UINT64_MAX diff --git a/contrib/elf2dmp/addrspace.c b/contrib/elf2dmp/addrspace.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/elf2dmp/addrspace.c +++ b/contrib/elf2dmp/addrspace.c @@ -XXX,XX +XXX,XX @@ static struct pa_block *pa_space_find_block(struct pa_space *ps, uint64_t pa) for (i = 0; i < ps->block_nr; i++) { if (ps->block[i].paddr <= pa && - pa <= ps->block[i].paddr + ps->block[i].size) { + pa < ps->block[i].paddr + ps->block[i].size) { return ps->block + i; } } @@ -XXX,XX +XXX,XX @@ static uint8_t *pa_space_resolve(struct pa_space *ps, uint64_t pa) return block->addr + (pa - block->paddr); } +static void pa_block_align(struct pa_block *b) +{ + uint64_t low_align = ((b->paddr - 1) | ELF2DMP_PAGE_MASK) + 1 - b->paddr; + uint64_t high_align = (b->paddr + b->size) & ELF2DMP_PAGE_MASK; + + if (low_align == 0 && high_align == 0) { + return; + } + + if (low_align + high_align < b->size) { + printf("Block 0x%"PRIx64"+:0x%"PRIx64" will be aligned to " + "0x%"PRIx64"+:0x%"PRIx64"\n", b->paddr, b->size, + b->paddr + low_align, b->size - low_align - high_align); + b->size -= low_align + high_align; + } else { + printf("Block 0x%"PRIx64"+:0x%"PRIx64" is too small to align\n", + b->paddr, b->size); + b->size = 0; + } + + b->addr += low_align; + b->paddr += low_align; +} + int pa_space_create(struct pa_space *ps, QEMU_Elf *qemu_elf) { Elf64_Half phdr_nr = elf_getphdrnum(qemu_elf->map); @@ -XXX,XX +XXX,XX @@ int pa_space_create(struct pa_space *ps, QEMU_Elf *qemu_elf) .paddr = phdr[i].p_paddr, .size = phdr[i].p_filesz, }; - block_i++; + pa_block_align(&ps->block[block_i]); + block_i = ps->block[block_i].size ? (block_i + 1) : block_i; } } + ps->block_nr = block_i; + return 0; } diff --git a/contrib/elf2dmp/main.c b/contrib/elf2dmp/main.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/elf2dmp/main.c +++ b/contrib/elf2dmp/main.c @@ -XXX,XX +XXX,XX @@ static int write_dump(struct pa_space *ps, for (i = 0; i < ps->block_nr; i++) { struct pa_block *b = &ps->block[i]; - printf("Writing block #%zu/%zu to file...\n", i, ps->block_nr); + printf("Writing block #%zu/%zu of %"PRIu64" bytes to file...\n", i, + ps->block_nr, b->size); if (fwrite(b->addr, b->size, 1, dmp_file) != 1) { - eprintf("Failed to write dump header\n"); + eprintf("Failed to write block\n"); fclose(dmp_file); return 1; } -- 2.34.1 From: Viktor Prutyanov <viktor@daynix.com> DMP supports 42 physical memory runs at most. So, merge adjacent physical memory ranges from QEMU ELF when possible to minimize total number of runs. Signed-off-by: Viktor Prutyanov <viktor@daynix.com> Reviewed-by: Akihiko Odaki <akihiko.odaki@daynix.com> Message-id: 20230915170153.10959-4-viktor@daynix.com [PMM: fixed format string for printing size_t values] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- contrib/elf2dmp/main.c | 56 ++++++++++++++++++++++++++++++++++++------ 1 file changed, 48 insertions(+), 8 deletions(-) diff --git a/contrib/elf2dmp/main.c b/contrib/elf2dmp/main.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/elf2dmp/main.c +++ b/contrib/elf2dmp/main.c @@ -XXX,XX +XXX,XX @@ #define PE_NAME "ntoskrnl.exe" #define INITIAL_MXCSR 0x1f80 +#define MAX_NUMBER_OF_RUNS 42 typedef struct idt_desc { uint16_t offset1; /* offset bits 0..15 */ @@ -XXX,XX +XXX,XX @@ static int fix_dtb(struct va_space *vs, QEMU_Elf *qe) return 1; } +static void try_merge_runs(struct pa_space *ps, + WinDumpPhyMemDesc64 *PhysicalMemoryBlock) +{ + unsigned int merge_cnt = 0, run_idx = 0; + + PhysicalMemoryBlock->NumberOfRuns = 0; + + for (size_t idx = 0; idx < ps->block_nr; idx++) { + struct pa_block *blk = ps->block + idx; + struct pa_block *next = blk + 1; + + PhysicalMemoryBlock->NumberOfPages += blk->size / ELF2DMP_PAGE_SIZE; + + if (idx + 1 != ps->block_nr && blk->paddr + blk->size == next->paddr) { + printf("Block #%zu 0x%"PRIx64"+:0x%"PRIx64" and %u previous will be" + " merged\n", idx, blk->paddr, blk->size, merge_cnt); + merge_cnt++; + } else { + struct pa_block *first_merged = blk - merge_cnt; + + printf("Block #%zu 0x%"PRIx64"+:0x%"PRIx64" and %u previous will be" + " merged to 0x%"PRIx64"+:0x%"PRIx64" (run #%u)\n", + idx, blk->paddr, blk->size, merge_cnt, first_merged->paddr, + blk->paddr + blk->size - first_merged->paddr, run_idx); + PhysicalMemoryBlock->Run[run_idx] = (WinDumpPhyMemRun64) { + .BasePage = first_merged->paddr / ELF2DMP_PAGE_SIZE, + .PageCount = (blk->paddr + blk->size - first_merged->paddr) / + ELF2DMP_PAGE_SIZE, + }; + PhysicalMemoryBlock->NumberOfRuns++; + run_idx++; + merge_cnt = 0; + } + } +} + static int fill_header(WinDumpHeader64 *hdr, struct pa_space *ps, struct va_space *vs, uint64_t KdDebuggerDataBlock, KDDEBUGGER_DATA64 *kdbg, uint64_t KdVersionBlock, int nr_cpus) @@ -XXX,XX +XXX,XX @@ static int fill_header(WinDumpHeader64 *hdr, struct pa_space *ps, KUSD_OFFSET_PRODUCT_TYPE); DBGKD_GET_VERSION64 kvb; WinDumpHeader64 h; - size_t i; QEMU_BUILD_BUG_ON(KUSD_OFFSET_SUITE_MASK >= ELF2DMP_PAGE_SIZE); QEMU_BUILD_BUG_ON(KUSD_OFFSET_PRODUCT_TYPE >= ELF2DMP_PAGE_SIZE); @@ -XXX,XX +XXX,XX @@ static int fill_header(WinDumpHeader64 *hdr, struct pa_space *ps, .RequiredDumpSpace = sizeof(h), }; - for (i = 0; i < ps->block_nr; i++) { - h.PhysicalMemoryBlock.NumberOfPages += - ps->block[i].size / ELF2DMP_PAGE_SIZE; - h.PhysicalMemoryBlock.Run[i] = (WinDumpPhyMemRun64) { - .BasePage = ps->block[i].paddr / ELF2DMP_PAGE_SIZE, - .PageCount = ps->block[i].size / ELF2DMP_PAGE_SIZE, - }; + if (h.PhysicalMemoryBlock.NumberOfRuns <= MAX_NUMBER_OF_RUNS) { + for (size_t idx = 0; idx < ps->block_nr; idx++) { + h.PhysicalMemoryBlock.NumberOfPages += + ps->block[idx].size / ELF2DMP_PAGE_SIZE; + h.PhysicalMemoryBlock.Run[idx] = (WinDumpPhyMemRun64) { + .BasePage = ps->block[idx].paddr / ELF2DMP_PAGE_SIZE, + .PageCount = ps->block[idx].size / ELF2DMP_PAGE_SIZE, + }; + } + } else { + try_merge_runs(ps, &h.PhysicalMemoryBlock); } h.RequiredDumpSpace += -- 2.34.1 From: Viktor Prutyanov <viktor@daynix.com> Glib's g_mapped_file_new maps file with PROT_READ|PROT_WRITE and MAP_PRIVATE. This leads to premature physical memory allocation of dump file size on Linux hosts and may fail. On Linux, mapping the file with MAP_NORESERVE limits the allocation by available memory. Signed-off-by: Viktor Prutyanov <viktor@daynix.com> Reviewed-by: Akihiko Odaki <akihiko.odaki@daynix.com> Message-id: 20230915170153.10959-5-viktor@daynix.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- contrib/elf2dmp/qemu_elf.h | 2 ++ contrib/elf2dmp/qemu_elf.c | 68 +++++++++++++++++++++++++++++++------- 2 files changed, 58 insertions(+), 12 deletions(-) diff --git a/contrib/elf2dmp/qemu_elf.h b/contrib/elf2dmp/qemu_elf.h index XXXXXXX..XXXXXXX 100644 --- a/contrib/elf2dmp/qemu_elf.h +++ b/contrib/elf2dmp/qemu_elf.h @@ -XXX,XX +XXX,XX @@ typedef struct QEMUCPUState { int is_system(QEMUCPUState *s); typedef struct QEMU_Elf { +#ifndef CONFIG_LINUX GMappedFile *gmf; +#endif size_t size; void *map; QEMUCPUState **state; diff --git a/contrib/elf2dmp/qemu_elf.c b/contrib/elf2dmp/qemu_elf.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/elf2dmp/qemu_elf.c +++ b/contrib/elf2dmp/qemu_elf.c @@ -XXX,XX +XXX,XX @@ static bool check_ehdr(QEMU_Elf *qe) return true; } -int QEMU_Elf_init(QEMU_Elf *qe, const char *filename) +static int QEMU_Elf_map(QEMU_Elf *qe, const char *filename) { +#ifdef CONFIG_LINUX + struct stat st; + int fd; + + printf("Using Linux mmap\n"); + + fd = open(filename, O_RDONLY, 0); + if (fd == -1) { + eprintf("Failed to open ELF dump file \'%s\'\n", filename); + return 1; + } + + if (fstat(fd, &st)) { + eprintf("Failed to get size of ELF dump file\n"); + close(fd); + return 1; + } + qe->size = st.st_size; + + qe->map = mmap(NULL, qe->size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_NORESERVE, fd, 0); + if (qe->map == MAP_FAILED) { + eprintf("Failed to map ELF file\n"); + close(fd); + return 1; + } + + close(fd); +#else GError *gerr = NULL; - int err = 0; + + printf("Using GLib mmap\n"); qe->gmf = g_mapped_file_new(filename, TRUE, &gerr); if (gerr) { @@ -XXX,XX +XXX,XX @@ int QEMU_Elf_init(QEMU_Elf *qe, const char *filename) qe->map = g_mapped_file_get_contents(qe->gmf); qe->size = g_mapped_file_get_length(qe->gmf); +#endif + + return 0; +} + +static void QEMU_Elf_unmap(QEMU_Elf *qe) +{ +#ifdef CONFIG_LINUX + munmap(qe->map, qe->size); +#else + g_mapped_file_unref(qe->gmf); +#endif +} + +int QEMU_Elf_init(QEMU_Elf *qe, const char *filename) +{ + if (QEMU_Elf_map(qe, filename)) { + return 1; + } if (!check_ehdr(qe)) { eprintf("Input file has the wrong format\n"); - err = 1; - goto out_unmap; + QEMU_Elf_unmap(qe); + return 1; } if (init_states(qe)) { eprintf("Failed to extract QEMU CPU states\n"); - err = 1; - goto out_unmap; + QEMU_Elf_unmap(qe); + return 1; } return 0; - -out_unmap: - g_mapped_file_unref(qe->gmf); - - return err; } void QEMU_Elf_exit(QEMU_Elf *qe) { exit_states(qe); - g_mapped_file_unref(qe->gmf); + QEMU_Elf_unmap(qe); } -- 2.34.1 From: Viktor Prutyanov <viktor@daynix.com> PDB for Windows 11 kernel has slightly different structure compared to previous versions. Since elf2dmp don't use the other fields, copy only 'segments' field from PDB_STREAM_INDEXES. Signed-off-by: Viktor Prutyanov <viktor@daynix.com> Reviewed-by: Akihiko Odaki <akihiko.odaki@daynix.com> Message-id: 20230915170153.10959-6-viktor@daynix.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- contrib/elf2dmp/pdb.h | 2 +- contrib/elf2dmp/pdb.c | 15 ++++----------- 2 files changed, 5 insertions(+), 12 deletions(-) diff --git a/contrib/elf2dmp/pdb.h b/contrib/elf2dmp/pdb.h index XXXXXXX..XXXXXXX 100644 --- a/contrib/elf2dmp/pdb.h +++ b/contrib/elf2dmp/pdb.h @@ -XXX,XX +XXX,XX @@ struct pdb_reader { } ds; uint32_t file_used[1024]; PDB_SYMBOLS *symbols; - PDB_STREAM_INDEXES sidx; + uint16_t segments; uint8_t *modimage; char *segs; size_t segs_size; diff --git a/contrib/elf2dmp/pdb.c b/contrib/elf2dmp/pdb.c index XXXXXXX..XXXXXXX 100644 --- a/contrib/elf2dmp/pdb.c +++ b/contrib/elf2dmp/pdb.c @@ -XXX,XX +XXX,XX @@ static void *pdb_ds_read_file(struct pdb_reader* r, uint32_t file_number) static int pdb_init_segments(struct pdb_reader *r) { char *segs; - unsigned stream_idx = r->sidx.segments; + unsigned stream_idx = r->segments; segs = pdb_ds_read_file(r, stream_idx); if (!segs) { @@ -XXX,XX +XXX,XX @@ static int pdb_init_symbols(struct pdb_reader *r) { int err = 0; PDB_SYMBOLS *symbols; - PDB_STREAM_INDEXES *sidx = &r->sidx; - - memset(sidx, -1, sizeof(*sidx)); symbols = pdb_ds_read_file(r, 3); if (!symbols) { @@ -XXX,XX +XXX,XX @@ static int pdb_init_symbols(struct pdb_reader *r) r->symbols = symbols; - if (symbols->stream_index_size != sizeof(PDB_STREAM_INDEXES)) { - err = 1; - goto out_symbols; - } - - memcpy(sidx, (const char *)symbols + sizeof(PDB_SYMBOLS) + + r->segments = *(uint16_t *)((const char *)symbols + sizeof(PDB_SYMBOLS) + symbols->module_size + symbols->offset_size + symbols->hash_size + symbols->srcmodule_size + - symbols->pdbimport_size + symbols->unknown2_size, sizeof(*sidx)); + symbols->pdbimport_size + symbols->unknown2_size + + offsetof(PDB_STREAM_INDEXES, segments)); /* Read global symbol table */ r->modimage = pdb_ds_read_file(r, symbols->gsym_file); -- 2.34.1 Hi; here's the latest target-arm queue. Mostly this is refactoring and cleanup type patches. thanks -- PMM The following changes since commit c60be6e3e38cb36dc66129e757ec4b34152232be: Merge tag 'pull-sp-20231025' of https://gitlab.com/rth7680/qemu into staging (2023-10-27 09:43:53 +0900) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20231027 for you to fetch changes up to df93de987f423a0ed918c425f5dbd9a25d3c6229: hw/net/cadence_gem: enforce 32 bits variable size for CRC (2023-10-27 15:27:06 +0100) ---------------------------------------------------------------- target-arm queue: * Correct minor errors in Cortex-A710 definition * Implement Neoverse N2 CPU model * Refactor feature test functions out into separate header * Fix syndrome for FGT traps on ERET * Remove 'hw/arm/boot.h' includes from various header files * pxa2xx: Refactoring/cleanup * Avoid using 'first_cpu' when first ARM CPU is reachable * misc/led: LED state is set opposite of what is expected * hw/net/cadence_gen: clean up to use FIELD macros * hw/net/cadence_gem: perform PHY access on write only * hw/net/cadence_gem: enforce 32 bits variable size for CRC ---------------------------------------------------------------- Glenn Miles (1): misc/led: LED state is set opposite of what is expected Luc Michel (11): hw/net/cadence_gem: use REG32 macro for register definitions hw/net/cadence_gem: use FIELD for screening registers hw/net/cadence_gem: use FIELD to describe NWCTRL register fields hw/net/cadence_gem: use FIELD to describe NWCFG register fields hw/net/cadence_gem: use FIELD to describe DMACFG register fields hw/net/cadence_gem: use FIELD to describe [TX|RX]STATUS register fields hw/net/cadence_gem: use FIELD to describe IRQ register fields hw/net/cadence_gem: use FIELD to describe DESCONF6 register fields hw/net/cadence_gem: use FIELD to describe PHYMNTNC register fields hw/net/cadence_gem: perform PHY access on write only hw/net/cadence_gem: enforce 32 bits variable size for CRC Peter Maydell (9): target/arm: Correct minor errors in Cortex-A710 definition target/arm: Implement Neoverse N2 CPU model target/arm: Move feature test functions to their own header target/arm: Move ID_AA64MMFR1 and ID_AA64MMFR2 tests together target/arm: Move ID_AA64MMFR0 tests up to before MMFR1 and MMFR2 target/arm: Move ID_AA64ISAR* test functions together target/arm: Move ID_AA64PFR* tests together target/arm: Move ID_AA64DFR* feature tests together target/arm: Fix syndrome for FGT traps on ERET Philippe Mathieu-Daudé (20): hw/arm/allwinner-a10: Remove 'hw/arm/boot.h' from header hw/arm/allwinner-h3: Remove 'hw/arm/boot.h' from header hw/arm/allwinner-r40: Remove 'hw/arm/boot.h' from header hw/arm/fsl-imx25: Remove 'hw/arm/boot.h' from header hw/arm/fsl-imx31: Remove 'hw/arm/boot.h' from header hw/arm/fsl-imx6: Remove 'hw/arm/boot.h' from header hw/arm/fsl-imx6ul: Remove 'hw/arm/boot.h' from header hw/arm/fsl-imx7: Remove 'hw/arm/boot.h' from header hw/arm/xlnx-versal: Remove 'hw/arm/boot.h' from header hw/arm/xlnx-zynqmp: Remove 'hw/arm/boot.h' from header hw/sd/pxa2xx: Realize sysbus device before accessing it hw/sd/pxa2xx: Do not open-code sysbus_create_simple() hw/pcmcia/pxa2xx: Realize sysbus device before accessing it hw/pcmcia/pxa2xx: Do not open-code sysbus_create_simple() hw/pcmcia/pxa2xx: Inline pxa2xx_pcmcia_init() hw/intc/pxa2xx: Convert to Resettable interface hw/intc/pxa2xx: Pass CPU reference using QOM link property hw/intc/pxa2xx: Factor pxa2xx_pic_realize() out of pxa2xx_pic_init() hw/arm/pxa2xx: Realize PXA2XX_I2C device before accessing it hw/arm: Avoid using 'first_cpu' when first ARM CPU is reachable docs/system/arm/virt.rst | 1 + bsd-user/arm/target_arch.h | 1 + include/hw/arm/allwinner-a10.h | 1 - include/hw/arm/allwinner-h3.h | 1 - include/hw/arm/allwinner-r40.h | 1 - include/hw/arm/fsl-imx25.h | 1 - include/hw/arm/fsl-imx31.h | 1 - include/hw/arm/fsl-imx6.h | 1 - include/hw/arm/fsl-imx6ul.h | 1 - include/hw/arm/fsl-imx7.h | 1 - include/hw/arm/pxa.h | 2 - include/hw/arm/xlnx-versal.h | 1 - include/hw/arm/xlnx-zynqmp.h | 1 - linux-user/aarch64/target_prctl.h | 2 + target/arm/cpu-features.h | 994 ++++++++++++++++++++++++++++++++++++++ target/arm/cpu.h | 971 ------------------------------------- target/arm/internals.h | 1 + target/arm/tcg/translate.h | 2 +- hw/arm/armv7m.c | 1 + hw/arm/bananapi_m2u.c | 3 +- hw/arm/cubieboard.c | 1 + hw/arm/exynos4_boards.c | 7 +- hw/arm/imx25_pdk.c | 1 + hw/arm/kzm.c | 1 + hw/arm/mcimx6ul-evk.c | 1 + hw/arm/mcimx7d-sabre.c | 1 + hw/arm/orangepi.c | 3 +- hw/arm/pxa2xx.c | 17 +- hw/arm/pxa2xx_pic.c | 38 +- hw/arm/realview.c | 2 +- hw/arm/sabrelite.c | 1 + hw/arm/sbsa-ref.c | 1 + hw/arm/virt.c | 1 + hw/arm/xilinx_zynq.c | 2 +- hw/arm/xlnx-versal-virt.c | 1 + hw/arm/xlnx-zcu102.c | 1 + hw/intc/armv7m_nvic.c | 1 + hw/misc/led.c | 2 +- hw/net/cadence_gem.c | 884 ++++++++++++++++++--------------- hw/pcmcia/pxa2xx.c | 15 - hw/sd/pxa2xx_mmci.c | 7 +- linux-user/aarch64/cpu_loop.c | 1 + linux-user/aarch64/signal.c | 1 + linux-user/arm/signal.c | 1 + linux-user/elfload.c | 4 + linux-user/mmap.c | 4 + target/arm/arch_dump.c | 1 + target/arm/cpu.c | 1 + target/arm/cpu64.c | 1 + target/arm/debug_helper.c | 1 + target/arm/gdbstub.c | 1 + target/arm/helper.c | 1 + target/arm/kvm64.c | 1 + target/arm/machine.c | 1 + target/arm/ptw.c | 1 + target/arm/tcg/cpu64.c | 115 ++++- target/arm/tcg/hflags.c | 1 + target/arm/tcg/m_helper.c | 1 + target/arm/tcg/op_helper.c | 1 + target/arm/tcg/pauth_helper.c | 1 + target/arm/tcg/tlb_helper.c | 1 + target/arm/tcg/translate-a64.c | 4 +- target/arm/vfp_helper.c | 1 + 63 files changed, 1702 insertions(+), 1419 deletions(-) create mode 100644 target/arm/cpu-features.h Correct a couple of minor errors in the Cortex-A710 definition: * ID_AA64DFR0_EL1.DebugVer is 9 (indicating Armv8.4 debug architecture) * ID_AA64ISAR1_EL1.APA is 5 (indicating more PAuth support) * there is an IMPDEF CPUCFR_EL1, like that on the Neoverse-N1 Fixes: e3d45c0a89576 ("target/arm: Implement cortex-a710") Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20230915185453.1871167-2-peter.maydell@linaro.org --- target/arm/tcg/cpu64.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo cortex_a710_cp_reginfo[] = { { .name = "CPUPFR_EL3", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 6, .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + /* + * Report CPUCFR_EL1.SCU as 1, as we do not implement the DSU + * (and in particular its system registers). + */ + { .name = "CPUCFR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 0, .opc2 = 0, + .access = PL1_R, .type = ARM_CP_CONST, .resetvalue = 4 }, /* * Stub RAMINDEX, as we don't actually implement caches, BTB, @@ -XXX,XX +XXX,XX @@ static void aarch64_a710_initfn(Object *obj) cpu->isar.id_aa64pfr0 = 0x1201111120111112ull; /* GIC filled in later */ cpu->isar.id_aa64pfr1 = 0x0000000000000221ull; cpu->isar.id_aa64zfr0 = 0x0000110100110021ull; /* with Crypto */ - cpu->isar.id_aa64dfr0 = 0x000011f010305611ull; + cpu->isar.id_aa64dfr0 = 0x000011f010305619ull; cpu->isar.id_aa64dfr1 = 0; cpu->id_aa64afr0 = 0; cpu->id_aa64afr1 = 0; cpu->isar.id_aa64isar0 = 0x0221111110212120ull; /* with Crypto */ - cpu->isar.id_aa64isar1 = 0x0010111101211032ull; + cpu->isar.id_aa64isar1 = 0x0010111101211052ull; cpu->isar.id_aa64mmfr0 = 0x0000022200101122ull; cpu->isar.id_aa64mmfr1 = 0x0000000010212122ull; cpu->isar.id_aa64mmfr2 = 0x1221011110101011ull; -- 2.34.1 Implement a model of the Neoverse N2 CPU. This is an Armv9.0-A processor very similar to the Cortex-A710. The differences are: * no FEAT_EVT * FEAT_DGH (data gathering hint) * FEAT_NV (not yet implemented in QEMU) * Statistical Profiling Extension (not implemented in QEMU) * 48 bit physical address range, not 40 * CTR_EL0.DIC = 1 (no explicit icache cleaning needed) * PMCR_EL0.N = 6 (always 6 PMU counters, not 20) Because it has 48-bit physical address support, we can use this CPU in the sbsa-ref board as well as the virt board. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20230915185453.1871167-3-peter.maydell@linaro.org --- docs/system/arm/virt.rst | 1 + hw/arm/sbsa-ref.c | 1 + hw/arm/virt.c | 1 + target/arm/tcg/cpu64.c | 103 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 106 insertions(+) diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/virt.rst +++ b/docs/system/arm/virt.rst @@ -XXX,XX +XXX,XX @@ Supported guest CPU types: - ``host`` (with KVM only) - ``neoverse-n1`` (64-bit) - ``neoverse-v1`` (64-bit) +- ``neoverse-n2`` (64-bit) - ``max`` (same as ``host`` for KVM; best possible emulation with TCG) Note that the default is ``cortex-a15``, so for an AArch64 guest you must diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ static const char * const valid_cpus[] = { ARM_CPU_TYPE_NAME("cortex-a72"), ARM_CPU_TYPE_NAME("neoverse-n1"), ARM_CPU_TYPE_NAME("neoverse-v1"), + ARM_CPU_TYPE_NAME("neoverse-n2"), ARM_CPU_TYPE_NAME("max"), }; diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static const char *valid_cpus[] = { ARM_CPU_TYPE_NAME("a64fx"), ARM_CPU_TYPE_NAME("neoverse-n1"), ARM_CPU_TYPE_NAME("neoverse-v1"), + ARM_CPU_TYPE_NAME("neoverse-n2"), #endif ARM_CPU_TYPE_NAME("cortex-a53"), ARM_CPU_TYPE_NAME("cortex-a57"), diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_a710_initfn(Object *obj) aarch64_add_sve_properties(obj); } +/* Extra IMPDEF regs in the N2 beyond those in the A710 */ +static const ARMCPRegInfo neoverse_n2_cp_reginfo[] = { + { .name = "CPURNDBR_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 3, .opc2 = 0, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPURNDPEID_EL3", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 3, .opc2 = 1, + .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, +}; + +static void aarch64_neoverse_n2_initfn(Object *obj) +{ + ARMCPU *cpu = ARM_CPU(obj); + + cpu->dtb_compatible = "arm,neoverse-n2"; + set_feature(&cpu->env, ARM_FEATURE_V8); + set_feature(&cpu->env, ARM_FEATURE_NEON); + set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_AARCH64); + set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); + set_feature(&cpu->env, ARM_FEATURE_EL2); + set_feature(&cpu->env, ARM_FEATURE_EL3); + set_feature(&cpu->env, ARM_FEATURE_PMU); + + /* Ordered by Section B.5: AArch64 ID registers */ + cpu->midr = 0x410FD493; /* r0p3 */ + cpu->revidr = 0; + cpu->isar.id_pfr0 = 0x21110131; + cpu->isar.id_pfr1 = 0x00010000; /* GIC filled in later */ + cpu->isar.id_dfr0 = 0x16011099; + cpu->id_afr0 = 0; + cpu->isar.id_mmfr0 = 0x10201105; + cpu->isar.id_mmfr1 = 0x40000000; + cpu->isar.id_mmfr2 = 0x01260000; + cpu->isar.id_mmfr3 = 0x02122211; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232042; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x00010142; + cpu->isar.id_isar5 = 0x11011121; /* with Crypto */ + cpu->isar.id_mmfr4 = 0x01021110; + cpu->isar.id_isar6 = 0x01111111; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x13211111; + cpu->isar.mvfr2 = 0x00000043; + cpu->isar.id_pfr2 = 0x00000011; + cpu->isar.id_aa64pfr0 = 0x1201111120111112ull; /* GIC filled in later */ + cpu->isar.id_aa64pfr1 = 0x0000000000000221ull; + cpu->isar.id_aa64zfr0 = 0x0000110100110021ull; /* with Crypto */ + cpu->isar.id_aa64dfr0 = 0x000011f210305619ull; + cpu->isar.id_aa64dfr1 = 0; + cpu->id_aa64afr0 = 0; + cpu->id_aa64afr1 = 0; + cpu->isar.id_aa64isar0 = 0x0221111110212120ull; /* with Crypto */ + cpu->isar.id_aa64isar1 = 0x0011111101211052ull; + cpu->isar.id_aa64mmfr0 = 0x0000022200101125ull; + cpu->isar.id_aa64mmfr1 = 0x0000000010212122ull; + cpu->isar.id_aa64mmfr2 = 0x1221011112101011ull; + cpu->clidr = 0x0000001482000023ull; + cpu->gm_blocksize = 4; + cpu->ctr = 0x00000004b444c004ull; + cpu->dcz_blocksize = 4; + /* TODO FEAT_MPAM: mpamidr_el1 = 0x0000_0001_001e_01ff */ + + /* Section B.7.2: PMCR_EL0 */ + cpu->isar.reset_pmcr_el0 = 0x3000; /* with 6 counters */ + + /* Section B.8.9: ICH_VTR_EL2 */ + cpu->gic_num_lrs = 4; + cpu->gic_vpribits = 5; + cpu->gic_vprebits = 5; + cpu->gic_pribits = 5; + + /* Section 14: Scalable Vector Extensions support */ + cpu->sve_vq.supported = 1 << 0; /* 128bit */ + + /* + * The Neoverse N2 TRM does not list CCSIDR values. The layout of + * the caches are in text in Table 7-1, Table 8-1, and Table 9-1. + * + * L1: 4-way set associative 64-byte line size, total 64K. + * L2: 8-way set associative 64 byte line size, total either 512K or 1024K. + */ + cpu->ccsidr[0] = make_ccsidr64(4, 64, 64 * KiB); /* L1 dcache */ + cpu->ccsidr[1] = cpu->ccsidr[0]; /* L1 icache */ + cpu->ccsidr[2] = make_ccsidr64(8, 64, 512 * KiB); /* L2 cache */ + + /* FIXME: Not documented -- copied from neoverse-v1 */ + cpu->reset_sctlr = 0x30c50838; + + /* + * The Neoverse N2 has all of the Cortex-A710 IMPDEF registers, + * and a few more RNG related ones. + */ + define_arm_cp_regs(cpu, cortex_a710_cp_reginfo); + define_arm_cp_regs(cpu, neoverse_n2_cp_reginfo); + + aarch64_add_pauth_properties(obj); + aarch64_add_sve_properties(obj); +} + /* * -cpu max: a CPU with as many features enabled as our emulation supports. * The version of '-cpu max' for qemu-system-arm is defined in cpu32.c; @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo aarch64_cpus[] = { { .name = "a64fx", .initfn = aarch64_a64fx_initfn }, { .name = "neoverse-n1", .initfn = aarch64_neoverse_n1_initfn }, { .name = "neoverse-v1", .initfn = aarch64_neoverse_v1_initfn }, + { .name = "neoverse-n2", .initfn = aarch64_neoverse_n2_initfn }, }; static void aarch64_cpu_register_types(void) -- 2.34.1 The feature test functions isar_feature_*() now take up nearly a thousand lines in target/arm/cpu.h. This header file is included by a lot of source files, most of which don't need these functions. Move the feature test functions to their own header file. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024163510.2972081-2-peter.maydell@linaro.org --- bsd-user/arm/target_arch.h | 1 + linux-user/aarch64/target_prctl.h | 2 + target/arm/cpu-features.h | 994 ++++++++++++++++++++++++++++++ target/arm/cpu.h | 971 ----------------------------- target/arm/internals.h | 1 + target/arm/tcg/translate.h | 2 +- hw/arm/armv7m.c | 1 + hw/intc/armv7m_nvic.c | 1 + linux-user/aarch64/cpu_loop.c | 1 + linux-user/aarch64/signal.c | 1 + linux-user/arm/signal.c | 1 + linux-user/elfload.c | 4 + linux-user/mmap.c | 4 + target/arm/arch_dump.c | 1 + target/arm/cpu.c | 1 + target/arm/cpu64.c | 1 + target/arm/debug_helper.c | 1 + target/arm/gdbstub.c | 1 + target/arm/helper.c | 1 + target/arm/kvm64.c | 1 + target/arm/machine.c | 1 + target/arm/ptw.c | 1 + target/arm/tcg/cpu64.c | 1 + target/arm/tcg/hflags.c | 1 + target/arm/tcg/m_helper.c | 1 + target/arm/tcg/op_helper.c | 1 + target/arm/tcg/pauth_helper.c | 1 + target/arm/tcg/tlb_helper.c | 1 + target/arm/vfp_helper.c | 1 + 29 files changed, 1028 insertions(+), 972 deletions(-) create mode 100644 target/arm/cpu-features.h diff --git a/bsd-user/arm/target_arch.h b/bsd-user/arm/target_arch.h index XXXXXXX..XXXXXXX 100644 --- a/bsd-user/arm/target_arch.h +++ b/bsd-user/arm/target_arch.h @@ -XXX,XX +XXX,XX @@ #define TARGET_ARCH_H #include "qemu.h" +#include "target/arm/cpu-features.h" void target_cpu_set_tls(CPUARMState *env, target_ulong newtls); target_ulong target_cpu_get_tls(CPUARMState *env); diff --git a/linux-user/aarch64/target_prctl.h b/linux-user/aarch64/target_prctl.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/target_prctl.h +++ b/linux-user/aarch64/target_prctl.h @@ -XXX,XX +XXX,XX @@ #ifndef AARCH64_TARGET_PRCTL_H #define AARCH64_TARGET_PRCTL_H +#include "target/arm/cpu-features.h" + static abi_long do_prctl_sve_get_vl(CPUArchState *env) { ARMCPU *cpu = env_archcpu(env); diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/cpu-features.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU Arm CPU -- feature test functions + * + * Copyright (c) 2023 Linaro Ltd + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library 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 + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef TARGET_ARM_FEATURES_H +#define TARGET_ARM_FEATURES_H + +/* + * Naming convention for isar_feature functions: + * Functions which test 32-bit ID registers should have _aa32_ in + * their name. Functions which test 64-bit ID registers should have + * _aa64_ in their name. These must only be used in code where we + * know for certain that the CPU has AArch32 or AArch64 respectively + * or where the correct answer for a CPU which doesn't implement that + * CPU state is "false" (eg when generating A32 or A64 code, if adding + * system registers that are specific to that CPU state, for "should + * we let this system register bit be set" tests where the 32-bit + * flavour of the register doesn't have the bit, and so on). + * Functions which simply ask "does this feature exist at all" have + * _any_ in their name, and always return the logical OR of the _aa64_ + * and the _aa32_ function. + */ + +/* + * 32-bit feature tests via id registers. + */ +static inline bool isar_feature_aa32_thumb_div(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) != 0; +} + +static inline bool isar_feature_aa32_arm_div(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) > 1; +} + +static inline bool isar_feature_aa32_lob(const ARMISARegisters *id) +{ + /* (M-profile) low-overhead loops and branch future */ + return FIELD_EX32(id->id_isar0, ID_ISAR0, CMPBRANCH) >= 3; +} + +static inline bool isar_feature_aa32_jazelle(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar1, ID_ISAR1, JAZELLE) != 0; +} + +static inline bool isar_feature_aa32_aes(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) != 0; +} + +static inline bool isar_feature_aa32_pmull(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) > 1; +} + +static inline bool isar_feature_aa32_sha1(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, SHA1) != 0; +} + +static inline bool isar_feature_aa32_sha2(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, SHA2) != 0; +} + +static inline bool isar_feature_aa32_crc32(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, CRC32) != 0; +} + +static inline bool isar_feature_aa32_rdm(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, RDM) != 0; +} + +static inline bool isar_feature_aa32_vcma(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, VCMA) != 0; +} + +static inline bool isar_feature_aa32_jscvt(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, JSCVT) != 0; +} + +static inline bool isar_feature_aa32_dp(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, DP) != 0; +} + +static inline bool isar_feature_aa32_fhm(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, FHM) != 0; +} + +static inline bool isar_feature_aa32_sb(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, SB) != 0; +} + +static inline bool isar_feature_aa32_predinv(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, SPECRES) != 0; +} + +static inline bool isar_feature_aa32_bf16(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, BF16) != 0; +} + +static inline bool isar_feature_aa32_i8mm(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, I8MM) != 0; +} + +static inline bool isar_feature_aa32_ras(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_pfr0, ID_PFR0, RAS) != 0; +} + +static inline bool isar_feature_aa32_mprofile(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_pfr1, ID_PFR1, MPROGMOD) != 0; +} + +static inline bool isar_feature_aa32_m_sec_state(const ARMISARegisters *id) +{ + /* + * Return true if M-profile state handling insns + * (VSCCLRM, CLRM, FPCTX access insns) are implemented + */ + return FIELD_EX32(id->id_pfr1, ID_PFR1, SECURITY) >= 3; +} + +static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id) +{ + /* Sadly this is encoded differently for A-profile and M-profile */ + if (isar_feature_aa32_mprofile(id)) { + return FIELD_EX32(id->mvfr1, MVFR1, FP16) > 0; + } else { + return FIELD_EX32(id->mvfr1, MVFR1, FPHP) >= 3; + } +} + +static inline bool isar_feature_aa32_mve(const ARMISARegisters *id) +{ + /* + * Return true if MVE is supported (either integer or floating point). + * We must check for M-profile as the MVFR1 field means something + * else for A-profile. + */ + return isar_feature_aa32_mprofile(id) && + FIELD_EX32(id->mvfr1, MVFR1, MVE) > 0; +} + +static inline bool isar_feature_aa32_mve_fp(const ARMISARegisters *id) +{ + /* + * Return true if MVE is supported (either integer or floating point). + * We must check for M-profile as the MVFR1 field means something + * else for A-profile. + */ + return isar_feature_aa32_mprofile(id) && + FIELD_EX32(id->mvfr1, MVFR1, MVE) >= 2; +} + +static inline bool isar_feature_aa32_vfp_simd(const ARMISARegisters *id) +{ + /* + * Return true if either VFP or SIMD is implemented. + * In this case, a minimum of VFP w/ D0-D15. + */ + return FIELD_EX32(id->mvfr0, MVFR0, SIMDREG) > 0; +} + +static inline bool isar_feature_aa32_simd_r32(const ARMISARegisters *id) +{ + /* Return true if D16-D31 are implemented */ + return FIELD_EX32(id->mvfr0, MVFR0, SIMDREG) >= 2; +} + +static inline bool isar_feature_aa32_fpshvec(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr0, MVFR0, FPSHVEC) > 0; +} + +static inline bool isar_feature_aa32_fpsp_v2(const ARMISARegisters *id) +{ + /* Return true if CPU supports single precision floating point, VFPv2 */ + return FIELD_EX32(id->mvfr0, MVFR0, FPSP) > 0; +} + +static inline bool isar_feature_aa32_fpsp_v3(const ARMISARegisters *id) +{ + /* Return true if CPU supports single precision floating point, VFPv3 */ + return FIELD_EX32(id->mvfr0, MVFR0, FPSP) >= 2; +} + +static inline bool isar_feature_aa32_fpdp_v2(const ARMISARegisters *id) +{ + /* Return true if CPU supports double precision floating point, VFPv2 */ + return FIELD_EX32(id->mvfr0, MVFR0, FPDP) > 0; +} + +static inline bool isar_feature_aa32_fpdp_v3(const ARMISARegisters *id) +{ + /* Return true if CPU supports double precision floating point, VFPv3 */ + return FIELD_EX32(id->mvfr0, MVFR0, FPDP) >= 2; +} + +static inline bool isar_feature_aa32_vfp(const ARMISARegisters *id) +{ + return isar_feature_aa32_fpsp_v2(id) || isar_feature_aa32_fpdp_v2(id); +} + +/* + * We always set the FP and SIMD FP16 fields to indicate identical + * levels of support (assuming SIMD is implemented at all), so + * we only need one set of accessors. + */ +static inline bool isar_feature_aa32_fp16_spconv(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr1, MVFR1, FPHP) > 0; +} + +static inline bool isar_feature_aa32_fp16_dpconv(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr1, MVFR1, FPHP) > 1; +} + +/* + * Note that this ID register field covers both VFP and Neon FMAC, + * so should usually be tested in combination with some other + * check that confirms the presence of whichever of VFP or Neon is + * relevant, to avoid accidentally enabling a Neon feature on + * a VFP-no-Neon core or vice-versa. + */ +static inline bool isar_feature_aa32_simdfmac(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr1, MVFR1, SIMDFMAC) != 0; +} + +static inline bool isar_feature_aa32_vsel(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 1; +} + +static inline bool isar_feature_aa32_vcvt_dr(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 2; +} + +static inline bool isar_feature_aa32_vrint(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 3; +} + +static inline bool isar_feature_aa32_vminmaxnm(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 4; +} + +static inline bool isar_feature_aa32_pxn(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr0, ID_MMFR0, VMSA) >= 4; +} + +static inline bool isar_feature_aa32_pan(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr3, ID_MMFR3, PAN) != 0; +} + +static inline bool isar_feature_aa32_ats1e1(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr3, ID_MMFR3, PAN) >= 2; +} + +static inline bool isar_feature_aa32_pmuv3p1(const ARMISARegisters *id) +{ + /* 0xf means "non-standard IMPDEF PMU" */ + return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 4 && + FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; +} + +static inline bool isar_feature_aa32_pmuv3p4(const ARMISARegisters *id) +{ + /* 0xf means "non-standard IMPDEF PMU" */ + return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 5 && + FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; +} + +static inline bool isar_feature_aa32_pmuv3p5(const ARMISARegisters *id) +{ + /* 0xf means "non-standard IMPDEF PMU" */ + return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 6 && + FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; +} + +static inline bool isar_feature_aa32_hpd(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, HPDS) != 0; +} + +static inline bool isar_feature_aa32_ac2(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, AC2) != 0; +} + +static inline bool isar_feature_aa32_ccidx(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, CCIDX) != 0; +} + +static inline bool isar_feature_aa32_tts2uxn(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, XNX) != 0; +} + +static inline bool isar_feature_aa32_half_evt(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, EVT) >= 1; +} + +static inline bool isar_feature_aa32_evt(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, EVT) >= 2; +} + +static inline bool isar_feature_aa32_dit(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_pfr0, ID_PFR0, DIT) != 0; +} + +static inline bool isar_feature_aa32_ssbs(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_pfr2, ID_PFR2, SSBS) != 0; +} + +static inline bool isar_feature_aa32_debugv7p1(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_dfr0, ID_DFR0, COPDBG) >= 5; +} + +static inline bool isar_feature_aa32_debugv8p2(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_dfr0, ID_DFR0, COPDBG) >= 8; +} + +static inline bool isar_feature_aa32_doublelock(const ARMISARegisters *id) +{ + return FIELD_EX32(id->dbgdevid, DBGDEVID, DOUBLELOCK) > 0; +} + +/* + * 64-bit feature tests via id registers. + */ +static inline bool isar_feature_aa64_aes(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, AES) != 0; +} + +static inline bool isar_feature_aa64_pmull(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, AES) > 1; +} + +static inline bool isar_feature_aa64_sha1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA1) != 0; +} + +static inline bool isar_feature_aa64_sha256(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA2) != 0; +} + +static inline bool isar_feature_aa64_sha512(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA2) > 1; +} + +static inline bool isar_feature_aa64_crc32(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, CRC32) != 0; +} + +static inline bool isar_feature_aa64_atomics(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, ATOMIC) != 0; +} + +static inline bool isar_feature_aa64_rdm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, RDM) != 0; +} + +static inline bool isar_feature_aa64_sha3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA3) != 0; +} + +static inline bool isar_feature_aa64_sm3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SM3) != 0; +} + +static inline bool isar_feature_aa64_sm4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SM4) != 0; +} + +static inline bool isar_feature_aa64_dp(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, DP) != 0; +} + +static inline bool isar_feature_aa64_fhm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, FHM) != 0; +} + +static inline bool isar_feature_aa64_condm_4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TS) != 0; +} + +static inline bool isar_feature_aa64_condm_5(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TS) >= 2; +} + +static inline bool isar_feature_aa64_rndr(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, RNDR) != 0; +} + +static inline bool isar_feature_aa64_jscvt(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, JSCVT) != 0; +} + +static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; +} + +/* + * These are the values from APA/API/APA3. + * In general these must be compared '>=', per the normal Arm ARM + * treatment of fields in ID registers. + */ +typedef enum { + PauthFeat_None = 0, + PauthFeat_1 = 1, + PauthFeat_EPAC = 2, + PauthFeat_2 = 3, + PauthFeat_FPAC = 4, + PauthFeat_FPACCOMBINED = 5, +} ARMPauthFeature; + +static inline ARMPauthFeature +isar_feature_pauth_feature(const ARMISARegisters *id) +{ + /* + * Architecturally, only one of {APA,API,APA3} may be active (non-zero) + * and the other two must be zero. Thus we may avoid conditionals. + */ + return (FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, APA) | + FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, API) | + FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, APA3)); +} + +static inline bool isar_feature_aa64_pauth(const ARMISARegisters *id) +{ + /* + * Return true if any form of pauth is enabled, as this + * predicate controls migration of the 128-bit keys. + */ + return isar_feature_pauth_feature(id) != PauthFeat_None; +} + +static inline bool isar_feature_aa64_pauth_qarma5(const ARMISARegisters *id) +{ + /* + * Return true if pauth is enabled with the architected QARMA5 algorithm. + * QEMU will always enable or disable both APA and GPA. + */ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, APA) != 0; +} + +static inline bool isar_feature_aa64_pauth_qarma3(const ARMISARegisters *id) +{ + /* + * Return true if pauth is enabled with the architected QARMA3 algorithm. + * QEMU will always enable or disable both APA3 and GPA3. + */ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, APA3) != 0; +} + +static inline bool isar_feature_aa64_tlbirange(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) == 2; +} + +static inline bool isar_feature_aa64_tlbios(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) != 0; +} + +static inline bool isar_feature_aa64_sb(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SB) != 0; +} + +static inline bool isar_feature_aa64_predinv(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SPECRES) != 0; +} + +static inline bool isar_feature_aa64_frint(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FRINTTS) != 0; +} + +static inline bool isar_feature_aa64_dcpop(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, DPB) != 0; +} + +static inline bool isar_feature_aa64_dcpodp(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, DPB) >= 2; +} + +static inline bool isar_feature_aa64_bf16(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, BF16) != 0; +} + +static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id) +{ + /* We always set the AdvSIMD and FP fields identically. */ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) != 0xf; +} + +static inline bool isar_feature_aa64_fp16(const ARMISARegisters *id) +{ + /* We always set the AdvSIMD and FP fields identically wrt FP16. */ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) == 1; +} + +static inline bool isar_feature_aa64_aa32(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, EL0) >= 2; +} + +static inline bool isar_feature_aa64_aa32_el1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, EL1) >= 2; +} + +static inline bool isar_feature_aa64_aa32_el2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, EL2) >= 2; +} + +static inline bool isar_feature_aa64_ras(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RAS) != 0; +} + +static inline bool isar_feature_aa64_doublefault(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RAS) >= 2; +} + +static inline bool isar_feature_aa64_sve(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SVE) != 0; +} + +static inline bool isar_feature_aa64_sel2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SEL2) != 0; +} + +static inline bool isar_feature_aa64_rme(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RME) != 0; +} + +static inline bool isar_feature_aa64_vh(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, VH) != 0; +} + +static inline bool isar_feature_aa64_lor(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, LO) != 0; +} + +static inline bool isar_feature_aa64_pan(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) != 0; +} + +static inline bool isar_feature_aa64_ats1e1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) >= 2; +} + +static inline bool isar_feature_aa64_pan3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) >= 3; +} + +static inline bool isar_feature_aa64_hcx(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HCX) != 0; +} + +static inline bool isar_feature_aa64_tidcp1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR1, TIDCP1) != 0; +} + +static inline bool isar_feature_aa64_uao(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, UAO) != 0; +} + +static inline bool isar_feature_aa64_st(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, ST) != 0; +} + +static inline bool isar_feature_aa64_lse2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, AT) != 0; +} + +static inline bool isar_feature_aa64_fwb(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, FWB) != 0; +} + +static inline bool isar_feature_aa64_ids(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, IDS) != 0; +} + +static inline bool isar_feature_aa64_half_evt(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, EVT) >= 1; +} + +static inline bool isar_feature_aa64_evt(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, EVT) >= 2; +} + +static inline bool isar_feature_aa64_bti(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0; +} + +static inline bool isar_feature_aa64_mte_insn_reg(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) != 0; +} + +static inline bool isar_feature_aa64_mte(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) >= 2; +} + +static inline bool isar_feature_aa64_sme(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SME) != 0; +} + +static inline bool isar_feature_aa64_pmuv3p1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 4 && + FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; +} + +static inline bool isar_feature_aa64_pmuv3p4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 5 && + FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; +} + +static inline bool isar_feature_aa64_pmuv3p5(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 6 && + FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; +} + +static inline bool isar_feature_aa64_rcpc_8_3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) != 0; +} + +static inline bool isar_feature_aa64_rcpc_8_4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) >= 2; +} + +static inline bool isar_feature_aa64_i8mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 0; +} + +static inline bool isar_feature_aa64_hbc(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, BC) != 0; +} + +static inline bool isar_feature_aa64_tgran4_lpa2(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 1; +} + +static inline bool isar_feature_aa64_tgran4_2_lpa2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); + return t >= 3 || (t == 0 && isar_feature_aa64_tgran4_lpa2(id)); +} + +static inline bool isar_feature_aa64_tgran16_lpa2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 2; +} + +static inline bool isar_feature_aa64_tgran16_2_lpa2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); + return t >= 3 || (t == 0 && isar_feature_aa64_tgran16_lpa2(id)); +} + +static inline bool isar_feature_aa64_tgran4(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 0; +} + +static inline bool isar_feature_aa64_tgran16(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 1; +} + +static inline bool isar_feature_aa64_tgran64(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64) >= 0; +} + +static inline bool isar_feature_aa64_tgran4_2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); + return t >= 2 || (t == 0 && isar_feature_aa64_tgran4(id)); +} + +static inline bool isar_feature_aa64_tgran16_2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); + return t >= 2 || (t == 0 && isar_feature_aa64_tgran16(id)); +} + +static inline bool isar_feature_aa64_tgran64_2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64_2); + return t >= 2 || (t == 0 && isar_feature_aa64_tgran64(id)); +} + +static inline bool isar_feature_aa64_fgt(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, FGT) != 0; +} + +static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0; +} + +static inline bool isar_feature_aa64_lva(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, VARANGE) != 0; +} + +static inline bool isar_feature_aa64_e0pd(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, E0PD) != 0; +} + +static inline bool isar_feature_aa64_hafs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) != 0; +} + +static inline bool isar_feature_aa64_hdbs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) >= 2; +} + +static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0; +} + +static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; +} + +static inline bool isar_feature_aa64_scxtnum(const ARMISARegisters *id) +{ + int key = FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, CSV2); + if (key >= 2) { + return true; /* FEAT_CSV2_2 */ + } + if (key == 1) { + key = FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, CSV2_FRAC); + return key >= 2; /* FEAT_CSV2_1p2 */ + } + return false; +} + +static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0; +} + +static inline bool isar_feature_aa64_debugv8p2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, DEBUGVER) >= 8; +} + +static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SVEVER) != 0; +} + +static inline bool isar_feature_aa64_sve2_aes(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) != 0; +} + +static inline bool isar_feature_aa64_sve2_pmull128(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) >= 2; +} + +static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0; +} + +static inline bool isar_feature_aa64_sve_bf16(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BFLOAT16) != 0; +} + +static inline bool isar_feature_aa64_sve2_sha3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SHA3) != 0; +} + +static inline bool isar_feature_aa64_sve2_sm4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SM4) != 0; +} + +static inline bool isar_feature_aa64_sve_i8mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, I8MM) != 0; +} + +static inline bool isar_feature_aa64_sve_f32mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F32MM) != 0; +} + +static inline bool isar_feature_aa64_sve_f64mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F64MM) != 0; +} + +static inline bool isar_feature_aa64_sme_f64f64(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, F64F64); +} + +static inline bool isar_feature_aa64_sme_i16i64(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, I16I64) == 0xf; +} + +static inline bool isar_feature_aa64_sme_fa64(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, FA64); +} + +static inline bool isar_feature_aa64_doublelock(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64dfr0, ID_AA64DFR0, DOUBLELOCK) >= 0; +} + +static inline bool isar_feature_aa64_mops(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, MOPS); +} + +/* + * Feature tests for "does this exist in either 32-bit or 64-bit?" + */ +static inline bool isar_feature_any_fp16(const ARMISARegisters *id) +{ + return isar_feature_aa64_fp16(id) || isar_feature_aa32_fp16_arith(id); +} + +static inline bool isar_feature_any_predinv(const ARMISARegisters *id) +{ + return isar_feature_aa64_predinv(id) || isar_feature_aa32_predinv(id); +} + +static inline bool isar_feature_any_pmuv3p1(const ARMISARegisters *id) +{ + return isar_feature_aa64_pmuv3p1(id) || isar_feature_aa32_pmuv3p1(id); +} + +static inline bool isar_feature_any_pmuv3p4(const ARMISARegisters *id) +{ + return isar_feature_aa64_pmuv3p4(id) || isar_feature_aa32_pmuv3p4(id); +} + +static inline bool isar_feature_any_pmuv3p5(const ARMISARegisters *id) +{ + return isar_feature_aa64_pmuv3p5(id) || isar_feature_aa32_pmuv3p5(id); +} + +static inline bool isar_feature_any_ccidx(const ARMISARegisters *id) +{ + return isar_feature_aa64_ccidx(id) || isar_feature_aa32_ccidx(id); +} + +static inline bool isar_feature_any_tts2uxn(const ARMISARegisters *id) +{ + return isar_feature_aa64_tts2uxn(id) || isar_feature_aa32_tts2uxn(id); +} + +static inline bool isar_feature_any_debugv8p2(const ARMISARegisters *id) +{ + return isar_feature_aa64_debugv8p2(id) || isar_feature_aa32_debugv8p2(id); +} + +static inline bool isar_feature_any_ras(const ARMISARegisters *id) +{ + return isar_feature_aa64_ras(id) || isar_feature_aa32_ras(id); +} + +static inline bool isar_feature_any_half_evt(const ARMISARegisters *id) +{ + return isar_feature_aa64_half_evt(id) || isar_feature_aa32_half_evt(id); +} + +static inline bool isar_feature_any_evt(const ARMISARegisters *id) +{ + return isar_feature_aa64_evt(id) || isar_feature_aa32_evt(id); +} + +/* + * Forward to the above feature tests given an ARMCPU pointer. + */ +#define cpu_isar_feature(name, cpu) \ + ({ ARMCPU *cpu_ = (cpu); isar_feature_##name(&cpu_->isar); }) + +#endif diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline target_ulong cpu_untagged_addr(CPUState *cs, target_ulong x) } #endif -/* - * Naming convention for isar_feature functions: - * Functions which test 32-bit ID registers should have _aa32_ in - * their name. Functions which test 64-bit ID registers should have - * _aa64_ in their name. These must only be used in code where we - * know for certain that the CPU has AArch32 or AArch64 respectively - * or where the correct answer for a CPU which doesn't implement that - * CPU state is "false" (eg when generating A32 or A64 code, if adding - * system registers that are specific to that CPU state, for "should - * we let this system register bit be set" tests where the 32-bit - * flavour of the register doesn't have the bit, and so on). - * Functions which simply ask "does this feature exist at all" have - * _any_ in their name, and always return the logical OR of the _aa64_ - * and the _aa32_ function. - */ - -/* - * 32-bit feature tests via id registers. - */ -static inline bool isar_feature_aa32_thumb_div(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) != 0; -} - -static inline bool isar_feature_aa32_arm_div(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) > 1; -} - -static inline bool isar_feature_aa32_lob(const ARMISARegisters *id) -{ - /* (M-profile) low-overhead loops and branch future */ - return FIELD_EX32(id->id_isar0, ID_ISAR0, CMPBRANCH) >= 3; -} - -static inline bool isar_feature_aa32_jazelle(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar1, ID_ISAR1, JAZELLE) != 0; -} - -static inline bool isar_feature_aa32_aes(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) != 0; -} - -static inline bool isar_feature_aa32_pmull(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) > 1; -} - -static inline bool isar_feature_aa32_sha1(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, SHA1) != 0; -} - -static inline bool isar_feature_aa32_sha2(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, SHA2) != 0; -} - -static inline bool isar_feature_aa32_crc32(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, CRC32) != 0; -} - -static inline bool isar_feature_aa32_rdm(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, RDM) != 0; -} - -static inline bool isar_feature_aa32_vcma(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar5, ID_ISAR5, VCMA) != 0; -} - -static inline bool isar_feature_aa32_jscvt(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, JSCVT) != 0; -} - -static inline bool isar_feature_aa32_dp(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, DP) != 0; -} - -static inline bool isar_feature_aa32_fhm(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, FHM) != 0; -} - -static inline bool isar_feature_aa32_sb(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, SB) != 0; -} - -static inline bool isar_feature_aa32_predinv(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, SPECRES) != 0; -} - -static inline bool isar_feature_aa32_bf16(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, BF16) != 0; -} - -static inline bool isar_feature_aa32_i8mm(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_isar6, ID_ISAR6, I8MM) != 0; -} - -static inline bool isar_feature_aa32_ras(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_pfr0, ID_PFR0, RAS) != 0; -} - -static inline bool isar_feature_aa32_mprofile(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_pfr1, ID_PFR1, MPROGMOD) != 0; -} - -static inline bool isar_feature_aa32_m_sec_state(const ARMISARegisters *id) -{ - /* - * Return true if M-profile state handling insns - * (VSCCLRM, CLRM, FPCTX access insns) are implemented - */ - return FIELD_EX32(id->id_pfr1, ID_PFR1, SECURITY) >= 3; -} - -static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id) -{ - /* Sadly this is encoded differently for A-profile and M-profile */ - if (isar_feature_aa32_mprofile(id)) { - return FIELD_EX32(id->mvfr1, MVFR1, FP16) > 0; - } else { - return FIELD_EX32(id->mvfr1, MVFR1, FPHP) >= 3; - } -} - -static inline bool isar_feature_aa32_mve(const ARMISARegisters *id) -{ - /* - * Return true if MVE is supported (either integer or floating point). - * We must check for M-profile as the MVFR1 field means something - * else for A-profile. - */ - return isar_feature_aa32_mprofile(id) && - FIELD_EX32(id->mvfr1, MVFR1, MVE) > 0; -} - -static inline bool isar_feature_aa32_mve_fp(const ARMISARegisters *id) -{ - /* - * Return true if MVE is supported (either integer or floating point). - * We must check for M-profile as the MVFR1 field means something - * else for A-profile. - */ - return isar_feature_aa32_mprofile(id) && - FIELD_EX32(id->mvfr1, MVFR1, MVE) >= 2; -} - -static inline bool isar_feature_aa32_vfp_simd(const ARMISARegisters *id) -{ - /* - * Return true if either VFP or SIMD is implemented. - * In this case, a minimum of VFP w/ D0-D15. - */ - return FIELD_EX32(id->mvfr0, MVFR0, SIMDREG) > 0; -} - -static inline bool isar_feature_aa32_simd_r32(const ARMISARegisters *id) -{ - /* Return true if D16-D31 are implemented */ - return FIELD_EX32(id->mvfr0, MVFR0, SIMDREG) >= 2; -} - -static inline bool isar_feature_aa32_fpshvec(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr0, MVFR0, FPSHVEC) > 0; -} - -static inline bool isar_feature_aa32_fpsp_v2(const ARMISARegisters *id) -{ - /* Return true if CPU supports single precision floating point, VFPv2 */ - return FIELD_EX32(id->mvfr0, MVFR0, FPSP) > 0; -} - -static inline bool isar_feature_aa32_fpsp_v3(const ARMISARegisters *id) -{ - /* Return true if CPU supports single precision floating point, VFPv3 */ - return FIELD_EX32(id->mvfr0, MVFR0, FPSP) >= 2; -} - -static inline bool isar_feature_aa32_fpdp_v2(const ARMISARegisters *id) -{ - /* Return true if CPU supports double precision floating point, VFPv2 */ - return FIELD_EX32(id->mvfr0, MVFR0, FPDP) > 0; -} - -static inline bool isar_feature_aa32_fpdp_v3(const ARMISARegisters *id) -{ - /* Return true if CPU supports double precision floating point, VFPv3 */ - return FIELD_EX32(id->mvfr0, MVFR0, FPDP) >= 2; -} - -static inline bool isar_feature_aa32_vfp(const ARMISARegisters *id) -{ - return isar_feature_aa32_fpsp_v2(id) || isar_feature_aa32_fpdp_v2(id); -} - -/* - * We always set the FP and SIMD FP16 fields to indicate identical - * levels of support (assuming SIMD is implemented at all), so - * we only need one set of accessors. - */ -static inline bool isar_feature_aa32_fp16_spconv(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr1, MVFR1, FPHP) > 0; -} - -static inline bool isar_feature_aa32_fp16_dpconv(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr1, MVFR1, FPHP) > 1; -} - -/* - * Note that this ID register field covers both VFP and Neon FMAC, - * so should usually be tested in combination with some other - * check that confirms the presence of whichever of VFP or Neon is - * relevant, to avoid accidentally enabling a Neon feature on - * a VFP-no-Neon core or vice-versa. - */ -static inline bool isar_feature_aa32_simdfmac(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr1, MVFR1, SIMDFMAC) != 0; -} - -static inline bool isar_feature_aa32_vsel(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 1; -} - -static inline bool isar_feature_aa32_vcvt_dr(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 2; -} - -static inline bool isar_feature_aa32_vrint(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 3; -} - -static inline bool isar_feature_aa32_vminmaxnm(const ARMISARegisters *id) -{ - return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 4; -} - -static inline bool isar_feature_aa32_pxn(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr0, ID_MMFR0, VMSA) >= 4; -} - -static inline bool isar_feature_aa32_pan(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr3, ID_MMFR3, PAN) != 0; -} - -static inline bool isar_feature_aa32_ats1e1(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr3, ID_MMFR3, PAN) >= 2; -} - -static inline bool isar_feature_aa32_pmuv3p1(const ARMISARegisters *id) -{ - /* 0xf means "non-standard IMPDEF PMU" */ - return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 4 && - FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; -} - -static inline bool isar_feature_aa32_pmuv3p4(const ARMISARegisters *id) -{ - /* 0xf means "non-standard IMPDEF PMU" */ - return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 5 && - FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; -} - -static inline bool isar_feature_aa32_pmuv3p5(const ARMISARegisters *id) -{ - /* 0xf means "non-standard IMPDEF PMU" */ - return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 6 && - FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf; -} - -static inline bool isar_feature_aa32_hpd(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr4, ID_MMFR4, HPDS) != 0; -} - -static inline bool isar_feature_aa32_ac2(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr4, ID_MMFR4, AC2) != 0; -} - -static inline bool isar_feature_aa32_ccidx(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr4, ID_MMFR4, CCIDX) != 0; -} - -static inline bool isar_feature_aa32_tts2uxn(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr4, ID_MMFR4, XNX) != 0; -} - -static inline bool isar_feature_aa32_half_evt(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr4, ID_MMFR4, EVT) >= 1; -} - -static inline bool isar_feature_aa32_evt(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_mmfr4, ID_MMFR4, EVT) >= 2; -} - -static inline bool isar_feature_aa32_dit(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_pfr0, ID_PFR0, DIT) != 0; -} - -static inline bool isar_feature_aa32_ssbs(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_pfr2, ID_PFR2, SSBS) != 0; -} - -static inline bool isar_feature_aa32_debugv7p1(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_dfr0, ID_DFR0, COPDBG) >= 5; -} - -static inline bool isar_feature_aa32_debugv8p2(const ARMISARegisters *id) -{ - return FIELD_EX32(id->id_dfr0, ID_DFR0, COPDBG) >= 8; -} - -static inline bool isar_feature_aa32_doublelock(const ARMISARegisters *id) -{ - return FIELD_EX32(id->dbgdevid, DBGDEVID, DOUBLELOCK) > 0; -} - -/* - * 64-bit feature tests via id registers. - */ -static inline bool isar_feature_aa64_aes(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, AES) != 0; -} - -static inline bool isar_feature_aa64_pmull(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, AES) > 1; -} - -static inline bool isar_feature_aa64_sha1(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA1) != 0; -} - -static inline bool isar_feature_aa64_sha256(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA2) != 0; -} - -static inline bool isar_feature_aa64_sha512(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA2) > 1; -} - -static inline bool isar_feature_aa64_crc32(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, CRC32) != 0; -} - -static inline bool isar_feature_aa64_atomics(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, ATOMIC) != 0; -} - -static inline bool isar_feature_aa64_rdm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, RDM) != 0; -} - -static inline bool isar_feature_aa64_sha3(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA3) != 0; -} - -static inline bool isar_feature_aa64_sm3(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SM3) != 0; -} - -static inline bool isar_feature_aa64_sm4(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SM4) != 0; -} - -static inline bool isar_feature_aa64_dp(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, DP) != 0; -} - -static inline bool isar_feature_aa64_fhm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, FHM) != 0; -} - -static inline bool isar_feature_aa64_condm_4(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TS) != 0; -} - -static inline bool isar_feature_aa64_condm_5(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TS) >= 2; -} - -static inline bool isar_feature_aa64_rndr(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, RNDR) != 0; -} - -static inline bool isar_feature_aa64_jscvt(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, JSCVT) != 0; -} - -static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; -} - -/* - * These are the values from APA/API/APA3. - * In general these must be compared '>=', per the normal Arm ARM - * treatment of fields in ID registers. - */ -typedef enum { - PauthFeat_None = 0, - PauthFeat_1 = 1, - PauthFeat_EPAC = 2, - PauthFeat_2 = 3, - PauthFeat_FPAC = 4, - PauthFeat_FPACCOMBINED = 5, -} ARMPauthFeature; - -static inline ARMPauthFeature -isar_feature_pauth_feature(const ARMISARegisters *id) -{ - /* - * Architecturally, only one of {APA,API,APA3} may be active (non-zero) - * and the other two must be zero. Thus we may avoid conditionals. - */ - return (FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, APA) | - FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, API) | - FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, APA3)); -} - -static inline bool isar_feature_aa64_pauth(const ARMISARegisters *id) -{ - /* - * Return true if any form of pauth is enabled, as this - * predicate controls migration of the 128-bit keys. - */ - return isar_feature_pauth_feature(id) != PauthFeat_None; -} - -static inline bool isar_feature_aa64_pauth_qarma5(const ARMISARegisters *id) -{ - /* - * Return true if pauth is enabled with the architected QARMA5 algorithm. - * QEMU will always enable or disable both APA and GPA. - */ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, APA) != 0; -} - -static inline bool isar_feature_aa64_pauth_qarma3(const ARMISARegisters *id) -{ - /* - * Return true if pauth is enabled with the architected QARMA3 algorithm. - * QEMU will always enable or disable both APA3 and GPA3. - */ - return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, APA3) != 0; -} - -static inline bool isar_feature_aa64_tlbirange(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) == 2; -} - -static inline bool isar_feature_aa64_tlbios(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) != 0; -} - -static inline bool isar_feature_aa64_sb(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SB) != 0; -} - -static inline bool isar_feature_aa64_predinv(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SPECRES) != 0; -} - -static inline bool isar_feature_aa64_frint(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FRINTTS) != 0; -} - -static inline bool isar_feature_aa64_dcpop(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, DPB) != 0; -} - -static inline bool isar_feature_aa64_dcpodp(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, DPB) >= 2; -} - -static inline bool isar_feature_aa64_bf16(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, BF16) != 0; -} - -static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id) -{ - /* We always set the AdvSIMD and FP fields identically. */ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) != 0xf; -} - -static inline bool isar_feature_aa64_fp16(const ARMISARegisters *id) -{ - /* We always set the AdvSIMD and FP fields identically wrt FP16. */ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) == 1; -} - -static inline bool isar_feature_aa64_aa32(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, EL0) >= 2; -} - -static inline bool isar_feature_aa64_aa32_el1(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, EL1) >= 2; -} - -static inline bool isar_feature_aa64_aa32_el2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, EL2) >= 2; -} - -static inline bool isar_feature_aa64_ras(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RAS) != 0; -} - -static inline bool isar_feature_aa64_doublefault(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RAS) >= 2; -} - -static inline bool isar_feature_aa64_sve(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SVE) != 0; -} - -static inline bool isar_feature_aa64_sel2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SEL2) != 0; -} - -static inline bool isar_feature_aa64_rme(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RME) != 0; -} - -static inline bool isar_feature_aa64_vh(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, VH) != 0; -} - -static inline bool isar_feature_aa64_lor(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, LO) != 0; -} - -static inline bool isar_feature_aa64_pan(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) != 0; -} - -static inline bool isar_feature_aa64_ats1e1(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) >= 2; -} - -static inline bool isar_feature_aa64_pan3(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, PAN) >= 3; -} - -static inline bool isar_feature_aa64_hcx(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HCX) != 0; -} - -static inline bool isar_feature_aa64_tidcp1(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR1, TIDCP1) != 0; -} - -static inline bool isar_feature_aa64_uao(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, UAO) != 0; -} - -static inline bool isar_feature_aa64_st(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, ST) != 0; -} - -static inline bool isar_feature_aa64_lse2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, AT) != 0; -} - -static inline bool isar_feature_aa64_fwb(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, FWB) != 0; -} - -static inline bool isar_feature_aa64_ids(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, IDS) != 0; -} - -static inline bool isar_feature_aa64_half_evt(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, EVT) >= 1; -} - -static inline bool isar_feature_aa64_evt(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, EVT) >= 2; -} - -static inline bool isar_feature_aa64_bti(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0; -} - -static inline bool isar_feature_aa64_mte_insn_reg(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) != 0; -} - -static inline bool isar_feature_aa64_mte(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) >= 2; -} - -static inline bool isar_feature_aa64_sme(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SME) != 0; -} - -static inline bool isar_feature_aa64_pmuv3p1(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 4 && - FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; -} - -static inline bool isar_feature_aa64_pmuv3p4(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 5 && - FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; -} - -static inline bool isar_feature_aa64_pmuv3p5(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 6 && - FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; -} - -static inline bool isar_feature_aa64_rcpc_8_3(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) != 0; -} - -static inline bool isar_feature_aa64_rcpc_8_4(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) >= 2; -} - -static inline bool isar_feature_aa64_i8mm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 0; -} - -static inline bool isar_feature_aa64_hbc(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, BC) != 0; -} - -static inline bool isar_feature_aa64_tgran4_lpa2(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 1; -} - -static inline bool isar_feature_aa64_tgran4_2_lpa2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); - return t >= 3 || (t == 0 && isar_feature_aa64_tgran4_lpa2(id)); -} - -static inline bool isar_feature_aa64_tgran16_lpa2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 2; -} - -static inline bool isar_feature_aa64_tgran16_2_lpa2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); - return t >= 3 || (t == 0 && isar_feature_aa64_tgran16_lpa2(id)); -} - -static inline bool isar_feature_aa64_tgran4(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 0; -} - -static inline bool isar_feature_aa64_tgran16(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 1; -} - -static inline bool isar_feature_aa64_tgran64(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64) >= 0; -} - -static inline bool isar_feature_aa64_tgran4_2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); - return t >= 2 || (t == 0 && isar_feature_aa64_tgran4(id)); -} - -static inline bool isar_feature_aa64_tgran16_2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); - return t >= 2 || (t == 0 && isar_feature_aa64_tgran16(id)); -} - -static inline bool isar_feature_aa64_tgran64_2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64_2); - return t >= 2 || (t == 0 && isar_feature_aa64_tgran64(id)); -} - -static inline bool isar_feature_aa64_fgt(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, FGT) != 0; -} - -static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0; -} - -static inline bool isar_feature_aa64_lva(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, VARANGE) != 0; -} - -static inline bool isar_feature_aa64_e0pd(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, E0PD) != 0; -} - -static inline bool isar_feature_aa64_hafs(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) != 0; -} - -static inline bool isar_feature_aa64_hdbs(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) >= 2; -} - -static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0; -} - -static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; -} - -static inline bool isar_feature_aa64_scxtnum(const ARMISARegisters *id) -{ - int key = FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, CSV2); - if (key >= 2) { - return true; /* FEAT_CSV2_2 */ - } - if (key == 1) { - key = FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, CSV2_FRAC); - return key >= 2; /* FEAT_CSV2_1p2 */ - } - return false; -} - -static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0; -} - -static inline bool isar_feature_aa64_debugv8p2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, DEBUGVER) >= 8; -} - -static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SVEVER) != 0; -} - -static inline bool isar_feature_aa64_sve2_aes(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) != 0; -} - -static inline bool isar_feature_aa64_sve2_pmull128(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, AES) >= 2; -} - -static inline bool isar_feature_aa64_sve2_bitperm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BITPERM) != 0; -} - -static inline bool isar_feature_aa64_sve_bf16(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, BFLOAT16) != 0; -} - -static inline bool isar_feature_aa64_sve2_sha3(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SHA3) != 0; -} - -static inline bool isar_feature_aa64_sve2_sm4(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SM4) != 0; -} - -static inline bool isar_feature_aa64_sve_i8mm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, I8MM) != 0; -} - -static inline bool isar_feature_aa64_sve_f32mm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F32MM) != 0; -} - -static inline bool isar_feature_aa64_sve_f64mm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, F64MM) != 0; -} - -static inline bool isar_feature_aa64_sme_f64f64(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, F64F64); -} - -static inline bool isar_feature_aa64_sme_i16i64(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, I16I64) == 0xf; -} - -static inline bool isar_feature_aa64_sme_fa64(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, FA64); -} - -static inline bool isar_feature_aa64_doublelock(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64dfr0, ID_AA64DFR0, DOUBLELOCK) >= 0; -} - -static inline bool isar_feature_aa64_mops(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, MOPS); -} - -/* - * Feature tests for "does this exist in either 32-bit or 64-bit?" - */ -static inline bool isar_feature_any_fp16(const ARMISARegisters *id) -{ - return isar_feature_aa64_fp16(id) || isar_feature_aa32_fp16_arith(id); -} - -static inline bool isar_feature_any_predinv(const ARMISARegisters *id) -{ - return isar_feature_aa64_predinv(id) || isar_feature_aa32_predinv(id); -} - -static inline bool isar_feature_any_pmuv3p1(const ARMISARegisters *id) -{ - return isar_feature_aa64_pmuv3p1(id) || isar_feature_aa32_pmuv3p1(id); -} - -static inline bool isar_feature_any_pmuv3p4(const ARMISARegisters *id) -{ - return isar_feature_aa64_pmuv3p4(id) || isar_feature_aa32_pmuv3p4(id); -} - -static inline bool isar_feature_any_pmuv3p5(const ARMISARegisters *id) -{ - return isar_feature_aa64_pmuv3p5(id) || isar_feature_aa32_pmuv3p5(id); -} - -static inline bool isar_feature_any_ccidx(const ARMISARegisters *id) -{ - return isar_feature_aa64_ccidx(id) || isar_feature_aa32_ccidx(id); -} - -static inline bool isar_feature_any_tts2uxn(const ARMISARegisters *id) -{ - return isar_feature_aa64_tts2uxn(id) || isar_feature_aa32_tts2uxn(id); -} - -static inline bool isar_feature_any_debugv8p2(const ARMISARegisters *id) -{ - return isar_feature_aa64_debugv8p2(id) || isar_feature_aa32_debugv8p2(id); -} - -static inline bool isar_feature_any_ras(const ARMISARegisters *id) -{ - return isar_feature_aa64_ras(id) || isar_feature_aa32_ras(id); -} - -static inline bool isar_feature_any_half_evt(const ARMISARegisters *id) -{ - return isar_feature_aa64_half_evt(id) || isar_feature_aa32_half_evt(id); -} - -static inline bool isar_feature_any_evt(const ARMISARegisters *id) -{ - return isar_feature_aa64_evt(id) || isar_feature_aa32_evt(id); -} - -/* - * Forward to the above feature tests given an ARMCPU pointer. - */ -#define cpu_isar_feature(name, cpu) \ - ({ ARMCPU *cpu_ = (cpu); isar_feature_##name(&cpu_->isar); }) - #endif diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ #include "hw/registerfields.h" #include "tcg/tcg-gvec-desc.h" #include "syndrome.h" +#include "cpu-features.h" /* register banks for CPU modes */ #define BANK_USRSYS 0 diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ #include "exec/translator.h" #include "exec/helper-gen.h" #include "internals.h" - +#include "cpu-features.h" /* internal defines */ diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ #include "qemu/module.h" #include "qemu/log.h" #include "target/arm/idau.h" +#include "target/arm/cpu-features.h" #include "migration/vmstate.h" /* Bitbanded IO. Each word corresponds to a single bit. */ diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/tcg.h" #include "sysemu/runstate.h" #include "target/arm/cpu.h" +#include "target/arm/cpu-features.h" #include "exec/exec-all.h" #include "exec/memop.h" #include "qemu/log.h" diff --git a/linux-user/aarch64/cpu_loop.c b/linux-user/aarch64/cpu_loop.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/cpu_loop.c +++ b/linux-user/aarch64/cpu_loop.c @@ -XXX,XX +XXX,XX @@ #include "qemu/guest-random.h" #include "semihosting/common-semi.h" #include "target/arm/syndrome.h" +#include "target/arm/cpu-features.h" #define get_user_code_u32(x, gaddr, env) \ ({ abi_long __r = get_user_u32((x), (gaddr)); \ diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ #include "user-internals.h" #include "signal-common.h" #include "linux-user/trace.h" +#include "target/arm/cpu-features.h" struct target_sigcontext { uint64_t fault_address; diff --git a/linux-user/arm/signal.c b/linux-user/arm/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/arm/signal.c +++ b/linux-user/arm/signal.c @@ -XXX,XX +XXX,XX @@ #include "user-internals.h" #include "signal-common.h" #include "linux-user/trace.h" +#include "target/arm/cpu-features.h" struct target_sigcontext { abi_ulong trap_no; diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ #include "target_signal.h" #include "accel/tcg/debuginfo.h" +#ifdef TARGET_ARM +#include "target/arm/cpu-features.h" +#endif + #ifdef _ARCH_PPC64 #undef ARCH_DLINFO #undef ELF_PLATFORM diff --git a/linux-user/mmap.c b/linux-user/mmap.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/mmap.c +++ b/linux-user/mmap.c @@ -XXX,XX +XXX,XX @@ #include "target_mman.h" #include "qemu/interval-tree.h" +#ifdef TARGET_ARM +#include "target/arm/cpu-features.h" +#endif + static pthread_mutex_t mmap_mutex = PTHREAD_MUTEX_INITIALIZER; static __thread int mmap_lock_count; diff --git a/target/arm/arch_dump.c b/target/arm/arch_dump.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/arch_dump.c +++ b/target/arm/arch_dump.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "elf.h" #include "sysemu/dump.h" +#include "cpu-features.h" /* struct user_pt_regs from arch/arm64/include/uapi/asm/ptrace.h */ struct aarch64_user_regs { diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ #include "hw/core/tcg-cpu-ops.h" #endif /* CONFIG_TCG */ #include "internals.h" +#include "cpu-features.h" #include "exec/exec-all.h" #include "hw/qdev-properties.h" #if !defined(CONFIG_USER_ONLY) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ #include "qapi/visitor.h" #include "hw/qdev-properties.h" #include "internals.h" +#include "cpu-features.h" #include "cpregs.h" void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/debug_helper.c +++ b/target/arm/debug_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/log.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "cpregs.h" #include "exec/exec-all.h" #include "exec/helper-proto.h" diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub.c +++ b/target/arm/gdbstub.c @@ -XXX,XX +XXX,XX @@ #include "gdbstub/helpers.h" #include "sysemu/tcg.h" #include "internals.h" +#include "cpu-features.h" #include "cpregs.h" typedef struct RegisterSysregXmlParam { diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ #include "trace.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "exec/helper-proto.h" #include "qemu/main-loop.h" #include "qemu/timer.h" diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/kvm_int.h" #include "kvm_arm.h" #include "internals.h" +#include "cpu-features.h" #include "hw/acpi/acpi.h" #include "hw/acpi/ghes.h" diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/tcg.h" #include "kvm_arm.h" #include "internals.h" +#include "cpu-features.h" #include "migration/cpu.h" static bool vfp_needed(void *opaque) diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ #include "exec/exec-all.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "idau.h" #ifdef CONFIG_TCG # include "tcg/oversized-guest.h" diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties.h" #include "qemu/units.h" #include "internals.h" +#include "cpu-features.h" #include "cpregs.h" static uint64_t make_ccsidr64(unsigned assoc, unsigned linesize, diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/hflags.c +++ b/target/arm/tcg/hflags.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "exec/helper-proto.h" #include "cpregs.h" diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "gdbstub/helpers.h" #include "exec/helper-proto.h" #include "qemu/main-loop.h" diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/op_helper.c +++ b/target/arm/tcg/op_helper.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "exec/helper-proto.h" #include "internals.h" +#include "cpu-features.h" #include "exec/exec-all.h" #include "exec/cpu_ldst.h" #include "cpregs.h" diff --git a/target/arm/tcg/pauth_helper.c b/target/arm/tcg/pauth_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/pauth_helper.c +++ b/target/arm/tcg/pauth_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "exec/exec-all.h" #include "exec/cpu_ldst.h" #include "exec/helper-proto.h" diff --git a/target/arm/tcg/tlb_helper.c b/target/arm/tcg/tlb_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/tlb_helper.c +++ b/target/arm/tcg/tlb_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" #include "internals.h" +#include "cpu-features.h" #include "exec/exec-all.h" #include "exec/helper-proto.h" diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "exec/helper-proto.h" #include "internals.h" +#include "cpu-features.h" #ifdef CONFIG_TCG #include "qemu/log.h" #include "fpu/softfloat.h" -- 2.34.1 Our list of isar_feature functions is not in any particular order, but tests on fields of the same ID register tend to be grouped together. A few functions that are tests of fields in ID_AA64MMFR1 and ID_AA64MMFR2 are not in the same place as the rest; move them into their groups. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024163510.2972081-3-peter.maydell@linaro.org --- target/arm/cpu-features.h | 60 +++++++++++++++++++-------------------- 1 file changed, 30 insertions(+), 30 deletions(-) diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_tidcp1(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR1, TIDCP1) != 0; } +static inline bool isar_feature_aa64_hafs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) != 0; +} + +static inline bool isar_feature_aa64_hdbs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) >= 2; +} + +static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0; +} + static inline bool isar_feature_aa64_uao(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, UAO) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_evt(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, EVT) >= 2; } +static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0; +} + +static inline bool isar_feature_aa64_lva(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, VARANGE) != 0; +} + +static inline bool isar_feature_aa64_e0pd(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, E0PD) != 0; +} + static inline bool isar_feature_aa64_bti(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_fgt(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, FGT) != 0; } -static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0; -} - -static inline bool isar_feature_aa64_lva(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, VARANGE) != 0; -} - -static inline bool isar_feature_aa64_e0pd(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, E0PD) != 0; -} - -static inline bool isar_feature_aa64_hafs(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) != 0; -} - -static inline bool isar_feature_aa64_hdbs(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, HAFDBS) >= 2; -} - -static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0; -} - static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; -- 2.34.1 Move the ID_AA64MMFR0 feature test functions up so they are before the ones for ID_AA64MMFR1 and ID_AA64MMFR2. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024163510.2972081-4-peter.maydell@linaro.org --- target/arm/cpu-features.h | 120 +++++++++++++++++++------------------- 1 file changed, 60 insertions(+), 60 deletions(-) diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_rme(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RME) != 0; } +static inline bool isar_feature_aa64_tgran4_lpa2(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 1; +} + +static inline bool isar_feature_aa64_tgran4_2_lpa2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); + return t >= 3 || (t == 0 && isar_feature_aa64_tgran4_lpa2(id)); +} + +static inline bool isar_feature_aa64_tgran16_lpa2(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 2; +} + +static inline bool isar_feature_aa64_tgran16_2_lpa2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); + return t >= 3 || (t == 0 && isar_feature_aa64_tgran16_lpa2(id)); +} + +static inline bool isar_feature_aa64_tgran4(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 0; +} + +static inline bool isar_feature_aa64_tgran16(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 1; +} + +static inline bool isar_feature_aa64_tgran64(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64) >= 0; +} + +static inline bool isar_feature_aa64_tgran4_2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); + return t >= 2 || (t == 0 && isar_feature_aa64_tgran4(id)); +} + +static inline bool isar_feature_aa64_tgran16_2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); + return t >= 2 || (t == 0 && isar_feature_aa64_tgran16(id)); +} + +static inline bool isar_feature_aa64_tgran64_2(const ARMISARegisters *id) +{ + unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64_2); + return t >= 2 || (t == 0 && isar_feature_aa64_tgran64(id)); +} + +static inline bool isar_feature_aa64_fgt(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, FGT) != 0; +} + static inline bool isar_feature_aa64_vh(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, VH) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_hbc(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, BC) != 0; } -static inline bool isar_feature_aa64_tgran4_lpa2(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 1; -} - -static inline bool isar_feature_aa64_tgran4_2_lpa2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); - return t >= 3 || (t == 0 && isar_feature_aa64_tgran4_lpa2(id)); -} - -static inline bool isar_feature_aa64_tgran16_lpa2(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 2; -} - -static inline bool isar_feature_aa64_tgran16_2_lpa2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); - return t >= 3 || (t == 0 && isar_feature_aa64_tgran16_lpa2(id)); -} - -static inline bool isar_feature_aa64_tgran4(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 0; -} - -static inline bool isar_feature_aa64_tgran16(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16) >= 1; -} - -static inline bool isar_feature_aa64_tgran64(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64) >= 0; -} - -static inline bool isar_feature_aa64_tgran4_2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4_2); - return t >= 2 || (t == 0 && isar_feature_aa64_tgran4(id)); -} - -static inline bool isar_feature_aa64_tgran16_2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN16_2); - return t >= 2 || (t == 0 && isar_feature_aa64_tgran16(id)); -} - -static inline bool isar_feature_aa64_tgran64_2(const ARMISARegisters *id) -{ - unsigned t = FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN64_2); - return t >= 2 || (t == 0 && isar_feature_aa64_tgran64(id)); -} - -static inline bool isar_feature_aa64_fgt(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64mmfr0, ID_AA64MMFR0, FGT) != 0; -} - static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; -- 2.34.1 Move the feature test functions that test ID_AA64ISAR* fields together. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024163510.2972081-5-peter.maydell@linaro.org --- target/arm/cpu-features.h | 70 +++++++++++++++++++-------------------- 1 file changed, 35 insertions(+), 35 deletions(-) diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_rndr(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, RNDR) != 0; } +static inline bool isar_feature_aa64_tlbirange(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) == 2; +} + +static inline bool isar_feature_aa64_tlbios(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) != 0; +} + static inline bool isar_feature_aa64_jscvt(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, JSCVT) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_pauth_qarma3(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, APA3) != 0; } -static inline bool isar_feature_aa64_tlbirange(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) == 2; -} - -static inline bool isar_feature_aa64_tlbios(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, TLB) != 0; -} - static inline bool isar_feature_aa64_sb(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, SB) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_bf16(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, BF16) != 0; } +static inline bool isar_feature_aa64_rcpc_8_3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) != 0; +} + +static inline bool isar_feature_aa64_rcpc_8_4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) >= 2; +} + +static inline bool isar_feature_aa64_i8mm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 0; +} + +static inline bool isar_feature_aa64_hbc(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, BC) != 0; +} + +static inline bool isar_feature_aa64_mops(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, MOPS); +} + static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id) { /* We always set the AdvSIMD and FP fields identically. */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_pmuv3p5(const ARMISARegisters *id) FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; } -static inline bool isar_feature_aa64_rcpc_8_3(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) != 0; -} - -static inline bool isar_feature_aa64_rcpc_8_4(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) >= 2; -} - -static inline bool isar_feature_aa64_i8mm(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, I8MM) != 0; -} - -static inline bool isar_feature_aa64_hbc(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, BC) != 0; -} - static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_doublelock(const ARMISARegisters *id) return FIELD_SEX64(id->id_aa64dfr0, ID_AA64DFR0, DOUBLELOCK) >= 0; } -static inline bool isar_feature_aa64_mops(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64isar2, ID_AA64ISAR2, MOPS); -} - /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ -- 2.34.1 Move all the ID_AA64PFR* feature test functions together. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024163510.2972081-6-peter.maydell@linaro.org --- target/arm/cpu-features.h | 86 +++++++++++++++++++-------------------- 1 file changed, 43 insertions(+), 43 deletions(-) diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_rme(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, RME) != 0; } +static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; +} + +static inline bool isar_feature_aa64_scxtnum(const ARMISARegisters *id) +{ + int key = FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, CSV2); + if (key >= 2) { + return true; /* FEAT_CSV2_2 */ + } + if (key == 1) { + key = FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, CSV2_FRAC); + return key >= 2; /* FEAT_CSV2_1p2 */ + } + return false; +} + +static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0; +} + +static inline bool isar_feature_aa64_bti(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0; +} + +static inline bool isar_feature_aa64_mte_insn_reg(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) != 0; +} + +static inline bool isar_feature_aa64_mte(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) >= 2; +} + +static inline bool isar_feature_aa64_sme(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SME) != 0; +} + static inline bool isar_feature_aa64_tgran4_lpa2(const ARMISARegisters *id) { return FIELD_SEX64(id->id_aa64mmfr0, ID_AA64MMFR0, TGRAN4) >= 1; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_e0pd(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, E0PD) != 0; } -static inline bool isar_feature_aa64_bti(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, BT) != 0; -} - -static inline bool isar_feature_aa64_mte_insn_reg(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) != 0; -} - -static inline bool isar_feature_aa64_mte(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, MTE) >= 2; -} - -static inline bool isar_feature_aa64_sme(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SME) != 0; -} - static inline bool isar_feature_aa64_pmuv3p1(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 4 && @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_pmuv3p5(const ARMISARegisters *id) FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; } -static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; -} - -static inline bool isar_feature_aa64_scxtnum(const ARMISARegisters *id) -{ - int key = FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, CSV2); - if (key >= 2) { - return true; /* FEAT_CSV2_2 */ - } - if (key == 1) { - key = FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, CSV2_FRAC); - return key >= 2; /* FEAT_CSV2_1p2 */ - } - return false; -} - -static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id) -{ - return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0; -} - static inline bool isar_feature_aa64_debugv8p2(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, DEBUGVER) >= 8; -- 2.34.1 Move all the ID_AA64DFR* feature test functions together. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024163510.2972081-7-peter.maydell@linaro.org --- target/arm/cpu-features.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_debugv8p2(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, DEBUGVER) >= 8; } +static inline bool isar_feature_aa64_doublelock(const ARMISARegisters *id) +{ + return FIELD_SEX64(id->id_aa64dfr0, ID_AA64DFR0, DOUBLELOCK) >= 0; +} + static inline bool isar_feature_aa64_sve2(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64zfr0, ID_AA64ZFR0, SVEVER) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_sme_fa64(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64smfr0, ID_AA64SMFR0, FA64); } -static inline bool isar_feature_aa64_doublelock(const ARMISARegisters *id) -{ - return FIELD_SEX64(id->id_aa64dfr0, ID_AA64DFR0, DOUBLELOCK) >= 0; -} - /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ -- 2.34.1 In commit 442c9d682c94fc2 when we converted the ERET, ERETAA, ERETAB instructions to decodetree, the conversion accidentally lost the correct setting of the syndrome register when taking a trap because of the FEAT_FGT HFGITR_EL1.ERET bit. Instead of reporting a correct full syndrome value with the EC and IL bits, we only reported the low two bits of the syndrome, because the call to syn_erettrap() got dropped. Fix the syndrome values for these traps by reinstating the syn_erettrap() calls. Fixes: 442c9d682c94fc2 ("target/arm: Convert ERET, ERETAA, ERETAB to decodetree") Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231024172438.2990945-1-peter.maydell@linaro.org --- target/arm/tcg/translate-a64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_ERET(DisasContext *s, arg_ERET *a) return false; } if (s->fgt_eret) { - gen_exception_insn_el(s, 0, EXCP_UDEF, 0, 2); + gen_exception_insn_el(s, 0, EXCP_UDEF, syn_erettrap(0), 2); return true; } dst = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static bool trans_ERETA(DisasContext *s, arg_reta *a) } /* The FGT trap takes precedence over an auth trap. */ if (s->fgt_eret) { - gen_exception_insn_el(s, 0, EXCP_UDEF, a->m ? 3 : 2, 2); + gen_exception_insn_el(s, 0, EXCP_UDEF, syn_erettrap(a->m ? 3 : 2), 2); return true; } dst = tcg_temp_new_i64(); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-a10.h | 1 - hw/arm/cubieboard.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #ifndef HW_ARM_ALLWINNER_A10_H #define HW_ARM_ALLWINNER_A10_H -#include "hw/arm/boot.h" #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/allwinner-a10-pic.h" #include "hw/net/allwinner_emac.h" diff --git a/hw/arm/cubieboard.c b/hw/arm/cubieboard.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/cubieboard.c +++ b/hw/arm/cubieboard.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/qdev-properties.h" #include "hw/arm/allwinner-a10.h" +#include "hw/arm/boot.h" #include "hw/i2c/i2c.h" static struct arm_boot_info cubieboard_binfo = { -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-h3.h | 1 - hw/arm/orangepi.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #define HW_ARM_ALLWINNER_H3_H #include "qom/object.h" -#include "hw/arm/boot.h" #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/arm_gic.h" #include "hw/misc/allwinner-h3-ccu.h" diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/qdev-properties.h" #include "hw/arm/allwinner-h3.h" +#include "hw/arm/boot.h" static struct arm_boot_info orangepi_binfo; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-r40.h | 1 - hw/arm/bananapi_m2u.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/allwinner-r40.h b/include/hw/arm/allwinner-r40.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-r40.h +++ b/include/hw/arm/allwinner-r40.h @@ -XXX,XX +XXX,XX @@ #define HW_ARM_ALLWINNER_R40_H #include "qom/object.h" -#include "hw/arm/boot.h" #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/arm_gic.h" #include "hw/sd/allwinner-sdhost.h" diff --git a/hw/arm/bananapi_m2u.c b/hw/arm/bananapi_m2u.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bananapi_m2u.c +++ b/hw/arm/bananapi_m2u.c @@ -XXX,XX +XXX,XX @@ #include "hw/i2c/i2c.h" #include "hw/qdev-properties.h" #include "hw/arm/allwinner-r40.h" +#include "hw/arm/boot.h" static struct arm_boot_info bpim2u_binfo; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx25.h | 1 - hw/arm/imx25_pdk.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/fsl-imx25.h b/include/hw/arm/fsl-imx25.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx25.h +++ b/include/hw/arm/fsl-imx25.h @@ -XXX,XX +XXX,XX @@ #ifndef FSL_IMX25_H #define FSL_IMX25_H -#include "hw/arm/boot.h" #include "hw/intc/imx_avic.h" #include "hw/misc/imx25_ccm.h" #include "hw/char/imx_serial.h" diff --git a/hw/arm/imx25_pdk.c b/hw/arm/imx25_pdk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/imx25_pdk.c +++ b/hw/arm/imx25_pdk.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "hw/qdev-properties.h" #include "hw/arm/fsl-imx25.h" +#include "hw/arm/boot.h" #include "hw/boards.h" #include "qemu/error-report.h" #include "sysemu/qtest.h" -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-6-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx31.h | 1 - hw/arm/kzm.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/fsl-imx31.h b/include/hw/arm/fsl-imx31.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx31.h +++ b/include/hw/arm/fsl-imx31.h @@ -XXX,XX +XXX,XX @@ #ifndef FSL_IMX31_H #define FSL_IMX31_H -#include "hw/arm/boot.h" #include "hw/intc/imx_avic.h" #include "hw/misc/imx31_ccm.h" #include "hw/char/imx_serial.h" diff --git a/hw/arm/kzm.c b/hw/arm/kzm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/kzm.c +++ b/hw/arm/kzm.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/arm/fsl-imx31.h" +#include "hw/arm/boot.h" #include "hw/boards.h" #include "qemu/error-report.h" #include "exec/address-spaces.h" -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-7-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx6.h | 1 - hw/arm/sabrelite.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/fsl-imx6.h b/include/hw/arm/fsl-imx6.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx6.h +++ b/include/hw/arm/fsl-imx6.h @@ -XXX,XX +XXX,XX @@ #ifndef FSL_IMX6_H #define FSL_IMX6_H -#include "hw/arm/boot.h" #include "hw/cpu/a9mpcore.h" #include "hw/misc/imx6_ccm.h" #include "hw/misc/imx6_src.h" diff --git a/hw/arm/sabrelite.c b/hw/arm/sabrelite.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sabrelite.c +++ b/hw/arm/sabrelite.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/arm/fsl-imx6.h" +#include "hw/arm/boot.h" #include "hw/boards.h" #include "hw/qdev-properties.h" #include "qemu/error-report.h" -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-8-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx6ul.h | 1 - hw/arm/mcimx6ul-evk.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/fsl-imx6ul.h b/include/hw/arm/fsl-imx6ul.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx6ul.h +++ b/include/hw/arm/fsl-imx6ul.h @@ -XXX,XX +XXX,XX @@ #ifndef FSL_IMX6UL_H #define FSL_IMX6UL_H -#include "hw/arm/boot.h" #include "hw/cpu/a15mpcore.h" #include "hw/misc/imx6ul_ccm.h" #include "hw/misc/imx6_src.h" diff --git a/hw/arm/mcimx6ul-evk.c b/hw/arm/mcimx6ul-evk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mcimx6ul-evk.c +++ b/hw/arm/mcimx6ul-evk.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/arm/fsl-imx6ul.h" +#include "hw/arm/boot.h" #include "hw/boards.h" #include "hw/qdev-properties.h" #include "qemu/error-report.h" -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-9-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx7.h | 1 - hw/arm/mcimx7d-sabre.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx7.h +++ b/include/hw/arm/fsl-imx7.h @@ -XXX,XX +XXX,XX @@ #ifndef FSL_IMX7_H #define FSL_IMX7_H -#include "hw/arm/boot.h" #include "hw/cpu/a15mpcore.h" #include "hw/intc/imx_gpcv2.h" #include "hw/misc/imx7_ccm.h" diff --git a/hw/arm/mcimx7d-sabre.c b/hw/arm/mcimx7d-sabre.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mcimx7d-sabre.c +++ b/hw/arm/mcimx7d-sabre.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/arm/fsl-imx7.h" +#include "hw/arm/boot.h" #include "hw/boards.h" #include "hw/qdev-properties.h" #include "qemu/error-report.h" -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-10-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 1 - hw/arm/xlnx-versal-virt.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ #define XLNX_VERSAL_H #include "hw/sysbus.h" -#include "hw/arm/boot.h" #include "hw/cpu/cluster.h" #include "hw/or-irq.h" #include "hw/sd/sdhci.h" diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "hw/qdev-properties.h" #include "hw/arm/xlnx-versal.h" +#include "hw/arm/boot.h" #include "qom/object.h" #define TYPE_XLNX_VERSAL_VIRT_MACHINE MACHINE_TYPE_NAME("xlnx-versal-virt") -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> "hw/arm/boot.h" is only required on the source file. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Luc Michel <luc.michel@amd.com> Message-id: 20231025065316.56817-11-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-zynqmp.h | 1 - hw/arm/xlnx-zcu102.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/arm/xlnx-zynqmp.h b/include/hw/arm/xlnx-zynqmp.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-zynqmp.h +++ b/include/hw/arm/xlnx-zynqmp.h @@ -XXX,XX +XXX,XX @@ #ifndef XLNX_ZYNQMP_H #define XLNX_ZYNQMP_H -#include "hw/arm/boot.h" #include "hw/intc/arm_gic.h" #include "hw/net/cadence_gem.h" #include "hw/char/cadence_uart.h" diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/arm/xlnx-zynqmp.h" +#include "hw/arm/boot.h" #include "hw/boards.h" #include "qemu/error-report.h" #include "qemu/log.h" -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> sysbus_mmio_map() and sysbus_connect_irq() should not be called on unrealized device. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231020130331.50048-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/pxa2xx_mmci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/sd/pxa2xx_mmci.c b/hw/sd/pxa2xx_mmci.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/pxa2xx_mmci.c +++ b/hw/sd/pxa2xx_mmci.c @@ -XXX,XX +XXX,XX @@ PXA2xxMMCIState *pxa2xx_mmci_init(MemoryRegion *sysmem, dev = qdev_new(TYPE_PXA2XX_MMCI); sbd = SYS_BUS_DEVICE(dev); + sysbus_realize_and_unref(sbd, &error_fatal); sysbus_mmio_map(sbd, 0, base); sysbus_connect_irq(sbd, 0, irq); qdev_connect_gpio_out_named(dev, "rx-dma", 0, rx_dma); qdev_connect_gpio_out_named(dev, "tx-dma", 0, tx_dma); - sysbus_realize_and_unref(sbd, &error_fatal); return PXA2XX_MMCI(dev); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231020130331.50048-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/pxa2xx_mmci.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/hw/sd/pxa2xx_mmci.c b/hw/sd/pxa2xx_mmci.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/pxa2xx_mmci.c +++ b/hw/sd/pxa2xx_mmci.c @@ -XXX,XX +XXX,XX @@ PXA2xxMMCIState *pxa2xx_mmci_init(MemoryRegion *sysmem, qemu_irq irq, qemu_irq rx_dma, qemu_irq tx_dma) { DeviceState *dev; - SysBusDevice *sbd; - dev = qdev_new(TYPE_PXA2XX_MMCI); - sbd = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(sbd, &error_fatal); - sysbus_mmio_map(sbd, 0, base); - sysbus_connect_irq(sbd, 0, irq); + dev = sysbus_create_simple(TYPE_PXA2XX_MMCI, base, irq); qdev_connect_gpio_out_named(dev, "rx-dma", 0, rx_dma); qdev_connect_gpio_out_named(dev, "tx-dma", 0, tx_dma); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> sysbus_mmio_map() should not be called on unrealized device. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231020130331.50048-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/pcmcia/pxa2xx.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/hw/pcmcia/pxa2xx.c b/hw/pcmcia/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pcmcia/pxa2xx.c +++ b/hw/pcmcia/pxa2xx.c @@ -XXX,XX +XXX,XX @@ PXA2xxPCMCIAState *pxa2xx_pcmcia_init(MemoryRegion *sysmem, hwaddr base) { DeviceState *dev; - PXA2xxPCMCIAState *s; dev = qdev_new(TYPE_PXA2XX_PCMCIA); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - s = PXA2XX_PCMCIA(dev); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); - return s; + return PXA2XX_PCMCIA(dev); } static void pxa2xx_pcmcia_initfn(Object *obj) -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231020130331.50048-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/pcmcia/pxa2xx.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/hw/pcmcia/pxa2xx.c b/hw/pcmcia/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pcmcia/pxa2xx.c +++ b/hw/pcmcia/pxa2xx.c @@ -XXX,XX +XXX,XX @@ PXA2xxPCMCIAState *pxa2xx_pcmcia_init(MemoryRegion *sysmem, { DeviceState *dev; - dev = qdev_new(TYPE_PXA2XX_PCMCIA); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); + dev = sysbus_create_simple(TYPE_PXA2XX_PCMCIA, base, NULL); return PXA2XX_PCMCIA(dev); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231020130331.50048-6-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/pxa.h | 2 -- hw/arm/pxa2xx.c | 12 ++++++++---- hw/pcmcia/pxa2xx.c | 10 ---------- 3 files changed, 8 insertions(+), 16 deletions(-) diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ void pxa2xx_mmci_handlers(PXA2xxMMCIState *s, qemu_irq readonly, #define TYPE_PXA2XX_PCMCIA "pxa2xx-pcmcia" OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxPCMCIAState, PXA2XX_PCMCIA) -PXA2xxPCMCIAState *pxa2xx_pcmcia_init(MemoryRegion *sysmem, - hwaddr base); int pxa2xx_pcmcia_attach(void *opaque, PCMCIACardState *card); int pxa2xx_pcmcia_detach(void *opaque); void pxa2xx_pcmcia_set_irq_cb(void *opaque, qemu_irq irq, qemu_irq cd_irq); diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -XXX,XX +XXX,XX @@ PXA2xxState *pxa270_init(unsigned int sdram_size, const char *cpu_type) sysbus_create_simple("sysbus-ohci", 0x4c000000, qdev_get_gpio_in(s->pic, PXA2XX_PIC_USBH1)); - s->pcmcia[0] = pxa2xx_pcmcia_init(address_space, 0x20000000); - s->pcmcia[1] = pxa2xx_pcmcia_init(address_space, 0x30000000); + s->pcmcia[0] = PXA2XX_PCMCIA(sysbus_create_simple(TYPE_PXA2XX_PCMCIA, + 0x20000000, NULL)); + s->pcmcia[1] = PXA2XX_PCMCIA(sysbus_create_simple(TYPE_PXA2XX_PCMCIA, + 0x30000000, NULL)); sysbus_create_simple(TYPE_PXA2XX_RTC, 0x40900000, qdev_get_gpio_in(s->pic, PXA2XX_PIC_RTCALARM)); @@ -XXX,XX +XXX,XX @@ PXA2xxState *pxa255_init(unsigned int sdram_size) s->ssp[i] = (SSIBus *)qdev_get_child_bus(dev, "ssi"); } - s->pcmcia[0] = pxa2xx_pcmcia_init(address_space, 0x20000000); - s->pcmcia[1] = pxa2xx_pcmcia_init(address_space, 0x30000000); + s->pcmcia[0] = PXA2XX_PCMCIA(sysbus_create_simple(TYPE_PXA2XX_PCMCIA, + 0x20000000, NULL)); + s->pcmcia[1] = PXA2XX_PCMCIA(sysbus_create_simple(TYPE_PXA2XX_PCMCIA, + 0x30000000, NULL)); sysbus_create_simple(TYPE_PXA2XX_RTC, 0x40900000, qdev_get_gpio_in(s->pic, PXA2XX_PIC_RTCALARM)); diff --git a/hw/pcmcia/pxa2xx.c b/hw/pcmcia/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pcmcia/pxa2xx.c +++ b/hw/pcmcia/pxa2xx.c @@ -XXX,XX +XXX,XX @@ static void pxa2xx_pcmcia_set_irq(void *opaque, int line, int level) qemu_set_irq(s->irq, level); } -PXA2xxPCMCIAState *pxa2xx_pcmcia_init(MemoryRegion *sysmem, - hwaddr base) -{ - DeviceState *dev; - - dev = sysbus_create_simple(TYPE_PXA2XX_PCMCIA, base, NULL); - - return PXA2XX_PCMCIA(dev); -} - static void pxa2xx_pcmcia_initfn(Object *obj) { SysBusDevice *sbd = SYS_BUS_DEVICE(obj); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Factor reset code out of the DeviceRealize() handler. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20231020130331.50048-7-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/pxa2xx_pic.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/hw/arm/pxa2xx_pic.c b/hw/arm/pxa2xx_pic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx_pic.c +++ b/hw/arm/pxa2xx_pic.c @@ -XXX,XX +XXX,XX @@ static int pxa2xx_pic_post_load(void *opaque, int version_id) return 0; } -DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu) +static void pxa2xx_pic_reset_hold(Object *obj) { - DeviceState *dev = qdev_new(TYPE_PXA2XX_PIC); - PXA2xxPICState *s = PXA2XX_PIC(dev); - - s->cpu = cpu; + PXA2xxPICState *s = PXA2XX_PIC(obj); s->int_pending[0] = 0; s->int_pending[1] = 0; @@ -XXX,XX +XXX,XX @@ DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu) s->int_enabled[1] = 0; s->is_fiq[0] = 0; s->is_fiq[1] = 0; +} + +DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu) +{ + DeviceState *dev = qdev_new(TYPE_PXA2XX_PIC); + PXA2xxPICState *s = PXA2XX_PIC(dev); + + s->cpu = cpu; sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_pxa2xx_pic_regs = { static void pxa2xx_pic_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); dc->desc = "PXA2xx PIC"; dc->vmsd = &vmstate_pxa2xx_pic_regs; + rc->phases.hold = pxa2xx_pic_reset_hold; } static const TypeInfo pxa2xx_pic_info = { -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> QOM objects shouldn't access each other internals fields except using the QOM API. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20231020130331.50048-8-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/pxa2xx_pic.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/hw/arm/pxa2xx_pic.c b/hw/arm/pxa2xx_pic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx_pic.c +++ b/hw/arm/pxa2xx_pic.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "hw/arm/pxa.h" #include "hw/sysbus.h" +#include "hw/qdev-properties.h" #include "migration/vmstate.h" #include "qom/object.h" #include "target/arm/cpregs.h" @@ -XXX,XX +XXX,XX @@ DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu) DeviceState *dev = qdev_new(TYPE_PXA2XX_PIC); PXA2xxPICState *s = PXA2XX_PIC(dev); - s->cpu = cpu; + object_property_set_link(OBJECT(dev), "arm-cpu", + OBJECT(cpu), &error_abort); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_pxa2xx_pic_regs = { }, }; +static Property pxa2xx_pic_properties[] = { + DEFINE_PROP_LINK("arm-cpu", PXA2xxPICState, cpu, + TYPE_ARM_CPU, ARMCPU *), + DEFINE_PROP_END_OF_LIST(), +}; + static void pxa2xx_pic_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); ResettableClass *rc = RESETTABLE_CLASS(klass); + device_class_set_props(dc, pxa2xx_pic_properties); dc->desc = "PXA2xx PIC"; dc->vmsd = &vmstate_pxa2xx_pic_regs; rc->phases.hold = pxa2xx_pic_reset_hold; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20231020130331.50048-9-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/pxa2xx_pic.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/hw/arm/pxa2xx_pic.c b/hw/arm/pxa2xx_pic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx_pic.c +++ b/hw/arm/pxa2xx_pic.c @@ -XXX,XX +XXX,XX @@ static void pxa2xx_pic_reset_hold(Object *obj) DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu) { DeviceState *dev = qdev_new(TYPE_PXA2XX_PIC); - PXA2xxPICState *s = PXA2XX_PIC(dev); object_property_set_link(OBJECT(dev), "arm-cpu", OBJECT(cpu), &error_abort); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); + + return dev; +} + +static void pxa2xx_pic_realize(DeviceState *dev, Error **errp) +{ + PXA2xxPICState *s = PXA2XX_PIC(dev); qdev_init_gpio_in(dev, pxa2xx_pic_set_irq, PXA2XX_PIC_SRCS); @@ -XXX,XX +XXX,XX @@ DeviceState *pxa2xx_pic_init(hwaddr base, ARMCPU *cpu) memory_region_init_io(&s->iomem, OBJECT(s), &pxa2xx_pic_ops, s, "pxa2xx-pic", 0x00100000); sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); /* Enable IC coprocessor access. */ - define_arm_cp_regs_with_opaque(cpu, pxa_pic_cp_reginfo, s); - - return dev; + define_arm_cp_regs_with_opaque(s->cpu, pxa_pic_cp_reginfo, s); } static const VMStateDescription vmstate_pxa2xx_pic_regs = { @@ -XXX,XX +XXX,XX @@ static void pxa2xx_pic_class_init(ObjectClass *klass, void *data) ResettableClass *rc = RESETTABLE_CLASS(klass); device_class_set_props(dc, pxa2xx_pic_properties); + dc->realize = pxa2xx_pic_realize; dc->desc = "PXA2xx PIC"; dc->vmsd = &vmstate_pxa2xx_pic_regs; rc->phases.hold = pxa2xx_pic_reset_hold; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> qbus_new(), called in i2c_init_bus(), should not be called on unrealized device. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20231020130331.50048-10-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/pxa2xx.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -XXX,XX +XXX,XX @@ PXA2xxI2CState *pxa2xx_i2c_init(hwaddr base, qdev_prop_set_uint32(dev, "size", region_size + 1); qdev_prop_set_uint32(dev, "offset", base & region_size); + /* FIXME: Should the slave device really be on a separate bus? */ + i2cbus = i2c_init_bus(dev, "dummy"); + i2c_dev = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(i2c_dev, &error_fatal); sysbus_mmio_map(i2c_dev, 0, base & ~region_size); sysbus_connect_irq(i2c_dev, 0, irq); s = PXA2XX_I2C(i2c_dev); - /* FIXME: Should the slave device really be on a separate bus? */ - i2cbus = i2c_init_bus(dev, "dummy"); s->slave = PXA2XX_I2C_SLAVE(i2c_slave_create_simple(i2cbus, TYPE_PXA2XX_I2C_SLAVE, 0)); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Prefer using a well known local first CPU rather than a global one. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20231025065909.57344-1-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/bananapi_m2u.c | 2 +- hw/arm/exynos4_boards.c | 7 ++++--- hw/arm/orangepi.c | 2 +- hw/arm/realview.c | 2 +- hw/arm/xilinx_zynq.c | 2 +- 5 files changed, 8 insertions(+), 7 deletions(-) diff --git a/hw/arm/bananapi_m2u.c b/hw/arm/bananapi_m2u.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bananapi_m2u.c +++ b/hw/arm/bananapi_m2u.c @@ -XXX,XX +XXX,XX @@ static void bpim2u_init(MachineState *machine) bpim2u_binfo.loader_start = r40->memmap[AW_R40_DEV_SDRAM]; bpim2u_binfo.ram_size = machine->ram_size; bpim2u_binfo.psci_conduit = QEMU_PSCI_CONDUIT_SMC; - arm_load_kernel(ARM_CPU(first_cpu), machine, &bpim2u_binfo); + arm_load_kernel(&r40->cpus[0], machine, &bpim2u_binfo); } static void bpim2u_machine_init(MachineClass *mc) diff --git a/hw/arm/exynos4_boards.c b/hw/arm/exynos4_boards.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4_boards.c +++ b/hw/arm/exynos4_boards.c @@ -XXX,XX +XXX,XX @@ exynos4_boards_init_common(MachineState *machine, static void nuri_init(MachineState *machine) { - exynos4_boards_init_common(machine, EXYNOS4_BOARD_NURI); + Exynos4BoardState *s = exynos4_boards_init_common(machine, + EXYNOS4_BOARD_NURI); - arm_load_kernel(ARM_CPU(first_cpu), machine, &exynos4_board_binfo); + arm_load_kernel(s->soc.cpu[0], machine, &exynos4_board_binfo); } static void smdkc210_init(MachineState *machine) @@ -XXX,XX +XXX,XX @@ static void smdkc210_init(MachineState *machine) lan9215_init(SMDK_LAN9118_BASE_ADDR, qemu_irq_invert(s->soc.irq_table[exynos4210_get_irq(37, 1)])); - arm_load_kernel(ARM_CPU(first_cpu), machine, &exynos4_board_binfo); + arm_load_kernel(s->soc.cpu[0], machine, &exynos4_board_binfo); } static void nuri_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ static void orangepi_init(MachineState *machine) orangepi_binfo.loader_start = h3->memmap[AW_H3_DEV_SDRAM]; orangepi_binfo.ram_size = machine->ram_size; orangepi_binfo.psci_conduit = QEMU_PSCI_CONDUIT_SMC; - arm_load_kernel(ARM_CPU(first_cpu), machine, &orangepi_binfo); + arm_load_kernel(&h3->cpus[0], machine, &orangepi_binfo); } static void orangepi_machine_init(MachineClass *mc) diff --git a/hw/arm/realview.c b/hw/arm/realview.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/realview.c +++ b/hw/arm/realview.c @@ -XXX,XX +XXX,XX @@ static void realview_init(MachineState *machine, realview_binfo.ram_size = ram_size; realview_binfo.board_id = realview_board_id[board_type]; realview_binfo.loader_start = (board_type == BOARD_PB_A8 ? 0x70000000 : 0); - arm_load_kernel(ARM_CPU(first_cpu), machine, &realview_binfo); + arm_load_kernel(cpu, machine, &realview_binfo); } static void realview_eb_init(MachineState *machine) diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) zynq_binfo.board_setup_addr = BOARD_SETUP_ADDR; zynq_binfo.write_board_setup = zynq_write_board_setup; - arm_load_kernel(ARM_CPU(first_cpu), machine, &zynq_binfo); + arm_load_kernel(cpu, machine, &zynq_binfo); } static void zynq_machine_class_init(ObjectClass *oc, void *data) -- 2.34.1 From: Glenn Miles <milesg@linux.vnet.ibm.com> Testing of the LED state showed that when the LED polarity was set to GPIO_POLARITY_ACTIVE_LOW and a low logic value was set on the input GPIO of the LED, the LED was being turn off when it was expected to be turned on. Fixes: ddb67f6402 ("hw/misc/led: Allow connecting from GPIO output") Signed-off-by: Glenn Miles <milesg@linux.vnet.ibm.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Andrew Jeffery <andrew@codeconstruct.com.au> Message-id: 20231024191945.4135036-1-milesg@linux.vnet.ibm.com Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/led.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/misc/led.c b/hw/misc/led.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/led.c +++ b/hw/misc/led.c @@ -XXX,XX +XXX,XX @@ static void led_set_state_gpio_handler(void *opaque, int line, int new_state) LEDState *s = LED(opaque); assert(line == 0); - led_set_state(s, !!new_state != s->gpio_active_high); + led_set_state(s, !!new_state == s->gpio_active_high); } static void led_reset(DeviceState *dev) -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Replace register defines with the REG32 macro from registerfields.h in the Cadence GEM device. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-2-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 527 +++++++++++++++++++++---------------------- 1 file changed, 261 insertions(+), 266 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ #include "hw/irq.h" #include "hw/net/cadence_gem.h" #include "hw/qdev-properties.h" +#include "hw/registerfields.h" #include "migration/vmstate.h" #include "qapi/error.h" #include "qemu/log.h" @@ -XXX,XX +XXX,XX @@ } \ } while (0) -#define GEM_NWCTRL (0x00000000 / 4) /* Network Control reg */ -#define GEM_NWCFG (0x00000004 / 4) /* Network Config reg */ -#define GEM_NWSTATUS (0x00000008 / 4) /* Network Status reg */ -#define GEM_USERIO (0x0000000C / 4) /* User IO reg */ -#define GEM_DMACFG (0x00000010 / 4) /* DMA Control reg */ -#define GEM_TXSTATUS (0x00000014 / 4) /* TX Status reg */ -#define GEM_RXQBASE (0x00000018 / 4) /* RX Q Base address reg */ -#define GEM_TXQBASE (0x0000001C / 4) /* TX Q Base address reg */ -#define GEM_RXSTATUS (0x00000020 / 4) /* RX Status reg */ -#define GEM_ISR (0x00000024 / 4) /* Interrupt Status reg */ -#define GEM_IER (0x00000028 / 4) /* Interrupt Enable reg */ -#define GEM_IDR (0x0000002C / 4) /* Interrupt Disable reg */ -#define GEM_IMR (0x00000030 / 4) /* Interrupt Mask reg */ -#define GEM_PHYMNTNC (0x00000034 / 4) /* Phy Maintenance reg */ -#define GEM_RXPAUSE (0x00000038 / 4) /* RX Pause Time reg */ -#define GEM_TXPAUSE (0x0000003C / 4) /* TX Pause Time reg */ -#define GEM_TXPARTIALSF (0x00000040 / 4) /* TX Partial Store and Forward */ -#define GEM_RXPARTIALSF (0x00000044 / 4) /* RX Partial Store and Forward */ -#define GEM_JUMBO_MAX_LEN (0x00000048 / 4) /* Max Jumbo Frame Size */ -#define GEM_HASHLO (0x00000080 / 4) /* Hash Low address reg */ -#define GEM_HASHHI (0x00000084 / 4) /* Hash High address reg */ -#define GEM_SPADDR1LO (0x00000088 / 4) /* Specific addr 1 low reg */ -#define GEM_SPADDR1HI (0x0000008C / 4) /* Specific addr 1 high reg */ -#define GEM_SPADDR2LO (0x00000090 / 4) /* Specific addr 2 low reg */ -#define GEM_SPADDR2HI (0x00000094 / 4) /* Specific addr 2 high reg */ -#define GEM_SPADDR3LO (0x00000098 / 4) /* Specific addr 3 low reg */ -#define GEM_SPADDR3HI (0x0000009C / 4) /* Specific addr 3 high reg */ -#define GEM_SPADDR4LO (0x000000A0 / 4) /* Specific addr 4 low reg */ -#define GEM_SPADDR4HI (0x000000A4 / 4) /* Specific addr 4 high reg */ -#define GEM_TIDMATCH1 (0x000000A8 / 4) /* Type ID1 Match reg */ -#define GEM_TIDMATCH2 (0x000000AC / 4) /* Type ID2 Match reg */ -#define GEM_TIDMATCH3 (0x000000B0 / 4) /* Type ID3 Match reg */ -#define GEM_TIDMATCH4 (0x000000B4 / 4) /* Type ID4 Match reg */ -#define GEM_WOLAN (0x000000B8 / 4) /* Wake on LAN reg */ -#define GEM_IPGSTRETCH (0x000000BC / 4) /* IPG Stretch reg */ -#define GEM_SVLAN (0x000000C0 / 4) /* Stacked VLAN reg */ -#define GEM_MODID (0x000000FC / 4) /* Module ID reg */ -#define GEM_OCTTXLO (0x00000100 / 4) /* Octets transmitted Low reg */ -#define GEM_OCTTXHI (0x00000104 / 4) /* Octets transmitted High reg */ -#define GEM_TXCNT (0x00000108 / 4) /* Error-free Frames transmitted */ -#define GEM_TXBCNT (0x0000010C / 4) /* Error-free Broadcast Frames */ -#define GEM_TXMCNT (0x00000110 / 4) /* Error-free Multicast Frame */ -#define GEM_TXPAUSECNT (0x00000114 / 4) /* Pause Frames Transmitted */ -#define GEM_TX64CNT (0x00000118 / 4) /* Error-free 64 TX */ -#define GEM_TX65CNT (0x0000011C / 4) /* Error-free 65-127 TX */ -#define GEM_TX128CNT (0x00000120 / 4) /* Error-free 128-255 TX */ -#define GEM_TX256CNT (0x00000124 / 4) /* Error-free 256-511 */ -#define GEM_TX512CNT (0x00000128 / 4) /* Error-free 512-1023 TX */ -#define GEM_TX1024CNT (0x0000012C / 4) /* Error-free 1024-1518 TX */ -#define GEM_TX1519CNT (0x00000130 / 4) /* Error-free larger than 1519 TX */ -#define GEM_TXURUNCNT (0x00000134 / 4) /* TX under run error counter */ -#define GEM_SINGLECOLLCNT (0x00000138 / 4) /* Single Collision Frames */ -#define GEM_MULTCOLLCNT (0x0000013C / 4) /* Multiple Collision Frames */ -#define GEM_EXCESSCOLLCNT (0x00000140 / 4) /* Excessive Collision Frames */ -#define GEM_LATECOLLCNT (0x00000144 / 4) /* Late Collision Frames */ -#define GEM_DEFERTXCNT (0x00000148 / 4) /* Deferred Transmission Frames */ -#define GEM_CSENSECNT (0x0000014C / 4) /* Carrier Sense Error Counter */ -#define GEM_OCTRXLO (0x00000150 / 4) /* Octets Received register Low */ -#define GEM_OCTRXHI (0x00000154 / 4) /* Octets Received register High */ -#define GEM_RXCNT (0x00000158 / 4) /* Error-free Frames Received */ -#define GEM_RXBROADCNT (0x0000015C / 4) /* Error-free Broadcast Frames RX */ -#define GEM_RXMULTICNT (0x00000160 / 4) /* Error-free Multicast Frames RX */ -#define GEM_RXPAUSECNT (0x00000164 / 4) /* Pause Frames Received Counter */ -#define GEM_RX64CNT (0x00000168 / 4) /* Error-free 64 byte Frames RX */ -#define GEM_RX65CNT (0x0000016C / 4) /* Error-free 65-127B Frames RX */ -#define GEM_RX128CNT (0x00000170 / 4) /* Error-free 128-255B Frames RX */ -#define GEM_RX256CNT (0x00000174 / 4) /* Error-free 256-512B Frames RX */ -#define GEM_RX512CNT (0x00000178 / 4) /* Error-free 512-1023B Frames RX */ -#define GEM_RX1024CNT (0x0000017C / 4) /* Error-free 1024-1518B Frames RX */ -#define GEM_RX1519CNT (0x00000180 / 4) /* Error-free 1519-max Frames RX */ -#define GEM_RXUNDERCNT (0x00000184 / 4) /* Undersize Frames Received */ -#define GEM_RXOVERCNT (0x00000188 / 4) /* Oversize Frames Received */ -#define GEM_RXJABCNT (0x0000018C / 4) /* Jabbers Received Counter */ -#define GEM_RXFCSCNT (0x00000190 / 4) /* Frame Check seq. Error Counter */ -#define GEM_RXLENERRCNT (0x00000194 / 4) /* Length Field Error Counter */ -#define GEM_RXSYMERRCNT (0x00000198 / 4) /* Symbol Error Counter */ -#define GEM_RXALIGNERRCNT (0x0000019C / 4) /* Alignment Error Counter */ -#define GEM_RXRSCERRCNT (0x000001A0 / 4) /* Receive Resource Error Counter */ -#define GEM_RXORUNCNT (0x000001A4 / 4) /* Receive Overrun Counter */ -#define GEM_RXIPCSERRCNT (0x000001A8 / 4) /* IP header Checksum Err Counter */ -#define GEM_RXTCPCCNT (0x000001AC / 4) /* TCP Checksum Error Counter */ -#define GEM_RXUDPCCNT (0x000001B0 / 4) /* UDP Checksum Error Counter */ +REG32(NWCTRL, 0x0) /* Network Control reg */ +REG32(NWCFG, 0x4) /* Network Config reg */ +REG32(NWSTATUS, 0x8) /* Network Status reg */ +REG32(USERIO, 0xc) /* User IO reg */ +REG32(DMACFG, 0x10) /* DMA Control reg */ +REG32(TXSTATUS, 0x14) /* TX Status reg */ +REG32(RXQBASE, 0x18) /* RX Q Base address reg */ +REG32(TXQBASE, 0x1c) /* TX Q Base address reg */ +REG32(RXSTATUS, 0x20) /* RX Status reg */ +REG32(ISR, 0x24) /* Interrupt Status reg */ +REG32(IER, 0x28) /* Interrupt Enable reg */ +REG32(IDR, 0x2c) /* Interrupt Disable reg */ +REG32(IMR, 0x30) /* Interrupt Mask reg */ +REG32(PHYMNTNC, 0x34) /* Phy Maintenance reg */ +REG32(RXPAUSE, 0x38) /* RX Pause Time reg */ +REG32(TXPAUSE, 0x3c) /* TX Pause Time reg */ +REG32(TXPARTIALSF, 0x40) /* TX Partial Store and Forward */ +REG32(RXPARTIALSF, 0x44) /* RX Partial Store and Forward */ +REG32(JUMBO_MAX_LEN, 0x48) /* Max Jumbo Frame Size */ +REG32(HASHLO, 0x80) /* Hash Low address reg */ +REG32(HASHHI, 0x84) /* Hash High address reg */ +REG32(SPADDR1LO, 0x88) /* Specific addr 1 low reg */ +REG32(SPADDR1HI, 0x8c) /* Specific addr 1 high reg */ +REG32(SPADDR2LO, 0x90) /* Specific addr 2 low reg */ +REG32(SPADDR2HI, 0x94) /* Specific addr 2 high reg */ +REG32(SPADDR3LO, 0x98) /* Specific addr 3 low reg */ +REG32(SPADDR3HI, 0x9c) /* Specific addr 3 high reg */ +REG32(SPADDR4LO, 0xa0) /* Specific addr 4 low reg */ +REG32(SPADDR4HI, 0xa4) /* Specific addr 4 high reg */ +REG32(TIDMATCH1, 0xa8) /* Type ID1 Match reg */ +REG32(TIDMATCH2, 0xac) /* Type ID2 Match reg */ +REG32(TIDMATCH3, 0xb0) /* Type ID3 Match reg */ +REG32(TIDMATCH4, 0xb4) /* Type ID4 Match reg */ +REG32(WOLAN, 0xb8) /* Wake on LAN reg */ +REG32(IPGSTRETCH, 0xbc) /* IPG Stretch reg */ +REG32(SVLAN, 0xc0) /* Stacked VLAN reg */ +REG32(MODID, 0xfc) /* Module ID reg */ +REG32(OCTTXLO, 0x100) /* Octects transmitted Low reg */ +REG32(OCTTXHI, 0x104) /* Octects transmitted High reg */ +REG32(TXCNT, 0x108) /* Error-free Frames transmitted */ +REG32(TXBCNT, 0x10c) /* Error-free Broadcast Frames */ +REG32(TXMCNT, 0x110) /* Error-free Multicast Frame */ +REG32(TXPAUSECNT, 0x114) /* Pause Frames Transmitted */ +REG32(TX64CNT, 0x118) /* Error-free 64 TX */ +REG32(TX65CNT, 0x11c) /* Error-free 65-127 TX */ +REG32(TX128CNT, 0x120) /* Error-free 128-255 TX */ +REG32(TX256CNT, 0x124) /* Error-free 256-511 */ +REG32(TX512CNT, 0x128) /* Error-free 512-1023 TX */ +REG32(TX1024CNT, 0x12c) /* Error-free 1024-1518 TX */ +REG32(TX1519CNT, 0x130) /* Error-free larger than 1519 TX */ +REG32(TXURUNCNT, 0x134) /* TX under run error counter */ +REG32(SINGLECOLLCNT, 0x138) /* Single Collision Frames */ +REG32(MULTCOLLCNT, 0x13c) /* Multiple Collision Frames */ +REG32(EXCESSCOLLCNT, 0x140) /* Excessive Collision Frames */ +REG32(LATECOLLCNT, 0x144) /* Late Collision Frames */ +REG32(DEFERTXCNT, 0x148) /* Deferred Transmission Frames */ +REG32(CSENSECNT, 0x14c) /* Carrier Sense Error Counter */ +REG32(OCTRXLO, 0x150) /* Octects Received register Low */ +REG32(OCTRXHI, 0x154) /* Octects Received register High */ +REG32(RXCNT, 0x158) /* Error-free Frames Received */ +REG32(RXBROADCNT, 0x15c) /* Error-free Broadcast Frames RX */ +REG32(RXMULTICNT, 0x160) /* Error-free Multicast Frames RX */ +REG32(RXPAUSECNT, 0x164) /* Pause Frames Received Counter */ +REG32(RX64CNT, 0x168) /* Error-free 64 byte Frames RX */ +REG32(RX65CNT, 0x16c) /* Error-free 65-127B Frames RX */ +REG32(RX128CNT, 0x170) /* Error-free 128-255B Frames RX */ +REG32(RX256CNT, 0x174) /* Error-free 256-512B Frames RX */ +REG32(RX512CNT, 0x178) /* Error-free 512-1023B Frames RX */ +REG32(RX1024CNT, 0x17c) /* Error-free 1024-1518B Frames RX */ +REG32(RX1519CNT, 0x180) /* Error-free 1519-max Frames RX */ +REG32(RXUNDERCNT, 0x184) /* Undersize Frames Received */ +REG32(RXOVERCNT, 0x188) /* Oversize Frames Received */ +REG32(RXJABCNT, 0x18c) /* Jabbers Received Counter */ +REG32(RXFCSCNT, 0x190) /* Frame Check seq. Error Counter */ +REG32(RXLENERRCNT, 0x194) /* Length Field Error Counter */ +REG32(RXSYMERRCNT, 0x198) /* Symbol Error Counter */ +REG32(RXALIGNERRCNT, 0x19c) /* Alignment Error Counter */ +REG32(RXRSCERRCNT, 0x1a0) /* Receive Resource Error Counter */ +REG32(RXORUNCNT, 0x1a4) /* Receive Overrun Counter */ +REG32(RXIPCSERRCNT, 0x1a8) /* IP header Checksum Err Counter */ +REG32(RXTCPCCNT, 0x1ac) /* TCP Checksum Error Counter */ +REG32(RXUDPCCNT, 0x1b0) /* UDP Checksum Error Counter */ -#define GEM_1588S (0x000001D0 / 4) /* 1588 Timer Seconds */ -#define GEM_1588NS (0x000001D4 / 4) /* 1588 Timer Nanoseconds */ -#define GEM_1588ADJ (0x000001D8 / 4) /* 1588 Timer Adjust */ -#define GEM_1588INC (0x000001DC / 4) /* 1588 Timer Increment */ -#define GEM_PTPETXS (0x000001E0 / 4) /* PTP Event Frame Transmitted (s) */ -#define GEM_PTPETXNS (0x000001E4 / 4) /* - * PTP Event Frame Transmitted (ns) - */ -#define GEM_PTPERXS (0x000001E8 / 4) /* PTP Event Frame Received (s) */ -#define GEM_PTPERXNS (0x000001EC / 4) /* PTP Event Frame Received (ns) */ -#define GEM_PTPPTXS (0x000001E0 / 4) /* PTP Peer Frame Transmitted (s) */ -#define GEM_PTPPTXNS (0x000001E4 / 4) /* PTP Peer Frame Transmitted (ns) */ -#define GEM_PTPPRXS (0x000001E8 / 4) /* PTP Peer Frame Received (s) */ -#define GEM_PTPPRXNS (0x000001EC / 4) /* PTP Peer Frame Received (ns) */ +REG32(1588S, 0x1d0) /* 1588 Timer Seconds */ +REG32(1588NS, 0x1d4) /* 1588 Timer Nanoseconds */ +REG32(1588ADJ, 0x1d8) /* 1588 Timer Adjust */ +REG32(1588INC, 0x1dc) /* 1588 Timer Increment */ +REG32(PTPETXS, 0x1e0) /* PTP Event Frame Transmitted (s) */ +REG32(PTPETXNS, 0x1e4) /* PTP Event Frame Transmitted (ns) */ +REG32(PTPERXS, 0x1e8) /* PTP Event Frame Received (s) */ +REG32(PTPERXNS, 0x1ec) /* PTP Event Frame Received (ns) */ +REG32(PTPPTXS, 0x1e0) /* PTP Peer Frame Transmitted (s) */ +REG32(PTPPTXNS, 0x1e4) /* PTP Peer Frame Transmitted (ns) */ +REG32(PTPPRXS, 0x1e8) /* PTP Peer Frame Received (s) */ +REG32(PTPPRXNS, 0x1ec) /* PTP Peer Frame Received (ns) */ /* Design Configuration Registers */ -#define GEM_DESCONF (0x00000280 / 4) -#define GEM_DESCONF2 (0x00000284 / 4) -#define GEM_DESCONF3 (0x00000288 / 4) -#define GEM_DESCONF4 (0x0000028C / 4) -#define GEM_DESCONF5 (0x00000290 / 4) -#define GEM_DESCONF6 (0x00000294 / 4) +REG32(DESCONF, 0x280) +REG32(DESCONF2, 0x284) +REG32(DESCONF3, 0x288) +REG32(DESCONF4, 0x28c) +REG32(DESCONF5, 0x290) +REG32(DESCONF6, 0x294) #define GEM_DESCONF6_64B_MASK (1U << 23) -#define GEM_DESCONF7 (0x00000298 / 4) +REG32(DESCONF7, 0x298) -#define GEM_INT_Q1_STATUS (0x00000400 / 4) -#define GEM_INT_Q1_MASK (0x00000640 / 4) +REG32(INT_Q1_STATUS, 0x400) +REG32(INT_Q1_MASK, 0x640) -#define GEM_TRANSMIT_Q1_PTR (0x00000440 / 4) -#define GEM_TRANSMIT_Q7_PTR (GEM_TRANSMIT_Q1_PTR + 6) +REG32(TRANSMIT_Q1_PTR, 0x440) +REG32(TRANSMIT_Q7_PTR, 0x458) -#define GEM_RECEIVE_Q1_PTR (0x00000480 / 4) -#define GEM_RECEIVE_Q7_PTR (GEM_RECEIVE_Q1_PTR + 6) +REG32(RECEIVE_Q1_PTR, 0x480) +REG32(RECEIVE_Q7_PTR, 0x498) -#define GEM_TBQPH (0x000004C8 / 4) -#define GEM_RBQPH (0x000004D4 / 4) +REG32(TBQPH, 0x4c8) +REG32(RBQPH, 0x4d4) -#define GEM_INT_Q1_ENABLE (0x00000600 / 4) -#define GEM_INT_Q7_ENABLE (GEM_INT_Q1_ENABLE + 6) +REG32(INT_Q1_ENABLE, 0x600) +REG32(INT_Q7_ENABLE, 0x618) -#define GEM_INT_Q1_DISABLE (0x00000620 / 4) -#define GEM_INT_Q7_DISABLE (GEM_INT_Q1_DISABLE + 6) +REG32(INT_Q1_DISABLE, 0x620) +REG32(INT_Q7_DISABLE, 0x638) -#define GEM_INT_Q1_MASK (0x00000640 / 4) -#define GEM_INT_Q7_MASK (GEM_INT_Q1_MASK + 6) - -#define GEM_SCREENING_TYPE1_REGISTER_0 (0x00000500 / 4) +REG32(SCREENING_TYPE1_REG0, 0x500) #define GEM_ST1R_UDP_PORT_MATCH_ENABLE (1 << 29) #define GEM_ST1R_DSTC_ENABLE (1 << 28) @@ -XXX,XX +XXX,XX @@ #define GEM_ST1R_QUEUE_SHIFT (0) #define GEM_ST1R_QUEUE_WIDTH (3 - GEM_ST1R_QUEUE_SHIFT + 1) -#define GEM_SCREENING_TYPE2_REGISTER_0 (0x00000540 / 4) +REG32(SCREENING_TYPE2_REG0, 0x540) #define GEM_ST2R_COMPARE_A_ENABLE (1 << 18) #define GEM_ST2R_COMPARE_A_SHIFT (13) @@ -XXX,XX +XXX,XX @@ #define GEM_ST2R_QUEUE_SHIFT (0) #define GEM_ST2R_QUEUE_WIDTH (3 - GEM_ST2R_QUEUE_SHIFT + 1) -#define GEM_SCREENING_TYPE2_ETHERTYPE_REG_0 (0x000006e0 / 4) -#define GEM_TYPE2_COMPARE_0_WORD_0 (0x00000700 / 4) +REG32(SCREENING_TYPE2_ETHERTYPE_REG0, 0x6e0) +REG32(TYPE2_COMPARE_0_WORD_0, 0x700) #define GEM_T2CW1_COMPARE_OFFSET_SHIFT (7) #define GEM_T2CW1_COMPARE_OFFSET_WIDTH (8 - GEM_T2CW1_COMPARE_OFFSET_SHIFT + 1) @@ -XXX,XX +XXX,XX @@ static inline uint64_t tx_desc_get_buffer(CadenceGEMState *s, uint32_t *desc) { uint64_t ret = desc[0]; - if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { ret |= (uint64_t)desc[2] << 32; } return ret; @@ -XXX,XX +XXX,XX @@ static inline uint64_t rx_desc_get_buffer(CadenceGEMState *s, uint32_t *desc) { uint64_t ret = desc[0] & ~0x3UL; - if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { ret |= (uint64_t)desc[2] << 32; } return ret; @@ -XXX,XX +XXX,XX @@ static inline int gem_get_desc_len(CadenceGEMState *s, bool rx_n_tx) { int ret = 2; - if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { ret += 2; } - if (s->regs[GEM_DMACFG] & (rx_n_tx ? GEM_DMACFG_RX_BD_EXT + if (s->regs[R_DMACFG] & (rx_n_tx ? GEM_DMACFG_RX_BD_EXT : GEM_DMACFG_TX_BD_EXT)) { ret += 2; } @@ -XXX,XX +XXX,XX @@ static const uint8_t broadcast_addr[] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; static uint32_t gem_get_max_buf_len(CadenceGEMState *s, bool tx) { uint32_t size; - if (s->regs[GEM_NWCFG] & GEM_NWCFG_JUMBO_FRAME) { - size = s->regs[GEM_JUMBO_MAX_LEN]; + if (s->regs[R_NWCFG] & GEM_NWCFG_JUMBO_FRAME) { + size = s->regs[R_JUMBO_MAX_LEN]; if (size > s->jumbo_max_len) { size = s->jumbo_max_len; qemu_log_mask(LOG_GUEST_ERROR, "GEM_JUMBO_MAX_LEN reg cannot be" @@ -XXX,XX +XXX,XX @@ static uint32_t gem_get_max_buf_len(CadenceGEMState *s, bool tx) } else if (tx) { size = 1518; } else { - size = s->regs[GEM_NWCFG] & GEM_NWCFG_RCV_1538 ? 1538 : 1518; + size = s->regs[R_NWCFG] & GEM_NWCFG_RCV_1538 ? 1538 : 1518; } return size; } @@ -XXX,XX +XXX,XX @@ static uint32_t gem_get_max_buf_len(CadenceGEMState *s, bool tx) static void gem_set_isr(CadenceGEMState *s, int q, uint32_t flag) { if (q == 0) { - s->regs[GEM_ISR] |= flag & ~(s->regs[GEM_IMR]); + s->regs[R_ISR] |= flag & ~(s->regs[R_IMR]); } else { - s->regs[GEM_INT_Q1_STATUS + q - 1] |= flag & - ~(s->regs[GEM_INT_Q1_MASK + q - 1]); + s->regs[R_INT_Q1_STATUS + q - 1] |= flag & + ~(s->regs[R_INT_Q1_MASK + q - 1]); } } @@ -XXX,XX +XXX,XX @@ static void gem_init_register_masks(CadenceGEMState *s) unsigned int i; /* Mask of register bits which are read only */ memset(&s->regs_ro[0], 0, sizeof(s->regs_ro)); - s->regs_ro[GEM_NWCTRL] = 0xFFF80000; - s->regs_ro[GEM_NWSTATUS] = 0xFFFFFFFF; - s->regs_ro[GEM_DMACFG] = 0x8E00F000; - s->regs_ro[GEM_TXSTATUS] = 0xFFFFFE08; - s->regs_ro[GEM_RXQBASE] = 0x00000003; - s->regs_ro[GEM_TXQBASE] = 0x00000003; - s->regs_ro[GEM_RXSTATUS] = 0xFFFFFFF0; - s->regs_ro[GEM_ISR] = 0xFFFFFFFF; - s->regs_ro[GEM_IMR] = 0xFFFFFFFF; - s->regs_ro[GEM_MODID] = 0xFFFFFFFF; + s->regs_ro[R_NWCTRL] = 0xFFF80000; + s->regs_ro[R_NWSTATUS] = 0xFFFFFFFF; + s->regs_ro[R_DMACFG] = 0x8E00F000; + s->regs_ro[R_TXSTATUS] = 0xFFFFFE08; + s->regs_ro[R_RXQBASE] = 0x00000003; + s->regs_ro[R_TXQBASE] = 0x00000003; + s->regs_ro[R_RXSTATUS] = 0xFFFFFFF0; + s->regs_ro[R_ISR] = 0xFFFFFFFF; + s->regs_ro[R_IMR] = 0xFFFFFFFF; + s->regs_ro[R_MODID] = 0xFFFFFFFF; for (i = 0; i < s->num_priority_queues; i++) { - s->regs_ro[GEM_INT_Q1_STATUS + i] = 0xFFFFFFFF; - s->regs_ro[GEM_INT_Q1_ENABLE + i] = 0xFFFFF319; - s->regs_ro[GEM_INT_Q1_DISABLE + i] = 0xFFFFF319; - s->regs_ro[GEM_INT_Q1_MASK + i] = 0xFFFFFFFF; + s->regs_ro[R_INT_Q1_STATUS + i] = 0xFFFFFFFF; + s->regs_ro[R_INT_Q1_ENABLE + i] = 0xFFFFF319; + s->regs_ro[R_INT_Q1_DISABLE + i] = 0xFFFFF319; + s->regs_ro[R_INT_Q1_MASK + i] = 0xFFFFFFFF; } /* Mask of register bits which are clear on read */ memset(&s->regs_rtc[0], 0, sizeof(s->regs_rtc)); - s->regs_rtc[GEM_ISR] = 0xFFFFFFFF; + s->regs_rtc[R_ISR] = 0xFFFFFFFF; for (i = 0; i < s->num_priority_queues; i++) { - s->regs_rtc[GEM_INT_Q1_STATUS + i] = 0x00000CE6; + s->regs_rtc[R_INT_Q1_STATUS + i] = 0x00000CE6; } /* Mask of register bits which are write 1 to clear */ memset(&s->regs_w1c[0], 0, sizeof(s->regs_w1c)); - s->regs_w1c[GEM_TXSTATUS] = 0x000001F7; - s->regs_w1c[GEM_RXSTATUS] = 0x0000000F; + s->regs_w1c[R_TXSTATUS] = 0x000001F7; + s->regs_w1c[R_RXSTATUS] = 0x0000000F; /* Mask of register bits which are write only */ memset(&s->regs_wo[0], 0, sizeof(s->regs_wo)); - s->regs_wo[GEM_NWCTRL] = 0x00073E60; - s->regs_wo[GEM_IER] = 0x07FFFFFF; - s->regs_wo[GEM_IDR] = 0x07FFFFFF; + s->regs_wo[R_NWCTRL] = 0x00073E60; + s->regs_wo[R_IER] = 0x07FFFFFF; + s->regs_wo[R_IDR] = 0x07FFFFFF; for (i = 0; i < s->num_priority_queues; i++) { - s->regs_wo[GEM_INT_Q1_ENABLE + i] = 0x00000CE6; - s->regs_wo[GEM_INT_Q1_DISABLE + i] = 0x00000CE6; + s->regs_wo[R_INT_Q1_ENABLE + i] = 0x00000CE6; + s->regs_wo[R_INT_Q1_DISABLE + i] = 0x00000CE6; } } @@ -XXX,XX +XXX,XX @@ static bool gem_can_receive(NetClientState *nc) s = qemu_get_nic_opaque(nc); /* Do nothing if receive is not enabled. */ - if (!(s->regs[GEM_NWCTRL] & GEM_NWCTRL_RXENA)) { + if (!(s->regs[R_NWCTRL] & GEM_NWCTRL_RXENA)) { if (s->can_rx_state != 1) { s->can_rx_state = 1; DB_PRINT("can't receive - no enable\n"); @@ -XXX,XX +XXX,XX @@ static void gem_update_int_status(CadenceGEMState *s) { int i; - qemu_set_irq(s->irq[0], !!s->regs[GEM_ISR]); + qemu_set_irq(s->irq[0], !!s->regs[R_ISR]); for (i = 1; i < s->num_priority_queues; ++i) { - qemu_set_irq(s->irq[i], !!s->regs[GEM_INT_Q1_STATUS + i - 1]); + qemu_set_irq(s->irq[i], !!s->regs[R_INT_Q1_STATUS + i - 1]); } } @@ -XXX,XX +XXX,XX @@ static void gem_receive_updatestats(CadenceGEMState *s, const uint8_t *packet, uint64_t octets; /* Total octets (bytes) received */ - octets = ((uint64_t)(s->regs[GEM_OCTRXLO]) << 32) | - s->regs[GEM_OCTRXHI]; + octets = ((uint64_t)(s->regs[R_OCTRXLO]) << 32) | + s->regs[R_OCTRXHI]; octets += bytes; - s->regs[GEM_OCTRXLO] = octets >> 32; - s->regs[GEM_OCTRXHI] = octets; + s->regs[R_OCTRXLO] = octets >> 32; + s->regs[R_OCTRXHI] = octets; /* Error-free Frames received */ - s->regs[GEM_RXCNT]++; + s->regs[R_RXCNT]++; /* Error-free Broadcast Frames counter */ if (!memcmp(packet, broadcast_addr, 6)) { - s->regs[GEM_RXBROADCNT]++; + s->regs[R_RXBROADCNT]++; } /* Error-free Multicast Frames counter */ if (packet[0] == 0x01) { - s->regs[GEM_RXMULTICNT]++; + s->regs[R_RXMULTICNT]++; } if (bytes <= 64) { - s->regs[GEM_RX64CNT]++; + s->regs[R_RX64CNT]++; } else if (bytes <= 127) { - s->regs[GEM_RX65CNT]++; + s->regs[R_RX65CNT]++; } else if (bytes <= 255) { - s->regs[GEM_RX128CNT]++; + s->regs[R_RX128CNT]++; } else if (bytes <= 511) { - s->regs[GEM_RX256CNT]++; + s->regs[R_RX256CNT]++; } else if (bytes <= 1023) { - s->regs[GEM_RX512CNT]++; + s->regs[R_RX512CNT]++; } else if (bytes <= 1518) { - s->regs[GEM_RX1024CNT]++; + s->regs[R_RX1024CNT]++; } else { - s->regs[GEM_RX1519CNT]++; + s->regs[R_RX1519CNT]++; } } @@ -XXX,XX +XXX,XX @@ static int gem_mac_address_filter(CadenceGEMState *s, const uint8_t *packet) int i, is_mc; /* Promiscuous mode? */ - if (s->regs[GEM_NWCFG] & GEM_NWCFG_PROMISC) { + if (s->regs[R_NWCFG] & GEM_NWCFG_PROMISC) { return GEM_RX_PROMISCUOUS_ACCEPT; } if (!memcmp(packet, broadcast_addr, 6)) { /* Reject broadcast packets? */ - if (s->regs[GEM_NWCFG] & GEM_NWCFG_BCAST_REJ) { + if (s->regs[R_NWCFG] & GEM_NWCFG_BCAST_REJ) { return GEM_RX_REJECT; } return GEM_RX_BROADCAST_ACCEPT; @@ -XXX,XX +XXX,XX @@ static int gem_mac_address_filter(CadenceGEMState *s, const uint8_t *packet) /* Accept packets -w- hash match? */ is_mc = is_multicast_ether_addr(packet); - if ((is_mc && (s->regs[GEM_NWCFG] & GEM_NWCFG_MCAST_HASH)) || - (!is_mc && (s->regs[GEM_NWCFG] & GEM_NWCFG_UCAST_HASH))) { + if ((is_mc && (s->regs[R_NWCFG] & GEM_NWCFG_MCAST_HASH)) || + (!is_mc && (s->regs[R_NWCFG] & GEM_NWCFG_UCAST_HASH))) { uint64_t buckets; unsigned hash_index; hash_index = calc_mac_hash(packet); - buckets = ((uint64_t)s->regs[GEM_HASHHI] << 32) | s->regs[GEM_HASHLO]; + buckets = ((uint64_t)s->regs[R_HASHHI] << 32) | s->regs[R_HASHLO]; if ((buckets >> hash_index) & 1) { return is_mc ? GEM_RX_MULTICAST_HASH_ACCEPT : GEM_RX_UNICAST_HASH_ACCEPT; @@ -XXX,XX +XXX,XX @@ static int gem_mac_address_filter(CadenceGEMState *s, const uint8_t *packet) } /* Check all 4 specific addresses */ - gem_spaddr = (uint8_t *)&(s->regs[GEM_SPADDR1LO]); + gem_spaddr = (uint8_t *)&(s->regs[R_SPADDR1LO]); for (i = 3; i >= 0; i--) { if (s->sar_active[i] && !memcmp(packet, gem_spaddr + 8 * i, 6)) { return GEM_RX_SAR_ACCEPT + i; @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, int i, j; for (i = 0; i < s->num_type1_screeners; i++) { - reg = s->regs[GEM_SCREENING_TYPE1_REGISTER_0 + i]; + reg = s->regs[R_SCREENING_TYPE1_REG0 + i]; matched = false; mismatched = false; @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, } for (i = 0; i < s->num_type2_screeners; i++) { - reg = s->regs[GEM_SCREENING_TYPE2_REGISTER_0 + i]; + reg = s->regs[R_SCREENING_TYPE2_REG0 + i]; matched = false; mismatched = false; @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, qemu_log_mask(LOG_GUEST_ERROR, "Out of range ethertype " "register index: %d\n", et_idx); } - if (type == s->regs[GEM_SCREENING_TYPE2_ETHERTYPE_REG_0 + + if (type == s->regs[R_SCREENING_TYPE2_ETHERTYPE_REG0 + et_idx]) { matched = true; } else { @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, "register index: %d\n", cr_idx); } - cr0 = s->regs[GEM_TYPE2_COMPARE_0_WORD_0 + cr_idx * 2]; - cr1 = s->regs[GEM_TYPE2_COMPARE_0_WORD_0 + cr_idx * 2 + 1]; + cr0 = s->regs[R_TYPE2_COMPARE_0_WORD_0 + cr_idx * 2]; + cr1 = s->regs[R_TYPE2_COMPARE_0_WORD_0 + cr_idx * 2 + 1]; offset = extract32(cr1, GEM_T2CW1_OFFSET_VALUE_SHIFT, GEM_T2CW1_OFFSET_VALUE_WIDTH); @@ -XXX,XX +XXX,XX @@ static uint32_t gem_get_queue_base_addr(CadenceGEMState *s, bool tx, int q) switch (q) { case 0: - base_addr = s->regs[tx ? GEM_TXQBASE : GEM_RXQBASE]; + base_addr = s->regs[tx ? R_TXQBASE : R_RXQBASE]; break; case 1 ... (MAX_PRIORITY_QUEUES - 1): - base_addr = s->regs[(tx ? GEM_TRANSMIT_Q1_PTR : - GEM_RECEIVE_Q1_PTR) + q - 1]; + base_addr = s->regs[(tx ? R_TRANSMIT_Q1_PTR : + R_RECEIVE_Q1_PTR) + q - 1]; break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static hwaddr gem_get_desc_addr(CadenceGEMState *s, bool tx, int q) { hwaddr desc_addr = 0; - if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) { - desc_addr = s->regs[tx ? GEM_TBQPH : GEM_RBQPH]; + if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + desc_addr = s->regs[tx ? R_TBQPH : R_RBQPH]; } desc_addr <<= 32; desc_addr |= tx ? s->tx_desc_addr[q] : s->rx_desc_addr[q]; @@ -XXX,XX +XXX,XX @@ static void gem_get_rx_desc(CadenceGEMState *s, int q) /* Descriptor owned by software ? */ if (rx_desc_get_ownership(s->rx_desc[q]) == 1) { DB_PRINT("descriptor 0x%" HWADDR_PRIx " owned by sw.\n", desc_addr); - s->regs[GEM_RXSTATUS] |= GEM_RXSTATUS_NOBUF; + s->regs[R_RXSTATUS] |= GEM_RXSTATUS_NOBUF; gem_set_isr(s, q, GEM_INT_RXUSED); /* Handle interrupt consequences */ gem_update_int_status(s); @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) } /* Discard packets with receive length error enabled ? */ - if (s->regs[GEM_NWCFG] & GEM_NWCFG_LERR_DISC) { + if (s->regs[R_NWCFG] & GEM_NWCFG_LERR_DISC) { unsigned type_len; /* Fish the ethertype / length field out of the RX packet */ @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) /* * Determine configured receive buffer offset (probably 0) */ - rxbuf_offset = (s->regs[GEM_NWCFG] & GEM_NWCFG_BUFF_OFST_M) >> + rxbuf_offset = (s->regs[R_NWCFG] & GEM_NWCFG_BUFF_OFST_M) >> GEM_NWCFG_BUFF_OFST_S; /* The configure size of each receive buffer. Determines how many * buffers needed to hold this packet. */ - rxbufsize = ((s->regs[GEM_DMACFG] & GEM_DMACFG_RBUFSZ_M) >> + rxbufsize = ((s->regs[R_DMACFG] & GEM_DMACFG_RBUFSZ_M) >> GEM_DMACFG_RBUFSZ_S) * GEM_DMACFG_RBUFSZ_MUL; bytes_to_copy = size; @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) } /* Strip of FCS field ? (usually yes) */ - if (s->regs[GEM_NWCFG] & GEM_NWCFG_STRIP_FCS) { + if (s->regs[R_NWCFG] & GEM_NWCFG_STRIP_FCS) { rxbuf_ptr = (void *)buf; } else { unsigned crc_val; @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) /* Count it */ gem_receive_updatestats(s, buf, size); - s->regs[GEM_RXSTATUS] |= GEM_RXSTATUS_FRMRCVD; + s->regs[R_RXSTATUS] |= GEM_RXSTATUS_FRMRCVD; gem_set_isr(s, q, GEM_INT_RXCMPL); /* Handle interrupt consequences */ @@ -XXX,XX +XXX,XX @@ static void gem_transmit_updatestats(CadenceGEMState *s, const uint8_t *packet, uint64_t octets; /* Total octets (bytes) transmitted */ - octets = ((uint64_t)(s->regs[GEM_OCTTXLO]) << 32) | - s->regs[GEM_OCTTXHI]; + octets = ((uint64_t)(s->regs[R_OCTTXLO]) << 32) | + s->regs[R_OCTTXHI]; octets += bytes; - s->regs[GEM_OCTTXLO] = octets >> 32; - s->regs[GEM_OCTTXHI] = octets; + s->regs[R_OCTTXLO] = octets >> 32; + s->regs[R_OCTTXHI] = octets; /* Error-free Frames transmitted */ - s->regs[GEM_TXCNT]++; + s->regs[R_TXCNT]++; /* Error-free Broadcast Frames counter */ if (!memcmp(packet, broadcast_addr, 6)) { - s->regs[GEM_TXBCNT]++; + s->regs[R_TXBCNT]++; } /* Error-free Multicast Frames counter */ if (packet[0] == 0x01) { - s->regs[GEM_TXMCNT]++; + s->regs[R_TXMCNT]++; } if (bytes <= 64) { - s->regs[GEM_TX64CNT]++; + s->regs[R_TX64CNT]++; } else if (bytes <= 127) { - s->regs[GEM_TX65CNT]++; + s->regs[R_TX65CNT]++; } else if (bytes <= 255) { - s->regs[GEM_TX128CNT]++; + s->regs[R_TX128CNT]++; } else if (bytes <= 511) { - s->regs[GEM_TX256CNT]++; + s->regs[R_TX256CNT]++; } else if (bytes <= 1023) { - s->regs[GEM_TX512CNT]++; + s->regs[R_TX512CNT]++; } else if (bytes <= 1518) { - s->regs[GEM_TX1024CNT]++; + s->regs[R_TX1024CNT]++; } else { - s->regs[GEM_TX1519CNT]++; + s->regs[R_TX1519CNT]++; } } @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) int q = 0; /* Do nothing if transmit is not enabled. */ - if (!(s->regs[GEM_NWCTRL] & GEM_NWCTRL_TXENA)) { + if (!(s->regs[R_NWCTRL] & GEM_NWCTRL_TXENA)) { return; } @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) while (tx_desc_get_used(desc) == 0) { /* Do nothing if transmit is not enabled. */ - if (!(s->regs[GEM_NWCTRL] & GEM_NWCTRL_TXENA)) { + if (!(s->regs[R_NWCTRL] & GEM_NWCTRL_TXENA)) { return; } print_gem_tx_desc(desc, q); @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) } DB_PRINT("TX descriptor next: 0x%08x\n", s->tx_desc_addr[q]); - s->regs[GEM_TXSTATUS] |= GEM_TXSTATUS_TXCMPL; + s->regs[R_TXSTATUS] |= GEM_TXSTATUS_TXCMPL; gem_set_isr(s, q, GEM_INT_TXCMPL); /* Handle interrupt consequences */ gem_update_int_status(s); /* Is checksum offload enabled? */ - if (s->regs[GEM_DMACFG] & GEM_DMACFG_TXCSUM_OFFL) { + if (s->regs[R_DMACFG] & GEM_DMACFG_TXCSUM_OFFL) { net_checksum_calculate(s->tx_packet, total_bytes, CSUM_ALL); } @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) gem_transmit_updatestats(s, s->tx_packet, total_bytes); /* Send the packet somewhere */ - if (s->phy_loop || (s->regs[GEM_NWCTRL] & + if (s->phy_loop || (s->regs[R_NWCTRL] & GEM_NWCTRL_LOCALLOOP)) { qemu_receive_packet(qemu_get_queue(s->nic), s->tx_packet, total_bytes); @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) /* read next descriptor */ if (tx_desc_get_wrap(desc)) { - - if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) { - packet_desc_addr = s->regs[GEM_TBQPH]; + if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + packet_desc_addr = s->regs[R_TBQPH]; packet_desc_addr <<= 32; } else { packet_desc_addr = 0; @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) } if (tx_desc_get_used(desc)) { - s->regs[GEM_TXSTATUS] |= GEM_TXSTATUS_USED; + s->regs[R_TXSTATUS] |= GEM_TXSTATUS_USED; /* IRQ TXUSED is defined only for queue 0 */ if (q == 0) { gem_set_isr(s, 0, GEM_INT_TXUSED); @@ -XXX,XX +XXX,XX @@ static void gem_reset(DeviceState *d) /* Set post reset register values */ memset(&s->regs[0], 0, sizeof(s->regs)); - s->regs[GEM_NWCFG] = 0x00080000; - s->regs[GEM_NWSTATUS] = 0x00000006; - s->regs[GEM_DMACFG] = 0x00020784; - s->regs[GEM_IMR] = 0x07ffffff; - s->regs[GEM_TXPAUSE] = 0x0000ffff; - s->regs[GEM_TXPARTIALSF] = 0x000003ff; - s->regs[GEM_RXPARTIALSF] = 0x000003ff; - s->regs[GEM_MODID] = s->revision; - s->regs[GEM_DESCONF] = 0x02D00111; - s->regs[GEM_DESCONF2] = 0x2ab10000 | s->jumbo_max_len; - s->regs[GEM_DESCONF5] = 0x002f2045; - s->regs[GEM_DESCONF6] = GEM_DESCONF6_64B_MASK; - s->regs[GEM_INT_Q1_MASK] = 0x00000CE6; - s->regs[GEM_JUMBO_MAX_LEN] = s->jumbo_max_len; + s->regs[R_NWCFG] = 0x00080000; + s->regs[R_NWSTATUS] = 0x00000006; + s->regs[R_DMACFG] = 0x00020784; + s->regs[R_IMR] = 0x07ffffff; + s->regs[R_TXPAUSE] = 0x0000ffff; + s->regs[R_TXPARTIALSF] = 0x000003ff; + s->regs[R_RXPARTIALSF] = 0x000003ff; + s->regs[R_MODID] = s->revision; + s->regs[R_DESCONF] = 0x02D00111; + s->regs[R_DESCONF2] = 0x2ab10000 | s->jumbo_max_len; + s->regs[R_DESCONF5] = 0x002f2045; + s->regs[R_DESCONF6] = GEM_DESCONF6_64B_MASK; + s->regs[R_INT_Q1_MASK] = 0x00000CE6; + s->regs[R_JUMBO_MAX_LEN] = s->jumbo_max_len; if (s->num_priority_queues > 1) { queues_mask = MAKE_64BIT_MASK(1, s->num_priority_queues - 1); - s->regs[GEM_DESCONF6] |= queues_mask; + s->regs[R_DESCONF6] |= queues_mask; } /* Set MAC address */ a = &s->conf.macaddr.a[0]; - s->regs[GEM_SPADDR1LO] = a[0] | (a[1] << 8) | (a[2] << 16) | (a[3] << 24); - s->regs[GEM_SPADDR1HI] = a[4] | (a[5] << 8); + s->regs[R_SPADDR1LO] = a[0] | (a[1] << 8) | (a[2] << 16) | (a[3] << 24); + s->regs[R_SPADDR1HI] = a[4] | (a[5] << 8); for (i = 0; i < 4; i++) { s->sar_active[i] = false; @@ -XXX,XX +XXX,XX @@ static uint64_t gem_read(void *opaque, hwaddr offset, unsigned size) DB_PRINT("offset: 0x%04x read: 0x%08x\n", (unsigned)offset*4, retval); switch (offset) { - case GEM_ISR: + case R_ISR: DB_PRINT("lowering irqs on ISR read\n"); /* The interrupts get updated at the end of the function. */ break; - case GEM_PHYMNTNC: + case R_PHYMNTNC: if (retval & GEM_PHYMNTNC_OP_R) { uint32_t phy_addr, reg_num; @@ -XXX,XX +XXX,XX @@ static void gem_write(void *opaque, hwaddr offset, uint64_t val, /* Handle register write side effects */ switch (offset) { - case GEM_NWCTRL: + case R_NWCTRL: if (val & GEM_NWCTRL_RXENA) { for (i = 0; i < s->num_priority_queues; ++i) { gem_get_rx_desc(s, i); @@ -XXX,XX +XXX,XX @@ static void gem_write(void *opaque, hwaddr offset, uint64_t val, } break; - case GEM_TXSTATUS: + case R_TXSTATUS: gem_update_int_status(s); break; - case GEM_RXQBASE: + case R_RXQBASE: s->rx_desc_addr[0] = val; break; - case GEM_RECEIVE_Q1_PTR ... GEM_RECEIVE_Q7_PTR: - s->rx_desc_addr[offset - GEM_RECEIVE_Q1_PTR + 1] = val; + case R_RECEIVE_Q1_PTR ... R_RECEIVE_Q7_PTR: + s->rx_desc_addr[offset - R_RECEIVE_Q1_PTR + 1] = val; break; - case GEM_TXQBASE: + case R_TXQBASE: s->tx_desc_addr[0] = val; break; - case GEM_TRANSMIT_Q1_PTR ... GEM_TRANSMIT_Q7_PTR: - s->tx_desc_addr[offset - GEM_TRANSMIT_Q1_PTR + 1] = val; + case R_TRANSMIT_Q1_PTR ... R_TRANSMIT_Q7_PTR: + s->tx_desc_addr[offset - R_TRANSMIT_Q1_PTR + 1] = val; break; - case GEM_RXSTATUS: + case R_RXSTATUS: gem_update_int_status(s); break; - case GEM_IER: - s->regs[GEM_IMR] &= ~val; + case R_IER: + s->regs[R_IMR] &= ~val; gem_update_int_status(s); break; - case GEM_JUMBO_MAX_LEN: - s->regs[GEM_JUMBO_MAX_LEN] = val & MAX_JUMBO_FRAME_SIZE_MASK; + case R_JUMBO_MAX_LEN: + s->regs[R_JUMBO_MAX_LEN] = val & MAX_JUMBO_FRAME_SIZE_MASK; break; - case GEM_INT_Q1_ENABLE ... GEM_INT_Q7_ENABLE: - s->regs[GEM_INT_Q1_MASK + offset - GEM_INT_Q1_ENABLE] &= ~val; + case R_INT_Q1_ENABLE ... R_INT_Q7_ENABLE: + s->regs[R_INT_Q1_MASK + offset - R_INT_Q1_ENABLE] &= ~val; gem_update_int_status(s); break; - case GEM_IDR: - s->regs[GEM_IMR] |= val; + case R_IDR: + s->regs[R_IMR] |= val; gem_update_int_status(s); break; - case GEM_INT_Q1_DISABLE ... GEM_INT_Q7_DISABLE: - s->regs[GEM_INT_Q1_MASK + offset - GEM_INT_Q1_DISABLE] |= val; + case R_INT_Q1_DISABLE ... R_INT_Q7_DISABLE: + s->regs[R_INT_Q1_MASK + offset - R_INT_Q1_DISABLE] |= val; gem_update_int_status(s); break; - case GEM_SPADDR1LO: - case GEM_SPADDR2LO: - case GEM_SPADDR3LO: - case GEM_SPADDR4LO: - s->sar_active[(offset - GEM_SPADDR1LO) / 2] = false; + case R_SPADDR1LO: + case R_SPADDR2LO: + case R_SPADDR3LO: + case R_SPADDR4LO: + s->sar_active[(offset - R_SPADDR1LO) / 2] = false; break; - case GEM_SPADDR1HI: - case GEM_SPADDR2HI: - case GEM_SPADDR3HI: - case GEM_SPADDR4HI: - s->sar_active[(offset - GEM_SPADDR1HI) / 2] = true; + case R_SPADDR1HI: + case R_SPADDR2HI: + case R_SPADDR3HI: + case R_SPADDR4HI: + s->sar_active[(offset - R_SPADDR1HI) / 2] = true; break; - case GEM_PHYMNTNC: + case R_PHYMNTNC: if (val & GEM_PHYMNTNC_OP_W) { uint32_t phy_addr, reg_num; -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Describe screening registers fields using the FIELD macros. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-3-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 94 ++++++++++++++++++++++---------------------- 1 file changed, 48 insertions(+), 46 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(INT_Q1_DISABLE, 0x620) REG32(INT_Q7_DISABLE, 0x638) REG32(SCREENING_TYPE1_REG0, 0x500) - -#define GEM_ST1R_UDP_PORT_MATCH_ENABLE (1 << 29) -#define GEM_ST1R_DSTC_ENABLE (1 << 28) -#define GEM_ST1R_UDP_PORT_MATCH_SHIFT (12) -#define GEM_ST1R_UDP_PORT_MATCH_WIDTH (27 - GEM_ST1R_UDP_PORT_MATCH_SHIFT + 1) -#define GEM_ST1R_DSTC_MATCH_SHIFT (4) -#define GEM_ST1R_DSTC_MATCH_WIDTH (11 - GEM_ST1R_DSTC_MATCH_SHIFT + 1) -#define GEM_ST1R_QUEUE_SHIFT (0) -#define GEM_ST1R_QUEUE_WIDTH (3 - GEM_ST1R_QUEUE_SHIFT + 1) + FIELD(SCREENING_TYPE1_REG0, QUEUE_NUM, 0, 4) + FIELD(SCREENING_TYPE1_REG0, DSTC_MATCH, 4, 8) + FIELD(SCREENING_TYPE1_REG0, UDP_PORT_MATCH, 12, 16) + FIELD(SCREENING_TYPE1_REG0, DSTC_ENABLE, 28, 1) + FIELD(SCREENING_TYPE1_REG0, UDP_PORT_MATCH_EN, 29, 1) + FIELD(SCREENING_TYPE1_REG0, DROP_ON_MATCH, 30, 1) REG32(SCREENING_TYPE2_REG0, 0x540) - -#define GEM_ST2R_COMPARE_A_ENABLE (1 << 18) -#define GEM_ST2R_COMPARE_A_SHIFT (13) -#define GEM_ST2R_COMPARE_WIDTH (17 - GEM_ST2R_COMPARE_A_SHIFT + 1) -#define GEM_ST2R_ETHERTYPE_ENABLE (1 << 12) -#define GEM_ST2R_ETHERTYPE_INDEX_SHIFT (9) -#define GEM_ST2R_ETHERTYPE_INDEX_WIDTH (11 - GEM_ST2R_ETHERTYPE_INDEX_SHIFT \ - + 1) -#define GEM_ST2R_QUEUE_SHIFT (0) -#define GEM_ST2R_QUEUE_WIDTH (3 - GEM_ST2R_QUEUE_SHIFT + 1) + FIELD(SCREENING_TYPE2_REG0, QUEUE_NUM, 0, 4) + FIELD(SCREENING_TYPE2_REG0, VLAN_PRIORITY, 4, 3) + FIELD(SCREENING_TYPE2_REG0, VLAN_ENABLE, 8, 1) + FIELD(SCREENING_TYPE2_REG0, ETHERTYPE_REG_INDEX, 9, 3) + FIELD(SCREENING_TYPE2_REG0, ETHERTYPE_ENABLE, 12, 1) + FIELD(SCREENING_TYPE2_REG0, COMPARE_A, 13, 5) + FIELD(SCREENING_TYPE2_REG0, COMPARE_A_ENABLE, 18, 1) + FIELD(SCREENING_TYPE2_REG0, COMPARE_B, 19, 5) + FIELD(SCREENING_TYPE2_REG0, COMPARE_B_ENABLE, 24, 1) + FIELD(SCREENING_TYPE2_REG0, COMPARE_C, 25, 5) + FIELD(SCREENING_TYPE2_REG0, COMPARE_C_ENABLE, 30, 1) + FIELD(SCREENING_TYPE2_REG0, DROP_ON_MATCH, 31, 1) REG32(SCREENING_TYPE2_ETHERTYPE_REG0, 0x6e0) -REG32(TYPE2_COMPARE_0_WORD_0, 0x700) -#define GEM_T2CW1_COMPARE_OFFSET_SHIFT (7) -#define GEM_T2CW1_COMPARE_OFFSET_WIDTH (8 - GEM_T2CW1_COMPARE_OFFSET_SHIFT + 1) -#define GEM_T2CW1_OFFSET_VALUE_SHIFT (0) -#define GEM_T2CW1_OFFSET_VALUE_WIDTH (6 - GEM_T2CW1_OFFSET_VALUE_SHIFT + 1) +REG32(TYPE2_COMPARE_0_WORD_0, 0x700) + FIELD(TYPE2_COMPARE_0_WORD_0, MASK_VALUE, 0, 16) + FIELD(TYPE2_COMPARE_0_WORD_0, COMPARE_VALUE, 16, 16) + +REG32(TYPE2_COMPARE_0_WORD_1, 0x704) + FIELD(TYPE2_COMPARE_0_WORD_1, OFFSET_VALUE, 0, 7) + FIELD(TYPE2_COMPARE_0_WORD_1, COMPARE_OFFSET, 7, 2) + FIELD(TYPE2_COMPARE_0_WORD_1, DISABLE_MASK, 9, 1) + FIELD(TYPE2_COMPARE_0_WORD_1, COMPARE_VLAN_ID, 10, 1) /*****************************************/ #define GEM_NWCTRL_TXSTART 0x00000200 /* Transmit Enable */ @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, mismatched = false; /* Screening is based on UDP Port */ - if (reg & GEM_ST1R_UDP_PORT_MATCH_ENABLE) { + if (FIELD_EX32(reg, SCREENING_TYPE1_REG0, UDP_PORT_MATCH_EN)) { uint16_t udp_port = rxbuf_ptr[14 + 22] << 8 | rxbuf_ptr[14 + 23]; - if (udp_port == extract32(reg, GEM_ST1R_UDP_PORT_MATCH_SHIFT, - GEM_ST1R_UDP_PORT_MATCH_WIDTH)) { + if (udp_port == FIELD_EX32(reg, SCREENING_TYPE1_REG0, UDP_PORT_MATCH)) { matched = true; } else { mismatched = true; @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, } /* Screening is based on DS/TC */ - if (reg & GEM_ST1R_DSTC_ENABLE) { + if (FIELD_EX32(reg, SCREENING_TYPE1_REG0, DSTC_ENABLE)) { uint8_t dscp = rxbuf_ptr[14 + 1]; - if (dscp == extract32(reg, GEM_ST1R_DSTC_MATCH_SHIFT, - GEM_ST1R_DSTC_MATCH_WIDTH)) { + if (dscp == FIELD_EX32(reg, SCREENING_TYPE1_REG0, DSTC_MATCH)) { matched = true; } else { mismatched = true; @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, } if (matched && !mismatched) { - return extract32(reg, GEM_ST1R_QUEUE_SHIFT, GEM_ST1R_QUEUE_WIDTH); + return FIELD_EX32(reg, SCREENING_TYPE1_REG0, QUEUE_NUM); } } @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, matched = false; mismatched = false; - if (reg & GEM_ST2R_ETHERTYPE_ENABLE) { + if (FIELD_EX32(reg, SCREENING_TYPE2_REG0, ETHERTYPE_ENABLE)) { uint16_t type = rxbuf_ptr[12] << 8 | rxbuf_ptr[13]; - int et_idx = extract32(reg, GEM_ST2R_ETHERTYPE_INDEX_SHIFT, - GEM_ST2R_ETHERTYPE_INDEX_WIDTH); + int et_idx = FIELD_EX32(reg, SCREENING_TYPE2_REG0, + ETHERTYPE_REG_INDEX); if (et_idx > s->num_type2_screeners) { qemu_log_mask(LOG_GUEST_ERROR, "Out of range ethertype " @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, /* Compare A, B, C */ for (j = 0; j < 3; j++) { - uint32_t cr0, cr1, mask; + uint32_t cr0, cr1, mask, compare; uint16_t rx_cmp; int offset; - int cr_idx = extract32(reg, GEM_ST2R_COMPARE_A_SHIFT + j * 6, - GEM_ST2R_COMPARE_WIDTH); + int cr_idx = extract32(reg, R_SCREENING_TYPE2_REG0_COMPARE_A_SHIFT + j * 6, + R_SCREENING_TYPE2_REG0_COMPARE_A_LENGTH); - if (!(reg & (GEM_ST2R_COMPARE_A_ENABLE << (j * 6)))) { + if (!extract32(reg, R_SCREENING_TYPE2_REG0_COMPARE_A_ENABLE_SHIFT + j * 6, + R_SCREENING_TYPE2_REG0_COMPARE_A_ENABLE_LENGTH)) { continue; } + if (cr_idx > s->num_type2_screeners) { qemu_log_mask(LOG_GUEST_ERROR, "Out of range compare " "register index: %d\n", cr_idx); } cr0 = s->regs[R_TYPE2_COMPARE_0_WORD_0 + cr_idx * 2]; - cr1 = s->regs[R_TYPE2_COMPARE_0_WORD_0 + cr_idx * 2 + 1]; - offset = extract32(cr1, GEM_T2CW1_OFFSET_VALUE_SHIFT, - GEM_T2CW1_OFFSET_VALUE_WIDTH); + cr1 = s->regs[R_TYPE2_COMPARE_0_WORD_1 + cr_idx * 2]; + offset = FIELD_EX32(cr1, TYPE2_COMPARE_0_WORD_1, OFFSET_VALUE); - switch (extract32(cr1, GEM_T2CW1_COMPARE_OFFSET_SHIFT, - GEM_T2CW1_COMPARE_OFFSET_WIDTH)) { + switch (FIELD_EX32(cr1, TYPE2_COMPARE_0_WORD_1, COMPARE_OFFSET)) { case 3: /* Skip UDP header */ qemu_log_mask(LOG_UNIMP, "TCP compare offsets" "unimplemented - assuming UDP\n"); @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, } rx_cmp = rxbuf_ptr[offset] << 8 | rxbuf_ptr[offset]; - mask = extract32(cr0, 0, 16); + mask = FIELD_EX32(cr0, TYPE2_COMPARE_0_WORD_0, MASK_VALUE); + compare = FIELD_EX32(cr0, TYPE2_COMPARE_0_WORD_0, COMPARE_VALUE); - if ((rx_cmp & mask) == (extract32(cr0, 16, 16) & mask)) { + if ((rx_cmp & mask) == (compare & mask)) { matched = true; } else { mismatched = true; @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, } if (matched && !mismatched) { - return extract32(reg, GEM_ST2R_QUEUE_SHIFT, GEM_ST2R_QUEUE_WIDTH); + return FIELD_EX32(reg, SCREENING_TYPE2_REG0, QUEUE_NUM); } } -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use the FIELD macro to describe the NWCTRL register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-4-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 53 +++++++++++++++++++++++++++++++++----------- 1 file changed, 40 insertions(+), 13 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ } while (0) REG32(NWCTRL, 0x0) /* Network Control reg */ + FIELD(NWCTRL, LOOPBACK , 0, 1) + FIELD(NWCTRL, LOOPBACK_LOCAL , 1, 1) + FIELD(NWCTRL, ENABLE_RECEIVE, 2, 1) + FIELD(NWCTRL, ENABLE_TRANSMIT, 3, 1) + FIELD(NWCTRL, MAN_PORT_EN , 4, 1) + FIELD(NWCTRL, CLEAR_ALL_STATS_REGS , 5, 1) + FIELD(NWCTRL, INC_ALL_STATS_REGS, 6, 1) + FIELD(NWCTRL, STATS_WRITE_EN, 7, 1) + FIELD(NWCTRL, BACK_PRESSURE, 8, 1) + FIELD(NWCTRL, TRANSMIT_START , 9, 1) + FIELD(NWCTRL, TRANSMIT_HALT, 10, 1) + FIELD(NWCTRL, TX_PAUSE_FRAME_RE, 11, 1) + FIELD(NWCTRL, TX_PAUSE_FRAME_ZE, 12, 1) + FIELD(NWCTRL, STATS_TAKE_SNAP, 13, 1) + FIELD(NWCTRL, STATS_READ_SNAP, 14, 1) + FIELD(NWCTRL, STORE_RX_TS, 15, 1) + FIELD(NWCTRL, PFC_ENABLE, 16, 1) + FIELD(NWCTRL, PFC_PRIO_BASED, 17, 1) + FIELD(NWCTRL, FLUSH_RX_PKT_PCLK , 18, 1) + FIELD(NWCTRL, TX_LPI_EN, 19, 1) + FIELD(NWCTRL, PTP_UNICAST_ENA, 20, 1) + FIELD(NWCTRL, ALT_SGMII_MODE, 21, 1) + FIELD(NWCTRL, STORE_UDP_OFFSET, 22, 1) + FIELD(NWCTRL, EXT_TSU_PORT_EN, 23, 1) + FIELD(NWCTRL, ONE_STEP_SYNC_MO, 24, 1) + FIELD(NWCTRL, PFC_CTRL , 25, 1) + FIELD(NWCTRL, EXT_RXQ_SEL_EN , 26, 1) + FIELD(NWCTRL, OSS_CORRECTION_FIELD, 27, 1) + FIELD(NWCTRL, SEL_MII_ON_RGMII, 28, 1) + FIELD(NWCTRL, TWO_PT_FIVE_GIG, 29, 1) + FIELD(NWCTRL, IFG_EATS_QAV_CREDIT, 30, 1) + REG32(NWCFG, 0x4) /* Network Config reg */ REG32(NWSTATUS, 0x8) /* Network Status reg */ REG32(USERIO, 0xc) /* User IO reg */ @@ -XXX,XX +XXX,XX @@ REG32(TYPE2_COMPARE_0_WORD_1, 0x704) FIELD(TYPE2_COMPARE_0_WORD_1, COMPARE_VLAN_ID, 10, 1) /*****************************************/ -#define GEM_NWCTRL_TXSTART 0x00000200 /* Transmit Enable */ -#define GEM_NWCTRL_TXENA 0x00000008 /* Transmit Enable */ -#define GEM_NWCTRL_RXENA 0x00000004 /* Receive Enable */ -#define GEM_NWCTRL_LOCALLOOP 0x00000002 /* Local Loopback */ - #define GEM_NWCFG_STRIP_FCS 0x00020000 /* Strip FCS field */ #define GEM_NWCFG_LERR_DISC 0x00010000 /* Discard RX frames with len err */ #define GEM_NWCFG_BUFF_OFST_M 0x0000C000 /* Receive buffer offset mask */ @@ -XXX,XX +XXX,XX @@ static bool gem_can_receive(NetClientState *nc) s = qemu_get_nic_opaque(nc); /* Do nothing if receive is not enabled. */ - if (!(s->regs[R_NWCTRL] & GEM_NWCTRL_RXENA)) { + if (!FIELD_EX32(s->regs[R_NWCTRL], NWCTRL, ENABLE_RECEIVE)) { if (s->can_rx_state != 1) { s->can_rx_state = 1; DB_PRINT("can't receive - no enable\n"); @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) int q = 0; /* Do nothing if transmit is not enabled. */ - if (!(s->regs[R_NWCTRL] & GEM_NWCTRL_TXENA)) { + if (!FIELD_EX32(s->regs[R_NWCTRL], NWCTRL, ENABLE_TRANSMIT)) { return; } @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) while (tx_desc_get_used(desc) == 0) { /* Do nothing if transmit is not enabled. */ - if (!(s->regs[R_NWCTRL] & GEM_NWCTRL_TXENA)) { + if (!FIELD_EX32(s->regs[R_NWCTRL], NWCTRL, ENABLE_TRANSMIT)) { return; } print_gem_tx_desc(desc, q); @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) gem_transmit_updatestats(s, s->tx_packet, total_bytes); /* Send the packet somewhere */ - if (s->phy_loop || (s->regs[R_NWCTRL] & - GEM_NWCTRL_LOCALLOOP)) { + if (s->phy_loop || FIELD_EX32(s->regs[R_NWCTRL], NWCTRL, + LOOPBACK_LOCAL)) { qemu_receive_packet(qemu_get_queue(s->nic), s->tx_packet, total_bytes); } else { @@ -XXX,XX +XXX,XX @@ static void gem_write(void *opaque, hwaddr offset, uint64_t val, /* Handle register write side effects */ switch (offset) { case R_NWCTRL: - if (val & GEM_NWCTRL_RXENA) { + if (FIELD_EX32(val, NWCTRL, ENABLE_RECEIVE)) { for (i = 0; i < s->num_priority_queues; ++i) { gem_get_rx_desc(s, i); } } - if (val & GEM_NWCTRL_TXSTART) { + if (FIELD_EX32(val, NWCTRL, TRANSMIT_START)) { gem_transmit(s); } - if (!(val & GEM_NWCTRL_TXENA)) { + if (!(FIELD_EX32(val, NWCTRL, ENABLE_TRANSMIT))) { /* Reset to start of Q when transmit disabled. */ for (i = 0; i < s->num_priority_queues; i++) { s->tx_desc_addr[i] = gem_get_tx_queue_base_addr(s, i); -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use de FIELD macro to describe the NWCFG register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-5-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 60 ++++++++++++++++++++++++++++---------------- 1 file changed, 39 insertions(+), 21 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(NWCTRL, 0x0) /* Network Control reg */ FIELD(NWCTRL, IFG_EATS_QAV_CREDIT, 30, 1) REG32(NWCFG, 0x4) /* Network Config reg */ + FIELD(NWCFG, SPEED, 0, 1) + FIELD(NWCFG, FULL_DUPLEX, 1, 1) + FIELD(NWCFG, DISCARD_NON_VLAN_FRAMES, 2, 1) + FIELD(NWCFG, JUMBO_FRAMES, 3, 1) + FIELD(NWCFG, PROMISC, 4, 1) + FIELD(NWCFG, NO_BROADCAST, 5, 1) + FIELD(NWCFG, MULTICAST_HASH_EN, 6, 1) + FIELD(NWCFG, UNICAST_HASH_EN, 7, 1) + FIELD(NWCFG, RECV_1536_BYTE_FRAMES, 8, 1) + FIELD(NWCFG, EXTERNAL_ADDR_MATCH_EN, 9, 1) + FIELD(NWCFG, GIGABIT_MODE_ENABLE, 10, 1) + FIELD(NWCFG, PCS_SELECT, 11, 1) + FIELD(NWCFG, RETRY_TEST, 12, 1) + FIELD(NWCFG, PAUSE_ENABLE, 13, 1) + FIELD(NWCFG, RECV_BUF_OFFSET, 14, 2) + FIELD(NWCFG, LEN_ERR_DISCARD, 16, 1) + FIELD(NWCFG, FCS_REMOVE, 17, 1) + FIELD(NWCFG, MDC_CLOCK_DIV, 18, 3) + FIELD(NWCFG, DATA_BUS_WIDTH, 21, 2) + FIELD(NWCFG, DISABLE_COPY_PAUSE_FRAMES, 23, 1) + FIELD(NWCFG, RECV_CSUM_OFFLOAD_EN, 24, 1) + FIELD(NWCFG, EN_HALF_DUPLEX_RX, 25, 1) + FIELD(NWCFG, IGNORE_RX_FCS, 26, 1) + FIELD(NWCFG, SGMII_MODE_ENABLE, 27, 1) + FIELD(NWCFG, IPG_STRETCH_ENABLE, 28, 1) + FIELD(NWCFG, NSP_ACCEPT, 29, 1) + FIELD(NWCFG, IGNORE_IPG_RX_ER, 30, 1) + FIELD(NWCFG, UNI_DIRECTION_ENABLE, 31, 1) + REG32(NWSTATUS, 0x8) /* Network Status reg */ REG32(USERIO, 0xc) /* User IO reg */ REG32(DMACFG, 0x10) /* DMA Control reg */ @@ -XXX,XX +XXX,XX @@ REG32(TYPE2_COMPARE_0_WORD_1, 0x704) FIELD(TYPE2_COMPARE_0_WORD_1, COMPARE_VLAN_ID, 10, 1) /*****************************************/ -#define GEM_NWCFG_STRIP_FCS 0x00020000 /* Strip FCS field */ -#define GEM_NWCFG_LERR_DISC 0x00010000 /* Discard RX frames with len err */ -#define GEM_NWCFG_BUFF_OFST_M 0x0000C000 /* Receive buffer offset mask */ -#define GEM_NWCFG_BUFF_OFST_S 14 /* Receive buffer offset shift */ -#define GEM_NWCFG_RCV_1538 0x00000100 /* Receive 1538 bytes frame */ -#define GEM_NWCFG_UCAST_HASH 0x00000080 /* accept unicast if hash match */ -#define GEM_NWCFG_MCAST_HASH 0x00000040 /* accept multicast if hash match */ -#define GEM_NWCFG_BCAST_REJ 0x00000020 /* Reject broadcast packets */ -#define GEM_NWCFG_PROMISC 0x00000010 /* Accept all packets */ -#define GEM_NWCFG_JUMBO_FRAME 0x00000008 /* Jumbo Frames enable */ - #define GEM_DMACFG_ADDR_64B (1U << 30) #define GEM_DMACFG_TX_BD_EXT (1U << 29) #define GEM_DMACFG_RX_BD_EXT (1U << 28) @@ -XXX,XX +XXX,XX @@ static const uint8_t broadcast_addr[] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF }; static uint32_t gem_get_max_buf_len(CadenceGEMState *s, bool tx) { uint32_t size; - if (s->regs[R_NWCFG] & GEM_NWCFG_JUMBO_FRAME) { + if (FIELD_EX32(s->regs[R_NWCFG], NWCFG, JUMBO_FRAMES)) { size = s->regs[R_JUMBO_MAX_LEN]; if (size > s->jumbo_max_len) { size = s->jumbo_max_len; @@ -XXX,XX +XXX,XX @@ static uint32_t gem_get_max_buf_len(CadenceGEMState *s, bool tx) } else if (tx) { size = 1518; } else { - size = s->regs[R_NWCFG] & GEM_NWCFG_RCV_1538 ? 1538 : 1518; + size = FIELD_EX32(s->regs[R_NWCFG], + NWCFG, RECV_1536_BYTE_FRAMES) ? 1538 : 1518; } return size; } @@ -XXX,XX +XXX,XX @@ static int gem_mac_address_filter(CadenceGEMState *s, const uint8_t *packet) int i, is_mc; /* Promiscuous mode? */ - if (s->regs[R_NWCFG] & GEM_NWCFG_PROMISC) { + if (FIELD_EX32(s->regs[R_NWCFG], NWCFG, PROMISC)) { return GEM_RX_PROMISCUOUS_ACCEPT; } if (!memcmp(packet, broadcast_addr, 6)) { /* Reject broadcast packets? */ - if (s->regs[R_NWCFG] & GEM_NWCFG_BCAST_REJ) { + if (FIELD_EX32(s->regs[R_NWCFG], NWCFG, NO_BROADCAST)) { return GEM_RX_REJECT; } return GEM_RX_BROADCAST_ACCEPT; @@ -XXX,XX +XXX,XX @@ static int gem_mac_address_filter(CadenceGEMState *s, const uint8_t *packet) /* Accept packets -w- hash match? */ is_mc = is_multicast_ether_addr(packet); - if ((is_mc && (s->regs[R_NWCFG] & GEM_NWCFG_MCAST_HASH)) || - (!is_mc && (s->regs[R_NWCFG] & GEM_NWCFG_UCAST_HASH))) { + if ((is_mc && (FIELD_EX32(s->regs[R_NWCFG], NWCFG, MULTICAST_HASH_EN))) || + (!is_mc && FIELD_EX32(s->regs[R_NWCFG], NWCFG, UNICAST_HASH_EN))) { uint64_t buckets; unsigned hash_index; @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) } /* Discard packets with receive length error enabled ? */ - if (s->regs[R_NWCFG] & GEM_NWCFG_LERR_DISC) { + if (FIELD_EX32(s->regs[R_NWCFG], NWCFG, LEN_ERR_DISCARD)) { unsigned type_len; /* Fish the ethertype / length field out of the RX packet */ @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) /* * Determine configured receive buffer offset (probably 0) */ - rxbuf_offset = (s->regs[R_NWCFG] & GEM_NWCFG_BUFF_OFST_M) >> - GEM_NWCFG_BUFF_OFST_S; + rxbuf_offset = FIELD_EX32(s->regs[R_NWCFG], NWCFG, RECV_BUF_OFFSET); /* The configure size of each receive buffer. Determines how many * buffers needed to hold this packet. @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) } /* Strip of FCS field ? (usually yes) */ - if (s->regs[R_NWCFG] & GEM_NWCFG_STRIP_FCS) { + if (FIELD_EX32(s->regs[R_NWCFG], NWCFG, FCS_REMOVE)) { rxbuf_ptr = (void *)buf; } else { unsigned crc_val; -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use de FIELD macro to describe the DMACFG register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-6-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 48 ++++++++++++++++++++++++++++---------------- 1 file changed, 31 insertions(+), 17 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(NWCFG, 0x4) /* Network Config reg */ REG32(NWSTATUS, 0x8) /* Network Status reg */ REG32(USERIO, 0xc) /* User IO reg */ + REG32(DMACFG, 0x10) /* DMA Control reg */ + FIELD(DMACFG, SEND_BCAST_TO_ALL_QS, 31, 1) + FIELD(DMACFG, DMA_ADDR_BUS_WIDTH, 30, 1) + FIELD(DMACFG, TX_BD_EXT_MODE_EN , 29, 1) + FIELD(DMACFG, RX_BD_EXT_MODE_EN , 28, 1) + FIELD(DMACFG, FORCE_MAX_AMBA_BURST_TX, 26, 1) + FIELD(DMACFG, FORCE_MAX_AMBA_BURST_RX, 25, 1) + FIELD(DMACFG, FORCE_DISCARD_ON_ERR, 24, 1) + FIELD(DMACFG, RX_BUF_SIZE, 16, 8) + FIELD(DMACFG, CRC_ERROR_REPORT, 13, 1) + FIELD(DMACFG, INF_LAST_DBUF_SIZE_EN, 12, 1) + FIELD(DMACFG, TX_PBUF_CSUM_OFFLOAD, 11, 1) + FIELD(DMACFG, TX_PBUF_SIZE, 10, 1) + FIELD(DMACFG, RX_PBUF_SIZE, 8, 2) + FIELD(DMACFG, ENDIAN_SWAP_PACKET, 7, 1) + FIELD(DMACFG, ENDIAN_SWAP_MGNT, 6, 1) + FIELD(DMACFG, HDR_DATA_SPLIT_EN, 5, 1) + FIELD(DMACFG, AMBA_BURST_LEN , 0, 5) +#define GEM_DMACFG_RBUFSZ_MUL 64 /* DMA RX Buffer Size multiplier */ + REG32(TXSTATUS, 0x14) /* TX Status reg */ REG32(RXQBASE, 0x18) /* RX Q Base address reg */ REG32(TXQBASE, 0x1c) /* TX Q Base address reg */ @@ -XXX,XX +XXX,XX @@ REG32(TYPE2_COMPARE_0_WORD_1, 0x704) FIELD(TYPE2_COMPARE_0_WORD_1, COMPARE_VLAN_ID, 10, 1) /*****************************************/ -#define GEM_DMACFG_ADDR_64B (1U << 30) -#define GEM_DMACFG_TX_BD_EXT (1U << 29) -#define GEM_DMACFG_RX_BD_EXT (1U << 28) -#define GEM_DMACFG_RBUFSZ_M 0x00FF0000 /* DMA RX Buffer Size mask */ -#define GEM_DMACFG_RBUFSZ_S 16 /* DMA RX Buffer Size shift */ -#define GEM_DMACFG_RBUFSZ_MUL 64 /* DMA RX Buffer Size multiplier */ -#define GEM_DMACFG_TXCSUM_OFFL 0x00000800 /* Transmit checksum offload */ #define GEM_TXSTATUS_TXCMPL 0x00000020 /* Transmit Complete */ #define GEM_TXSTATUS_USED 0x00000001 /* sw owned descriptor encountered */ @@ -XXX,XX +XXX,XX @@ static inline uint64_t tx_desc_get_buffer(CadenceGEMState *s, uint32_t *desc) { uint64_t ret = desc[0]; - if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (FIELD_EX32(s->regs[R_DMACFG], DMACFG, DMA_ADDR_BUS_WIDTH)) { ret |= (uint64_t)desc[2] << 32; } return ret; @@ -XXX,XX +XXX,XX @@ static inline uint64_t rx_desc_get_buffer(CadenceGEMState *s, uint32_t *desc) { uint64_t ret = desc[0] & ~0x3UL; - if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (FIELD_EX32(s->regs[R_DMACFG], DMACFG, DMA_ADDR_BUS_WIDTH)) { ret |= (uint64_t)desc[2] << 32; } return ret; @@ -XXX,XX +XXX,XX @@ static inline int gem_get_desc_len(CadenceGEMState *s, bool rx_n_tx) { int ret = 2; - if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (FIELD_EX32(s->regs[R_DMACFG], DMACFG, DMA_ADDR_BUS_WIDTH)) { ret += 2; } - if (s->regs[R_DMACFG] & (rx_n_tx ? GEM_DMACFG_RX_BD_EXT - : GEM_DMACFG_TX_BD_EXT)) { + if (s->regs[R_DMACFG] & (rx_n_tx ? R_DMACFG_RX_BD_EXT_MODE_EN_MASK + : R_DMACFG_TX_BD_EXT_MODE_EN_MASK)) { ret += 2; } @@ -XXX,XX +XXX,XX @@ static hwaddr gem_get_desc_addr(CadenceGEMState *s, bool tx, int q) { hwaddr desc_addr = 0; - if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (FIELD_EX32(s->regs[R_DMACFG], DMACFG, DMA_ADDR_BUS_WIDTH)) { desc_addr = s->regs[tx ? R_TBQPH : R_RBQPH]; } desc_addr <<= 32; @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) /* The configure size of each receive buffer. Determines how many * buffers needed to hold this packet. */ - rxbufsize = ((s->regs[R_DMACFG] & GEM_DMACFG_RBUFSZ_M) >> - GEM_DMACFG_RBUFSZ_S) * GEM_DMACFG_RBUFSZ_MUL; + rxbufsize = FIELD_EX32(s->regs[R_DMACFG], DMACFG, RX_BUF_SIZE); + rxbufsize *= GEM_DMACFG_RBUFSZ_MUL; + bytes_to_copy = size; /* Hardware allows a zero value here but warns against it. To avoid QEMU @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) gem_update_int_status(s); /* Is checksum offload enabled? */ - if (s->regs[R_DMACFG] & GEM_DMACFG_TXCSUM_OFFL) { + if (FIELD_EX32(s->regs[R_DMACFG], DMACFG, TX_PBUF_CSUM_OFFLOAD)) { net_checksum_calculate(s->tx_packet, total_bytes, CSUM_ALL); } @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) /* read next descriptor */ if (tx_desc_get_wrap(desc)) { - if (s->regs[R_DMACFG] & GEM_DMACFG_ADDR_64B) { + if (FIELD_EX32(s->regs[R_DMACFG], DMACFG, DMA_ADDR_BUS_WIDTH)) { packet_desc_addr = s->regs[R_TBQPH]; packet_desc_addr <<= 32; } else { -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use de FIELD macro to describe the TXSTATUS and RXSTATUS register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-7-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 34 +++++++++++++++++++++++++--------- 1 file changed, 25 insertions(+), 9 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(DMACFG, 0x10) /* DMA Control reg */ #define GEM_DMACFG_RBUFSZ_MUL 64 /* DMA RX Buffer Size multiplier */ REG32(TXSTATUS, 0x14) /* TX Status reg */ + FIELD(TXSTATUS, TX_USED_BIT_READ_MIDFRAME, 12, 1) + FIELD(TXSTATUS, TX_FRAME_TOO_LARGE, 11, 1) + FIELD(TXSTATUS, TX_DMA_LOCKUP, 10, 1) + FIELD(TXSTATUS, TX_MAC_LOCKUP, 9, 1) + FIELD(TXSTATUS, RESP_NOT_OK, 8, 1) + FIELD(TXSTATUS, LATE_COLLISION, 7, 1) + FIELD(TXSTATUS, TRANSMIT_UNDER_RUN, 6, 1) + FIELD(TXSTATUS, TRANSMIT_COMPLETE, 5, 1) + FIELD(TXSTATUS, AMBA_ERROR, 4, 1) + FIELD(TXSTATUS, TRANSMIT_GO, 3, 1) + FIELD(TXSTATUS, RETRY_LIMIT, 2, 1) + FIELD(TXSTATUS, COLLISION, 1, 1) + FIELD(TXSTATUS, USED_BIT_READ, 0, 1) + REG32(RXQBASE, 0x18) /* RX Q Base address reg */ REG32(TXQBASE, 0x1c) /* TX Q Base address reg */ REG32(RXSTATUS, 0x20) /* RX Status reg */ + FIELD(RXSTATUS, RX_DMA_LOCKUP, 5, 1) + FIELD(RXSTATUS, RX_MAC_LOCKUP, 4, 1) + FIELD(RXSTATUS, RESP_NOT_OK, 3, 1) + FIELD(RXSTATUS, RECEIVE_OVERRUN, 2, 1) + FIELD(RXSTATUS, FRAME_RECEIVED, 1, 1) + FIELD(RXSTATUS, BUF_NOT_AVAILABLE, 0, 1) + REG32(ISR, 0x24) /* Interrupt Status reg */ REG32(IER, 0x28) /* Interrupt Enable reg */ REG32(IDR, 0x2c) /* Interrupt Disable reg */ @@ -XXX,XX +XXX,XX @@ REG32(TYPE2_COMPARE_0_WORD_1, 0x704) /*****************************************/ -#define GEM_TXSTATUS_TXCMPL 0x00000020 /* Transmit Complete */ -#define GEM_TXSTATUS_USED 0x00000001 /* sw owned descriptor encountered */ - -#define GEM_RXSTATUS_FRMRCVD 0x00000002 /* Frame received */ -#define GEM_RXSTATUS_NOBUF 0x00000001 /* Buffer unavailable */ /* GEM_ISR GEM_IER GEM_IDR GEM_IMR */ #define GEM_INT_TXCMPL 0x00000080 /* Transmit Complete */ @@ -XXX,XX +XXX,XX @@ static void gem_get_rx_desc(CadenceGEMState *s, int q) /* Descriptor owned by software ? */ if (rx_desc_get_ownership(s->rx_desc[q]) == 1) { DB_PRINT("descriptor 0x%" HWADDR_PRIx " owned by sw.\n", desc_addr); - s->regs[R_RXSTATUS] |= GEM_RXSTATUS_NOBUF; + s->regs[R_RXSTATUS] |= R_RXSTATUS_BUF_NOT_AVAILABLE_MASK; gem_set_isr(s, q, GEM_INT_RXUSED); /* Handle interrupt consequences */ gem_update_int_status(s); @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) /* Count it */ gem_receive_updatestats(s, buf, size); - s->regs[R_RXSTATUS] |= GEM_RXSTATUS_FRMRCVD; + s->regs[R_RXSTATUS] |= R_RXSTATUS_FRAME_RECEIVED_MASK; gem_set_isr(s, q, GEM_INT_RXCMPL); /* Handle interrupt consequences */ @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) } DB_PRINT("TX descriptor next: 0x%08x\n", s->tx_desc_addr[q]); - s->regs[R_TXSTATUS] |= GEM_TXSTATUS_TXCMPL; + s->regs[R_TXSTATUS] |= R_TXSTATUS_TRANSMIT_COMPLETE_MASK; gem_set_isr(s, q, GEM_INT_TXCMPL); /* Handle interrupt consequences */ @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) } if (tx_desc_get_used(desc)) { - s->regs[R_TXSTATUS] |= GEM_TXSTATUS_USED; + s->regs[R_TXSTATUS] |= R_TXSTATUS_USED_BIT_READ_MASK; /* IRQ TXUSED is defined only for queue 0 */ if (q == 0) { gem_set_isr(s, 0, GEM_INT_TXUSED); -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use de FIELD macro to describe the IRQ related register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-8-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 51 +++++++++++++++++++++++++++++++++----------- 1 file changed, 39 insertions(+), 12 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(RXSTATUS, 0x20) /* RX Status reg */ FIELD(RXSTATUS, BUF_NOT_AVAILABLE, 0, 1) REG32(ISR, 0x24) /* Interrupt Status reg */ + FIELD(ISR, TX_LOCKUP, 31, 1) + FIELD(ISR, RX_LOCKUP, 30, 1) + FIELD(ISR, TSU_TIMER, 29, 1) + FIELD(ISR, WOL, 28, 1) + FIELD(ISR, RECV_LPI, 27, 1) + FIELD(ISR, TSU_SEC_INCR, 26, 1) + FIELD(ISR, PTP_PDELAY_RESP_XMIT, 25, 1) + FIELD(ISR, PTP_PDELAY_REQ_XMIT, 24, 1) + FIELD(ISR, PTP_PDELAY_RESP_RECV, 23, 1) + FIELD(ISR, PTP_PDELAY_REQ_RECV, 22, 1) + FIELD(ISR, PTP_SYNC_XMIT, 21, 1) + FIELD(ISR, PTP_DELAY_REQ_XMIT, 20, 1) + FIELD(ISR, PTP_SYNC_RECV, 19, 1) + FIELD(ISR, PTP_DELAY_REQ_RECV, 18, 1) + FIELD(ISR, PCS_LP_PAGE_RECV, 17, 1) + FIELD(ISR, PCS_AN_COMPLETE, 16, 1) + FIELD(ISR, EXT_IRQ, 15, 1) + FIELD(ISR, PAUSE_FRAME_XMIT, 14, 1) + FIELD(ISR, PAUSE_TIME_ELAPSED, 13, 1) + FIELD(ISR, PAUSE_FRAME_RECV, 12, 1) + FIELD(ISR, RESP_NOT_OK, 11, 1) + FIELD(ISR, RECV_OVERRUN, 10, 1) + FIELD(ISR, LINK_CHANGE, 9, 1) + FIELD(ISR, USXGMII_INT, 8, 1) + FIELD(ISR, XMIT_COMPLETE, 7, 1) + FIELD(ISR, AMBA_ERROR, 6, 1) + FIELD(ISR, RETRY_EXCEEDED, 5, 1) + FIELD(ISR, XMIT_UNDER_RUN, 4, 1) + FIELD(ISR, TX_USED, 3, 1) + FIELD(ISR, RX_USED, 2, 1) + FIELD(ISR, RECV_COMPLETE, 1, 1) + FIELD(ISR, MGNT_FRAME_SENT, 0, 1) REG32(IER, 0x28) /* Interrupt Enable reg */ REG32(IDR, 0x2c) /* Interrupt Disable reg */ REG32(IMR, 0x30) /* Interrupt Mask reg */ + REG32(PHYMNTNC, 0x34) /* Phy Maintenance reg */ REG32(RXPAUSE, 0x38) /* RX Pause Time reg */ REG32(TXPAUSE, 0x3c) /* TX Pause Time reg */ @@ -XXX,XX +XXX,XX @@ REG32(TYPE2_COMPARE_0_WORD_1, 0x704) /*****************************************/ -/* GEM_ISR GEM_IER GEM_IDR GEM_IMR */ -#define GEM_INT_TXCMPL 0x00000080 /* Transmit Complete */ -#define GEM_INT_AMBA_ERR 0x00000040 -#define GEM_INT_TXUSED 0x00000008 -#define GEM_INT_RXUSED 0x00000004 -#define GEM_INT_RXCMPL 0x00000002 #define GEM_PHYMNTNC_OP_R 0x20000000 /* read operation */ #define GEM_PHYMNTNC_OP_W 0x10000000 /* write operation */ @@ -XXX,XX +XXX,XX @@ static void gem_get_rx_desc(CadenceGEMState *s, int q) if (rx_desc_get_ownership(s->rx_desc[q]) == 1) { DB_PRINT("descriptor 0x%" HWADDR_PRIx " owned by sw.\n", desc_addr); s->regs[R_RXSTATUS] |= R_RXSTATUS_BUF_NOT_AVAILABLE_MASK; - gem_set_isr(s, q, GEM_INT_RXUSED); + gem_set_isr(s, q, R_ISR_RX_USED_MASK); /* Handle interrupt consequences */ gem_update_int_status(s); } @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) if (size > gem_get_max_buf_len(s, false)) { qemu_log_mask(LOG_GUEST_ERROR, "rx frame too long\n"); - gem_set_isr(s, q, GEM_INT_AMBA_ERR); + gem_set_isr(s, q, R_ISR_AMBA_ERROR_MASK); return -1; } @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) gem_receive_updatestats(s, buf, size); s->regs[R_RXSTATUS] |= R_RXSTATUS_FRAME_RECEIVED_MASK; - gem_set_isr(s, q, GEM_INT_RXCMPL); + gem_set_isr(s, q, R_ISR_RECV_COMPLETE_MASK); /* Handle interrupt consequences */ gem_update_int_status(s); @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) HWADDR_PRIx " too large: size 0x%x space 0x%zx\n", packet_desc_addr, tx_desc_get_length(desc), gem_get_max_buf_len(s, true) - (p - s->tx_packet)); - gem_set_isr(s, q, GEM_INT_AMBA_ERR); + gem_set_isr(s, q, R_ISR_AMBA_ERROR_MASK); break; } @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) DB_PRINT("TX descriptor next: 0x%08x\n", s->tx_desc_addr[q]); s->regs[R_TXSTATUS] |= R_TXSTATUS_TRANSMIT_COMPLETE_MASK; - gem_set_isr(s, q, GEM_INT_TXCMPL); + gem_set_isr(s, q, R_ISR_XMIT_COMPLETE_MASK); /* Handle interrupt consequences */ gem_update_int_status(s); @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) s->regs[R_TXSTATUS] |= R_TXSTATUS_USED_BIT_READ_MASK; /* IRQ TXUSED is defined only for queue 0 */ if (q == 0) { - gem_set_isr(s, 0, GEM_INT_TXUSED); + gem_set_isr(s, 0, R_ISR_TX_USED_MASK); } gem_update_int_status(s); } -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use the FIELD macro to describe the DESCONF6 register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20231017194422.4124691-9-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(DESCONF3, 0x288) REG32(DESCONF4, 0x28c) REG32(DESCONF5, 0x290) REG32(DESCONF6, 0x294) -#define GEM_DESCONF6_64B_MASK (1U << 23) + FIELD(DESCONF6, DMA_ADDR_64B, 23, 1) REG32(DESCONF7, 0x298) REG32(INT_Q1_STATUS, 0x400) @@ -XXX,XX +XXX,XX @@ static void gem_reset(DeviceState *d) s->regs[R_DESCONF] = 0x02D00111; s->regs[R_DESCONF2] = 0x2ab10000 | s->jumbo_max_len; s->regs[R_DESCONF5] = 0x002f2045; - s->regs[R_DESCONF6] = GEM_DESCONF6_64B_MASK; + s->regs[R_DESCONF6] = R_DESCONF6_DMA_ADDR_64B_MASK; s->regs[R_INT_Q1_MASK] = 0x00000CE6; s->regs[R_JUMBO_MAX_LEN] = s->jumbo_max_len; -- 2.34.1 From: Luc Michel <luc.michel@amd.com> Use the FIELD macro to describe the PHYMNTNC register fields. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-10-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ REG32(IDR, 0x2c) /* Interrupt Disable reg */ REG32(IMR, 0x30) /* Interrupt Mask reg */ REG32(PHYMNTNC, 0x34) /* Phy Maintenance reg */ + FIELD(PHYMNTNC, DATA, 0, 16) + FIELD(PHYMNTNC, REG_ADDR, 18, 5) + FIELD(PHYMNTNC, PHY_ADDR, 23, 5) + FIELD(PHYMNTNC, OP, 28, 2) + FIELD(PHYMNTNC, ST, 30, 2) +#define MDIO_OP_READ 0x3 +#define MDIO_OP_WRITE 0x2 + REG32(RXPAUSE, 0x38) /* RX Pause Time reg */ REG32(TXPAUSE, 0x3c) /* TX Pause Time reg */ REG32(TXPARTIALSF, 0x40) /* TX Partial Store and Forward */ @@ -XXX,XX +XXX,XX @@ REG32(TYPE2_COMPARE_0_WORD_1, 0x704) -#define GEM_PHYMNTNC_OP_R 0x20000000 /* read operation */ -#define GEM_PHYMNTNC_OP_W 0x10000000 /* write operation */ -#define GEM_PHYMNTNC_ADDR 0x0F800000 /* Address bits */ -#define GEM_PHYMNTNC_ADDR_SHFT 23 -#define GEM_PHYMNTNC_REG 0x007C0000 /* register bits */ -#define GEM_PHYMNTNC_REG_SHIFT 18 - /* Marvell PHY definitions */ #define BOARD_PHY_ADDRESS 0 /* PHY address we will emulate a device at */ @@ -XXX,XX +XXX,XX @@ static uint64_t gem_read(void *opaque, hwaddr offset, unsigned size) /* The interrupts get updated at the end of the function. */ break; case R_PHYMNTNC: - if (retval & GEM_PHYMNTNC_OP_R) { + if (FIELD_EX32(retval, PHYMNTNC, OP) == MDIO_OP_READ) { uint32_t phy_addr, reg_num; - phy_addr = (retval & GEM_PHYMNTNC_ADDR) >> GEM_PHYMNTNC_ADDR_SHFT; + phy_addr = FIELD_EX32(retval, PHYMNTNC, PHY_ADDR); if (phy_addr == s->phy_addr) { - reg_num = (retval & GEM_PHYMNTNC_REG) >> GEM_PHYMNTNC_REG_SHIFT; + reg_num = FIELD_EX32(retval, PHYMNTNC, REG_ADDR); retval &= 0xFFFF0000; retval |= gem_phy_read(s, reg_num); } else { @@ -XXX,XX +XXX,XX @@ static void gem_write(void *opaque, hwaddr offset, uint64_t val, s->sar_active[(offset - R_SPADDR1HI) / 2] = true; break; case R_PHYMNTNC: - if (val & GEM_PHYMNTNC_OP_W) { + if (FIELD_EX32(val, PHYMNTNC, OP) == MDIO_OP_WRITE) { uint32_t phy_addr, reg_num; - phy_addr = (val & GEM_PHYMNTNC_ADDR) >> GEM_PHYMNTNC_ADDR_SHFT; + phy_addr = FIELD_EX32(val, PHYMNTNC, PHY_ADDR); if (phy_addr == s->phy_addr) { - reg_num = (val & GEM_PHYMNTNC_REG) >> GEM_PHYMNTNC_REG_SHIFT; + reg_num = FIELD_EX32(val, PHYMNTNC, REG_ADDR); gem_phy_write(s, reg_num, val); } } -- 2.34.1 From: Luc Michel <luc.michel@amd.com> The MDIO access is done only on a write to the PHYMNTNC register. A subsequent read is used to retrieve the result but does not trigger an MDIO access by itself. Refactor the PHY access logic to perform all accesses (MDIO reads and writes) at PHYMNTNC write time. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-11-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 56 ++++++++++++++++++++++++++------------------ 1 file changed, 33 insertions(+), 23 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static void gem_phy_write(CadenceGEMState *s, unsigned reg_num, uint16_t val) s->phy_regs[reg_num] = val; } +static void gem_handle_phy_access(CadenceGEMState *s) +{ + uint32_t val = s->regs[R_PHYMNTNC]; + uint32_t phy_addr, reg_num; + + phy_addr = FIELD_EX32(val, PHYMNTNC, PHY_ADDR); + + if (phy_addr != s->phy_addr) { + /* no phy at this address */ + if (FIELD_EX32(val, PHYMNTNC, OP) == MDIO_OP_READ) { + s->regs[R_PHYMNTNC] = FIELD_DP32(val, PHYMNTNC, DATA, 0xffff); + } + return; + } + + reg_num = FIELD_EX32(val, PHYMNTNC, REG_ADDR); + + switch (FIELD_EX32(val, PHYMNTNC, OP)) { + case MDIO_OP_READ: + s->regs[R_PHYMNTNC] = FIELD_DP32(val, PHYMNTNC, DATA, + gem_phy_read(s, reg_num)); + break; + + case MDIO_OP_WRITE: + gem_phy_write(s, reg_num, val); + break; + + default: + break; /* only clause 22 operations are supported */ + } +} + /* * gem_read32: * Read a GEM register. @@ -XXX,XX +XXX,XX @@ static uint64_t gem_read(void *opaque, hwaddr offset, unsigned size) DB_PRINT("lowering irqs on ISR read\n"); /* The interrupts get updated at the end of the function. */ break; - case R_PHYMNTNC: - if (FIELD_EX32(retval, PHYMNTNC, OP) == MDIO_OP_READ) { - uint32_t phy_addr, reg_num; - - phy_addr = FIELD_EX32(retval, PHYMNTNC, PHY_ADDR); - if (phy_addr == s->phy_addr) { - reg_num = FIELD_EX32(retval, PHYMNTNC, REG_ADDR); - retval &= 0xFFFF0000; - retval |= gem_phy_read(s, reg_num); - } else { - retval |= 0xFFFF; /* No device at this address */ - } - } - break; } /* Squash read to clear bits */ @@ -XXX,XX +XXX,XX @@ static void gem_write(void *opaque, hwaddr offset, uint64_t val, s->sar_active[(offset - R_SPADDR1HI) / 2] = true; break; case R_PHYMNTNC: - if (FIELD_EX32(val, PHYMNTNC, OP) == MDIO_OP_WRITE) { - uint32_t phy_addr, reg_num; - - phy_addr = FIELD_EX32(val, PHYMNTNC, PHY_ADDR); - if (phy_addr == s->phy_addr) { - reg_num = FIELD_EX32(val, PHYMNTNC, REG_ADDR); - gem_phy_write(s, reg_num, val); - } - } + gem_handle_phy_access(s); break; } -- 2.34.1 From: Luc Michel <luc.michel@amd.com> The CRC was stored in an unsigned variable in gem_receive. Change it for a uint32_t to ensure we have the correct variable size here. Signed-off-by: Luc Michel <luc.michel@amd.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: sai.pavan.boddu@amd.com Message-id: 20231017194422.4124691-12-luc.michel@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) if (FIELD_EX32(s->regs[R_NWCFG], NWCFG, FCS_REMOVE)) { rxbuf_ptr = (void *)buf; } else { - unsigned crc_val; + uint32_t crc_val; if (size > MAX_FRAME_SIZE - sizeof(crc_val)) { size = MAX_FRAME_SIZE - sizeof(crc_val); -- 2.34.1