linaro-toolchain August 2021

linaro-toolchain@lists.linaro.org

12 participants
87 discussions

[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-master-arm-spec2k6-Os - Build # 9 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-master-arm-spec2k6-Os. So far, this commit has regressed CI configurations: - tcwg_bmk_llvm_tk1/llvm-master-arm-spec2k6-Os Culprit: <cut> commit 40b752d28d95158e52dba7cfeea92e41b7ccff9a Author: Sanjay Patel <spatel(a)rotateright.com> Date: Mon Jul 5 09:57:39 2021 -0400 [InstCombine] fold icmp slt/sgt of offset value with constant This follows up patches for the unsigned siblings: 0c400e895306 c7b658aeb526 We are translating an offset signed compare to its unsigned equivalent when one end of the range is at the limit (zero or unsigned max). (X + C2) >s C --> X <u (SMAX - C) (if C == C2 - 1) (X + C2) <s C --> X >u (C ^ SMAX) (if C == C2) This probably does not show up much in IR derived from C/C++ source because that would likely have 'nsw', and we have folds for that already. As with the previous unsigned transforms, the folds could be generalized to handle non-constant patterns: https://alive2.llvm.org/ce/z/Y8Xrrm ; sgt define i1 @src(i8 %a, i8 %c) { %c2 = add i8 %c, 1 %t = add i8 %a, %c2 %ov = icmp sgt i8 %t, %c ret i1 %ov } define i1 @tgt(i8 %a, i8 %c) { %c_off = sub i8 127, %c ; SMAX %ov = icmp ult i8 %a, %c_off ret i1 %ov } https://alive2.llvm.org/ce/z/c8uhnk ; slt define i1 @src(i8 %a, i8 %c) { %t = add i8 %a, %c %ov = icmp slt i8 %t, %c ret i1 %ov } define i1 @tgt(i8 %a, i8 %c) { %c_offnot = xor i8 %c, 127 ; SMAX %ov = icmp ugt i8 %a, %c_offnot ret i1 %ov } </cut> Results regressed to (for first_bad == 40b752d28d95158e52dba7cfeea92e41b7ccff9a) # reset_artifacts: -10 # build_abe binutils: -9 # build_abe stage1 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer: -8 # build_abe linux: -7 # build_abe glibc: -6 # build_abe stage2 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer: -5 # build_llvm true: -3 # true: 0 # benchmark -Os_mthumb -- artifacts/build-40b752d28d95158e52dba7cfeea92e41b7ccff9a/results_id: 1 # 401.bzip2,bzip2_base.default regressed by 110 # 401.bzip2,[.] BZ2_decompress regressed by 149 from (for last_good == 32dd914f7182875730eb3453f39dcc584b7219b2) # reset_artifacts: -10 # build_abe binutils: -9 # build_abe stage1 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer: -8 # build_abe linux: -7 # build_abe glibc: -6 # build_abe stage2 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer: -5 # build_llvm true: -3 # true: 0 # benchmark -Os_mthumb -- artifacts/build-32dd914f7182875730eb3453f39dcc584b7219b2/results_id: 1 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-master-arm-spec2k6-Os/1631 Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-master-arm-spec2k6-Os/1622 Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… Configuration details: Reproduce builds: <cut> mkdir investigate-llvm-40b752d28d95158e52dba7cfeea92e41b7ccff9a cd investigate-llvm-40b752d28d95158e52dba7cfeea92e41b7ccff9a git clone https://git.linaro.org/toolchain/jenkins-scripts mkdir -p artifacts/manifests curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail chmod +x artifacts/test.sh # Reproduce the baseline build (build all pre-requisites) ./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh # Save baseline build state (which is then restored in artifacts/test.sh) rsync -a --del --delete-excluded --exclude bisect/ --exclude artifacts/ --exclude llvm/ ./ ./bisect/baseline/ cd llvm # Reproduce first_bad build git checkout --detach 40b752d28d95158e52dba7cfeea92e41b7ccff9a ../artifacts/test.sh # Reproduce last_good build git checkout --detach 32dd914f7182875730eb3453f39dcc584b7219b2 ../artifacts/test.sh cd .. </cut> History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/… Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… Full commit (up to 1000 lines): <cut> commit 40b752d28d95158e52dba7cfeea92e41b7ccff9a Author: Sanjay Patel <spatel(a)rotateright.com> Date: Mon Jul 5 09:57:39 2021 -0400 [InstCombine] fold icmp slt/sgt of offset value with constant This follows up patches for the unsigned siblings: 0c400e895306 c7b658aeb526 We are translating an offset signed compare to its unsigned equivalent when one end of the range is at the limit (zero or unsigned max). (X + C2) >s C --> X <u (SMAX - C) (if C == C2 - 1) (X + C2) <s C --> X >u (C ^ SMAX) (if C == C2) This probably does not show up much in IR derived from C/C++ source because that would likely have 'nsw', and we have folds for that already. As with the previous unsigned transforms, the folds could be generalized to handle non-constant patterns: https://alive2.llvm.org/ce/z/Y8Xrrm ; sgt define i1 @src(i8 %a, i8 %c) { %c2 = add i8 %c, 1 %t = add i8 %a, %c2 %ov = icmp sgt i8 %t, %c ret i1 %ov } define i1 @tgt(i8 %a, i8 %c) { %c_off = sub i8 127, %c ; SMAX %ov = icmp ult i8 %a, %c_off ret i1 %ov } https://alive2.llvm.org/ce/z/c8uhnk ; slt define i1 @src(i8 %a, i8 %c) { %t = add i8 %a, %c %ov = icmp slt i8 %t, %c ret i1 %ov } define i1 @tgt(i8 %a, i8 %c) { %c_offnot = xor i8 %c, 127 ; SMAX %ov = icmp ugt i8 %a, %c_offnot ret i1 %ov } --- .../Transforms/InstCombine/InstCombineCompares.cpp | 21 ++++++++++++++------- llvm/test/Transforms/InstCombine/icmp-add.ll | 20 ++++++++++---------- 2 files changed, 24 insertions(+), 17 deletions(-) diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp index 6bd479def210..6e66c61f5e46 100644 --- a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp +++ b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp @@ -2636,20 +2636,27 @@ Instruction *InstCombinerImpl::foldICmpAddConstant(ICmpInst &Cmp, // Fold icmp pred (add X, C2), C. Value *X = Add->getOperand(0); Type *Ty = Add->getType(); - CmpInst::Predicate Pred = Cmp.getPredicate(); + const CmpInst::Predicate Pred = Cmp.getPredicate(); + const APInt SMax = APInt::getSignedMaxValue(Ty->getScalarSizeInBits()); + const APInt SMin = APInt::getSignedMinValue(Ty->getScalarSizeInBits()); - // Fold an unsigned compare with offset to signed compare: + // Fold compare with offset to opposite sign compare if it eliminates offset: // (X + C2) >u C --> X <s -C2 (if C == C2 + SMAX) - // TODO: Find the signed predicate siblings. - if (Pred == CmpInst::ICMP_UGT && - C == *C2 + APInt::getSignedMaxValue(Ty->getScalarSizeInBits())) + if (Pred == CmpInst::ICMP_UGT && C == *C2 + SMax) return new ICmpInst(ICmpInst::ICMP_SLT, X, ConstantInt::get(Ty, -(*C2))); // (X + C2) <u C --> X >s ~C2 (if C == C2 + SMIN) - if (Pred == CmpInst::ICMP_ULT && - C == *C2 + APInt::getSignedMinValue(Ty->getScalarSizeInBits())) + if (Pred == CmpInst::ICMP_ULT && C == *C2 + SMin) return new ICmpInst(ICmpInst::ICMP_SGT, X, ConstantInt::get(Ty, ~(*C2))); + // (X + C2) >s C --> X <u (SMAX - C) (if C == C2 - 1) + if (Pred == CmpInst::ICMP_SGT && C == *C2 - 1) + return new ICmpInst(ICmpInst::ICMP_ULT, X, ConstantInt::get(Ty, SMax - C)); + + // (X + C2) <s C --> X >u (C ^ SMAX) (if C == C2) + if (Pred == CmpInst::ICMP_SLT && C == *C2) + return new ICmpInst(ICmpInst::ICMP_UGT, X, ConstantInt::get(Ty, C ^ SMax)); + // If the add does not wrap, we can always adjust the compare by subtracting // the constants. Equality comparisons are handled elsewhere. SGE/SLE/UGE/ULE // are canonicalized to SGT/SLT/UGT/ULT. diff --git a/llvm/test/Transforms/InstCombine/icmp-add.ll b/llvm/test/Transforms/InstCombine/icmp-add.ll index 1f00dc6e2992..aa69325d716c 100644 --- a/llvm/test/Transforms/InstCombine/icmp-add.ll +++ b/llvm/test/Transforms/InstCombine/icmp-add.ll @@ -842,8 +842,7 @@ define i1 @ult_wrong_offset(i8 %a) { define i1 @sgt_offset(i8 %a) { ; CHECK-LABEL: @sgt_offset( -; CHECK-NEXT: [[T:%.*]] = add i8 [[A:%.*]], -6 -; CHECK-NEXT: [[OV:%.*]] = icmp sgt i8 [[T]], -7 +; CHECK-NEXT: [[OV:%.*]] = icmp ult i8 [[A:%.*]], -122 ; CHECK-NEXT: ret i1 [[OV]] ; %t = add i8 %a, -6 @@ -855,7 +854,7 @@ define i1 @sgt_offset_use(i32 %a) { ; CHECK-LABEL: @sgt_offset_use( ; CHECK-NEXT: [[T:%.*]] = add i32 [[A:%.*]], 42 ; CHECK-NEXT: call void @use(i32 [[T]]) -; CHECK-NEXT: [[OV:%.*]] = icmp sgt i32 [[T]], 41 +; CHECK-NEXT: [[OV:%.*]] = icmp ult i32 [[A]], 2147483606 ; CHECK-NEXT: ret i1 [[OV]] ; %t = add i32 %a, 42 @@ -866,8 +865,7 @@ define i1 @sgt_offset_use(i32 %a) { define <2 x i1> @sgt_offset_splat(<2 x i5> %a) { ; CHECK-LABEL: @sgt_offset_splat( -; CHECK-NEXT: [[T:%.*]] = add <2 x i5> [[A:%.*]], <i5 9, i5 9> -; CHECK-NEXT: [[OV:%.*]] = icmp sgt <2 x i5> [[T]], <i5 8, i5 8> +; CHECK-NEXT: [[OV:%.*]] = icmp ult <2 x i5> [[A:%.*]], <i5 7, i5 7> ; CHECK-NEXT: ret <2 x i1> [[OV]] ; %t = add <2 x i5> %a, <i5 9, i5 9> @@ -875,6 +873,8 @@ define <2 x i1> @sgt_offset_splat(<2 x i5> %a) { ret <2 x i1> %ov } +; negative test - constants must differ by 1 + define i1 @sgt_wrong_offset(i8 %a) { ; CHECK-LABEL: @sgt_wrong_offset( ; CHECK-NEXT: [[T:%.*]] = add i8 [[A:%.*]], -7 @@ -888,8 +888,7 @@ define i1 @sgt_wrong_offset(i8 %a) { define i1 @slt_offset(i8 %a) { ; CHECK-LABEL: @slt_offset( -; CHECK-NEXT: [[T:%.*]] = add i8 [[A:%.*]], -6 -; CHECK-NEXT: [[OV:%.*]] = icmp slt i8 [[T]], -6 +; CHECK-NEXT: [[OV:%.*]] = icmp ugt i8 [[A:%.*]], -123 ; CHECK-NEXT: ret i1 [[OV]] ; %t = add i8 %a, -6 @@ -901,7 +900,7 @@ define i1 @slt_offset_use(i32 %a) { ; CHECK-LABEL: @slt_offset_use( ; CHECK-NEXT: [[T:%.*]] = add i32 [[A:%.*]], 42 ; CHECK-NEXT: call void @use(i32 [[T]]) -; CHECK-NEXT: [[OV:%.*]] = icmp slt i32 [[T]], 42 +; CHECK-NEXT: [[OV:%.*]] = icmp ugt i32 [[A]], 2147483605 ; CHECK-NEXT: ret i1 [[OV]] ; %t = add i32 %a, 42 @@ -912,8 +911,7 @@ define i1 @slt_offset_use(i32 %a) { define <2 x i1> @slt_offset_splat(<2 x i5> %a) { ; CHECK-LABEL: @slt_offset_splat( -; CHECK-NEXT: [[T:%.*]] = add <2 x i5> [[A:%.*]], <i5 9, i5 9> -; CHECK-NEXT: [[OV:%.*]] = icmp slt <2 x i5> [[T]], <i5 9, i5 9> +; CHECK-NEXT: [[OV:%.*]] = icmp ugt <2 x i5> [[A:%.*]], <i5 6, i5 6> ; CHECK-NEXT: ret <2 x i1> [[OV]] ; %t = add <2 x i5> %a, <i5 9, i5 9> @@ -921,6 +919,8 @@ define <2 x i1> @slt_offset_splat(<2 x i5> %a) { ret <2 x i1> %ov } +; negative test - constants must be equal + define i1 @slt_wrong_offset(i8 %a) { ; CHECK-LABEL: @slt_wrong_offset( ; CHECK-NEXT: [[T:%.*]] = add i8 [[A:%.*]], -6 </cut>

3 years, 2 months

[CI-NOTIFY]: TCWG Bisect tcwg_kernel/llvm-release-aarch64-next-allnoconfig - Build # 10 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *linux* in CI configuration tcwg_kernel/llvm-release-aarch64-next-allnoconfig. So far, this commit has regressed CI configurations: - tcwg_kernel/llvm-release-aarch64-next-allnoconfig Culprit: <cut> commit 8633ef82f101c040427b57d4df7b706261420b94 Author: Javier Martinez Canillas <javierm(a)redhat.com> Date: Fri Jun 25 15:13:59 2021 +0200 drivers/firmware: consolidate EFI framebuffer setup for all arches The register_gop_device() function registers an "efi-framebuffer" platform device to match against the efifb driver, to have an early framebuffer for EFI platforms. But there is already support to do exactly the same by the Generic System Framebuffers (sysfb) driver. This used to be only for X86 but it has been moved to drivers/firmware and could be reused by other architectures. Also, besides supporting registering an "efi-framebuffer", this driver can register a "simple-framebuffer" allowing to use the siple{fb,drm} drivers on non-X86 EFI platforms. For example, on aarch64 these drivers can only be used with DT and doesn't have code to register a "simple-frambuffer" platform device when booting with EFI. For these reasons, let's remove the register_gop_device() duplicated code and instead move the platform specific logic that's there to sysfb driver. Signed-off-by: Javier Martinez Canillas <javierm(a)redhat.com> Acked-by: Borislav Petkov <bp(a)suse.de> Acked-by: Daniel Vetter <daniel.vetter(a)ffwll.ch> Signed-off-by: Thomas Zimmermann <tzimmermann(a)suse.de> Link: https://patchwork.freedesktop.org/patch/msgid/20210625131359.1804394-1-javi… </cut> Results regressed to (for first_bad == 8633ef82f101c040427b57d4df7b706261420b94) # reset_artifacts: -10 # build_abe binutils: -9 # build_llvm: -5 # build_abe qemu: -2 # linux_n_obj: 600 # First few build errors in logs: # 00:00:38 ld.lld: error: undefined symbol: screen_info # 00:00:38 make: *** [vmlinux] Error 1 from (for last_good == d391c58271072d0b0fad93c82018d495b2633448) # reset_artifacts: -10 # build_abe binutils: -9 # build_llvm: -5 # build_abe qemu: -2 # linux_n_obj: 601 # linux build successful: all # linux boot successful: boot Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next… Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next… Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next… Configuration details: rr[linux_git]="https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git#ff11764…" Reproduce builds: <cut> mkdir investigate-linux-8633ef82f101c040427b57d4df7b706261420b94 cd investigate-linux-8633ef82f101c040427b57d4df7b706261420b94 git clone https://git.linaro.org/toolchain/jenkins-scripts mkdir -p artifacts/manifests curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next… --fail chmod +x artifacts/test.sh # Reproduce the baseline build (build all pre-requisites) ./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh # Save baseline build state (which is then restored in artifacts/test.sh) mkdir -p ./bisect rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/ cd linux # Reproduce first_bad build git checkout --detach 8633ef82f101c040427b57d4df7b706261420b94 ../artifacts/test.sh # Reproduce last_good build git checkout --detach d391c58271072d0b0fad93c82018d495b2633448 ../artifacts/test.sh cd .. </cut> History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/… Artifacts: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next… Build log: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next… Full commit (up to 1000 lines): <cut> commit 8633ef82f101c040427b57d4df7b706261420b94 Author: Javier Martinez Canillas <javierm(a)redhat.com> Date: Fri Jun 25 15:13:59 2021 +0200 drivers/firmware: consolidate EFI framebuffer setup for all arches The register_gop_device() function registers an "efi-framebuffer" platform device to match against the efifb driver, to have an early framebuffer for EFI platforms. But there is already support to do exactly the same by the Generic System Framebuffers (sysfb) driver. This used to be only for X86 but it has been moved to drivers/firmware and could be reused by other architectures. Also, besides supporting registering an "efi-framebuffer", this driver can register a "simple-framebuffer" allowing to use the siple{fb,drm} drivers on non-X86 EFI platforms. For example, on aarch64 these drivers can only be used with DT and doesn't have code to register a "simple-frambuffer" platform device when booting with EFI. For these reasons, let's remove the register_gop_device() duplicated code and instead move the platform specific logic that's there to sysfb driver. Signed-off-by: Javier Martinez Canillas <javierm(a)redhat.com> Acked-by: Borislav Petkov <bp(a)suse.de> Acked-by: Daniel Vetter <daniel.vetter(a)ffwll.ch> Signed-off-by: Thomas Zimmermann <tzimmermann(a)suse.de> Link: https://patchwork.freedesktop.org/patch/msgid/20210625131359.1804394-1-javi… --- arch/arm/include/asm/efi.h | 5 +-- arch/arm64/include/asm/efi.h | 5 +-- arch/riscv/include/asm/efi.h | 5 +-- drivers/firmware/Kconfig | 8 ++-- drivers/firmware/Makefile | 2 +- drivers/firmware/efi/efi-init.c | 90 --------------------------------------- drivers/firmware/efi/sysfb_efi.c | 76 ++++++++++++++++++++++++++++++++- drivers/firmware/sysfb.c | 35 ++++++++++----- drivers/firmware/sysfb_simplefb.c | 31 ++++++++++---- drivers/gpu/drm/tiny/Kconfig | 4 +- include/linux/sysfb.h | 26 +++++------ 11 files changed, 143 insertions(+), 144 deletions(-) diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h index 9de7ab2ce05d..a6f3b179e8a9 100644 --- a/arch/arm/include/asm/efi.h +++ b/arch/arm/include/asm/efi.h @@ -17,6 +17,7 @@ #ifdef CONFIG_EFI void efi_init(void); +extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md); @@ -52,10 +53,6 @@ void efi_virtmap_unload(void); struct screen_info *alloc_screen_info(void); void free_screen_info(struct screen_info *si); -static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) -{ -} - /* * A reasonable upper bound for the uncompressed kernel size is 32 MBytes, * so we will reserve that amount of memory. We have no easy way to tell what diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h index 3578aba9c608..42d673a011c8 100644 --- a/arch/arm64/include/asm/efi.h +++ b/arch/arm64/include/asm/efi.h @@ -14,6 +14,7 @@ #ifdef CONFIG_EFI extern void efi_init(void); +extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); #else #define efi_init() #endif @@ -85,10 +86,6 @@ static inline void free_screen_info(struct screen_info *si) { } -static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) -{ -} - #define EFI_ALLOC_ALIGN SZ_64K /* diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h index 6d98cd999680..7a8f0d45b13a 100644 --- a/arch/riscv/include/asm/efi.h +++ b/arch/riscv/include/asm/efi.h @@ -13,6 +13,7 @@ #ifdef CONFIG_EFI extern void efi_init(void); +extern void efifb_setup_from_dmi(struct screen_info *si, const char *opt); #else #define efi_init() #endif @@ -39,10 +40,6 @@ static inline void free_screen_info(struct screen_info *si) { } -static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt) -{ -} - void efi_virtmap_load(void); void efi_virtmap_unload(void); diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig index 71f3d97f0c39..af6719cc576b 100644 --- a/drivers/firmware/Kconfig +++ b/drivers/firmware/Kconfig @@ -254,9 +254,9 @@ config QCOM_SCM_DOWNLOAD_MODE_DEFAULT config SYSFB bool default y - depends on X86 || COMPILE_TEST + depends on X86 || ARM || ARM64 || RISCV || COMPILE_TEST -config X86_SYSFB +config SYSFB_SIMPLEFB bool "Mark VGA/VBE/EFI FB as generic system framebuffer" depends on SYSFB help @@ -264,10 +264,10 @@ config X86_SYSFB bootloader or kernel can show basic video-output during boot for user-guidance and debugging. Historically, x86 used the VESA BIOS Extensions and EFI-framebuffers for this, which are mostly limited - to x86. + to x86 BIOS or EFI systems. This option, if enabled, marks VGA/VBE/EFI framebuffers as generic framebuffers so the new generic system-framebuffer drivers can be - used on x86. If the framebuffer is not compatible with the generic + used instead. If the framebuffer is not compatible with the generic modes, it is advertised as fallback platform framebuffer so legacy drivers like efifb, vesafb and uvesafb can pick it up. If this option is not selected, all system framebuffers are always diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile index ad78f78ffa8d..6ac637e422b9 100644 --- a/drivers/firmware/Makefile +++ b/drivers/firmware/Makefile @@ -19,7 +19,7 @@ obj-$(CONFIG_RASPBERRYPI_FIRMWARE) += raspberrypi.o obj-$(CONFIG_FW_CFG_SYSFS) += qemu_fw_cfg.o obj-$(CONFIG_QCOM_SCM) += qcom_scm.o qcom_scm-smc.o qcom_scm-legacy.o obj-$(CONFIG_SYSFB) += sysfb.o -obj-$(CONFIG_X86_SYSFB) += sysfb_simplefb.o +obj-$(CONFIG_SYSFB_SIMPLEFB) += sysfb_simplefb.o obj-$(CONFIG_TI_SCI_PROTOCOL) += ti_sci.o obj-$(CONFIG_TRUSTED_FOUNDATIONS) += trusted_foundations.o obj-$(CONFIG_TURRIS_MOX_RWTM) += turris-mox-rwtm.o diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c index a552a08a1741..b19ce1a83f91 100644 --- a/drivers/firmware/efi/efi-init.c +++ b/drivers/firmware/efi/efi-init.c @@ -275,93 +275,3 @@ void __init efi_init(void) } #endif } - -static bool efifb_overlaps_pci_range(const struct of_pci_range *range) -{ - u64 fb_base = screen_info.lfb_base; - - if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE) - fb_base |= (u64)(unsigned long)screen_info.ext_lfb_base << 32; - - return fb_base >= range->cpu_addr && - fb_base < (range->cpu_addr + range->size); -} - -static struct device_node *find_pci_overlap_node(void) -{ - struct device_node *np; - - for_each_node_by_type(np, "pci") { - struct of_pci_range_parser parser; - struct of_pci_range range; - int err; - - err = of_pci_range_parser_init(&parser, np); - if (err) { - pr_warn("of_pci_range_parser_init() failed: %d\n", err); - continue; - } - - for_each_of_pci_range(&parser, &range) - if (efifb_overlaps_pci_range(&range)) - return np; - } - return NULL; -} - -/* - * If the efifb framebuffer is backed by a PCI graphics controller, we have - * to ensure that this relation is expressed using a device link when - * running in DT mode, or the probe order may be reversed, resulting in a - * resource reservation conflict on the memory window that the efifb - * framebuffer steals from the PCIe host bridge. - */ -static int efifb_add_links(struct fwnode_handle *fwnode) -{ - struct device_node *sup_np; - - sup_np = find_pci_overlap_node(); - - /* - * If there's no PCI graphics controller backing the efifb, we are - * done here. - */ - if (!sup_np) - return 0; - - fwnode_link_add(fwnode, of_fwnode_handle(sup_np)); - of_node_put(sup_np); - - return 0; -} - -static const struct fwnode_operations efifb_fwnode_ops = { - .add_links = efifb_add_links, -}; - -static struct fwnode_handle efifb_fwnode; - -static int __init register_gop_device(void) -{ - struct platform_device *pd; - int err; - - if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI) - return 0; - - pd = platform_device_alloc("efi-framebuffer", 0); - if (!pd) - return -ENOMEM; - - if (IS_ENABLED(CONFIG_PCI)) { - fwnode_init(&efifb_fwnode, &efifb_fwnode_ops); - pd->dev.fwnode = &efifb_fwnode; - } - - err = platform_device_add_data(pd, &screen_info, sizeof(screen_info)); - if (err) - return err; - - return platform_device_add(pd); -} -subsys_initcall(register_gop_device); diff --git a/drivers/firmware/efi/sysfb_efi.c b/drivers/firmware/efi/sysfb_efi.c index 9f035b15501c..f51865e1b876 100644 --- a/drivers/firmware/efi/sysfb_efi.c +++ b/drivers/firmware/efi/sysfb_efi.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Generic System Framebuffers on x86 + * Generic System Framebuffers * Copyright (c) 2012-2013 David Herrmann <dh.herrmann(a)gmail.com> * * EFI Quirks Copyright (c) 2006 Edgar Hucek <gimli(a)dark-green.com> @@ -19,7 +19,9 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/of_address.h> #include <linux/pci.h> +#include <linux/platform_device.h> #include <linux/screen_info.h> #include <linux/sysfb.h> #include <video/vga.h> @@ -267,7 +269,72 @@ static const struct dmi_system_id efifb_dmi_swap_width_height[] __initconst = { {}, }; -__init void sysfb_apply_efi_quirks(void) +static bool efifb_overlaps_pci_range(const struct of_pci_range *range) +{ + u64 fb_base = screen_info.lfb_base; + + if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE) + fb_base |= (u64)(unsigned long)screen_info.ext_lfb_base << 32; + + return fb_base >= range->cpu_addr && + fb_base < (range->cpu_addr + range->size); +} + +static struct device_node *find_pci_overlap_node(void) +{ + struct device_node *np; + + for_each_node_by_type(np, "pci") { + struct of_pci_range_parser parser; + struct of_pci_range range; + int err; + + err = of_pci_range_parser_init(&parser, np); + if (err) { + pr_warn("of_pci_range_parser_init() failed: %d\n", err); + continue; + } + + for_each_of_pci_range(&parser, &range) + if (efifb_overlaps_pci_range(&range)) + return np; + } + return NULL; +} + +/* + * If the efifb framebuffer is backed by a PCI graphics controller, we have + * to ensure that this relation is expressed using a device link when + * running in DT mode, or the probe order may be reversed, resulting in a + * resource reservation conflict on the memory window that the efifb + * framebuffer steals from the PCIe host bridge. + */ +static int efifb_add_links(struct fwnode_handle *fwnode) +{ + struct device_node *sup_np; + + sup_np = find_pci_overlap_node(); + + /* + * If there's no PCI graphics controller backing the efifb, we are + * done here. + */ + if (!sup_np) + return 0; + + fwnode_link_add(fwnode, of_fwnode_handle(sup_np)); + of_node_put(sup_np); + + return 0; +} + +static const struct fwnode_operations efifb_fwnode_ops = { + .add_links = efifb_add_links, +}; + +static struct fwnode_handle efifb_fwnode; + +__init void sysfb_apply_efi_quirks(struct platform_device *pd) { if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS)) @@ -281,4 +348,9 @@ __init void sysfb_apply_efi_quirks(void) screen_info.lfb_height = temp; screen_info.lfb_linelength = 4 * screen_info.lfb_width; } + + if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI && IS_ENABLED(CONFIG_PCI)) { + fwnode_init(&efifb_fwnode, &efifb_fwnode_ops); + pd->dev.fwnode = &efifb_fwnode; + } } diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c index 1337515963d5..2bfbb05f7d89 100644 --- a/drivers/firmware/sysfb.c +++ b/drivers/firmware/sysfb.c @@ -1,11 +1,11 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Generic System Framebuffers on x86 + * Generic System Framebuffers * Copyright (c) 2012-2013 David Herrmann <dh.herrmann(a)gmail.com> */ /* - * Simple-Framebuffer support for x86 systems + * Simple-Framebuffer support * Create a platform-device for any available boot framebuffer. The * simple-framebuffer platform device is already available on DT systems, so * this module parses the global "screen_info" object and creates a suitable @@ -16,12 +16,12 @@ * to pick these devices up without messing with simple-framebuffer drivers. * The global "screen_info" is still valid at all times. * - * If CONFIG_X86_SYSFB is not selected, we never register "simple-framebuffer" + * If CONFIG_SYSFB_SIMPLEFB is not selected, never register "simple-framebuffer" * platform devices, but only use legacy framebuffer devices for * backwards compatibility. * * TODO: We set the dev_id field of all platform-devices to 0. This allows - * other x86 OF/DT parsers to create such devices, too. However, they must + * other OF/DT parsers to create such devices, too. However, they must * start at offset 1 for this to work. */ @@ -43,12 +43,10 @@ static __init int sysfb_init(void) bool compatible; int ret; - sysfb_apply_efi_quirks(); - /* try to create a simple-framebuffer device */ - compatible = parse_mode(si, &mode); + compatible = sysfb_parse_mode(si, &mode); if (compatible) { - ret = create_simplefb(si, &mode); + ret = sysfb_create_simplefb(si, &mode); if (!ret) return 0; } @@ -61,9 +59,24 @@ static __init int sysfb_init(void) else name = "platform-framebuffer"; - pd = platform_device_register_resndata(NULL, name, 0, - NULL, 0, si, sizeof(*si)); - return PTR_ERR_OR_ZERO(pd); + pd = platform_device_alloc(name, 0); + if (!pd) + return -ENOMEM; + + sysfb_apply_efi_quirks(pd); + + ret = platform_device_add_data(pd, si, sizeof(*si)); + if (ret) + goto err; + + ret = platform_device_add(pd); + if (ret) + goto err; + + return 0; +err: + platform_device_put(pd); + return ret; } /* must execute after PCI subsystem for EFI quirks */ diff --git a/drivers/firmware/sysfb_simplefb.c b/drivers/firmware/sysfb_simplefb.c index df892444ea17..b86761904949 100644 --- a/drivers/firmware/sysfb_simplefb.c +++ b/drivers/firmware/sysfb_simplefb.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Generic System Framebuffers on x86 + * Generic System Framebuffers * Copyright (c) 2012-2013 David Herrmann <dh.herrmann(a)gmail.com> */ @@ -23,9 +23,9 @@ static const char simplefb_resname[] = "BOOTFB"; static const struct simplefb_format formats[] = SIMPLEFB_FORMATS; -/* try parsing x86 screen_info into a simple-framebuffer mode struct */ -__init bool parse_mode(const struct screen_info *si, - struct simplefb_platform_data *mode) +/* try parsing screen_info into a simple-framebuffer mode struct */ +__init bool sysfb_parse_mode(const struct screen_info *si, + struct simplefb_platform_data *mode) { const struct simplefb_format *f; __u8 type; @@ -57,13 +57,14 @@ __init bool parse_mode(const struct screen_info *si, return false; } -__init int create_simplefb(const struct screen_info *si, - const struct simplefb_platform_data *mode) +__init int sysfb_create_simplefb(const struct screen_info *si, + const struct simplefb_platform_data *mode) { struct platform_device *pd; struct resource res; u64 base, size; u32 length; + int ret; /* * If the 64BIT_BASE capability is set, ext_lfb_base will contain the @@ -105,7 +106,19 @@ __init int create_simplefb(const struct screen_info *si, if (res.end <= res.start) return -EINVAL; - pd = platform_device_register_resndata(NULL, "simple-framebuffer", 0, - &res, 1, mode, sizeof(*mode)); - return PTR_ERR_OR_ZERO(pd); + pd = platform_device_alloc("simple-framebuffer", 0); + if (!pd) + return -ENOMEM; + + sysfb_apply_efi_quirks(pd); + + ret = platform_device_add_resources(pd, &res, 1); + if (ret) + return ret; + + ret = platform_device_add_data(pd, mode, sizeof(*mode)); + if (ret) + return ret; + + return platform_device_add(pd); } diff --git a/drivers/gpu/drm/tiny/Kconfig b/drivers/gpu/drm/tiny/Kconfig index 5593128eeff9..d31be274a2bd 100644 --- a/drivers/gpu/drm/tiny/Kconfig +++ b/drivers/gpu/drm/tiny/Kconfig @@ -64,8 +64,8 @@ config DRM_SIMPLEDRM buffer, size, and display format must be provided via device tree, UEFI, VESA, etc. - On x86 and compatible, you should also select CONFIG_X86_SYSFB to - use UEFI and VESA framebuffers. + On x86 BIOS or UEFI systems, you should also select SYSFB_SIMPLEFB + to use UEFI and VESA framebuffers. config TINYDRM_HX8357D tristate "DRM support for HX8357D display panels" diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h index 3e5355769dc3..b0dcfa26d07b 100644 --- a/include/linux/sysfb.h +++ b/include/linux/sysfb.h @@ -58,37 +58,37 @@ struct efifb_dmi_info { #ifdef CONFIG_EFI extern struct efifb_dmi_info efifb_dmi_list[]; -void sysfb_apply_efi_quirks(void); +void sysfb_apply_efi_quirks(struct platform_device *pd); #else /* CONFIG_EFI */ -static inline void sysfb_apply_efi_quirks(void) +static inline void sysfb_apply_efi_quirks(struct platform_device *pd) { } #endif /* CONFIG_EFI */ -#ifdef CONFIG_X86_SYSFB +#ifdef CONFIG_SYSFB_SIMPLEFB -bool parse_mode(const struct screen_info *si, - struct simplefb_platform_data *mode); -int create_simplefb(const struct screen_info *si, - const struct simplefb_platform_data *mode); +bool sysfb_parse_mode(const struct screen_info *si, + struct simplefb_platform_data *mode); +int sysfb_create_simplefb(const struct screen_info *si, + const struct simplefb_platform_data *mode); -#else /* CONFIG_X86_SYSFB */ +#else /* CONFIG_SYSFB_SIMPLE */ -static inline bool parse_mode(const struct screen_info *si, - struct simplefb_platform_data *mode) +static inline bool sysfb_parse_mode(const struct screen_info *si, + struct simplefb_platform_data *mode) { return false; } -static inline int create_simplefb(const struct screen_info *si, - const struct simplefb_platform_data *mode) +static inline int sysfb_create_simplefb(const struct screen_info *si, + const struct simplefb_platform_data *mode) { return -EINVAL; } -#endif /* CONFIG_X86_SYSFB */ +#endif /* CONFIG_SYSFB_SIMPLE */ #endif /* _LINUX_SYSFB_H */ </cut>

3 years, 3 months

[CI-NOTIFY]: TCWG Bisect tcwg_kernel/llvm-master-aarch64-next-allyesconfig - Build # 14 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *linux* in CI configuration tcwg_kernel/llvm-master-aarch64-next-allyesconfig. So far, this commit has regressed CI configurations: - tcwg_kernel/llvm-master-aarch64-next-allyesconfig Culprit: <cut> commit 3d463dd5023b5a58b3c37207d65eeb5acbac2be3 Author: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com> Date: Thu Jul 29 12:40:19 2021 +0200 nfc: fdp: constify several pointers Several functions do not modify pointed data so arguments and local variables can be const for correctness and safety. This allows also making file-scope nci_core_get_config_otp_ram_version array const. Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> </cut> Results regressed to (for first_bad == 3d463dd5023b5a58b3c37207d65eeb5acbac2be3) # reset_artifacts: -10 # build_abe binutils: -9 # build_llvm: -5 # build_abe qemu: -2 # linux_n_obj: 19928 # First few build errors in logs: # 00:02:04 drivers/nfc/fdp/fdp.c:116:60: error: passing 'const char *' to parameter of type '__u8 *' (aka 'unsigned char *') discards qualifiers [-Werror,-Wincompatible-pointer-types-discards-qualifiers] # 00:02:04 make[3]: *** [scripts/Makefile.build:271: drivers/nfc/fdp/fdp.o] Error 1 # 00:02:05 make[2]: *** [scripts/Makefile.build:514: drivers/nfc/fdp] Error 2 # 00:02:23 make[1]: *** [scripts/Makefile.build:514: drivers/nfc] Error 2 # 00:04:16 make: *** [Makefile:1842: drivers] Error 2 from (for last_good == c3e26b6dc1b4e3e8f57be4f004b1f2a410c5c468) # reset_artifacts: -10 # build_abe binutils: -9 # build_llvm: -5 # build_abe qemu: -2 # linux_n_obj: 20000 # linux build successful: all Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-next-… Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-next-… Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-next-… Configuration details: rr[linux_git]="https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git#cb16362…" Reproduce builds: <cut> mkdir investigate-linux-3d463dd5023b5a58b3c37207d65eeb5acbac2be3 cd investigate-linux-3d463dd5023b5a58b3c37207d65eeb5acbac2be3 git clone https://git.linaro.org/toolchain/jenkins-scripts mkdir -p artifacts/manifests curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-next-… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-next-… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-next-… --fail chmod +x artifacts/test.sh # Reproduce the baseline build (build all pre-requisites) ./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh # Save baseline build state (which is then restored in artifacts/test.sh) mkdir -p ./bisect rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/ cd linux # Reproduce first_bad build git checkout --detach 3d463dd5023b5a58b3c37207d65eeb5acbac2be3 ../artifacts/test.sh # Reproduce last_good build git checkout --detach c3e26b6dc1b4e3e8f57be4f004b1f2a410c5c468 ../artifacts/test.sh cd .. </cut> History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/… Artifacts: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-next-… Build log: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-next-… Full commit (up to 1000 lines): <cut> commit 3d463dd5023b5a58b3c37207d65eeb5acbac2be3 Author: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com> Date: Thu Jul 29 12:40:19 2021 +0200 nfc: fdp: constify several pointers Several functions do not modify pointed data so arguments and local variables can be const for correctness and safety. This allows also making file-scope nci_core_get_config_otp_ram_version array const. Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> --- drivers/nfc/fdp/fdp.c | 18 +++++++++--------- drivers/nfc/fdp/fdp.h | 2 +- drivers/nfc/fdp/i2c.c | 6 +++--- 3 files changed, 13 insertions(+), 13 deletions(-) diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c index 3f5fba922c4d..c6b3334f24c9 100644 --- a/drivers/nfc/fdp/fdp.c +++ b/drivers/nfc/fdp/fdp.c @@ -52,7 +52,7 @@ struct fdp_nci_info { u32 limited_otp_version; u8 key_index; - u8 *fw_vsc_cfg; + const u8 *fw_vsc_cfg; u8 clock_type; u32 clock_freq; @@ -65,7 +65,7 @@ struct fdp_nci_info { wait_queue_head_t setup_wq; }; -static u8 nci_core_get_config_otp_ram_version[5] = { +static const u8 nci_core_get_config_otp_ram_version[5] = { 0x04, NCI_PARAM_ID_FW_RAM_VERSION, NCI_PARAM_ID_FW_OTP_VERSION, @@ -111,7 +111,7 @@ static inline int fdp_nci_patch_cmd(struct nci_dev *ndev, u8 type) } static inline int fdp_nci_set_production_data(struct nci_dev *ndev, u8 len, - char *data) + const char *data) { return nci_prop_cmd(ndev, NCI_OP_PROP_SET_PDATA_OID, len, data); } @@ -236,7 +236,7 @@ static int fdp_nci_send_patch(struct nci_dev *ndev, u8 conn_id, u8 type) static int fdp_nci_open(struct nci_dev *ndev) { - struct fdp_nci_info *info = nci_get_drvdata(ndev); + const struct fdp_nci_info *info = nci_get_drvdata(ndev); return info->phy_ops->enable(info->phy); } @@ -260,7 +260,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev) { struct fdp_nci_info *info = nci_get_drvdata(ndev); struct device *dev = &info->phy->i2c_dev->dev; - u8 *data; + const u8 *data; int r; r = request_firmware(&info->ram_patch, FDP_RAM_PATCH_NAME, dev); @@ -269,7 +269,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev) return r; } - data = (u8 *) info->ram_patch->data; + data = info->ram_patch->data; info->ram_patch_version = data[FDP_FW_HEADER_SIZE] | (data[FDP_FW_HEADER_SIZE + 1] << 8) | @@ -610,9 +610,9 @@ static int fdp_nci_core_get_config_rsp_packet(struct nci_dev *ndev, { struct fdp_nci_info *info = nci_get_drvdata(ndev); struct device *dev = &info->phy->i2c_dev->dev; - struct nci_core_get_config_rsp *rsp = (void *) skb->data; + const struct nci_core_get_config_rsp *rsp = (void *) skb->data; unsigned int i; - u8 *p; + const u8 *p; if (rsp->status == NCI_STATUS_OK) { @@ -691,7 +691,7 @@ static const struct nci_ops nci_ops = { int fdp_nci_probe(struct fdp_i2c_phy *phy, const struct nfc_phy_ops *phy_ops, struct nci_dev **ndevp, int tx_headroom, int tx_tailroom, u8 clock_type, u32 clock_freq, - u8 *fw_vsc_cfg) + const u8 *fw_vsc_cfg) { struct device *dev = &phy->i2c_dev->dev; struct fdp_nci_info *info; diff --git a/drivers/nfc/fdp/fdp.h b/drivers/nfc/fdp/fdp.h index dc048d4b977e..2e9161a4d7bf 100644 --- a/drivers/nfc/fdp/fdp.h +++ b/drivers/nfc/fdp/fdp.h @@ -23,7 +23,7 @@ struct fdp_i2c_phy { int fdp_nci_probe(struct fdp_i2c_phy *phy, const struct nfc_phy_ops *phy_ops, struct nci_dev **ndev, int tx_headroom, int tx_tailroom, - u8 clock_type, u32 clock_freq, u8 *fw_vsc_cfg); + u8 clock_type, u32 clock_freq, const u8 *fw_vsc_cfg); void fdp_nci_remove(struct nci_dev *ndev); #endif /* __LOCAL_FDP_H_ */ diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c index 98e1876c9468..051c43a2a52f 100644 --- a/drivers/nfc/fdp/i2c.c +++ b/drivers/nfc/fdp/i2c.c @@ -36,7 +36,7 @@ print_hex_dump(KERN_DEBUG, prefix": ", DUMP_PREFIX_OFFSET, \ 16, 1, (skb)->data, (skb)->len, 0) -static void fdp_nci_i2c_reset(struct fdp_i2c_phy *phy) +static void fdp_nci_i2c_reset(const struct fdp_i2c_phy *phy) { /* Reset RST/WakeUP for at least 100 micro-second */ gpiod_set_value_cansleep(phy->power_gpio, FDP_POWER_OFF); @@ -47,7 +47,7 @@ static void fdp_nci_i2c_reset(struct fdp_i2c_phy *phy) static int fdp_nci_i2c_enable(void *phy_id) { - struct fdp_i2c_phy *phy = phy_id; + const struct fdp_i2c_phy *phy = phy_id; fdp_nci_i2c_reset(phy); @@ -56,7 +56,7 @@ static int fdp_nci_i2c_enable(void *phy_id) static void fdp_nci_i2c_disable(void *phy_id) { - struct fdp_i2c_phy *phy = phy_id; + const struct fdp_i2c_phy *phy = phy_id; fdp_nci_i2c_reset(phy); } </cut>

3 years, 3 months

[CI-NOTIFY]: TCWG Bisect tcwg_gnu_native_build/master-aarch64 - Build # 1 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *gcc* in CI configuration tcwg_gnu_native_build/master-aarch64. So far, this commit has regressed CI configurations: - tcwg_gnu_native_build/master-aarch64 Culprit: <cut> commit cad36f38576a6a781e3c62ab061c68f5b8dab13a Author: Roger Sayle <roger(a)nextmovesoftware.com> Date: Tue Aug 31 11:45:07 2021 +0100 Preserve SUBREG_PROMOTED_VAR_P on (extend:HI (subreg/s:QI (reg:SI))). SUBREG_PROMOTED_VAR_P is a mechanism for tracking that a partial subreg is correctly zero-extended or sign-extended in the parent register. For example, the RTL (subreg/s/v:QI (reg/v:SI 23 [ x ]) 0) indicates that the byte x is zero extended in reg:SI 23, which is useful for optimization. An example is that zero extending the above QImode value to HImode can simply use a wider subreg, i.e. (subreg:HI (reg/v:SI 23 [ x ]) 0). This patch addresses the oversight/missed optimization opportunity that the new HImode subreg above should retain its SUBREG_PROMOTED_VAR_P annotation as its value is guaranteed to be correctly extended in the SImode parent. The code below to preserve SUBREG_PROMOTED_VAR_P is already present in the middle-end (e.g. simplify-rtx.c:7232-7242) but missing from one or two (precisely three) places that (accidentally) strip it. Whilst there I also added another optimization. If we need to extend the above QImode value beyond the SImode register holding it, say to DImode, we can eliminate the SUBREG and simply extend from the SImode register to DImode. 2021-08-31 Roger Sayle <roger(a)nextmovesoftware.com> gcc/ChangeLog * expr.c (convert_modes): Preserve SUBREG_PROMOTED_VAR_P when creating a (wider) partial subreg from a SUBREG_PROMOTED_VAR_P subreg. * simplify-rtx.c (simplify_unary_operation_1) [SIGN_EXTEND]: Likewise, preserve SUBREG_PROMOTED_VAR_P when creating a (wider) partial subreg from a SUBREG_PROMOTED_VAR_P subreg. Generate SIGN_EXTEND of the SUBREG_REG when a subreg would be paradoxical. [ZERO_EXTEND]: Likewise, preserve SUBREG_PROMOTED_VAR_P when creating a (wider) partial subreg from a SUBREG_PROMOTED_VAR_P subreg. Generate ZERO_EXTEND of the SUBREG_REG when a subreg would be paradoxical. </cut> Results regressed to (for first_bad == cad36f38576a6a781e3c62ab061c68f5b8dab13a) # reset_artifacts: -10 # true: 0 # build_abe binutils: 1 # First few build errors in logs: # 00:05:59 /home/tcwg-buildslave/workspace/tcwg_gnu_6/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-2.h:249:37: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:05:59 /home/tcwg-buildslave/workspace/tcwg_gnu_6/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-2.h:249:37: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:05:59 /home/tcwg-buildslave/workspace/tcwg_gnu_6/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-2.h:249:37: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:05:59 /home/tcwg-buildslave/workspace/tcwg_gnu_6/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-1.h:127:36: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:05:59 /home/tcwg-buildslave/workspace/tcwg_gnu_6/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-1.h:127:36: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:05:59 /home/tcwg-buildslave/workspace/tcwg_gnu_6/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-2.h:249:37: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:05:59 /home/tcwg-buildslave/workspace/tcwg_gnu_6/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-2.h:249:37: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:05:59 /home/tcwg-buildslave/workspace/tcwg_gnu_6/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-1.h:127:36: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:05:59 /home/tcwg-buildslave/workspace/tcwg_gnu_6/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-2.h:249:37: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:05:59 make[2]: *** [/home/tcwg-buildslave/workspace/tcwg_gnu_6/abe/snapshots/gcc.git~master/libgcc/shared-object.mk:14: trunctfhf2.o] Error 1 from (for last_good == 0960d937d9bee3c831d0b64a9c828c263a58ff89) # reset_artifacts: -10 # true: 0 # build_abe binutils: 1 # build_abe gcc: 2 # build_abe linux: 4 # build_abe glibc: 5 # build_abe gdb: 6 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-aarch64/1/art… Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-aarch64/1/art… Build top page/logs: https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-aarch64/1/ Configuration details: Reproduce builds: <cut> mkdir investigate-gcc-cad36f38576a6a781e3c62ab061c68f5b8dab13a cd investigate-gcc-cad36f38576a6a781e3c62ab061c68f5b8dab13a git clone https://git.linaro.org/toolchain/jenkins-scripts mkdir -p artifacts/manifests curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-aarch64/1/art… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-aarch64/1/art… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-aarch64/1/art… --fail chmod +x artifacts/test.sh # Reproduce the baseline build (build all pre-requisites) ./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh # Save baseline build state (which is then restored in artifacts/test.sh) mkdir -p ./bisect rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/ cd gcc # Reproduce first_bad build git checkout --detach cad36f38576a6a781e3c62ab061c68f5b8dab13a ../artifacts/test.sh # Reproduce last_good build git checkout --detach 0960d937d9bee3c831d0b64a9c828c263a58ff89 ../artifacts/test.sh cd .. </cut> History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/… Artifacts: https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-aarch64/1/art… Build log: https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-aarch64/1/con… Full commit (up to 1000 lines): <cut> commit cad36f38576a6a781e3c62ab061c68f5b8dab13a Author: Roger Sayle <roger(a)nextmovesoftware.com> Date: Tue Aug 31 11:45:07 2021 +0100 Preserve SUBREG_PROMOTED_VAR_P on (extend:HI (subreg/s:QI (reg:SI))). SUBREG_PROMOTED_VAR_P is a mechanism for tracking that a partial subreg is correctly zero-extended or sign-extended in the parent register. For example, the RTL (subreg/s/v:QI (reg/v:SI 23 [ x ]) 0) indicates that the byte x is zero extended in reg:SI 23, which is useful for optimization. An example is that zero extending the above QImode value to HImode can simply use a wider subreg, i.e. (subreg:HI (reg/v:SI 23 [ x ]) 0). This patch addresses the oversight/missed optimization opportunity that the new HImode subreg above should retain its SUBREG_PROMOTED_VAR_P annotation as its value is guaranteed to be correctly extended in the SImode parent. The code below to preserve SUBREG_PROMOTED_VAR_P is already present in the middle-end (e.g. simplify-rtx.c:7232-7242) but missing from one or two (precisely three) places that (accidentally) strip it. Whilst there I also added another optimization. If we need to extend the above QImode value beyond the SImode register holding it, say to DImode, we can eliminate the SUBREG and simply extend from the SImode register to DImode. 2021-08-31 Roger Sayle <roger(a)nextmovesoftware.com> gcc/ChangeLog * expr.c (convert_modes): Preserve SUBREG_PROMOTED_VAR_P when creating a (wider) partial subreg from a SUBREG_PROMOTED_VAR_P subreg. * simplify-rtx.c (simplify_unary_operation_1) [SIGN_EXTEND]: Likewise, preserve SUBREG_PROMOTED_VAR_P when creating a (wider) partial subreg from a SUBREG_PROMOTED_VAR_P subreg. Generate SIGN_EXTEND of the SUBREG_REG when a subreg would be paradoxical. [ZERO_EXTEND]: Likewise, preserve SUBREG_PROMOTED_VAR_P when creating a (wider) partial subreg from a SUBREG_PROMOTED_VAR_P subreg. Generate ZERO_EXTEND of the SUBREG_REG when a subreg would be paradoxical. --- gcc/expr.c | 19 ++++++++++++++++++- gcc/simplify-rtx.c | 52 ++++++++++++++++++++++++++++++++++++++++++---------- 2 files changed, 60 insertions(+), 11 deletions(-) diff --git a/gcc/expr.c b/gcc/expr.c index 096c0315ecc..5dd98a9bccc 100644 --- a/gcc/expr.c +++ b/gcc/expr.c @@ -688,7 +688,24 @@ convert_modes (machine_mode mode, machine_mode oldmode, rtx x, int unsignedp) && (GET_MODE_PRECISION (subreg_promoted_mode (x)) >= GET_MODE_PRECISION (int_mode)) && SUBREG_CHECK_PROMOTED_SIGN (x, unsignedp)) - x = gen_lowpart (int_mode, SUBREG_REG (x)); + { + scalar_int_mode int_orig_mode; + machine_mode orig_mode = GET_MODE (x); + x = gen_lowpart (int_mode, SUBREG_REG (x)); + + /* Preserve SUBREG_PROMOTED_VAR_P if the new mode is wider than + the original mode, but narrower than the inner mode. */ + if (GET_CODE (x) == SUBREG + && GET_MODE_PRECISION (subreg_promoted_mode (x)) + > GET_MODE_PRECISION (int_mode) + && is_a <scalar_int_mode> (orig_mode, &int_orig_mode) + && GET_MODE_PRECISION (int_mode) + > GET_MODE_PRECISION (int_orig_mode)) + { + SUBREG_PROMOTED_VAR_P (x) = 1; + SUBREG_PROMOTED_SET (x, unsignedp); + } + } if (GET_MODE (x) != VOIDmode) oldmode = GET_MODE (x); diff --git a/gcc/simplify-rtx.c b/gcc/simplify-rtx.c index e431e0c19d7..ebad5cb5a79 100644 --- a/gcc/simplify-rtx.c +++ b/gcc/simplify-rtx.c @@ -1512,12 +1512,28 @@ simplify_context::simplify_unary_operation_1 (rtx_code code, machine_mode mode, target mode is the same as the variable's promotion. */ if (GET_CODE (op) == SUBREG && SUBREG_PROMOTED_VAR_P (op) - && SUBREG_PROMOTED_SIGNED_P (op) - && !paradoxical_subreg_p (mode, GET_MODE (SUBREG_REG (op)))) + && SUBREG_PROMOTED_SIGNED_P (op)) { - temp = rtl_hooks.gen_lowpart_no_emit (mode, SUBREG_REG (op)); - if (temp) - return temp; + rtx subreg = SUBREG_REG (op); + machine_mode subreg_mode = GET_MODE (subreg); + if (!paradoxical_subreg_p (mode, subreg_mode)) + { + temp = rtl_hooks.gen_lowpart_no_emit (mode, subreg); + if (temp) + { + /* Preserve SUBREG_PROMOTED_VAR_P. */ + if (partial_subreg_p (temp)) + { + SUBREG_PROMOTED_VAR_P (temp) = 1; + SUBREG_PROMOTED_SET (temp, 1); + } + return temp; + } + } + else + /* Sign-extending a sign-extended subreg. */ + return simplify_gen_unary (SIGN_EXTEND, mode, + subreg, subreg_mode); } /* (sign_extend:M (sign_extend:N <X>)) is (sign_extend:M <X>). @@ -1631,12 +1647,28 @@ simplify_context::simplify_unary_operation_1 (rtx_code code, machine_mode mode, target mode is the same as the variable's promotion. */ if (GET_CODE (op) == SUBREG && SUBREG_PROMOTED_VAR_P (op) - && SUBREG_PROMOTED_UNSIGNED_P (op) - && !paradoxical_subreg_p (mode, GET_MODE (SUBREG_REG (op)))) + && SUBREG_PROMOTED_UNSIGNED_P (op)) { - temp = rtl_hooks.gen_lowpart_no_emit (mode, SUBREG_REG (op)); - if (temp) - return temp; + rtx subreg = SUBREG_REG (op); + machine_mode subreg_mode = GET_MODE (subreg); + if (!paradoxical_subreg_p (mode, subreg_mode)) + { + temp = rtl_hooks.gen_lowpart_no_emit (mode, subreg); + if (temp) + { + /* Preserve SUBREG_PROMOTED_VAR_P. */ + if (partial_subreg_p (temp)) + { + SUBREG_PROMOTED_VAR_P (temp) = 1; + SUBREG_PROMOTED_SET (temp, 0); + } + return temp; + } + } + else + /* Zero-extending a zero-extended subreg. */ + return simplify_gen_unary (ZERO_EXTEND, mode, + subreg, subreg_mode); } /* Extending a widening multiplication should be canonicalized to </cut>

3 years, 3 months

[CI-NOTIFY]: TCWG Bisect tcwg_gnu_cross_build/master-aarch64 - Build # 1 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *gcc* in CI configuration tcwg_gnu_cross_build/master-aarch64. So far, this commit has regressed CI configurations: - tcwg_gnu_cross_build/master-aarch64 Culprit: <cut> commit cad36f38576a6a781e3c62ab061c68f5b8dab13a Author: Roger Sayle <roger(a)nextmovesoftware.com> Date: Tue Aug 31 11:45:07 2021 +0100 Preserve SUBREG_PROMOTED_VAR_P on (extend:HI (subreg/s:QI (reg:SI))). SUBREG_PROMOTED_VAR_P is a mechanism for tracking that a partial subreg is correctly zero-extended or sign-extended in the parent register. For example, the RTL (subreg/s/v:QI (reg/v:SI 23 [ x ]) 0) indicates that the byte x is zero extended in reg:SI 23, which is useful for optimization. An example is that zero extending the above QImode value to HImode can simply use a wider subreg, i.e. (subreg:HI (reg/v:SI 23 [ x ]) 0). This patch addresses the oversight/missed optimization opportunity that the new HImode subreg above should retain its SUBREG_PROMOTED_VAR_P annotation as its value is guaranteed to be correctly extended in the SImode parent. The code below to preserve SUBREG_PROMOTED_VAR_P is already present in the middle-end (e.g. simplify-rtx.c:7232-7242) but missing from one or two (precisely three) places that (accidentally) strip it. Whilst there I also added another optimization. If we need to extend the above QImode value beyond the SImode register holding it, say to DImode, we can eliminate the SUBREG and simply extend from the SImode register to DImode. 2021-08-31 Roger Sayle <roger(a)nextmovesoftware.com> gcc/ChangeLog * expr.c (convert_modes): Preserve SUBREG_PROMOTED_VAR_P when creating a (wider) partial subreg from a SUBREG_PROMOTED_VAR_P subreg. * simplify-rtx.c (simplify_unary_operation_1) [SIGN_EXTEND]: Likewise, preserve SUBREG_PROMOTED_VAR_P when creating a (wider) partial subreg from a SUBREG_PROMOTED_VAR_P subreg. Generate SIGN_EXTEND of the SUBREG_REG when a subreg would be paradoxical. [ZERO_EXTEND]: Likewise, preserve SUBREG_PROMOTED_VAR_P when creating a (wider) partial subreg from a SUBREG_PROMOTED_VAR_P subreg. Generate ZERO_EXTEND of the SUBREG_REG when a subreg would be paradoxical. </cut> Results regressed to (for first_bad == cad36f38576a6a781e3c62ab061c68f5b8dab13a) # reset_artifacts: -10 # true: 0 # build_abe binutils: 1 # First few build errors in logs: # 00:04:40 cc1: error: no include path in which to search for stdc-predef.h # 00:04:48 /home/tcwg-buildslave/workspace/tcwg_gnu_1/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-2.h:249:37: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:04:48 /home/tcwg-buildslave/workspace/tcwg_gnu_1/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-2.h:249:37: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:04:48 /home/tcwg-buildslave/workspace/tcwg_gnu_1/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-2.h:249:37: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:04:48 /home/tcwg-buildslave/workspace/tcwg_gnu_1/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-1.h:127:36: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:04:48 /home/tcwg-buildslave/workspace/tcwg_gnu_1/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-1.h:127:36: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:04:48 /home/tcwg-buildslave/workspace/tcwg_gnu_1/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-1.h:127:36: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:04:48 /home/tcwg-buildslave/workspace/tcwg_gnu_1/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-2.h:249:37: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 # 00:04:48 make[2]: *** [/home/tcwg-buildslave/workspace/tcwg_gnu_1/abe/snapshots/gcc.git~master/libgcc/static-object.mk:17: floatsitf.o] Error 1 # 00:04:48 /home/tcwg-buildslave/workspace/tcwg_gnu_1/abe/snapshots/gcc.git~master/libgcc/soft-fp/op-2.h:249:37: internal compiler error: in subreg_promoted_mode, at rtl.h:3132 from (for last_good == 0960d937d9bee3c831d0b64a9c828c263a58ff89) # reset_artifacts: -10 # true: 0 # build_abe binutils: 1 # build_abe stage1: 2 # build_abe linux: 3 # build_abe glibc: 4 # build_abe stage2: 5 # build_abe gdb: 6 # build_abe qemu: 7 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/1/arti… Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/1/arti… Build top page/logs: https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/1/ Configuration details: Reproduce builds: <cut> mkdir investigate-gcc-cad36f38576a6a781e3c62ab061c68f5b8dab13a cd investigate-gcc-cad36f38576a6a781e3c62ab061c68f5b8dab13a git clone https://git.linaro.org/toolchain/jenkins-scripts mkdir -p artifacts/manifests curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/1/arti… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/1/arti… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/1/arti… --fail chmod +x artifacts/test.sh # Reproduce the baseline build (build all pre-requisites) ./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh # Save baseline build state (which is then restored in artifacts/test.sh) mkdir -p ./bisect rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/ cd gcc # Reproduce first_bad build git checkout --detach cad36f38576a6a781e3c62ab061c68f5b8dab13a ../artifacts/test.sh # Reproduce last_good build git checkout --detach 0960d937d9bee3c831d0b64a9c828c263a58ff89 ../artifacts/test.sh cd .. </cut> History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/… Artifacts: https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/1/arti… Build log: https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-aarch64/1/cons… Full commit (up to 1000 lines): <cut> commit cad36f38576a6a781e3c62ab061c68f5b8dab13a Author: Roger Sayle <roger(a)nextmovesoftware.com> Date: Tue Aug 31 11:45:07 2021 +0100 Preserve SUBREG_PROMOTED_VAR_P on (extend:HI (subreg/s:QI (reg:SI))). SUBREG_PROMOTED_VAR_P is a mechanism for tracking that a partial subreg is correctly zero-extended or sign-extended in the parent register. For example, the RTL (subreg/s/v:QI (reg/v:SI 23 [ x ]) 0) indicates that the byte x is zero extended in reg:SI 23, which is useful for optimization. An example is that zero extending the above QImode value to HImode can simply use a wider subreg, i.e. (subreg:HI (reg/v:SI 23 [ x ]) 0). This patch addresses the oversight/missed optimization opportunity that the new HImode subreg above should retain its SUBREG_PROMOTED_VAR_P annotation as its value is guaranteed to be correctly extended in the SImode parent. The code below to preserve SUBREG_PROMOTED_VAR_P is already present in the middle-end (e.g. simplify-rtx.c:7232-7242) but missing from one or two (precisely three) places that (accidentally) strip it. Whilst there I also added another optimization. If we need to extend the above QImode value beyond the SImode register holding it, say to DImode, we can eliminate the SUBREG and simply extend from the SImode register to DImode. 2021-08-31 Roger Sayle <roger(a)nextmovesoftware.com> gcc/ChangeLog * expr.c (convert_modes): Preserve SUBREG_PROMOTED_VAR_P when creating a (wider) partial subreg from a SUBREG_PROMOTED_VAR_P subreg. * simplify-rtx.c (simplify_unary_operation_1) [SIGN_EXTEND]: Likewise, preserve SUBREG_PROMOTED_VAR_P when creating a (wider) partial subreg from a SUBREG_PROMOTED_VAR_P subreg. Generate SIGN_EXTEND of the SUBREG_REG when a subreg would be paradoxical. [ZERO_EXTEND]: Likewise, preserve SUBREG_PROMOTED_VAR_P when creating a (wider) partial subreg from a SUBREG_PROMOTED_VAR_P subreg. Generate ZERO_EXTEND of the SUBREG_REG when a subreg would be paradoxical. --- gcc/expr.c | 19 ++++++++++++++++++- gcc/simplify-rtx.c | 52 ++++++++++++++++++++++++++++++++++++++++++---------- 2 files changed, 60 insertions(+), 11 deletions(-) diff --git a/gcc/expr.c b/gcc/expr.c index 096c0315ecc..5dd98a9bccc 100644 --- a/gcc/expr.c +++ b/gcc/expr.c @@ -688,7 +688,24 @@ convert_modes (machine_mode mode, machine_mode oldmode, rtx x, int unsignedp) && (GET_MODE_PRECISION (subreg_promoted_mode (x)) >= GET_MODE_PRECISION (int_mode)) && SUBREG_CHECK_PROMOTED_SIGN (x, unsignedp)) - x = gen_lowpart (int_mode, SUBREG_REG (x)); + { + scalar_int_mode int_orig_mode; + machine_mode orig_mode = GET_MODE (x); + x = gen_lowpart (int_mode, SUBREG_REG (x)); + + /* Preserve SUBREG_PROMOTED_VAR_P if the new mode is wider than + the original mode, but narrower than the inner mode. */ + if (GET_CODE (x) == SUBREG + && GET_MODE_PRECISION (subreg_promoted_mode (x)) + > GET_MODE_PRECISION (int_mode) + && is_a <scalar_int_mode> (orig_mode, &int_orig_mode) + && GET_MODE_PRECISION (int_mode) + > GET_MODE_PRECISION (int_orig_mode)) + { + SUBREG_PROMOTED_VAR_P (x) = 1; + SUBREG_PROMOTED_SET (x, unsignedp); + } + } if (GET_MODE (x) != VOIDmode) oldmode = GET_MODE (x); diff --git a/gcc/simplify-rtx.c b/gcc/simplify-rtx.c index e431e0c19d7..ebad5cb5a79 100644 --- a/gcc/simplify-rtx.c +++ b/gcc/simplify-rtx.c @@ -1512,12 +1512,28 @@ simplify_context::simplify_unary_operation_1 (rtx_code code, machine_mode mode, target mode is the same as the variable's promotion. */ if (GET_CODE (op) == SUBREG && SUBREG_PROMOTED_VAR_P (op) - && SUBREG_PROMOTED_SIGNED_P (op) - && !paradoxical_subreg_p (mode, GET_MODE (SUBREG_REG (op)))) + && SUBREG_PROMOTED_SIGNED_P (op)) { - temp = rtl_hooks.gen_lowpart_no_emit (mode, SUBREG_REG (op)); - if (temp) - return temp; + rtx subreg = SUBREG_REG (op); + machine_mode subreg_mode = GET_MODE (subreg); + if (!paradoxical_subreg_p (mode, subreg_mode)) + { + temp = rtl_hooks.gen_lowpart_no_emit (mode, subreg); + if (temp) + { + /* Preserve SUBREG_PROMOTED_VAR_P. */ + if (partial_subreg_p (temp)) + { + SUBREG_PROMOTED_VAR_P (temp) = 1; + SUBREG_PROMOTED_SET (temp, 1); + } + return temp; + } + } + else + /* Sign-extending a sign-extended subreg. */ + return simplify_gen_unary (SIGN_EXTEND, mode, + subreg, subreg_mode); } /* (sign_extend:M (sign_extend:N <X>)) is (sign_extend:M <X>). @@ -1631,12 +1647,28 @@ simplify_context::simplify_unary_operation_1 (rtx_code code, machine_mode mode, target mode is the same as the variable's promotion. */ if (GET_CODE (op) == SUBREG && SUBREG_PROMOTED_VAR_P (op) - && SUBREG_PROMOTED_UNSIGNED_P (op) - && !paradoxical_subreg_p (mode, GET_MODE (SUBREG_REG (op)))) + && SUBREG_PROMOTED_UNSIGNED_P (op)) { - temp = rtl_hooks.gen_lowpart_no_emit (mode, SUBREG_REG (op)); - if (temp) - return temp; + rtx subreg = SUBREG_REG (op); + machine_mode subreg_mode = GET_MODE (subreg); + if (!paradoxical_subreg_p (mode, subreg_mode)) + { + temp = rtl_hooks.gen_lowpart_no_emit (mode, subreg); + if (temp) + { + /* Preserve SUBREG_PROMOTED_VAR_P. */ + if (partial_subreg_p (temp)) + { + SUBREG_PROMOTED_VAR_P (temp) = 1; + SUBREG_PROMOTED_SET (temp, 0); + } + return temp; + } + } + else + /* Zero-extending a zero-extended subreg. */ + return simplify_gen_unary (ZERO_EXTEND, mode, + subreg, subreg_mode); } /* Extending a widening multiplication should be canonicalized to </cut>

3 years, 3 months

[CI-NOTIFY]: TCWG Bisect tcwg_gnu_native_build/master-arm - Build # 1 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *gdb* in CI configuration tcwg_gnu_native_build/master-arm. So far, this commit has regressed CI configurations: - tcwg_gnu_native_build/master-arm Culprit: <cut> commit 282aa4f7d292eb4bc213d028465a3b96f5af2f22 Author: Tom Tromey <tom(a)tromey.com> Date: Sat Aug 28 13:16:50 2021 -0600 Add some parallel_for_each tests Tom de Vries noticed that a patch in the DWARF scanner rewrite series caused a regression in parallel_for_each -- it started crashing in the case where the number of threads is 0 (there was an unchecked use of "n-1" that was used to size an array). He also pointed out that there were no tests of parallel_for_each. This adds a few tests of parallel_for_each, primarily testing that different settings for the number of threads will work. This test catches the bug that he found in that series. </cut> Results regressed to (for first_bad == 282aa4f7d292eb4bc213d028465a3b96f5af2f22) # reset_artifacts: -10 # true: 0 # build_abe binutils: 1 # build_abe gcc: 2 # build_abe linux: 4 # build_abe glibc: 5 # First few build errors in logs: # 00:03:45 ../../../../../../gdb/gdb/unittests/parallel-for-selftests.c:53:30: error: use of deleted function ‘std::atomic<int>::atomic(const std::atomic<int>&)’ # 00:03:45 make[1]: *** [unittests/parallel-for-selftests.o] Error 1 # 00:03:46 make: *** [all-gdb] Error 2 from (for last_good == ee8b88452c1cb1be97199942aee7a76bbca210ee) # reset_artifacts: -10 # true: 0 # build_abe binutils: 1 # build_abe gcc: 2 # build_abe linux: 4 # build_abe glibc: 5 # build_abe gdb: 6 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/1/artifac… Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/1/artifac… Build top page/logs: https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/1/ Configuration details: Reproduce builds: <cut> mkdir investigate-gdb-282aa4f7d292eb4bc213d028465a3b96f5af2f22 cd investigate-gdb-282aa4f7d292eb4bc213d028465a3b96f5af2f22 git clone https://git.linaro.org/toolchain/jenkins-scripts mkdir -p artifacts/manifests curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/1/artifac… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/1/artifac… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/1/artifac… --fail chmod +x artifacts/test.sh # Reproduce the baseline build (build all pre-requisites) ./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh # Save baseline build state (which is then restored in artifacts/test.sh) mkdir -p ./bisect rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gdb/ ./ ./bisect/baseline/ cd gdb # Reproduce first_bad build git checkout --detach 282aa4f7d292eb4bc213d028465a3b96f5af2f22 ../artifacts/test.sh # Reproduce last_good build git checkout --detach ee8b88452c1cb1be97199942aee7a76bbca210ee ../artifacts/test.sh cd .. </cut> History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/… Artifacts: https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/1/artifac… Build log: https://ci.linaro.org/job/tcwg_gnu_native_build-bisect-master-arm/1/console… Full commit (up to 1000 lines): <cut> commit 282aa4f7d292eb4bc213d028465a3b96f5af2f22 Author: Tom Tromey <tom(a)tromey.com> Date: Sat Aug 28 13:16:50 2021 -0600 Add some parallel_for_each tests Tom de Vries noticed that a patch in the DWARF scanner rewrite series caused a regression in parallel_for_each -- it started crashing in the case where the number of threads is 0 (there was an unchecked use of "n-1" that was used to size an array). He also pointed out that there were no tests of parallel_for_each. This adds a few tests of parallel_for_each, primarily testing that different settings for the number of threads will work. This test catches the bug that he found in that series. --- gdb/Makefile.in | 1 + gdb/unittests/parallel-for-selftests.c | 86 ++++++++++++++++++++++++++++++++++ 2 files changed, 87 insertions(+) diff --git a/gdb/Makefile.in b/gdb/Makefile.in index 73a1bf83c85..320d3326a81 100644 --- a/gdb/Makefile.in +++ b/gdb/Makefile.in @@ -456,6 +456,7 @@ SELFTESTS_SRCS = \ unittests/offset-type-selftests.c \ unittests/observable-selftests.c \ unittests/optional-selftests.c \ + unittests/parallel-for-selftests.c \ unittests/parse-connection-spec-selftests.c \ unittests/ptid-selftests.c \ unittests/main-thread-selftests.c \ diff --git a/gdb/unittests/parallel-for-selftests.c b/gdb/unittests/parallel-for-selftests.c new file mode 100644 index 00000000000..7f61b709fa7 --- /dev/null +++ b/gdb/unittests/parallel-for-selftests.c @@ -0,0 +1,86 @@ +/* Self tests for parallel_for_each + + Copyright (C) 2021 Free Software Foundation, Inc. + + This file is part of GDB. + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. */ + +#include "defs.h" +#include "gdbsupport/selftest.h" +#include "gdbsupport/parallel-for.h" +#include "gdbsupport/thread-pool.h" + +#if CXX_STD_THREAD + +namespace selftests { +namespace parallel_for { + +struct save_restore_n_threads +{ + save_restore_n_threads () + : n_threads (gdb::thread_pool::g_thread_pool->thread_count ()) + { + } + + ~save_restore_n_threads () + { + gdb::thread_pool::g_thread_pool->set_thread_count (n_threads); + } + + int n_threads; +}; + +static void +test (int n_threads) +{ + save_restore_n_threads saver; + gdb::thread_pool::g_thread_pool->set_thread_count (n_threads); + +#define NUMBER 10000 + + std::atomic<int> counter = 0; + gdb::parallel_for_each (0, NUMBER, + [&] (int start, int end) + { + counter += end - start; + }); + + SELF_CHECK (counter == NUMBER); + +#undef NUMBER +} + +static void +test_n_threads () +{ + test (0); + test (1); + test (3); +} + +} +} + +#endif /* CXX_STD_THREAD */ + +void _initialize_parallel_for_selftests (); +void +_initialize_parallel_for_selftests () +{ +#ifdef CXX_STD_THREAD + selftests::register_test ("parallel_for", + selftests::parallel_for::test_n_threads); +#endif /* CXX_STD_THREAD */ +} </cut>

3 years, 4 months

[CI-NOTIFY]: TCWG Bisect tcwg_gnu_cross_build/master-arm - Build # 1 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *gcc* in CI configuration tcwg_gnu_cross_build/master-arm. So far, this commit has regressed CI configurations: - tcwg_gnu_cross_build/master-arm Culprit: <cut> commit caf81d3b57501b1f58dcd9b1ef9d7b4bc76f4ab1 Author: Sebastian Huber <sebastian.huber(a)embedded-brains.de> Date: Tue Aug 17 09:53:43 2021 +0200 Use __builtin_trap() for abort() if inhibit_libc abort() is used in gcc_assert() and gcc_unreachable() which is used by target libraries such as libgcov.a. This patch changes the abort() definition under certain conditions. If inhibit_libc is defined and abort is not already defined, then abort() is defined to __builtin_trap(). The inhibit_libc define is usually defined if GCC is built for targets running in embedded systems which may optionally use a C standard library. If inhibit_libc is defined, then there may be still a full featured abort() available. abort() is a heavy weight function which depends on signals and file streams. For statically linked applications, this means that a dependency on gcc_assert() pulls in the support for signals and file streams. This could prevent using gcov to test low end targets for example. Using __builtin_trap() avoids these dependencies if the target implements a "trap" instruction. The application or operating system could use a trap handler to react to failed GCC runtime checks which caused a trap. gcc/ * tsystem.h (abort): Define abort() if inhibit_libc is defined and it is not already defined. </cut> Results regressed to (for first_bad == caf81d3b57501b1f58dcd9b1ef9d7b4bc76f4ab1) # reset_artifacts: -10 # true: 0 # build_abe binutils: 1 # First few build errors in logs: # 00:01:44 cc1: error: no include path in which to search for stdc-predef.h # 00:02:05 /home/tcwg-buildslave/workspace/tcwg_gnu_1/abe/snapshots/gcc.git~master/libgcc/unwind-arm-common.inc:55:24: error: macro passed 1 arguments, but takes just 0 # 00:02:05 make[2]: *** [/home/tcwg-buildslave/workspace/tcwg_gnu_1/abe/snapshots/gcc.git~master/libgcc/static-object.mk:17: unwind-arm.o] Error 1 # 00:02:06 make[1]: *** [Makefile:12484: all-target-libgcc] Error 2 # 00:02:06 make: *** [Makefile:953: all] Error 2 from (for last_good == d7e56b084d0b230ae5ee280f569d679fa0f09f4d) # reset_artifacts: -10 # true: 0 # build_abe binutils: 1 # build_abe stage1: 2 # build_abe linux: 3 # build_abe glibc: 4 # build_abe stage2: 5 # build_abe gdb: 6 # build_abe qemu: 7 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-arm/1/artifact… Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-arm/1/artifact… Build top page/logs: https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-arm/1/ Configuration details: Reproduce builds: <cut> mkdir investigate-gcc-caf81d3b57501b1f58dcd9b1ef9d7b4bc76f4ab1 cd investigate-gcc-caf81d3b57501b1f58dcd9b1ef9d7b4bc76f4ab1 git clone https://git.linaro.org/toolchain/jenkins-scripts mkdir -p artifacts/manifests curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-arm/1/artifact… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-arm/1/artifact… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-arm/1/artifact… --fail chmod +x artifacts/test.sh # Reproduce the baseline build (build all pre-requisites) ./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh # Save baseline build state (which is then restored in artifacts/test.sh) mkdir -p ./bisect rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/ cd gcc # Reproduce first_bad build git checkout --detach caf81d3b57501b1f58dcd9b1ef9d7b4bc76f4ab1 ../artifacts/test.sh # Reproduce last_good build git checkout --detach d7e56b084d0b230ae5ee280f569d679fa0f09f4d ../artifacts/test.sh cd .. </cut> History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/… Artifacts: https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-arm/1/artifact… Build log: https://ci.linaro.org/job/tcwg_gnu_cross_build-bisect-master-arm/1/consoleT… Full commit (up to 1000 lines): <cut> commit caf81d3b57501b1f58dcd9b1ef9d7b4bc76f4ab1 Author: Sebastian Huber <sebastian.huber(a)embedded-brains.de> Date: Tue Aug 17 09:53:43 2021 +0200 Use __builtin_trap() for abort() if inhibit_libc abort() is used in gcc_assert() and gcc_unreachable() which is used by target libraries such as libgcov.a. This patch changes the abort() definition under certain conditions. If inhibit_libc is defined and abort is not already defined, then abort() is defined to __builtin_trap(). The inhibit_libc define is usually defined if GCC is built for targets running in embedded systems which may optionally use a C standard library. If inhibit_libc is defined, then there may be still a full featured abort() available. abort() is a heavy weight function which depends on signals and file streams. For statically linked applications, this means that a dependency on gcc_assert() pulls in the support for signals and file streams. This could prevent using gcov to test low end targets for example. Using __builtin_trap() avoids these dependencies if the target implements a "trap" instruction. The application or operating system could use a trap handler to react to failed GCC runtime checks which caused a trap. gcc/ * tsystem.h (abort): Define abort() if inhibit_libc is defined and it is not already defined. --- gcc/tsystem.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gcc/tsystem.h b/gcc/tsystem.h index e1e6a96a4f4..5c72c69ff3e 100644 --- a/gcc/tsystem.h +++ b/gcc/tsystem.h @@ -59,7 +59,7 @@ extern int atexit (void (*)(void)); #endif #ifndef abort -extern void abort (void) __attribute__ ((__noreturn__)); +#define abort() __builtin_trap () #endif #ifndef strlen </cut>

3 years, 4 months

[CI-NOTIFY]: TCWG Bisect tcwg_gcc_bootstrap/master-aarch64-bootstrap_profiled - Build # 3 - Fixed!

by ci_notify＠linaro.org

Successfully identified regression in *binutils* in CI configuration tcwg_gcc_bootstrap/master-aarch64-bootstrap_profiled. So far, this commit has regressed CI configurations: - tcwg_gcc_bootstrap/master-aarch64-bootstrap_profiled Culprit: <cut> commit a12ea97b9dab8eedf411fc5052ffaa8be29f5d36 Author: GDB Administrator <gdbadmin(a)sourceware.org> Date: Mon Aug 23 00:00:07 2021 +0000 Automatic date update in version.in </cut> Results regressed to (for first_bad == a12ea97b9dab8eedf411fc5052ffaa8be29f5d36) # reset_artifacts: -10 # true: 0 # First few build errors in logs: from (for last_good == fe7f0b013526b30ef657c5ad34a3c622a54499ac) # reset_artifacts: -10 # true: 0 # build_abe binutils: 1 # build_abe bootstrap_profiled: 2 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… Build top page/logs: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… Configuration details: Reproduce builds: <cut> mkdir investigate-binutils-a12ea97b9dab8eedf411fc5052ffaa8be29f5d36 cd investigate-binutils-a12ea97b9dab8eedf411fc5052ffaa8be29f5d36 git clone https://git.linaro.org/toolchain/jenkins-scripts mkdir -p artifacts/manifests curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… --fail chmod +x artifacts/test.sh # Reproduce the baseline build (build all pre-requisites) ./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh # Save baseline build state (which is then restored in artifacts/test.sh) mkdir -p ./bisect rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /binutils/ ./ ./bisect/baseline/ cd binutils # Reproduce first_bad build git checkout --detach a12ea97b9dab8eedf411fc5052ffaa8be29f5d36 ../artifacts/test.sh # Reproduce last_good build git checkout --detach fe7f0b013526b30ef657c5ad34a3c622a54499ac ../artifacts/test.sh cd .. </cut> History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/… Artifacts: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… Build log: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… Full commit (up to 1000 lines): <cut> commit a12ea97b9dab8eedf411fc5052ffaa8be29f5d36 Author: GDB Administrator <gdbadmin(a)sourceware.org> Date: Mon Aug 23 00:00:07 2021 +0000 Automatic date update in version.in --- bfd/version.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/bfd/version.h b/bfd/version.h index d22e02c7fd4..66d43d6f3a1 100644 --- a/bfd/version.h +++ b/bfd/version.h @@ -16,7 +16,7 @@ In releases, the date is not included in either version strings or sonames. */ -#define BFD_VERSION_DATE 20210822 +#define BFD_VERSION_DATE 20210823 #define BFD_VERSION @bfd_version@ #define BFD_VERSION_STRING @bfd_version_package@ @bfd_version_string@ #define REPORT_BUGS_TO @report_bugs_to@ </cut>

3 years, 4 months

[ACTIVITY] report week ending 26 Aug

by Peter Maydell

Progress (short week, 3 days): * UM-2 [QEMU upstream maintainership] + QEMU 6.1.0 has now been released + Sent out the first arm pullreq for the 6.2 cycle, including another slice of the MVE patches + tried to work through some of the codereview backlog -- PMM

3 years, 4 months

[CI-NOTIFY]: TCWG Bisect tcwg_gcc_bootstrap/master-arm-bootstrap_debug - Build # 2 - Successful!

by ci_notify＠linaro.org

Successfully identified regression in *gcc* in CI configuration tcwg_gcc_bootstrap/master-arm-bootstrap_debug. So far, this commit has regressed CI configurations: - tcwg_gcc_bootstrap/master-arm-bootstrap_debug Culprit: <cut> commit 1d244020246cb155e4de62ca3b302b920a1f513f Author: Roger Sayle <roger(a)nextmovesoftware.com> Date: Mon Aug 23 12:37:04 2021 +0100 Fold sign of LSHIFT_EXPR to eliminate no-op conversions. This short patch teaches fold that it is "safe" to change the sign of a left shift, to reduce the number of type conversions in gimple. As an example: unsigned int foo(unsigned int i) { return (int)i << 8; } is currently optimized to: unsigned int foo (unsigned int i) { int i.0_1; int _2; unsigned int _4; <bb 2> [local count: 1073741824]: i.0_1 = (int) i_3(D); _2 = i.0_1 << 8; _4 = (unsigned int) _2; return _4; } with this patch, this now becomes: unsigned int foo (unsigned int i) { unsigned int _2; <bb 2> [local count: 1073741824]: _2 = i_1(D) << 8; return _2; } which generates exactly the same assembly language. Aside from the reduced memory usage, the real benefit is that no-op conversions tend to interfere with many folding optimizations. For example, unsigned int bar(unsigned char i) { return (i ^ (i<<16)) | (i<<8); } currently gets (tangled in conversions and) optimized to: unsigned int bar (unsigned char i) { unsigned int _1; unsigned int _2; int _3; int _4; unsigned int _6; unsigned int _8; <bb 2> [local count: 1073741824]: _1 = (unsigned int) i_5(D); _2 = _1 * 65537; _3 = (int) i_5(D); _4 = _3 << 8; _8 = (unsigned int) _4; _6 = _2 | _8; return _6; } but with this patch, bar now optimizes down to: unsigned int bar(unsigned char i) { unsigned int _1; unsigned int _4; <bb 2> [local count: 1073741824]: _1 = (unsigned int) i_3(D); _4 = _1 * 65793; return _4; } 2021-08-23 Roger Sayle <roger(a)nextmovesoftware.com> gcc/ChangeLog * match.pd (shift transformations): Change the sign of an LSHIFT_EXPR if it reduces the number of explicit conversions. gcc/testsuite/ChangeLog * gcc.dg/fold-convlshift-1.c: New test case. * gcc.dg/fold-convlshift-2.c: New test case. </cut> Results regressed to (for first_bad == 1d244020246cb155e4de62ca3b302b920a1f513f) # reset_artifacts: -10 # true: 0 # build_abe binutils: 1 # First few build errors in logs: # 00:06:26 make[3]: [armv8l-unknown-linux-gnueabihf/bits/largefile-config.h] Error 1 (ignored) # 00:25:39 make[3]: [armv8l-unknown-linux-gnueabihf/bits/largefile-config.h] Error 1 (ignored) # 00:29:38 /home/tcwg-buildslave/workspace/tcwg_gnu_8/abe/snapshots/gcc.git~master/gcc/bitmap.h:357:13: error: type mismatch in ‘lshift_expr’ # 00:29:38 /home/tcwg-buildslave/workspace/tcwg_gnu_8/abe/snapshots/gcc.git~master/gcc/bitmap.h:357:13: internal compiler error: ‘verify_gimple’ failed # 00:29:38 make[3]: *** [bitmap.o] Error 1 # 00:34:06 make[2]: *** [all-stage3-gcc] Error 2 # 00:34:06 make[1]: *** [stage3-bubble] Error 2 # 00:34:07 make: *** [all] Error 2 from (for last_good == b320edc0c29c838b0090c3c9be14187d132f73f2) # reset_artifacts: -10 # true: 0 # build_abe binutils: 1 # build_abe bootstrap_debug: 2 Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de… Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de… Build top page/logs: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de… Configuration details: Reproduce builds: <cut> mkdir investigate-gcc-1d244020246cb155e4de62ca3b302b920a1f513f cd investigate-gcc-1d244020246cb155e4de62ca3b302b920a1f513f git clone https://git.linaro.org/toolchain/jenkins-scripts mkdir -p artifacts/manifests curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de… --fail curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de… --fail curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de… --fail chmod +x artifacts/test.sh # Reproduce the baseline build (build all pre-requisites) ./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh # Save baseline build state (which is then restored in artifacts/test.sh) mkdir -p ./bisect rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/ cd gcc # Reproduce first_bad build git checkout --detach 1d244020246cb155e4de62ca3b302b920a1f513f ../artifacts/test.sh # Reproduce last_good build git checkout --detach b320edc0c29c838b0090c3c9be14187d132f73f2 ../artifacts/test.sh cd .. </cut> History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/… Artifacts: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de… Build log: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de… Full commit (up to 1000 lines): <cut> commit 1d244020246cb155e4de62ca3b302b920a1f513f Author: Roger Sayle <roger(a)nextmovesoftware.com> Date: Mon Aug 23 12:37:04 2021 +0100 Fold sign of LSHIFT_EXPR to eliminate no-op conversions. This short patch teaches fold that it is "safe" to change the sign of a left shift, to reduce the number of type conversions in gimple. As an example: unsigned int foo(unsigned int i) { return (int)i << 8; } is currently optimized to: unsigned int foo (unsigned int i) { int i.0_1; int _2; unsigned int _4; <bb 2> [local count: 1073741824]: i.0_1 = (int) i_3(D); _2 = i.0_1 << 8; _4 = (unsigned int) _2; return _4; } with this patch, this now becomes: unsigned int foo (unsigned int i) { unsigned int _2; <bb 2> [local count: 1073741824]: _2 = i_1(D) << 8; return _2; } which generates exactly the same assembly language. Aside from the reduced memory usage, the real benefit is that no-op conversions tend to interfere with many folding optimizations. For example, unsigned int bar(unsigned char i) { return (i ^ (i<<16)) | (i<<8); } currently gets (tangled in conversions and) optimized to: unsigned int bar (unsigned char i) { unsigned int _1; unsigned int _2; int _3; int _4; unsigned int _6; unsigned int _8; <bb 2> [local count: 1073741824]: _1 = (unsigned int) i_5(D); _2 = _1 * 65537; _3 = (int) i_5(D); _4 = _3 << 8; _8 = (unsigned int) _4; _6 = _2 | _8; return _6; } but with this patch, bar now optimizes down to: unsigned int bar(unsigned char i) { unsigned int _1; unsigned int _4; <bb 2> [local count: 1073741824]: _1 = (unsigned int) i_3(D); _4 = _1 * 65793; return _4; } 2021-08-23 Roger Sayle <roger(a)nextmovesoftware.com> gcc/ChangeLog * match.pd (shift transformations): Change the sign of an LSHIFT_EXPR if it reduces the number of explicit conversions. gcc/testsuite/ChangeLog * gcc.dg/fold-convlshift-1.c: New test case. * gcc.dg/fold-convlshift-2.c: New test case. --- gcc/match.pd | 9 +++++++++ gcc/testsuite/gcc.dg/fold-convlshift-1.c | 20 ++++++++++++++++++++ gcc/testsuite/gcc.dg/fold-convlshift-2.c | 20 ++++++++++++++++++++ 3 files changed, 49 insertions(+) diff --git a/gcc/match.pd b/gcc/match.pd index 0fcfd0ea62c..978a1b0172e 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -3385,6 +3385,15 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) (if (integer_zerop (@2) || integer_all_onesp (@2)) (cmp @0 @2))))) +/* Both signed and unsigned lshift produce the same result, so use + the form that minimizes the number of conversions. */ +(simplify + (convert (lshift:s@0 (convert:s@1 @2) INTEGER_CST@3)) + (if (tree_nop_conversion_p (type, TREE_TYPE (@0)) + && INTEGRAL_TYPE_P (TREE_TYPE (@2)) + && TYPE_PRECISION (TREE_TYPE (@2)) <= TYPE_PRECISION (type)) + (lshift (convert @2) @3))) + /* Simplifications of conversions. */ /* Basic strip-useless-type-conversions / strip_nops. */ diff --git a/gcc/testsuite/gcc.dg/fold-convlshift-1.c b/gcc/testsuite/gcc.dg/fold-convlshift-1.c new file mode 100644 index 00000000000..b6f57f81e72 --- /dev/null +++ b/gcc/testsuite/gcc.dg/fold-convlshift-1.c @@ -0,0 +1,20 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-optimized" } */ + +unsigned int foo(unsigned int i) +{ + int t1 = i; + int t2 = t1 << 8; + return t2; +} + +int bar(int i) +{ + unsigned int t1 = i; + unsigned int t2 = t1 << 8; + return t2; +} + +/* { dg-final { scan-tree-dump-not "\$int\$" "optimized" } } */ +/* { dg-final { scan-tree-dump-not "\$unsigned int\$" "optimized" } } */ + diff --git a/gcc/testsuite/gcc.dg/fold-convlshift-2.c b/gcc/testsuite/gcc.dg/fold-convlshift-2.c new file mode 100644 index 00000000000..f21358c4584 --- /dev/null +++ b/gcc/testsuite/gcc.dg/fold-convlshift-2.c @@ -0,0 +1,20 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-optimized" } */ + +unsigned int foo(unsigned char c) +{ + int t1 = c; + int t2 = t1 << 8; + return t2; +} + +int bar(unsigned char c) +{ + unsigned int t1 = c; + unsigned int t2 = t1 << 8; + return t2; +} + +/* { dg-final { scan-tree-dump-times "\$int\$" 1 "optimized" } } */ +/* { dg-final { scan-tree-dump-times "\$unsigned int\$" 1 "optimized" } } */ + </cut>

3 years, 4 months

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

linaro-toolchain August 2021