summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt4
-rw-r--r--Documentation/firmware-guide/acpi/apei/einj.rst4
-rw-r--r--MAINTAINERS5
-rw-r--r--Makefile2
-rw-r--r--arch/arm/xen/enlighten.c2
-rw-r--r--arch/arm64/Kconfig2
-rw-r--r--arch/arm64/include/asm/atomic.h10
-rw-r--r--arch/arm64/include/asm/processor.h3
-rw-r--r--arch/arm64/kernel/asm-offsets.c2
-rw-r--r--arch/arm64/kernel/entry-ftrace.S12
-rw-r--r--arch/arm64/kernel/entry.S14
-rw-r--r--arch/arm64/kernel/perf_event.c41
-rw-r--r--arch/arm64/kernel/probes/kprobes_trampoline.S6
-rw-r--r--arch/arm64/kernel/signal.c7
-rw-r--r--arch/arm64/kernel/syscall.c10
-rw-r--r--arch/arm64/mm/init.c33
-rw-r--r--arch/ia64/include/asm/sparsemem.h1
-rw-r--r--arch/mips/boot/compressed/decompress.c3
-rw-r--r--arch/mips/cavium-octeon/octeon-irq.c2
-rw-r--r--arch/mips/kernel/binfmt_elfn32.c7
-rw-r--r--arch/mips/kernel/binfmt_elfo32.c7
-rw-r--r--arch/mips/kernel/relocate.c10
-rw-r--r--arch/powerpc/include/asm/vdso/gettimeofday.h16
-rw-r--r--arch/powerpc/kernel/vmlinux.lds.S8
-rw-r--r--arch/riscv/Kconfig6
-rw-r--r--arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts2
-rw-r--r--arch/riscv/configs/defconfig2
-rw-r--r--arch/riscv/include/asm/pgtable.h1
-rw-r--r--arch/riscv/include/asm/vdso.h2
-rw-r--r--arch/riscv/kernel/cacheinfo.c11
-rw-r--r--arch/riscv/kernel/entry.S24
-rw-r--r--arch/riscv/kernel/setup.c24
-rw-r--r--arch/riscv/kernel/stacktrace.c5
-rw-r--r--arch/riscv/kernel/time.c3
-rw-r--r--arch/riscv/kernel/vdso.c2
-rw-r--r--arch/riscv/mm/init.c16
-rw-r--r--arch/riscv/mm/kasan_init.c4
-rw-r--r--arch/x86/hyperv/hv_init.c29
-rw-r--r--arch/x86/xen/enlighten_hvm.c15
-rw-r--r--arch/x86/xen/smp_hvm.c29
-rw-r--r--crypto/asymmetric_keys/public_key.c3
-rw-r--r--crypto/xor.c2
-rw-r--r--drivers/acpi/internal.h2
-rw-r--r--drivers/acpi/scan.c15
-rw-r--r--drivers/crypto/Kconfig1
-rw-r--r--drivers/dma-buf/heaps/cma_heap.c3
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c53
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c48
-rw-r--r--drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/soc15.c3
-rw-r--r--drivers/gpu/drm/amd/amdkfd/kfd_crat.c11
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c142
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h38
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c54
-rw-r--r--drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h5
-rw-r--r--drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c8
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c2
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c4
-rw-r--r--drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c1
-rw-r--r--drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c11
-rw-r--r--drivers/gpu/drm/drm_plane.c9
-rw-r--r--drivers/gpu/drm/i915/Makefile1
-rw-r--r--drivers/gpu/drm/i915/display/icl_dsi.c4
-rw-r--r--drivers/gpu/drm/i915/display/intel_panel.c9
-rw-r--r--drivers/gpu/drm/i915/display/vlv_dsi.c16
-rw-r--r--drivers/gpu/drm/i915/gt/gen7_renderclear.c157
-rw-r--r--drivers/gpu/drm/i915/gt/intel_ring_submission.c6
-rw-r--r--drivers/gpu/drm/i915/gvt/display.c81
-rw-r--r--drivers/gpu/drm/i915/gvt/vgpu.c5
-rw-r--r--drivers/gpu/drm/i915/i915_drv.c4
-rw-r--r--drivers/gpu/drm/i915/i915_mitigations.c146
-rw-r--r--drivers/gpu/drm/i915/i915_mitigations.h13
-rw-r--r--drivers/gpu/drm/nouveau/dispnv50/Kbuild1
-rw-r--r--drivers/gpu/drm/nouveau/dispnv50/core.c1
-rw-r--r--drivers/gpu/drm/nouveau/dispnv50/curs.c1
-rw-r--r--drivers/gpu/drm/nouveau/dispnv50/disp.c4
-rw-r--r--drivers/gpu/drm/nouveau/dispnv50/disp.h2
-rw-r--r--drivers/gpu/drm/nouveau/dispnv50/wimm.c1
-rw-r--r--drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c2
-rw-r--r--drivers/gpu/drm/nouveau/dispnv50/wndw.c1
-rw-r--r--drivers/gpu/drm/nouveau/dispnv50/wndw.h8
-rw-r--r--drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c10
-rw-r--r--drivers/gpu/drm/nouveau/dispnv50/wndwc67e.c106
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/cl0080.h1
-rw-r--r--drivers/gpu/drm/nouveau/include/nvif/class.h5
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/core/device.h1
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h1
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h1
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h2
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/subdev/gpio.h1
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/subdev/i2c.h1
-rw-r--r--drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h1
-rw-r--r--drivers/gpu/drm/nouveau/nouveau_backlight.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvif/disp.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/device/base.c87
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/device/user.c1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild3
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c33
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c46
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h4
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/disp/rootga102.c52
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/disp/sorga102.c140
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/disp/sortu102.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c3
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/devinit/ga100.c76
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/devinit/priv.h1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild3
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c40
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c40
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramga102.c40
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/gpio/ga102.c118
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.h7
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c10
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c17
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gk110.c45
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gm200.c7
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/i2c/pad.h2
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/i2c/priv.h4
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c10
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c10
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild1
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mc/ga100.c74
-rw-r--r--drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c6
-rw-r--r--drivers/gpu/drm/ttm/ttm_pool.c22
-rw-r--r--drivers/infiniband/core/cma_configfs.c4
-rw-r--r--drivers/infiniband/core/restrack.c1
-rw-r--r--drivers/infiniband/core/ucma.c135
-rw-r--r--drivers/infiniband/core/umem.c2
-rw-r--r--drivers/infiniband/hw/mlx5/main.c4
-rw-r--r--drivers/infiniband/hw/ocrdma/ocrdma_verbs.c2
-rw-r--r--drivers/infiniband/hw/usnic/usnic_ib_verbs.c3
-rw-r--r--drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c2
-rw-r--r--drivers/iommu/intel/iommu.c1
-rw-r--r--drivers/iommu/intel/svm.c22
-rw-r--r--drivers/md/Kconfig2
-rw-r--r--drivers/md/dm-bufio.c6
-rw-r--r--drivers/md/dm-crypt.c170
-rw-r--r--drivers/md/dm-integrity.c62
-rw-r--r--drivers/md/dm-raid.c6
-rw-r--r--drivers/md/dm-snap.c24
-rw-r--r--drivers/md/dm.c2
-rw-r--r--drivers/nvme/host/core.c11
-rw-r--r--drivers/nvme/host/tcp.c4
-rw-r--r--drivers/nvme/target/rdma.c16
-rw-r--r--drivers/perf/arm_pmu.c5
-rw-r--r--drivers/scsi/mpt3sas/Kconfig2
-rw-r--r--drivers/scsi/qedi/qedi_main.c4
-rw-r--r--drivers/scsi/scsi_debug.c5
-rw-r--r--drivers/scsi/sd.c6
-rw-r--r--drivers/scsi/ufs/ufshcd.c24
-rw-r--r--drivers/spi/spi-cadence.c6
-rw-r--r--drivers/spi/spi-fsl-spi.c5
-rw-r--r--drivers/tty/serial/sifive.c1
-rw-r--r--drivers/xen/events/events_base.c10
-rw-r--r--drivers/xen/platform-pci.c8
-rw-r--r--drivers/xen/privcmd.c25
-rw-r--r--drivers/xen/xenbus/xenbus.h1
-rw-r--r--drivers/xen/xenbus/xenbus_comms.c8
-rw-r--r--drivers/xen/xenbus/xenbus_probe.c81
-rw-r--r--fs/cachefiles/rdwr.c2
-rw-r--r--fs/cifs/connect.c2
-rw-r--r--fs/cifs/dfs_cache.c3
-rw-r--r--fs/cifs/fs_context.c4
-rw-r--r--fs/cifs/smb2pdu.c2
-rw-r--r--fs/cifs/smb2pdu.h2
-rw-r--r--fs/ext4/ext4_jbd2.c17
-rw-r--r--fs/ext4/ext4_jbd2.h5
-rw-r--r--fs/ext4/fast_commit.c35
-rw-r--r--fs/ext4/file.c7
-rw-r--r--fs/ext4/inode.c6
-rw-r--r--fs/ext4/ioctl.c3
-rw-r--r--fs/ext4/namei.c27
-rw-r--r--fs/ext4/resize.c20
-rw-r--r--fs/ext4/super.c190
-rw-r--r--fs/ext4/xattr.c5
-rw-r--r--fs/io_uring.c46
-rw-r--r--fs/namespace.c7
-rw-r--r--fs/nfsd/nfs3xdr.c7
-rw-r--r--fs/proc/task_mmu.c53
-rw-r--r--include/asm-generic/bitops/atomic.h6
-rw-r--r--include/linux/compiler-gcc.h6
-rw-r--r--include/linux/dm-bufio.h1
-rw-r--r--include/linux/kasan.h6
-rw-r--r--include/linux/memcontrol.h2
-rw-r--r--include/linux/perf/arm_pmu.h2
-rw-r--r--include/trace/events/sunrpc.h59
-rw-r--r--include/xen/xenbus.h2
-rw-r--r--kernel/signal.c3
-rw-r--r--lib/iov_iter.c2
-rw-r--r--mm/hugetlb.c2
-rw-r--r--mm/kasan/init.c3
-rw-r--r--mm/memory-failure.c2
-rw-r--r--mm/mempolicy.c2
-rw-r--r--mm/page_alloc.c31
-rw-r--r--mm/process_vm_access.c1
-rw-r--r--mm/slub.c2
-rw-r--r--mm/vmalloc.c4
-rw-r--r--mm/vmscan.c2
-rw-r--r--net/sunrpc/svc_xprt.c4
-rw-r--r--security/lsm_audit.c7
-rwxr-xr-xtools/bootconfig/scripts/bconf2ftrace.sh1
-rwxr-xr-xtools/bootconfig/scripts/ftrace2bconf.sh4
-rw-r--r--tools/include/linux/build_bug.h5
-rw-r--r--tools/include/uapi/linux/kvm.h2
-rw-r--r--tools/lib/perf/tests/test-cpumap.c2
-rw-r--r--tools/lib/perf/tests/test-evlist.c7
-rw-r--r--tools/lib/perf/tests/test-evsel.c2
-rw-r--r--tools/lib/perf/tests/test-threadmap.c2
-rw-r--r--tools/perf/examples/bpf/5sec.c2
-rwxr-xr-xtools/perf/tests/shell/stat+shadow_stat.sh30
-rw-r--r--tools/perf/util/header.c8
-rw-r--r--tools/perf/util/machine.c4
-rw-r--r--tools/perf/util/session.c2
-rw-r--r--tools/perf/util/stat-shadow.c366
-rw-r--r--tools/testing/selftests/arm64/fp/fpsimd-test.S2
-rw-r--r--tools/testing/selftests/arm64/fp/sve-test.S2
229 files changed, 2832 insertions, 1194 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 9e3cdb271d06..a10b545c2070 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5972,6 +5972,10 @@
This option is obsoleted by the "nopv" option, which
has equivalent effect for XEN platform.
+ xen_no_vector_callback
+ [KNL,X86,XEN] Disable the vector callback for Xen
+ event channel interrupts.
+
xen_scrub_pages= [XEN]
Boolean option to control scrubbing pages before giving them back
to Xen, for use by other domains. Can be also changed at runtime
diff --git a/Documentation/firmware-guide/acpi/apei/einj.rst b/Documentation/firmware-guide/acpi/apei/einj.rst
index e588bccf5158..c042176e1707 100644
--- a/Documentation/firmware-guide/acpi/apei/einj.rst
+++ b/Documentation/firmware-guide/acpi/apei/einj.rst
@@ -50,8 +50,8 @@ The following files belong to it:
0x00000010 Memory Uncorrectable non-fatal
0x00000020 Memory Uncorrectable fatal
0x00000040 PCI Express Correctable
- 0x00000080 PCI Express Uncorrectable fatal
- 0x00000100 PCI Express Uncorrectable non-fatal
+ 0x00000080 PCI Express Uncorrectable non-fatal
+ 0x00000100 PCI Express Uncorrectable fatal
0x00000200 Platform Correctable
0x00000400 Platform Uncorrectable non-fatal
0x00000800 Platform Uncorrectable fatal
diff --git a/MAINTAINERS b/MAINTAINERS
index 4d3b2c934d68..705776b31c8d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -906,7 +906,7 @@ AMD KFD
M: Felix Kuehling <Felix.Kuehling@amd.com>
L: amd-gfx@lists.freedesktop.org
S: Supported
-T: git git://people.freedesktop.org/~agd5f/linux
+T: git https://gitlab.freedesktop.org/agd5f/linux.git
F: drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd*.[ch]
F: drivers/gpu/drm/amd/amdkfd/
F: drivers/gpu/drm/amd/include/cik_structs.h
@@ -14812,7 +14812,7 @@ M: Alex Deucher <alexander.deucher@amd.com>
M: Christian König <christian.koenig@amd.com>
L: amd-gfx@lists.freedesktop.org
S: Supported
-T: git git://people.freedesktop.org/~agd5f/linux
+T: git https://gitlab.freedesktop.org/agd5f/linux.git
F: drivers/gpu/drm/amd/
F: drivers/gpu/drm/radeon/
F: include/uapi/drm/amdgpu_drm.h
@@ -16313,6 +16313,7 @@ M: Pekka Enberg <penberg@kernel.org>
M: David Rientjes <rientjes@google.com>
M: Joonsoo Kim <iamjoonsoo.kim@lge.com>
M: Andrew Morton <akpm@linux-foundation.org>
+M: Vlastimil Babka <vbabka@suse.cz>
L: linux-mm@kvack.org
S: Maintained
F: include/linux/sl?b*.h
diff --git a/Makefile b/Makefile
index 9e73f82e0d86..b0e4767735dc 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
VERSION = 5
PATCHLEVEL = 11
SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
NAME = Kleptomaniac Octopus
# *DOCUMENTATION*
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 60e901cd0de6..5a957a9a0984 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -371,7 +371,7 @@ static int __init xen_guest_init(void)
}
gnttab_init();
if (!xen_initial_domain())
- xenbus_probe(NULL);
+ xenbus_probe();
/*
* Making sure board specific code will not set up ops for
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 05e17351e4f3..f39568b28ec1 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -174,8 +174,6 @@ config ARM64
select HAVE_NMI
select HAVE_PATA_PLATFORM
select HAVE_PERF_EVENTS
- select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI && HW_PERF_EVENTS
- select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
select HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 015ddffaf6ca..b56a4b2bc248 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -17,7 +17,7 @@
#include <asm/lse.h>
#define ATOMIC_OP(op) \
-static inline void arch_##op(int i, atomic_t *v) \
+static __always_inline void arch_##op(int i, atomic_t *v) \
{ \
__lse_ll_sc_body(op, i, v); \
}
@@ -32,7 +32,7 @@ ATOMIC_OP(atomic_sub)
#undef ATOMIC_OP
#define ATOMIC_FETCH_OP(name, op) \
-static inline int arch_##op##name(int i, atomic_t *v) \
+static __always_inline int arch_##op##name(int i, atomic_t *v) \
{ \
return __lse_ll_sc_body(op##name, i, v); \
}
@@ -56,7 +56,7 @@ ATOMIC_FETCH_OPS(atomic_sub_return)
#undef ATOMIC_FETCH_OPS
#define ATOMIC64_OP(op) \
-static inline void arch_##op(long i, atomic64_t *v) \
+static __always_inline void arch_##op(long i, atomic64_t *v) \
{ \
__lse_ll_sc_body(op, i, v); \
}
@@ -71,7 +71,7 @@ ATOMIC64_OP(atomic64_sub)
#undef ATOMIC64_OP
#define ATOMIC64_FETCH_OP(name, op) \
-static inline long arch_##op##name(long i, atomic64_t *v) \
+static __always_inline long arch_##op##name(long i, atomic64_t *v) \
{ \
return __lse_ll_sc_body(op##name, i, v); \
}
@@ -94,7 +94,7 @@ ATOMIC64_FETCH_OPS(atomic64_sub_return)
#undef ATOMIC64_FETCH_OP
#undef ATOMIC64_FETCH_OPS
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
+static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v)
{
return __lse_ll_sc_body(atomic64_dec_if_positive, v);
}
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 69ad25fbeae4..ca2cd75d3286 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -94,8 +94,7 @@
#endif /* CONFIG_ARM64_FORCE_52BIT */
extern phys_addr_t arm64_dma_phys_limit;
-extern phys_addr_t arm64_dma32_phys_limit;
-#define ARCH_LOW_ADDRESS_LIMIT ((arm64_dma_phys_limit ? : arm64_dma32_phys_limit) - 1)
+#define ARCH_LOW_ADDRESS_LIMIT (arm64_dma_phys_limit - 1)
struct debug_info {
#ifdef CONFIG_HAVE_HW_BREAKPOINT
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index f42fd9e33981..301784463587 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -75,7 +75,7 @@ int main(void)
DEFINE(S_SDEI_TTBR1, offsetof(struct pt_regs, sdei_ttbr1));
DEFINE(S_PMR_SAVE, offsetof(struct pt_regs, pmr_save));
DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe));
- DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs));
+ DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs));
BLANK();
#ifdef CONFIG_COMPAT
DEFINE(COMPAT_SIGFRAME_REGS_OFFSET, offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0));
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index a338f40e64d3..b3e4f9a088b1 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -35,7 +35,7 @@
*/
.macro ftrace_regs_entry, allregs=0
/* Make room for pt_regs, plus a callee frame */
- sub sp, sp, #(S_FRAME_SIZE + 16)
+ sub sp, sp, #(PT_REGS_SIZE + 16)
/* Save function arguments (and x9 for simplicity) */
stp x0, x1, [sp, #S_X0]
@@ -61,15 +61,15 @@
.endif
/* Save the callsite's SP and LR */
- add x10, sp, #(S_FRAME_SIZE + 16)
+ add x10, sp, #(PT_REGS_SIZE + 16)
stp x9, x10, [sp, #S_LR]
/* Save the PC after the ftrace callsite */
str x30, [sp, #S_PC]
/* Create a frame record for the callsite above pt_regs */
- stp x29, x9, [sp, #S_FRAME_SIZE]
- add x29, sp, #S_FRAME_SIZE
+ stp x29, x9, [sp, #PT_REGS_SIZE]
+ add x29, sp, #PT_REGS_SIZE
/* Create our frame record within pt_regs. */
stp x29, x30, [sp, #S_STACKFRAME]
@@ -120,7 +120,7 @@ ftrace_common_return:
ldr x9, [sp, #S_PC]
/* Restore the callsite's SP */
- add sp, sp, #S_FRAME_SIZE + 16
+ add sp, sp, #PT_REGS_SIZE + 16
ret x9
SYM_CODE_END(ftrace_common)
@@ -130,7 +130,7 @@ SYM_CODE_START(ftrace_graph_caller)
ldr x0, [sp, #S_PC]
sub x0, x0, #AARCH64_INSN_SIZE // ip (callsite's BL insn)
add x1, sp, #S_LR // parent_ip (callsite's LR)
- ldr x2, [sp, #S_FRAME_SIZE] // parent fp (callsite's FP)
+ ldr x2, [sp, #PT_REGS_SIZE] // parent fp (callsite's FP)
bl prepare_ftrace_return
b ftrace_common_return
SYM_CODE_END(ftrace_graph_caller)
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a8c3e7aaca74..c9bae73f2621 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -75,7 +75,7 @@ alternative_else_nop_endif
.endif
#endif
- sub sp, sp, #S_FRAME_SIZE
+ sub sp, sp, #PT_REGS_SIZE
#ifdef CONFIG_VMAP_STACK
/*
* Test whether the SP has overflowed, without corrupting a GPR.
@@ -96,7 +96,7 @@ alternative_else_nop_endif
* userspace, and can clobber EL0 registers to free up GPRs.
*/
- /* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */
+ /* Stash the original SP (minus PT_REGS_SIZE) in tpidr_el0. */
msr tpidr_el0, x0
/* Recover the original x0 value and stash it in tpidrro_el0 */
@@ -253,7 +253,7 @@ alternative_else_nop_endif
scs_load tsk, x20
.else
- add x21, sp, #S_FRAME_SIZE
+ add x21, sp, #PT_REGS_SIZE
get_current_task tsk
.endif /* \el == 0 */
mrs x22, elr_el1
@@ -377,7 +377,7 @@ alternative_else_nop_endif
ldp x26, x27, [sp, #16 * 13]
ldp x28, x29, [sp, #16 * 14]
ldr lr, [sp, #S_LR]
- add sp, sp, #S_FRAME_SIZE // restore sp
+ add sp, sp, #PT_REGS_SIZE // restore sp
.if \el == 0
alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
@@ -580,12 +580,12 @@ __bad_stack:
/*
* Store the original GPRs to the new stack. The orginal SP (minus
- * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry.
+ * PT_REGS_SIZE) was stashed in tpidr_el0 by kernel_ventry.
*/
- sub sp, sp, #S_FRAME_SIZE
+ sub sp, sp, #PT_REGS_SIZE
kernel_entry 1
mrs x0, tpidr_el0
- add x0, x0, #S_FRAME_SIZE
+ add x0, x0, #PT_REGS_SIZE
str x0, [sp, #S_SP]
/* Stash the regs for handle_bad_stack */
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 38bb07eff872..3605f77ad4df 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -23,8 +23,6 @@
#include <linux/platform_device.h>
#include <linux/sched_clock.h>
#include <linux/smp.h>
-#include <linux/nmi.h>
-#include <linux/cpufreq.h>
/* ARMv8 Cortex-A53 specific event types. */
#define ARMV8_A53_PERFCTR_PREF_LINEFILL 0xC2
@@ -1250,21 +1248,10 @@ static struct platform_driver armv8_pmu_driver = {
static int __init armv8_pmu_driver_init(void)
{
- int ret;
-
if (acpi_disabled)
- ret = platform_driver_register(&armv8_pmu_driver);
+ return platform_driver_register(&armv8_pmu_driver);
else
- ret = arm_pmu_acpi_probe(armv8_pmuv3_init);
-
- /*
- * Try to re-initialize lockup detector after PMU init in
- * case PMU events are triggered via NMIs.
- */
- if (ret == 0 && arm_pmu_irq_is_nmi())
- lockup_detector_init();
-
- return ret;
+ return arm_pmu_acpi_probe(armv8_pmuv3_init);
}
device_initcall(armv8_pmu_driver_init)
@@ -1322,27 +1309,3 @@ void arch_perf_update_userpage(struct perf_event *event,
userpg->cap_user_time_zero = 1;
userpg->cap_user_time_short = 1;
}
-
-#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
-/*
- * Safe maximum CPU frequency in case a particular platform doesn't implement
- * cpufreq driver. Although, architecture doesn't put any restrictions on
- * maximum frequency but 5 GHz seems to be safe maximum given the available
- * Arm CPUs in the market which are clocked much less than 5 GHz. On the other
- * hand, we can't make it much higher as it would lead to a large hard-lockup
- * detection timeout on parts which are running slower (eg. 1GHz on
- * Developerbox) and doesn't possess a cpufreq driver.
- */
-#define SAFE_MAX_CPU_FREQ 5000000000UL // 5 GHz
-u64 hw_nmi_get_sample_period(int watchdog_thresh)
-{
- unsigned int cpu = smp_processor_id();
- unsigned long max_cpu_freq;
-
- max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL;
- if (!max_cpu_freq)
- max_cpu_freq = SAFE_MAX_CPU_FREQ;
-
- return (u64)max_cpu_freq * watchdog_thresh;
-}
-#endif
diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S
index 890ca72c5a51..288a84e253cc 100644
--- a/arch/arm64/kernel/probes/kprobes_trampoline.S
+++ b/arch/arm64/kernel/probes/kprobes_trampoline.S
@@ -25,7 +25,7 @@
stp x24, x25, [sp, #S_X24]
stp x26, x27, [sp, #S_X26]
stp x28, x29, [sp, #S_X28]
- add x0, sp, #S_FRAME_SIZE
+ add x0, sp, #PT_REGS_SIZE
stp lr, x0, [sp, #S_LR]
/*
* Construct a useful saved PSTATE
@@ -62,7 +62,7 @@
.endm
SYM_CODE_START(kretprobe_trampoline)
- sub sp, sp, #S_FRAME_SIZE
+ sub sp, sp, #PT_REGS_SIZE
save_all_base_regs
@@ -76,7 +76,7 @@ SYM_CODE_START(kretprobe_trampoline)
restore_all_base_regs
- add sp, sp, #S_FRAME_SIZE
+ add sp, sp, #PT_REGS_SIZE
ret
SYM_CODE_END(kretprobe_trampoline)
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index f71d6ce4673f..6237486ff6bb 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -914,13 +914,6 @@ static void do_signal(struct pt_regs *regs)
asmlinkage void do_notify_resume(struct pt_regs *regs,
unsigned long thread_flags)
{
- /*
- * The assembly code enters us with IRQs off, but it hasn't
- * informed the tracing code of that for efficiency reasons.
- * Update the trace code with the current status.
- */
- trace_hardirqs_off();
-
do {
if (thread_flags & _TIF_NEED_RESCHED) {
/* Unmask Debug and SError for the next task */
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index f61e9d8cc55a..c2877c332f2d 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -9,6 +9,7 @@
#include <asm/daifflags.h>
#include <asm/debug-monitors.h>
+#include <asm/exception.h>
#include <asm/fpsimd.h>
#include <asm/syscall.h>
#include <asm/thread_info.h>
@@ -165,15 +166,8 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
local_daif_mask();
flags = current_thread_info()->flags;
- if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
- /*
- * We're off to userspace, where interrupts are
- * always enabled after we restore the flags from
- * the SPSR.
- */
- trace_hardirqs_on();
+ if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP))
return;
- }
local_daif_restore(DAIF_PROCCTX);
}
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 7deddf56f7c3..709d98fea90c 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -53,13 +53,13 @@ s64 memstart_addr __ro_after_init = -1;
EXPORT_SYMBOL(memstart_addr);
/*
- * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of
- * memory as some devices, namely the Raspberry Pi 4, have peripherals with
- * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32
- * bit addressable memory area.
+ * If the corresponding config options are enabled, we create both ZONE_DMA
+ * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory
+ * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
+ * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
+ * otherwise it is empty.
*/
phys_addr_t arm64_dma_phys_limit __ro_after_init;
-phys_addr_t arm64_dma32_phys_limit __ro_after_init;
#ifdef CONFIG_KEXEC_CORE
/*
@@ -84,7 +84,7 @@ static void __init reserve_crashkernel(void)
if (crash_base == 0) {
/* Current arm64 boot protocol requires 2MB alignment */
- crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
+ crash_base = memblock_find_in_range(0, arm64_dma_phys_limit,
crash_size, SZ_2M);
if (crash_base == 0) {
pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
@@ -196,6 +196,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
unsigned long max_zone_pfns[MAX_NR_ZONES] = {0};
unsigned int __maybe_unused acpi_zone_dma_bits;
unsigned int __maybe_unused dt_zone_dma_bits;
+ phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32);
#ifdef CONFIG_ZONE_DMA
acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
@@ -205,8 +206,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
#endif
#ifdef CONFIG_ZONE_DMA32
- max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
+ max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
+ if (!arm64_dma_phys_limit)
+ arm64_dma_phys_limit = dma32_phys_limit;
#endif
+ if (!arm64_dma_phys_limit)
+ arm64_dma_phys_limit = PHYS_MASK + 1;
max_zone_pfns[ZONE_NORMAL] = max;
free_area_init(max_zone_pfns);
@@ -394,16 +399,9 @@ void __init arm64_memblock_init(void)
early_init_fdt_scan_reserved_mem();
- if (IS_ENABLED(CONFIG_ZONE_DMA32))
- arm64_dma32_phys_limit = max_zone_phys(32);
- else
- arm64_dma32_phys_limit = PHYS_MASK + 1;
-
reserve_elfcorehdr();
high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
-
- dma_contiguous_reserve(arm64_dma32_phys_limit);
}
void __init bootmem_init(void)
@@ -439,6 +437,11 @@ void __init bootmem_init(void)
zone_sizes_init(min, max);
/*
+ * Reserve the CMA area after arm64_dma_phys_limit was initialised.
+ */
+ dma_contiguous_reserve(arm64_dma_phys_limit);
+
+ /*
* request_standard_resources() depends on crashkernel's memory being
* reserved, so do it here.
*/
@@ -455,7 +458,7 @@ void __init bootmem_init(void)
void __init mem_init(void)
{
if (swiotlb_force == SWIOTLB_FORCE ||
- max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit))
+ max_pfn > PFN_DOWN(arm64_dma_phys_limit))
swiotlb_init(1);
else
swiotlb_force = SWIOTLB_NO_FORCE;
diff --git a/arch/ia64/include/asm/sparsemem.h b/arch/ia64/include/asm/sparsemem.h
index dd8c166ffd7b..42ed5248fae9 100644
--- a/arch/ia64/include/asm/sparsemem.h
+++ b/arch/ia64/include/asm/sparsemem.h
@@ -3,6 +3,7 @@
#define _ASM_IA64_SPARSEMEM_H
#ifdef CONFIG_SPARSEMEM
+#include <asm/page.h>
/*
* SECTION_SIZE_BITS 2^N: how big each section will be
* MAX_PHYSMEM_BITS 2^N: how much memory we can have in that space
diff --git a/arch/mips/boot/compressed/decompress.c b/arch/mips/boot/compressed/decompress.c
index c61c641674e6..e3946b06e840 100644
--- a/arch/mips/boot/compressed/decompress.c
+++ b/arch/mips/boot/compressed/decompress.c
@@ -13,6 +13,7 @@
#include <linux/libfdt.h>
#include <asm/addrspace.h>
+#include <asm/unaligned.h>
/*
* These two variables specify the free mem region
@@ -117,7 +118,7 @@ void decompress_kernel(unsigned long boot_heap_start)
dtb_size = fdt_totalsize((void *)&__appended_dtb);
/* last four bytes is always image size in little endian */
- image_size = le32_to_cpup((void *)&__image_end - 4);
+ image_size = get_unaligned_le32((void *)&__image_end - 4);
/* copy dtb to where the booted kernel will expect it */
memcpy((void *)VMLINUX_LOAD_ADDRESS_ULL + image_size,
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index bd47e15d02c7..be5d4afcd30f 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -1444,7 +1444,7 @@ static void octeon_irq_setup_secondary_ciu2(void)
static int __init octeon_irq_init_ciu(
struct device_node *ciu_node, struct device_node *parent)
{
- unsigned int i, r;
+ int i, r;
struct irq_chip *chip;
struct irq_chip *chip_edge;
struct irq_chip *chip_mbox;
diff --git a/arch/mips/kernel/binfmt_elfn32.c b/arch/mips/kernel/binfmt_elfn32.c
index 6ee3f7218c67..c4441416e96b 100644
--- a/arch/mips/kernel/binfmt_elfn32.c
+++ b/arch/mips/kernel/binfmt_elfn32.c
@@ -103,4 +103,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value)
#undef ns_to_kernel_old_timeval
#define ns_to_kernel_old_timeval ns_to_old_timeval32
+/*
+ * Some data types as stored in coredump.
+ */
+#define user_long_t compat_long_t
+#define user_siginfo_t compat_siginfo_t
+#define copy_siginfo_to_external copy_siginfo_to_external32
+
#include "../../../fs/binfmt_elf.c"
diff --git a/arch/mips/kernel/binfmt_elfo32.c b/arch/mips/kernel/binfmt_elfo32.c
index 6dd103d3cebb..7b2a23f48c1a 100644
--- a/arch/mips/kernel/binfmt_elfo32.c
+++ b/arch/mips/kernel/binfmt_elfo32.c
@@ -106,4 +106,11 @@ jiffies_to_old_timeval32(unsigned long jiffies, struct old_timeval32 *value)
#undef ns_to_kernel_old_timeval
#define ns_to_kernel_old_timeval ns_to_old_timeval32
+/*
+ * Some data types as stored in coredump.
+ */
+#define user_long_t compat_long_t
+#define user_siginfo_t compat_siginfo_t
+#define copy_siginfo_to_external copy_siginfo_to_external32
+
#include "../../../fs/binfmt_elf.c"
diff --git a/arch/mips/kernel/relocate.c b/arch/mips/kernel/relocate.c
index 47aeb3350a76..0e365b7c742d 100644
--- a/arch/mips/kernel/relocate.c
+++ b/arch/mips/kernel/relocate.c
@@ -187,8 +187,14 @@ static int __init relocate_exception_table(long offset)
static inline __init unsigned long rotate_xor(unsigned long hash,
const void *area, size_t size)
{
- size_t i;
- unsigned long *ptr = (unsigned long *)area;
+ const typeof(hash) *ptr = PTR_ALIGN(area, sizeof(hash));
+ size_t diff, i;
+
+ diff = (void *)ptr - area;
+ if (unlikely(size < diff + sizeof(hash)))
+ return hash;
+
+ size = ALIGN_DOWN(size - diff, sizeof(hash));
for (i = 0; i < size / sizeof(hash); i++) {
/* Rotate by odd number of bits and XOR. */
diff --git a/arch/powerpc/include/asm/vdso/gettimeofday.h b/arch/powerpc/include/asm/vdso/gettimeofday.h
index 81671aa365b3..77c635c2c90d 100644
--- a/arch/powerpc/include/asm/vdso/gettimeofday.h
+++ b/arch/powerpc/include/asm/vdso/gettimeofday.h
@@ -103,6 +103,8 @@ int gettimeofday_fallback(struct __kernel_old_timeval *_tv, struct timezone *_tz
return do_syscall_2(__NR_gettimeofday, (unsigned long)_tv, (unsigned long)_tz);
}
+#ifdef __powerpc64__
+
static __always_inline
int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
{
@@ -115,11 +117,23 @@ int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
return do_syscall_2(__NR_clock_getres, _clkid, (unsigned long)_ts);
}
-#ifdef CONFIG_VDSO32
+#else
#define BUILD_VDSO32 1
static __always_inline
+int clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ return do_syscall_2(__NR_clock_gettime64, _clkid, (unsigned long)_ts);
+}
+
+static __always_inline
+int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts)
+{
+ return do_syscall_2(__NR_clock_getres_time64, _clkid, (unsigned long)_ts);
+}
+
+static __always_inline
int clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts)
{
return do_syscall_2(__NR_clock_gettime, _clkid, (unsigned long)_ts);
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 8e0b1298bf19..4ab426b8b0e0 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -187,6 +187,12 @@ SECTIONS
.init.text : AT(ADDR(.init.text) - LOAD_OFFSET) {
_sinittext = .;
INIT_TEXT
+
+ /*
+ *.init.text might be RO so we must ensure this section ends on
+ * a page boundary.
+ */
+ . = ALIGN(PAGE_SIZE);
_einittext = .;
#ifdef CONFIG_PPC64
*(.tramp.ftrace.init);
@@ -200,6 +206,8 @@ SECTIONS
EXIT_TEXT
}
+ . = ALIGN(PAGE_SIZE);
+
INIT_DATA_SECTION(16)
. = ALIGN(8);
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 81b76d44725d..e9e2c1f0a690 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -137,7 +137,7 @@ config PA_BITS
config PAGE_OFFSET
hex
- default 0xC0000000 if 32BIT && MAXPHYSMEM_2GB
+ default 0xC0000000 if 32BIT && MAXPHYSMEM_1GB
default 0x80000000 if 64BIT && !MMU
default 0xffffffff80000000 if 64BIT && MAXPHYSMEM_2GB
default 0xffffffe000000000 if 64BIT && MAXPHYSMEM_128GB
@@ -247,10 +247,12 @@ config MODULE_SECTIONS
choice
prompt "Maximum Physical Memory"
- default MAXPHYSMEM_2GB if 32BIT
+ default MAXPHYSMEM_1GB if 32BIT
default MAXPHYSMEM_2GB if 64BIT && CMODEL_MEDLOW
default MAXPHYSMEM_128GB if 64BIT && CMODEL_MEDANY
+ config MAXPHYSMEM_1GB
+ bool "1GiB"
config MAXPHYSMEM_2GB
bool "2GiB"
config MAXPHYSMEM_128GB
diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
index 4a2729f5ca3f..24d75a146e02 100644
--- a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
+++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts
@@ -88,7 +88,9 @@
phy-mode = "gmii";
phy-handle = <&phy0>;
phy0: ethernet-phy@0 {
+ compatible = "ethernet-phy-id0007.0771";
reg = <0>;
+ reset-gpios = <&gpio 12 GPIO_ACTIVE_LOW>;
};
};
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index d222d353d86d..8c3d1e451703 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -64,6 +64,8 @@ CONFIG_HW_RANDOM=y
CONFIG_HW_RANDOM_VIRTIO=y
CONFIG_SPI=y
CONFIG_SPI_SIFIVE=y
+CONFIG_GPIOLIB=y
+CONFIG_GPIO_SIFIVE=y
# CONFIG_PTP_1588_CLOCK is not set
CONFIG_POWER_RESET=y
CONFIG_DRM=y
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 41a72861987c..251e1db088fa 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -99,7 +99,6 @@
| _PAGE_DIRTY)
#define PAGE_KERNEL __pgprot(_PAGE_KERNEL)
-#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC)
#define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE)
#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC)
#define PAGE_KERNEL_READ_EXEC __pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \
diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h
index 8454f746bbfd..1453a2f563bc 100644
--- a/arch/riscv/include/asm/vdso.h
+++ b/arch/riscv/include/asm/vdso.h
@@ -10,7 +10,7 @@
#include <linux/types.h>
-#ifndef GENERIC_TIME_VSYSCALL
+#ifndef CONFIG_GENERIC_TIME_VSYSCALL
struct vdso_data {
};
#endif
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
index de59dd457b41..d86781357044 100644
--- a/arch/riscv/kernel/cacheinfo.c
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -26,7 +26,16 @@ cache_get_priv_group(struct cacheinfo *this_leaf)
static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type)
{
- struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(smp_processor_id());
+ /*
+ * Using raw_smp_processor_id() elides a preemptability check, but this
+ * is really indicative of a larger problem: the cacheinfo UABI assumes
+ * that cores have a homonogenous view of the cache hierarchy. That
+ * happens to be the case for the current set of RISC-V systems, but
+ * likely won't be true in general. Since there's no way to provide
+ * correct information for these systems via the current UABI we're
+ * just eliding the check for now.
+ */
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id());
struct cacheinfo *this_leaf;
int index;
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 524d918f3601..744f3209c48d 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -124,15 +124,15 @@ skip_context_tracking:
REG_L a1, (a1)
jr a1
1:
-#ifdef CONFIG_TRACE_IRQFLAGS
- call trace_hardirqs_on
-#endif
/*
* Exceptions run with interrupts enabled or disabled depending on the
* state of SR_PIE in m/sstatus.
*/
andi t0, s1, SR_PIE
beqz t0, 1f
+#ifdef CONFIG_TRACE_IRQFLAGS
+ call trace_hardirqs_on
+#endif
csrs CSR_STATUS, SR_IE
1:
@@ -155,6 +155,15 @@ skip_context_tracking:
tail do_trap_unknown
handle_syscall:
+#ifdef CONFIG_RISCV_M_MODE
+ /*
+ * When running is M-Mode (no MMU config), MPIE does not get set.
+ * As a result, we need to force enable interrupts here because
+ * handle_exception did not do set SR_IE as it always sees SR_PIE
+ * being cleared.
+ */
+ csrs CSR_STATUS, SR_IE
+#endif
#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING)
/* Recover a0 - a7 for system calls */
REG_L a0, PT_A0(sp)
@@ -186,14 +195,7 @@ check_syscall_nr:
* Syscall number held in a7.
* If syscall number is above allowed value, redirect to ni_syscall.
*/
- bge a7, t0, 1f
- /*
- * Check if syscall is rejected by tracer, i.e., a7 == -1.
- * If yes, we pretend it was executed.
- */
- li t1, -1
- beq a7, t1, ret_from_syscall_rejected
- blt a7, t1, 1f
+ bgeu a7, t0, 1f
/* Call syscall */
la s0, sys_call_table
slli t0, a7, RISCV_LGPTR
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 1d85e9bf783c..3fa3f26dde85 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -127,7 +127,9 @@ static void __init init_resources(void)
{
struct memblock_region *region = NULL;
struct resource *res = NULL;
- int ret = 0;
+ struct resource *mem_res = NULL;
+ size_t mem_res_sz = 0;
+ int ret = 0, i = 0;
code_res.start = __pa_symbol(_text);
code_res.end = __pa_symbol(_etext) - 1;
@@ -145,16 +147,17 @@ static void __init init_resources(void)
bss_res.end = __pa_symbol(__bss_stop) - 1;
bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+ mem_res_sz = (memblock.memory.cnt + memblock.reserved.cnt) * sizeof(*mem_res);
+ mem_res = memblock_alloc(mem_res_sz, SMP_CACHE_BYTES);
+ if (!mem_res)
+ panic("%s: Failed to allocate %zu bytes\n", __func__, mem_res_sz);
/*
* Start by adding the reserved regions, if they overlap
* with /memory regions, insert_resource later on will take
* care of it.
*/
for_each_reserved_mem_region(region) {
- res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
- if (!res)
- panic("%s: Failed to allocate %zu bytes\n", __func__,
- sizeof(struct resource));
+ res = &mem_res[i++];
res->name = "Reserved";
res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
@@ -171,8 +174,10 @@ static void __init init_resources(void)
* Ignore any other reserved regions within
* system memory.
*/
- if (memblock_is_memory(res->start))
+ if (memblock_is_memory(res->start)) {
+ memblock_free((phys_addr_t) res, sizeof(struct resource));
continue;
+ }
ret = add_resource(&iomem_resource, res);
if (ret < 0)
@@ -181,10 +186,7 @@ static void __init init_resources(void)
/* Add /memory regions to the resource tree */
for_each_mem_region(region) {
- res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES);
- if (!res)
- panic("%s: Failed to allocate %zu bytes\n", __func__,
- sizeof(struct resource));
+ res = &mem_res[i++];
if (unlikely(memblock_is_nomap(region))) {
res->name = "Reserved";
@@ -205,9 +207,9 @@ static void __init init_resources(void)
return;
error:
- memblock_free((phys_addr_t) res, sizeof(struct resource));
/* Better an empty resource tree than an inconsistent one */
release_child_resources(&iomem_resource);
+ memblock_free((phys_addr_t) mem_res, mem_res_sz);
}
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index 48b870a685b3..df5d2da7c40b 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -14,7 +14,7 @@
#include <asm/stacktrace.h>
-register unsigned long sp_in_global __asm__("sp");
+register const unsigned long sp_in_global __asm__("sp");
#ifdef CONFIG_FRAME_POINTER
@@ -28,9 +28,8 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
sp = user_stack_pointer(regs);
pc = instruction_pointer(regs);
} else if (task == NULL || task == current) {
- const register unsigned long current_sp = sp_in_global;
fp = (unsigned long)__builtin_frame_address(0);
- sp = current_sp;
+ sp = sp_in_global;
pc = (unsigned long)walk_stackframe;
} else {
/* task blocked in __switch_to */
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
index 4d3a1048ad8b..8a5cf99c0776 100644
--- a/arch/riscv/kernel/time.c
+++ b/arch/riscv/kernel/time.c
@@ -4,6 +4,7 @@
* Copyright (C) 2017 SiFive
*/
+#include <linux/of_clk.h>
#include <linux/clocksource.h>
#include <linux/delay.h>
#include <asm/sbi.h>
@@ -24,6 +25,8 @@ void __init time_init(void)
riscv_timebase = prop;
lpj_fine = riscv_timebase / HZ;
+
+ of_clk_init(NULL);
timer_probe();
}
diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c
index 678204231700..3f1d35e7c98a 100644
--- a/arch/riscv/kernel/vdso.c
+++ b/arch/riscv/kernel/vdso.c
@@ -12,7 +12,7 @@
#include <linux/binfmts.h>
#include <linux/err.h>
#include <asm/page.h>
-#ifdef GENERIC_TIME_VSYSCALL
+#ifdef CONFIG_GENERIC_TIME_VSYSCALL
#include <vdso/datapage.h>
#else
#include <asm/vdso.h>
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index bf5379135e39..7cd4993f4ff2 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -157,9 +157,10 @@ disable:
void __init setup_bootmem(void)
{
phys_addr_t mem_start = 0;
- phys_addr_t start, end = 0;
+ phys_addr_t start, dram_end, end = 0;
phys_addr_t vmlinux_end = __pa_symbol(&_end);
phys_addr_t vmlinux_start = __pa_symbol(&_start);
+ phys_addr_t max_mapped_addr = __pa(~(ulong)0);
u64 i;
/* Find the memory region containing the kernel */
@@ -181,7 +182,18 @@ void __init setup_bootmem(void)
/* Reserve from the start of the kernel to the end of the kernel */
memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
- max_pfn = PFN_DOWN(memblock_end_of_DRAM());
+ dram_end = memblock_end_of_DRAM();
+
+ /*
+ * memblock allocator is not aware of the fact that last 4K bytes of
+ * the addressable memory can not be mapped because of IS_ERR_VALUE
+ * macro. Make sure that last 4k bytes are not usable by memblock
+ * if end of dram is equal to maximum addressable memory.
+ */
+ if (max_mapped_addr == (dram_end - 1))
+ memblock_set_current_limit(max_mapped_addr - 4096);
+
+ max_pfn = PFN_DOWN(dram_end);
max_low_pfn = max_pfn;
dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn));
set_max_mapnr(max_low_pfn);
diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c
index 12ddd1f6bf70..a8a2ffd9114a 100644
--- a/arch/riscv/mm/kasan_init.c
+++ b/arch/riscv/mm/kasan_init.c
@@ -93,8 +93,8 @@ void __init kasan_init(void)
VMALLOC_END));
for_each_mem_range(i, &_start, &_end) {
- void *start = (void *)_start;
- void *end = (void *)_end;
+ void *start = (void *)__va(_start);
+ void *end = (void *)__va(_end);
if (start >= end)
break;
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 4638a52d8eae..6375967a8244 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -315,6 +315,25 @@ static struct syscore_ops hv_syscore_ops = {
.resume = hv_resume,
};
+static void (* __initdata old_setup_percpu_clockev)(void);
+
+static void __init hv_stimer_setup_percpu_clockev(void)
+{
+ /*
+ * Ignore any errors in setting up stimer clockevents
+ * as we can run with the LAPIC timer as a fallback.
+ */
+ (void)hv_stimer_alloc();
+
+ /*
+ * Still register the LAPIC timer, because the direct-mode STIMER is
+ * not supported by old versions of Hyper-V. This also allows users
+ * to switch to LAPIC timer via /sys, if they want to.
+ */
+ if (old_setup_percpu_clockev)
+ old_setup_percpu_clockev();
+}
+
/*
* This function is to be invoked early in the boot sequence after the
* hypervisor has been detected.
@@ -393,10 +412,14 @@ void __init hyperv_init(void)
wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
/*
- * Ignore any errors in setting up stimer clockevents
- * as we can run with the LAPIC timer as a fallback.
+ * hyperv_init() is called before LAPIC is initialized: see
+ * apic_intr_mode_init() -> x86_platform.apic_post_init() and
+ * apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER
+ * depends on LAPIC, so hv_stimer_alloc() should be called from
+ * x86_init.timers.setup_percpu_clockev.
*/
- (void)hv_stimer_alloc();
+ old_setup_percpu_clockev = x86_init.timers.setup_percpu_clockev;
+ x86_init.timers.setup_percpu_clockev = hv_stimer_setup_percpu_clockev;
hv_apic_init();
diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c
index 9e87ab010c82..e68ea5f4ad1c 100644
--- a/arch/x86/xen/enlighten_hvm.c
+++ b/arch/x86/xen/enlighten_hvm.c
@@ -164,10 +164,10 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu)
else
per_cpu(xen_vcpu_id, cpu) = cpu;
rc = xen_vcpu_setup(cpu);
- if (rc)
+ if (rc || !xen_have_vector_callback)
return rc;
- if (xen_have_vector_callback && xen_feature(XENFEAT_hvm_safe_pvclock))
+ if (xen_feature(XENFEAT_hvm_safe_pvclock))
xen_setup_timer(cpu);
rc = xen_smp_intr_init(cpu);
@@ -188,6 +188,8 @@ static int xen_cpu_dead_hvm(unsigned int cpu)
return 0;
}
+static bool no_vector_callback __initdata;
+
static void __init xen_hvm_guest_init(void)
{
if (xen_pv_domain())
@@ -207,7 +209,7 @@ static void __init xen_hvm_guest_init(void)
xen_panic_handler_init();
- if (xen_feature(XENFEAT_hvm_callback_vector))
+ if (!no_vector_callback && xen_feature(XENFEAT_hvm_callback_vector))
xen_have_vector_callback = 1;
xen_hvm_smp_init();
@@ -233,6 +235,13 @@ static __init int xen_parse_nopv(char *arg)
}
early_param("xen_nopv", xen_parse_nopv);
+static __init int xen_parse_no_vector_callback(char *arg)
+{
+ no_vector_callback = true;
+ return 0;
+}
+early_param("xen_no_vector_callback", xen_parse_no_vector_callback);
+
bool __init xen_hvm_need_lapic(void)
{
if (xen_pv_domain())
diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c
index f5e7db4f82ab..6ff3c887e0b9 100644
--- a/arch/x86/xen/smp_hvm.c
+++ b/arch/x86/xen/smp_hvm.c
@@ -33,9 +33,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
int cpu;
native_smp_prepare_cpus(max_cpus);
- WARN_ON(xen_smp_intr_init(0));
- xen_init_lock_cpu(0);
+ if (xen_have_vector_callback) {
+ WARN_ON(xen_smp_intr_init(0));
+ xen_init_lock_cpu(0);
+ }
for_each_possible_cpu(cpu) {
if (cpu == 0)
@@ -50,9 +52,11 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
static void xen_hvm_cpu_die(unsigned int cpu)
{
if (common_cpu_die(cpu) == 0) {
- xen_smp_intr_free(cpu);
- xen_uninit_lock_cpu(cpu);
- xen_teardown_timer(cpu);
+ if (xen_have_vector_callback) {
+ xen_smp_intr_free(cpu);
+ xen_uninit_lock_cpu(cpu);
+ xen_teardown_timer(cpu);
+ }
}
}
#else
@@ -64,14 +68,19 @@ static void xen_hvm_cpu_die(unsigned int cpu)
void __init xen_hvm_smp_init(void)
{
- if (!xen_have_vector_callback)
+ smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
+ smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
+ smp_ops.smp_cpus_done = xen_smp_cpus_done;
+ smp_ops.cpu_die = xen_hvm_cpu_die;
+
+ if (!xen_have_vector_callback) {
+#ifdef CONFIG_PARAVIRT_SPINLOCKS
+ nopvspin = true;
+#endif
return;
+ }
- smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus;
smp_ops.smp_send_reschedule = xen_smp_send_reschedule;
- smp_ops.cpu_die = xen_hvm_cpu_die;
smp_ops.send_call_func_ipi = xen_smp_send_call_function_ipi;
smp_ops.send_call_func_single_ipi = xen_smp_send_call_function_single_ipi;
- smp_ops.smp_prepare_boot_cpu = xen_hvm_smp_prepare_boot_cpu;
- smp_ops.smp_cpus_done = xen_smp_cpus_done;
}
diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c
index 8892908ad58c..788a4ba1e2e7 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -356,7 +356,8 @@ int public_key_verify_signature(const struct public_key *pkey,
if (ret)
goto error_free_key;
- if (strcmp(sig->pkey_algo, "sm2") == 0 && sig->data_size) {
+ if (sig->pkey_algo && strcmp(sig->pkey_algo, "sm2") == 0 &&
+ sig->data_size) {
ret = cert_sig_digest_update(sig, tfm);
if (ret)
goto error_free_key;
diff --git a/crypto/xor.c b/crypto/xor.c
index eacbf4f93990..8f899f898ec9 100644
--- a/crypto/xor.c
+++ b/crypto/xor.c
@@ -107,6 +107,8 @@ do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2)
preempt_enable();
// bytes/ns == GB/s, multiply by 1000 to get MB/s [not MiB/s]
+ if (!min)
+ min = 1;
speed = (1000 * REPS * BENCH_SIZE) / (unsigned int)ktime_to_ns(min);
tmpl->speed = speed;
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index cb229e24c563..e6a5d997241c 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -97,7 +97,7 @@ void acpi_scan_table_handler(u32 event, void *table, void *context);
extern struct list_head acpi_bus_id_list;
struct acpi_device_bus_id {
- char bus_id[15];
+ const char *bus_id;
unsigned int instance_no;
struct list_head node;
};
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 80b668c80073..58ff36340cd7 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -486,6 +486,7 @@ static void acpi_device_del(struct acpi_device *device)
acpi_device_bus_id->instance_no--;
else {
list_del(&acpi_device_bus_id->node);
+ kfree_const(acpi_device_bus_id->bus_id);
kfree(acpi_device_bus_id);
}
break;
@@ -674,7 +675,14 @@ int acpi_device_add(struct acpi_device *device,
}
if (!found) {
acpi_device_bus_id = new_bus_id;
- strcpy(acpi_device_bus_id->bus_id, acpi_device_hid(device));
+ acpi_device_bus_id->bus_id =
+ kstrdup_const(acpi_device_hid(device), GFP_KERNEL);
+ if (!acpi_device_bus_id->bus_id) {
+ pr_err(PREFIX "Memory allocation error for bus id\n");
+ result = -ENOMEM;
+ goto err_free_new_bus_id;
+ }
+
acpi_device_bus_id->instance_no = 0;
list_add_tail(&acpi_device_bus_id->node, &acpi_bus_id_list);
}
@@ -709,6 +717,11 @@ int acpi_device_add(struct acpi_device *device,
if (device->parent)
list_del(&device->node);
list_del(&device->wakeup_list);
+
+ err_free_new_bus_id:
+ if (!found)
+ kfree(new_bus_id);
+
mutex_unlock(&acpi_device_lock);
err_detach:
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index bbd51703e738..e535f28a8028 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -366,6 +366,7 @@ if CRYPTO_DEV_OMAP
config CRYPTO_DEV_OMAP_SHAM
tristate "Support for OMAP MD5/SHA1/SHA2 hw accelerator"
depends on ARCH_OMAP2PLUS
+ select CRYPTO_ENGINE
select CRYPTO_SHA1
select CRYPTO_MD5
select CRYPTO_SHA256
diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
index 3c4e34301172..364fc2f3e499 100644
--- a/drivers/dma-buf/heaps/cma_heap.c
+++ b/drivers/dma-buf/heaps/cma_heap.c
@@ -251,6 +251,9 @@ static void cma_heap_dma_buf_release(struct dma_buf *dmabuf)
buffer->vaddr = NULL;
}
+ /* free page list */
+ kfree(buffer->pages);
+ /* release memory */
cma_release(cma_heap->cma, buffer->cma_pages, buffer->pagecount);
kfree(buffer);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
index 306077884a67..6107ac91db25 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c
@@ -112,6 +112,7 @@ int amdgpu_atomfirmware_allocate_fb_scratch(struct amdgpu_device *adev)
union igp_info {
struct atom_integrated_system_info_v1_11 v11;
struct atom_integrated_system_info_v1_12 v12;
+ struct atom_integrated_system_info_v2_1 v21;
};
union umc_info {
@@ -209,24 +210,42 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
if (adev->flags & AMD_IS_APU) {
igp_info = (union igp_info *)
(mode_info->atom_context->bios + data_offset);
- switch (crev) {
- case 11:
- mem_channel_number = igp_info->v11.umachannelnumber;
- /* channel width is 64 */
- if (vram_width)
- *vram_width = mem_channel_number * 64;
- mem_type = igp_info->v11.memorytype;
- if (vram_type)
- *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+ switch (frev) {
+ case 1:
+ switch (crev) {
+ case 11:
+ case 12:
+ mem_channel_number = igp_info->v11.umachannelnumber;
+ if (!mem_channel_number)
+ mem_channel_number = 1;
+ /* channel width is 64 */
+ if (vram_width)
+ *vram_width = mem_channel_number * 64;
+ mem_type = igp_info->v11.memorytype;
+ if (vram_type)
+ *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+ break;
+ default:
+ return -EINVAL;
+ }
break;
- case 12:
- mem_channel_number = igp_info->v12.umachannelnumber;
- /* channel width is 64 */
- if (vram_width)
- *vram_width = mem_channel_number * 64;
- mem_type = igp_info->v12.memorytype;
- if (vram_type)
- *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+ case 2:
+ switch (crev) {
+ case 1:
+ case 2:
+ mem_channel_number = igp_info->v21.umachannelnumber;
+ if (!mem_channel_number)
+ mem_channel_number = 1;
+ /* channel width is 64 */
+ if (vram_width)
+ *vram_width = mem_channel_number * 64;
+ mem_type = igp_info->v21.memorytype;
+ if (vram_type)
+ *vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
+ break;
+ default:
+ return -EINVAL;
+ }
break;
default:
return -EINVAL;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b69c34074d8d..087afab67e22 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3034,7 +3034,7 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
#endif
default:
if (amdgpu_dc > 0)
- DRM_INFO("Display Core has been requested via kernel parameter "
+ DRM_INFO_ONCE("Display Core has been requested via kernel parameter "
"but isn't supported by ASIC, ignoring\n");
return false;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 72efd579ec5e..7169fb5e3d9c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1085,6 +1085,8 @@ static const struct pci_device_id pciidlist[] = {
/* Renoir */
{0x1002, 0x1636, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
+ {0x1002, 0x1638, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
+ {0x1002, 0x164C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RENOIR|AMD_IS_APU},
/* Navi12 */
{0x1002, 0x7360, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_NAVI12},
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index ba1086784525..619d34c041ee 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -99,6 +99,10 @@
#define mmGCR_GENERAL_CNTL_Sienna_Cichlid 0x1580
#define mmGCR_GENERAL_CNTL_Sienna_Cichlid_BASE_IDX 0
+#define mmGOLDEN_TSC_COUNT_UPPER_Vangogh 0x0025
+#define mmGOLDEN_TSC_COUNT_UPPER_Vangogh_BASE_IDX 1
+#define mmGOLDEN_TSC_COUNT_LOWER_Vangogh 0x0026
+#define mmGOLDEN_TSC_COUNT_LOWER_Vangogh_BASE_IDX 1
#define mmSPI_CONFIG_CNTL_1_Vangogh 0x2441
#define mmSPI_CONFIG_CNTL_1_Vangogh_BASE_IDX 1
#define mmVGT_TF_MEMORY_BASE_HI_Vangogh 0x2261
@@ -160,6 +164,9 @@
#define mmGCVM_L2_CGTT_CLK_CTRL_Sienna_Cichlid 0x15db
#define mmGCVM_L2_CGTT_CLK_CTRL_Sienna_Cichlid_BASE_IDX 0
+#define mmGC_THROTTLE_CTRL_Sienna_Cichlid 0x2030
+#define mmGC_THROTTLE_CTRL_Sienna_Cichlid_BASE_IDX 0
+
MODULE_FIRMWARE("amdgpu/navi10_ce.bin");
MODULE_FIRMWARE("amdgpu/navi10_pfp.bin");
MODULE_FIRMWARE("amdgpu/navi10_me.bin");
@@ -3324,6 +3331,7 @@ static void gfx_v10_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume);
static void gfx_v10_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, bool start, bool secure);
static u32 gfx_v10_3_get_disabled_sa(struct amdgpu_device *adev);
static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev);
+static void gfx_v10_3_set_power_brake_sequence(struct amdgpu_device *adev);
static void gfx10_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue_mask)
{
@@ -7192,6 +7200,9 @@ static int gfx_v10_0_hw_init(void *handle)
if (adev->asic_type == CHIP_SIENNA_CICHLID)
gfx_v10_3_program_pbb_mode(adev);
+ if (adev->asic_type >= CHIP_SIENNA_CICHLID)
+ gfx_v10_3_set_power_brake_sequence(adev);
+
return r;
}
@@ -7377,8 +7388,16 @@ static uint64_t gfx_v10_0_get_gpu_clock_counter(struct amdgpu_device *adev)
amdgpu_gfx_off_ctrl(adev, false);
mutex_lock(&adev->gfx.gpu_clock_mutex);
- clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER) |
- ((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER) << 32ULL);
+ switch (adev->asic_type) {
+ case CHIP_VANGOGH:
+ clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER_Vangogh) |
+ ((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER_Vangogh) << 32ULL);
+ break;
+ default:
+ clock = (uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_LOWER) |
+ ((uint64_t)RREG32_SOC15(SMUIO, 0, mmGOLDEN_TSC_COUNT_UPPER) << 32ULL);
+ break;
+ }
mutex_unlock(&adev->gfx.gpu_clock_mutex);
amdgpu_gfx_off_ctrl(adev, true);
return clock;
@@ -9169,6 +9188,31 @@ static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev)
}
}
+static void gfx_v10_3_set_power_brake_sequence(struct amdgpu_device *adev)
+{
+ WREG32_SOC15(GC, 0, mmGRBM_GFX_INDEX,
+ (0x1 << GRBM_GFX_INDEX__SA_BROADCAST_WRITES__SHIFT) |
+ (0x1 << GRBM_GFX_INDEX__INSTANCE_BROADCAST_WRITES__SHIFT) |
+ (0x1 << GRBM_GFX_INDEX__SE_BROADCAST_WRITES__SHIFT));
+
+ WREG32_SOC15(GC, 0, mmGC_CAC_IND_INDEX, ixPWRBRK_STALL_PATTERN_CTRL);
+ WREG32_SOC15(GC, 0, mmGC_CAC_IND_DATA,
+ (0x1 << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_STEP_INTERVAL__SHIFT) |
+ (0x12 << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_BEGIN_STEP__SHIFT) |
+ (0x13 << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_END_STEP__SHIFT) |
+ (0xf << PWRBRK_STALL_PATTERN_CTRL__PWRBRK_THROTTLE_PATTERN_BIT_NUMS__SHIFT));
+
+ WREG32_SOC15(GC, 0, mmGC_THROTTLE_CTRL_Sienna_Cichlid,
+ (0x1 << GC_THROTTLE_CTRL__PWRBRK_STALL_EN__SHIFT) |
+ (0x1 << GC_THROTTLE_CTRL__PATTERN_MODE__SHIFT) |
+ (0x5 << GC_THROTTLE_CTRL__RELEASE_STEP_INTERVAL__SHIFT));
+
+ WREG32_SOC15(GC, 0, mmDIDT_IND_INDEX, ixDIDT_SQ_THROTTLE_CTRL);
+
+ WREG32_SOC15(GC, 0, mmDIDT_IND_DATA,
+ (0x1 << DIDT_SQ_THROTTLE_CTRL__PWRBRK_STALL_EN__SHIFT));
+}
+
const struct amdgpu_ip_block_version gfx_v10_0_ip_block =
{
.type = AMD_IP_BLOCK_TYPE_GFX,
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
index d65a5339d354..3ba7bdfde65d 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
@@ -47,7 +47,7 @@ enum psp_gfx_crtl_cmd_id
GFX_CTRL_CMD_ID_DISABLE_INT = 0x00060000, /* disable PSP-to-Gfx interrupt */
GFX_CTRL_CMD_ID_MODE1_RST = 0x00070000, /* trigger the Mode 1 reset */
GFX_CTRL_CMD_ID_GBR_IH_SET = 0x00080000, /* set Gbr IH_RB_CNTL registers */
- GFX_CTRL_CMD_ID_CONSUME_CMD = 0x000A0000, /* send interrupt to psp for updating write pointer of vf */
+ GFX_CTRL_CMD_ID_CONSUME_CMD = 0x00090000, /* send interrupt to psp for updating write pointer of vf */
GFX_CTRL_CMD_ID_DESTROY_GPCOM_RING = 0x000C0000, /* destroy GPCOM ring */
GFX_CTRL_CMD_ID_MAX = 0x000F0000, /* max command ID */
diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c
index 8a23636ecc27..0b3516c4eefb 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.c
@@ -1239,7 +1239,8 @@ static int soc15_common_early_init(void *handle)
break;
case CHIP_RENOIR:
adev->asic_funcs = &soc15_asic_funcs;
- if (adev->pdev->device == 0x1636)
+ if ((adev->pdev->device == 0x1636) ||
+ (adev->pdev->device == 0x164c))
adev->apu_flags |= AMD_APU_IS_RENOIR;
else
adev->apu_flags |= AMD_APU_IS_GREEN_SARDINE;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 8cac497c2c45..a5640a6138cf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -1040,11 +1040,14 @@ static int kfd_create_vcrat_image_cpu(void *pcrat_image, size_t *size)
(struct crat_subtype_iolink *)sub_type_hdr);
if (ret < 0)
return ret;
- crat_table->length += (sub_type_hdr->length * entries);
- crat_table->total_entries += entries;
- sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
- sub_type_hdr->length * entries);
+ if (entries) {
+ crat_table->length += (sub_type_hdr->length * entries);
+ crat_table->total_entries += entries;
+
+ sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
+ sub_type_hdr->length * entries);
+ }
#else
pr_info("IO link not available for non x86 platforms\n");
#endif
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 146486071d01..c6da89df055d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -939,41 +939,6 @@ static void mmhub_read_system_context(struct amdgpu_device *adev, struct dc_phy_
}
#endif
-#ifdef CONFIG_DEBUG_FS
-static int create_crtc_crc_properties(struct amdgpu_display_manager *dm)
-{
- dm->crc_win_x_start_property =
- drm_property_create_range(adev_to_drm(dm->adev),
- DRM_MODE_PROP_ATOMIC,
- "AMD_CRC_WIN_X_START", 0, U16_MAX);
- if (!dm->crc_win_x_start_property)
- return -ENOMEM;
-
- dm->crc_win_y_start_property =
- drm_property_create_range(adev_to_drm(dm->adev),
- DRM_MODE_PROP_ATOMIC,
- "AMD_CRC_WIN_Y_START", 0, U16_MAX);
- if (!dm->crc_win_y_start_property)
- return -ENOMEM;
-
- dm->crc_win_x_end_property =
- drm_property_create_range(adev_to_drm(dm->adev),
- DRM_MODE_PROP_ATOMIC,
- "AMD_CRC_WIN_X_END", 0, U16_MAX);
- if (!dm->crc_win_x_end_property)
- return -ENOMEM;
-
- dm->crc_win_y_end_property =
- drm_property_create_range(adev_to_drm(dm->adev),
- DRM_MODE_PROP_ATOMIC,
- "AMD_CRC_WIN_Y_END", 0, U16_MAX);
- if (!dm->crc_win_y_end_property)
- return -ENOMEM;
-
- return 0;
-}
-#endif
-
static int amdgpu_dm_init(struct amdgpu_device *adev)
{
struct dc_init_data init_data;
@@ -1121,10 +1086,6 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
dc_init_callbacks(adev->dm.dc, &init_params);
}
#endif
-#ifdef CONFIG_DEBUG_FS
- if (create_crtc_crc_properties(&adev->dm))
- DRM_ERROR("amdgpu: failed to create crc property.\n");
-#endif
if (amdgpu_dm_initialize_drm_device(adev)) {
DRM_ERROR(
"amdgpu: failed to initialize sw for display support.\n");
@@ -5333,64 +5294,12 @@ dm_crtc_duplicate_state(struct drm_crtc *crtc)
state->crc_src = cur->crc_src;
state->cm_has_degamma = cur->cm_has_degamma;
state->cm_is_degamma_srgb = cur->cm_is_degamma_srgb;
-#ifdef CONFIG_DEBUG_FS
- state->crc_window = cur->crc_window;
-#endif
+
/* TODO Duplicate dc_stream after objects are stream object is flattened */
return &state->base;
}
-#ifdef CONFIG_DEBUG_FS
-static int amdgpu_dm_crtc_atomic_set_property(struct drm_crtc *crtc,
- struct drm_crtc_state *crtc_state,
- struct drm_property *property,
- uint64_t val)
-{
- struct drm_device *dev = crtc->dev;
- struct amdgpu_device *adev = drm_to_adev(dev);
- struct dm_crtc_state *dm_new_state =
- to_dm_crtc_state(crtc_state);
-
- if (property == adev->dm.crc_win_x_start_property)
- dm_new_state->crc_window.x_start = val;
- else if (property == adev->dm.crc_win_y_start_property)
- dm_new_state->crc_window.y_start = val;
- else if (property == adev->dm.crc_win_x_end_property)
- dm_new_state->crc_window.x_end = val;
- else if (property == adev->dm.crc_win_y_end_property)
- dm_new_state->crc_window.y_end = val;
- else
- return -EINVAL;
-
- return 0;
-}
-
-static int amdgpu_dm_crtc_atomic_get_property(struct drm_crtc *crtc,
- const struct drm_crtc_state *state,
- struct drm_property *property,
- uint64_t *val)
-{
- struct drm_device *dev = crtc->dev;
- struct amdgpu_device *adev = drm_to_adev(dev);
- struct dm_crtc_state *dm_state =
- to_dm_crtc_state(state);
-
- if (property == adev->dm.crc_win_x_start_property)
- *val = dm_state->crc_window.x_start;
- else if (property == adev->dm.crc_win_y_start_property)
- *val = dm_state->crc_window.y_start;
- else if (property == adev->dm.crc_win_x_end_property)
- *val = dm_state->crc_window.x_end;
- else if (property == adev->dm.crc_win_y_end_property)
- *val = dm_state->crc_window.y_end;
- else
- return -EINVAL;
-
- return 0;
-}
-#endif
-
static inline int dm_set_vupdate_irq(struct drm_crtc *crtc, bool enable)
{
enum dc_irq_source irq_source;
@@ -5457,10 +5366,6 @@ static const struct drm_crtc_funcs amdgpu_dm_crtc_funcs = {
.enable_vblank = dm_enable_vblank,
.disable_vblank = dm_disable_vblank,
.get_vblank_timestamp = drm_crtc_vblank_helper_get_vblank_timestamp,
-#ifdef CONFIG_DEBUG_FS
- .atomic_set_property = amdgpu_dm_crtc_atomic_set_property,
- .atomic_get_property = amdgpu_dm_crtc_atomic_get_property,
-#endif
};
static enum drm_connector_status
@@ -6662,25 +6567,6 @@ static int amdgpu_dm_plane_init(struct amdgpu_display_manager *dm,
return 0;
}
-#ifdef CONFIG_DEBUG_FS
-static void attach_crtc_crc_properties(struct amdgpu_display_manager *dm,
- struct amdgpu_crtc *acrtc)
-{
- drm_object_attach_property(&acrtc->base.base,
- dm->crc_win_x_start_property,
- 0);
- drm_object_attach_property(&acrtc->base.base,
- dm->crc_win_y_start_property,
- 0);
- drm_object_attach_property(&acrtc->base.base,
- dm->crc_win_x_end_property,
- 0);
- drm_object_attach_property(&acrtc->base.base,
- dm->crc_win_y_end_property,
- 0);
-}
-#endif
-
static int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
struct drm_plane *plane,
uint32_t crtc_index)
@@ -6728,9 +6614,7 @@ static int amdgpu_dm_crtc_init(struct amdgpu_display_manager *dm,
drm_crtc_enable_color_mgmt(&acrtc->base, MAX_COLOR_LUT_ENTRIES,
true, MAX_COLOR_LUT_ENTRIES);
drm_mode_crtc_set_gamma_size(&acrtc->base, MAX_COLOR_LEGACY_LUT_ENTRIES);
-#ifdef CONFIG_DEBUG_FS
- attach_crtc_crc_properties(dm, acrtc);
-#endif
+
return 0;
fail:
@@ -8367,7 +8251,6 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
*/
for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) {
struct amdgpu_crtc *acrtc = to_amdgpu_crtc(crtc);
- bool configure_crc = false;
dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
@@ -8377,27 +8260,20 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
dc_stream_retain(dm_new_crtc_state->stream);
acrtc->dm_irq_params.stream = dm_new_crtc_state->stream;
manage_dm_interrupts(adev, acrtc, true);
- }
- if (IS_ENABLED(CONFIG_DEBUG_FS) && new_crtc_state->active &&
- amdgpu_dm_is_valid_crc_source(dm_new_crtc_state->crc_src)) {
+
+#ifdef CONFIG_DEBUG_FS
/**
* Frontend may have changed so reapply the CRC capture
* settings for the stream.
*/
dm_new_crtc_state = to_dm_crtc_state(new_crtc_state);
- dm_old_crtc_state = to_dm_crtc_state(old_crtc_state);
- if (amdgpu_dm_crc_window_is_default(dm_new_crtc_state)) {
- if (!old_crtc_state->active || drm_atomic_crtc_needs_modeset(new_crtc_state))
- configure_crc = true;
- } else {
- if (amdgpu_dm_crc_window_changed(dm_new_crtc_state, dm_old_crtc_state))
- configure_crc = true;
- }
-
- if (configure_crc)
+ if (amdgpu_dm_is_valid_crc_source(dm_new_crtc_state->crc_src)) {
amdgpu_dm_crtc_configure_crc_source(
- crtc, dm_new_crtc_state, dm_new_crtc_state->crc_src);
+ crtc, dm_new_crtc_state,
+ dm_new_crtc_state->crc_src);
+ }
+#endif
}
}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index 2ee6edb3df93..1182dafcef02 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -336,32 +336,6 @@ struct amdgpu_display_manager {
*/
const struct gpu_info_soc_bounding_box_v1_0 *soc_bounding_box;
-#ifdef CONFIG_DEBUG_FS
- /**
- * @crc_win_x_start_property:
- *
- * X start of the crc calculation window
- */
- struct drm_property *crc_win_x_start_property;
- /**
- * @crc_win_y_start_property:
- *
- * Y start of the crc calculation window
- */
- struct drm_property *crc_win_y_start_property;
- /**
- * @crc_win_x_end_property:
- *
- * X end of the crc calculation window
- */
- struct drm_property *crc_win_x_end_property;
- /**
- * @crc_win_y_end_property:
- *
- * Y end of the crc calculation window
- */
- struct drm_property *crc_win_y_end_property;
-#endif
/**
* @mst_encoders:
*
@@ -448,15 +422,6 @@ struct dm_plane_state {
struct dc_plane_state *dc_state;
};
-#ifdef CONFIG_DEBUG_FS
-struct crc_rec {
- uint16_t x_start;
- uint16_t y_start;
- uint16_t x_end;
- uint16_t y_end;
- };
-#endif
-
struct dm_crtc_state {
struct drm_crtc_state base;
struct dc_stream_state *stream;
@@ -479,9 +444,6 @@ struct dm_crtc_state {
struct dc_info_packet vrr_infopacket;
int abm_level;
-#ifdef CONFIG_DEBUG_FS
- struct crc_rec crc_window;
-#endif
};
#define to_dm_crtc_state(x) container_of(x, struct dm_crtc_state, base)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
index 7b886a779a8c..66cb8730586b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.c
@@ -81,41 +81,6 @@ const char *const *amdgpu_dm_crtc_get_crc_sources(struct drm_crtc *crtc,
return pipe_crc_sources;
}
-static void amdgpu_dm_set_crc_window_default(struct dm_crtc_state *dm_crtc_state)
-{
- dm_crtc_state->crc_window.x_start = 0;
- dm_crtc_state->crc_window.y_start = 0;
- dm_crtc_state->crc_window.x_end = 0;
- dm_crtc_state->crc_window.y_end = 0;
-}
-
-bool amdgpu_dm_crc_window_is_default(struct dm_crtc_state *dm_crtc_state)
-{
- bool ret = true;
-
- if ((dm_crtc_state->crc_window.x_start != 0) ||
- (dm_crtc_state->crc_window.y_start != 0) ||
- (dm_crtc_state->crc_window.x_end != 0) ||
- (dm_crtc_state->crc_window.y_end != 0))
- ret = false;
-
- return ret;
-}
-
-bool amdgpu_dm_crc_window_changed(struct dm_crtc_state *dm_new_crtc_state,
- struct dm_crtc_state *dm_old_crtc_state)
-{
- bool ret = false;
-
- if ((dm_new_crtc_state->crc_window.x_start != dm_old_crtc_state->crc_window.x_start) ||
- (dm_new_crtc_state->crc_window.y_start != dm_old_crtc_state->crc_window.y_start) ||
- (dm_new_crtc_state->crc_window.x_end != dm_old_crtc_state->crc_window.x_end) ||
- (dm_new_crtc_state->crc_window.y_end != dm_old_crtc_state->crc_window.y_end))
- ret = true;
-
- return ret;
-}
-
int
amdgpu_dm_crtc_verify_crc_source(struct drm_crtc *crtc, const char *src_name,
size_t *values_cnt)
@@ -140,7 +105,6 @@ int amdgpu_dm_crtc_configure_crc_source(struct drm_crtc *crtc,
struct dc_stream_state *stream_state = dm_crtc_state->stream;
bool enable = amdgpu_dm_is_valid_crc_source(source);
int ret = 0;
- struct crc_params *crc_window = NULL, tmp_window;
/* Configuration will be deferred to stream enable. */
if (!stream_state)
@@ -150,24 +114,8 @@ int amdgpu_dm_crtc_configure_crc_source(struct drm_crtc *crtc,
/* Enable CRTC CRC generation if necessary. */
if (dm_is_crc_source_crtc(source) || source == AMDGPU_DM_PIPE_CRC_SOURCE_NONE) {
- if (!enable)
- amdgpu_dm_set_crc_window_default(dm_crtc_state);
-
- if (!amdgpu_dm_crc_window_is_default(dm_crtc_state)) {
- crc_window = &tmp_window;
-
- tmp_window.windowa_x_start = dm_crtc_state->crc_window.x_start;
- tmp_window.windowa_y_start = dm_crtc_state->crc_window.y_start;
- tmp_window.windowa_x_end = dm_crtc_state->crc_window.x_end;
- tmp_window.windowa_y_end = dm_crtc_state->crc_window.y_end;
- tmp_window.windowb_x_start = dm_crtc_state->crc_window.x_start;
- tmp_window.windowb_y_start = dm_crtc_state->crc_window.y_start;
- tmp_window.windowb_x_end = dm_crtc_state->crc_window.x_end;
- tmp_window.windowb_y_end = dm_crtc_state->crc_window.y_end;
- }
-
if (!dc_stream_configure_crc(stream_state->ctx->dc,
- stream_state, crc_window, enable, enable)) {
+ stream_state, NULL, enable, enable)) {
ret = -EINVAL;
goto unlock;
}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h
index eba2f1d35d07..f7d731797d3f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_crc.h
@@ -46,13 +46,10 @@ static inline bool amdgpu_dm_is_valid_crc_source(enum amdgpu_dm_pipe_crc_source
}
/* amdgpu_dm_crc.c */
-bool amdgpu_dm_crc_window_is_default(struct dm_crtc_state *dm_crtc_state);
-bool amdgpu_dm_crc_window_changed(struct dm_crtc_state *dm_new_crtc_state,
- struct dm_crtc_state *dm_old_crtc_state);
+#ifdef CONFIG_DEBUG_FS
int amdgpu_dm_crtc_configure_crc_source(struct drm_crtc *crtc,
struct dm_crtc_state *dm_crtc_state,
enum amdgpu_dm_pipe_crc_source source);
-#ifdef CONFIG_DEBUG_FS
int amdgpu_dm_crtc_set_crc_source(struct drm_crtc *crtc, const char *src_name);
int amdgpu_dm_crtc_verify_crc_source(struct drm_crtc *crtc,
const char *src_name,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 2fc12239b22c..1bd1a0935290 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -3992,7 +3992,7 @@ bool dc_link_dp_set_test_pattern(
unsigned int cust_pattern_size)
{
struct pipe_ctx *pipes = link->dc->current_state->res_ctx.pipe_ctx;
- struct pipe_ctx *pipe_ctx = &pipes[0];
+ struct pipe_ctx *pipe_ctx = NULL;
unsigned int lane;
unsigned int i;
unsigned char link_qual_pattern[LANE_COUNT_DP_MAX] = {0};
@@ -4002,12 +4002,18 @@ bool dc_link_dp_set_test_pattern(
memset(&training_pattern, 0, sizeof(training_pattern));
for (i = 0; i < MAX_PIPES; i++) {
+ if (pipes[i].stream == NULL)
+ continue;
+
if (pipes[i].stream->link == link && !pipes[i].top_pipe && !pipes[i].prev_odm_pipe) {
pipe_ctx = &pipes[i];
break;
}
}
+ if (pipe_ctx == NULL)
+ return false;
+
/* Reset CRTC Test Pattern if it is currently running and request is VideoMode */
if (link->test_pattern_enabled && test_pattern ==
DP_TEST_PATTERN_VIDEO_MODE) {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 100ce0e28fd5..b096011acb49 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -470,7 +470,7 @@ void mpc1_cursor_lock(struct mpc *mpc, int opp_id, bool lock)
unsigned int mpc1_get_mpc_out_mux(struct mpc *mpc, int opp_id)
{
struct dcn10_mpc *mpc10 = TO_DCN10_MPC(mpc);
- uint32_t val = 0;
+ uint32_t val = 0xf;
if (opp_id < MAX_OPP && REG(MUX[opp_id]))
REG_GET(MUX[opp_id], MPC_OUT_MUX, &val);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 36745193c391..90e912fef2b3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -608,8 +608,8 @@ static const struct dc_debug_options debug_defaults_drv = {
.disable_pplib_clock_request = false,
.disable_pplib_wm_range = false,
.pplib_wm_report_mode = WM_REPORT_DEFAULT,
- .pipe_split_policy = MPC_SPLIT_DYNAMIC,
- .force_single_disp_pipe_split = true,
+ .pipe_split_policy = MPC_SPLIT_AVOID,
+ .force_single_disp_pipe_split = false,
.disable_dcc = DCC_ENABLE,
.voltage_align_fclk = true,
.disable_stereo_support = true,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c
index 4825c5c1c6ed..35f5bf08ae96 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_resource.c
@@ -1731,6 +1731,7 @@ static struct resource_funcs dcn301_res_pool_funcs = {
.populate_dml_pipes = dcn30_populate_dml_pipes_from_context,
.acquire_idle_pipe_for_layer = dcn20_acquire_idle_pipe_for_layer,
.add_stream_to_ctx = dcn30_add_stream_to_ctx,
+ .add_dsc_to_stream_resource = dcn20_add_dsc_to_stream_resource,
.remove_stream_from_ctx = dcn20_remove_stream_from_ctx,
.populate_dml_writeback_from_context = dcn30_populate_dml_writeback_from_context,
.set_mcif_arb_params = dcn30_set_mcif_arb_params,
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
index 860e72a51534..80170f9721ce 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_mode_vba_20v2.c
@@ -2635,14 +2635,15 @@ static void dml20v2_DISPCLKDPPCLKDCFCLKDeepSleepPrefetchParametersWatermarksAndP
}
if (mode_lib->vba.DRAMClockChangeSupportsVActive &&
- mode_lib->vba.MinActiveDRAMClockChangeMargin > 60 &&
- mode_lib->vba.PrefetchMode[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] == 0) {
+ mode_lib->vba.MinActiveDRAMClockChangeMargin > 60) {
mode_lib->vba.DRAMClockChangeWatermark += 25;
for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k) {
- if (mode_lib->vba.DRAMClockChangeWatermark >
- dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark))
- mode_lib->vba.MinTTUVBlank[k] += 25;
+ if (mode_lib->vba.PrefetchMode[mode_lib->vba.VoltageLevel][mode_lib->vba.maxMpcComb] == 0) {
+ if (mode_lib->vba.DRAMClockChangeWatermark >
+ dml_max(mode_lib->vba.StutterEnterPlusExitWatermark, mode_lib->vba.UrgentWatermark))
+ mode_lib->vba.MinTTUVBlank[k] += 25;
+ }
}
mode_lib->vba.DRAMClockChangeSupport[0][0] = dm_dram_clock_change_vactive;
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index e6231947f987..a0cb746bcb0a 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -1163,7 +1163,14 @@ retry:
if (ret)
goto out;
- if (old_fb->format != fb->format) {
+ /*
+ * Only check the FOURCC format code, excluding modifiers. This is
+ * enough for all legacy drivers. Atomic drivers have their own
+ * checks in their ->atomic_check implementation, which will
+ * return -EINVAL if any hw or driver constraint is violated due
+ * to modifier changes.
+ */
+ if (old_fb->format->format != fb->format->format) {
DRM_DEBUG_KMS("Page flip is not allowed to change frame buffer format.\n");
ret = -EINVAL;
goto out;
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index e5574e506a5c..6d9e81ea67f4 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -38,6 +38,7 @@ i915-y += i915_drv.o \
i915_config.o \
i915_irq.o \
i915_getparam.o \
+ i915_mitigations.o \
i915_params.o \
i915_pci.o \
i915_scatterlist.o \
diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index a9439b415603..b3533a32f8ba 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -1616,10 +1616,6 @@ static void gen11_dsi_get_power_domains(struct intel_encoder *encoder,
get_dsi_io_power_domains(i915,
enc_to_intel_dsi(encoder));
-
- if (crtc_state->dsc.compression_enable)
- intel_display_power_get(i915,
- intel_dsc_power_domain(crtc_state));
}
static bool gen11_dsi_get_hw_state(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/display/intel_panel.c b/drivers/gpu/drm/i915/display/intel_panel.c
index 9f23bac0d792..d64fce1a17cb 100644
--- a/drivers/gpu/drm/i915/display/intel_panel.c
+++ b/drivers/gpu/drm/i915/display/intel_panel.c
@@ -1650,16 +1650,13 @@ static int lpt_setup_backlight(struct intel_connector *connector, enum pipe unus
val = pch_get_backlight(connector);
else
val = lpt_get_backlight(connector);
- val = intel_panel_compute_brightness(connector, val);
- panel->backlight.level = clamp(val, panel->backlight.min,
- panel->backlight.max);
if (cpu_mode) {
drm_dbg_kms(&dev_priv->drm,
"CPU backlight register was enabled, switching to PCH override\n");
/* Write converted CPU PWM value to PCH override register */
- lpt_set_backlight(connector->base.state, panel->backlight.level);
+ lpt_set_backlight(connector->base.state, val);
intel_de_write(dev_priv, BLC_PWM_PCH_CTL1,
pch_ctl1 | BLM_PCH_OVERRIDE_ENABLE);
@@ -1667,6 +1664,10 @@ static int lpt_setup_backlight(struct intel_connector *connector, enum pipe unus
cpu_ctl2 & ~BLM_PWM_ENABLE);
}
+ val = intel_panel_compute_brightness(connector, val);
+ panel->backlight.level = clamp(val, panel->backlight.min,
+ panel->backlight.max);
+
return 0;
}
diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
index d52f9c177908..f94025ec603a 100644
--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
@@ -812,10 +812,20 @@ static void intel_dsi_pre_enable(struct intel_atomic_state *state,
intel_dsi_prepare(encoder, pipe_config);
intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON);
- intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
- /* Deassert reset */
- intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
+ /*
+ * Give the panel time to power-on and then deassert its reset.
+ * Depending on the VBT MIPI sequences version the deassert-seq
+ * may contain the necessary delay, intel_dsi_msleep() will skip
+ * the delay in that case. If there is no deassert-seq, then an
+ * unconditional msleep is used to give the panel time to power-on.
+ */
+ if (dev_priv->vbt.dsi.sequence[MIPI_SEQ_DEASSERT_RESET]) {
+ intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
+ intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
+ } else {
+ msleep(intel_dsi->panel_on_delay);
+ }
if (IS_GEMINILAKE(dev_priv)) {
glk_cold_boot = glk_dsi_enable_io(encoder);
diff --git a/drivers/gpu/drm/i915/gt/gen7_renderclear.c b/drivers/gpu/drm/i915/gt/gen7_renderclear.c
index d93d85cd3027..94465374ca2f 100644
--- a/drivers/gpu/drm/i915/gt/gen7_renderclear.c
+++ b/drivers/gpu/drm/i915/gt/gen7_renderclear.c
@@ -7,8 +7,6 @@
#include "i915_drv.h"
#include "intel_gpu_commands.h"
-#define MAX_URB_ENTRIES 64
-#define STATE_SIZE (4 * 1024)
#define GT3_INLINE_DATA_DELAYS 0x1E00
#define batch_advance(Y, CS) GEM_BUG_ON((Y)->end != (CS))
@@ -34,38 +32,59 @@ struct batch_chunk {
};
struct batch_vals {
- u32 max_primitives;
- u32 max_urb_entries;
- u32 cmd_size;
- u32 state_size;
+ u32 max_threads;
u32 state_start;
- u32 batch_size;
+ u32 surface_start;
u32 surface_height;
u32 surface_width;
- u32 scratch_size;
- u32 max_size;
+ u32 size;
};
+static inline int num_primitives(const struct batch_vals *bv)
+{
+ /*
+ * We need to saturate the GPU with work in order to dispatch
+ * a shader on every HW thread, and clear the thread-local registers.
+ * In short, we have to dispatch work faster than the shaders can
+ * run in order to fill the EU and occupy each HW thread.
+ */
+ return bv->max_threads;
+}
+
static void
batch_get_defaults(struct drm_i915_private *i915, struct batch_vals *bv)
{
if (IS_HASWELL(i915)) {
- bv->max_primitives = 280;
- bv->max_urb_entries = MAX_URB_ENTRIES;
+ switch (INTEL_INFO(i915)->gt) {
+ default:
+ case 1:
+ bv->max_threads = 70;
+ break;
+ case 2:
+ bv->max_threads = 140;
+ break;
+ case 3:
+ bv->max_threads = 280;
+ break;
+ }
bv->surface_height = 16 * 16;
bv->surface_width = 32 * 2 * 16;
} else {
- bv->max_primitives = 128;
- bv->max_urb_entries = MAX_URB_ENTRIES / 2;
+ switch (INTEL_INFO(i915)->gt) {
+ default:
+ case 1: /* including vlv */
+ bv->max_threads = 36;
+ break;
+ case 2:
+ bv->max_threads = 128;
+ break;
+ }
bv->surface_height = 16 * 8;
bv->surface_width = 32 * 16;
}
- bv->cmd_size = bv->max_primitives * 4096;
- bv->state_size = STATE_SIZE;
- bv->state_start = bv->cmd_size;
- bv->batch_size = bv->cmd_size + bv->state_size;
- bv->scratch_size = bv->surface_height * bv->surface_width;
- bv->max_size = bv->batch_size + bv->scratch_size;
+ bv->state_start = round_up(SZ_1K + num_primitives(bv) * 64, SZ_4K);
+ bv->surface_start = bv->state_start + SZ_4K;
+ bv->size = bv->surface_start + bv->surface_height * bv->surface_width;
}
static void batch_init(struct batch_chunk *bc,
@@ -155,7 +174,8 @@ static u32
gen7_fill_binding_table(struct batch_chunk *state,
const struct batch_vals *bv)
{
- u32 surface_start = gen7_fill_surface_state(state, bv->batch_size, bv);
+ u32 surface_start =
+ gen7_fill_surface_state(state, bv->surface_start, bv);
u32 *cs = batch_alloc_items(state, 32, 8);
u32 offset = batch_offset(state, cs);
@@ -214,9 +234,9 @@ static void
gen7_emit_state_base_address(struct batch_chunk *batch,
u32 surface_state_base)
{
- u32 *cs = batch_alloc_items(batch, 0, 12);
+ u32 *cs = batch_alloc_items(batch, 0, 10);
- *cs++ = STATE_BASE_ADDRESS | (12 - 2);
+ *cs++ = STATE_BASE_ADDRESS | (10 - 2);
/* general */
*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;
/* surface */
@@ -233,8 +253,6 @@ gen7_emit_state_base_address(struct batch_chunk *batch,
*cs++ = BASE_ADDRESS_MODIFY;
*cs++ = 0;
*cs++ = BASE_ADDRESS_MODIFY;
- *cs++ = 0;
- *cs++ = 0;
batch_advance(batch, cs);
}
@@ -244,8 +262,7 @@ gen7_emit_vfe_state(struct batch_chunk *batch,
u32 urb_size, u32 curbe_size,
u32 mode)
{
- u32 urb_entries = bv->max_urb_entries;
- u32 threads = bv->max_primitives - 1;
+ u32 threads = bv->max_threads - 1;
u32 *cs = batch_alloc_items(batch, 32, 8);
*cs++ = MEDIA_VFE_STATE | (8 - 2);
@@ -254,7 +271,7 @@ gen7_emit_vfe_state(struct batch_chunk *batch,
*cs++ = 0;
/* number of threads & urb entries for GPGPU vs Media Mode */
- *cs++ = threads << 16 | urb_entries << 8 | mode << 2;
+ *cs++ = threads << 16 | 1 << 8 | mode << 2;
*cs++ = 0;
@@ -293,17 +310,12 @@ gen7_emit_media_object(struct batch_chunk *batch,
{
unsigned int x_offset = (media_object_index % 16) * 64;
unsigned int y_offset = (media_object_index / 16) * 16;
- unsigned int inline_data_size;
- unsigned int media_batch_size;
- unsigned int i;
+ unsigned int pkt = 6 + 3;
u32 *cs;
- inline_data_size = 112 * 8;
- media_batch_size = inline_data_size + 6;
-
- cs = batch_alloc_items(batch, 8, media_batch_size);
+ cs = batch_alloc_items(batch, 8, pkt);
- *cs++ = MEDIA_OBJECT | (media_batch_size - 2);
+ *cs++ = MEDIA_OBJECT | (pkt - 2);
/* interface descriptor offset */
*cs++ = 0;
@@ -317,25 +329,44 @@ gen7_emit_media_object(struct batch_chunk *batch,
*cs++ = 0;
/* inline */
- *cs++ = (y_offset << 16) | (x_offset);
+ *cs++ = y_offset << 16 | x_offset;
*cs++ = 0;
*cs++ = GT3_INLINE_DATA_DELAYS;
- for (i = 3; i < inline_data_size; i++)
- *cs++ = 0;
batch_advance(batch, cs);
}
static void gen7_emit_pipeline_flush(struct batch_chunk *batch)
{
- u32 *cs = batch_alloc_items(batch, 0, 5);
+ u32 *cs = batch_alloc_items(batch, 0, 4);
- *cs++ = GFX_OP_PIPE_CONTROL(5);
- *cs++ = PIPE_CONTROL_STATE_CACHE_INVALIDATE |
- PIPE_CONTROL_GLOBAL_GTT_IVB;
+ *cs++ = GFX_OP_PIPE_CONTROL(4);
+ *cs++ = PIPE_CONTROL_RENDER_TARGET_CACHE_FLUSH |
+ PIPE_CONTROL_DEPTH_CACHE_FLUSH |
+ PIPE_CONTROL_DC_FLUSH_ENABLE |
+ PIPE_CONTROL_CS_STALL;
*cs++ = 0;
*cs++ = 0;
+
+ batch_advance(batch, cs);
+}
+
+static void gen7_emit_pipeline_invalidate(struct batch_chunk *batch)
+{
+ u32 *cs = batch_alloc_items(batch, 0, 8);
+
+ /* ivb: Stall before STATE_CACHE_INVALIDATE */
+ *cs++ = GFX_OP_PIPE_CONTROL(4);
+ *cs++ = PIPE_CONTROL_STALL_AT_SCOREBOARD |
+ PIPE_CONTROL_CS_STALL;
+ *cs++ = 0;
+ *cs++ = 0;
+
+ *cs++ = GFX_OP_PIPE_CONTROL(4);
+ *cs++ = PIPE_CONTROL_STATE_CACHE_INVALIDATE;
*cs++ = 0;
+ *cs++ = 0;
+
batch_advance(batch, cs);
}
@@ -344,34 +375,34 @@ static void emit_batch(struct i915_vma * const vma,
const struct batch_vals *bv)
{
struct drm_i915_private *i915 = vma->vm->i915;
- unsigned int desc_count = 64;
- const u32 urb_size = 112;
+ const unsigned int desc_count = 1;
+ const unsigned int urb_size = 1;
struct batch_chunk cmds, state;
- u32 interface_descriptor;
+ u32 descriptors;
unsigned int i;
- batch_init(&cmds, vma, start, 0, bv->cmd_size);
- batch_init(&state, vma, start, bv->state_start, bv->state_size);
+ batch_init(&cmds, vma, start, 0, bv->state_start);
+ batch_init(&state, vma, start, bv->state_start, SZ_4K);
- interface_descriptor =
- gen7_fill_interface_descriptor(&state, bv,
- IS_HASWELL(i915) ?
- &cb_kernel_hsw :
- &cb_kernel_ivb,
- desc_count);
- gen7_emit_pipeline_flush(&cmds);
+ descriptors = gen7_fill_interface_descriptor(&state, bv,
+ IS_HASWELL(i915) ?
+ &cb_kernel_hsw :
+ &cb_kernel_ivb,
+ desc_count);
+
+ gen7_emit_pipeline_invalidate(&cmds);
batch_add(&cmds, PIPELINE_SELECT | PIPELINE_SELECT_MEDIA);
batch_add(&cmds, MI_NOOP);
- gen7_emit_state_base_address(&cmds, interface_descriptor);
+ gen7_emit_pipeline_invalidate(&cmds);
+
gen7_emit_pipeline_flush(&cmds);
+ gen7_emit_state_base_address(&cmds, descriptors);
+ gen7_emit_pipeline_invalidate(&cmds);
gen7_emit_vfe_state(&cmds, bv, urb_size - 1, 0, 0);
+ gen7_emit_interface_descriptor_load(&cmds, descriptors, desc_count);
- gen7_emit_interface_descriptor_load(&cmds,
- interface_descriptor,
- desc_count);
-
- for (i = 0; i < bv->max_primitives; i++)
+ for (i = 0; i < num_primitives(bv); i++)
gen7_emit_media_object(&cmds, i);
batch_add(&cmds, MI_BATCH_BUFFER_END);
@@ -385,15 +416,15 @@ int gen7_setup_clear_gpr_bb(struct intel_engine_cs * const engine,
batch_get_defaults(engine->i915, &bv);
if (!vma)
- return bv.max_size;
+ return bv.size;
- GEM_BUG_ON(vma->obj->base.size < bv.max_size);
+ GEM_BUG_ON(vma->obj->base.size < bv.size);
batch = i915_gem_object_pin_map(vma->obj, I915_MAP_WC);
if (IS_ERR(batch))
return PTR_ERR(batch);
- emit_batch(vma, memset(batch, 0, bv.max_size), &bv);
+ emit_batch(vma, memset(batch, 0, bv.size), &bv);
i915_gem_object_flush_map(vma->obj);
__i915_gem_object_release_map(vma->obj);
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_submission.c b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
index a41b43f445b8..ecf3a6118a6d 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_submission.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring_submission.c
@@ -32,6 +32,7 @@
#include "gen6_ppgtt.h"
#include "gen7_renderclear.h"
#include "i915_drv.h"
+#include "i915_mitigations.h"
#include "intel_breadcrumbs.h"
#include "intel_context.h"
#include "intel_gt.h"
@@ -886,7 +887,8 @@ static int switch_context(struct i915_request *rq)
GEM_BUG_ON(HAS_EXECLISTS(engine->i915));
if (engine->wa_ctx.vma && ce != engine->kernel_context) {
- if (engine->wa_ctx.vma->private != ce) {
+ if (engine->wa_ctx.vma->private != ce &&
+ i915_mitigate_clear_residuals()) {
ret = clear_residuals(rq);
if (ret)
return ret;
@@ -1290,7 +1292,7 @@ int intel_ring_submission_setup(struct intel_engine_cs *engine)
GEM_BUG_ON(timeline->hwsp_ggtt != engine->status_page.vma);
- if (IS_HASWELL(engine->i915) && engine->class == RENDER_CLASS) {
+ if (IS_GEN(engine->i915, 7) && engine->class == RENDER_CLASS) {
err = gen7_ctx_switch_bb_init(engine);
if (err)
goto err_ring_unpin;
diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index a15f87539657..62a5b0dd2003 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -217,6 +217,15 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
DDI_BUF_CTL_ENABLE);
vgpu_vreg_t(vgpu, DDI_BUF_CTL(port)) |= DDI_BUF_IS_IDLE;
}
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+ ~(PORTA_HOTPLUG_ENABLE | PORTA_HOTPLUG_STATUS_MASK);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+ ~(PORTB_HOTPLUG_ENABLE | PORTB_HOTPLUG_STATUS_MASK);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+ ~(PORTC_HOTPLUG_ENABLE | PORTC_HOTPLUG_STATUS_MASK);
+ /* No hpd_invert set in vgpu vbt, need to clear invert mask */
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &= ~BXT_DDI_HPD_INVERT_MASK;
+ vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &= ~BXT_DE_PORT_HOTPLUG_MASK;
vgpu_vreg_t(vgpu, BXT_P_CR_GT_DISP_PWRON) &= ~(BIT(0) | BIT(1));
vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) &=
@@ -273,6 +282,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
vgpu_vreg_t(vgpu, TRANS_DDI_FUNC_CTL(TRANSCODER_EDP)) |=
(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
TRANS_DDI_FUNC_ENABLE);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+ PORTA_HOTPLUG_ENABLE;
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
}
@@ -301,6 +312,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
(PORT_B << TRANS_DDI_PORT_SHIFT) |
TRANS_DDI_FUNC_ENABLE);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+ PORTB_HOTPLUG_ENABLE;
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
}
@@ -329,6 +342,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
(TRANS_DDI_BPC_8 | TRANS_DDI_MODE_SELECT_DP_SST |
(PORT_B << TRANS_DDI_PORT_SHIFT) |
TRANS_DDI_FUNC_ENABLE);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+ PORTC_HOTPLUG_ENABLE;
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
}
@@ -661,44 +676,62 @@ void intel_vgpu_emulate_hotplug(struct intel_vgpu *vgpu, bool connected)
PORTD_HOTPLUG_STATUS_MASK;
intel_vgpu_trigger_virtual_event(vgpu, DP_D_HOTPLUG);
} else if (IS_BROXTON(i915)) {
- if (connected) {
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+ if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+ if (connected) {
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
+ } else {
+ vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
+ ~GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
}
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
- vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
- SFUSE_STRAP_DDIB_DETECTED;
+ vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+ GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+ ~PORTA_HOTPLUG_STATUS_MASK;
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+ PORTA_HOTPLUG_LONG_DETECT;
+ intel_vgpu_trigger_virtual_event(vgpu, DP_A_HOTPLUG);
+ }
+ if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+ if (connected) {
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
- }
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
- SFUSE_STRAP_DDIC_DETECTED;
- vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
- GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
- }
- } else {
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+ SFUSE_STRAP_DDIB_DETECTED;
+ } else {
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
- ~GEN8_DE_PORT_HOTPLUG(HPD_PORT_A);
- }
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+ ~GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
~SFUSE_STRAP_DDIB_DETECTED;
- vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
- ~GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
}
- if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
- vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
- ~SFUSE_STRAP_DDIC_DETECTED;
+ vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+ GEN8_DE_PORT_HOTPLUG(HPD_PORT_B);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+ ~PORTB_HOTPLUG_STATUS_MASK;
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+ PORTB_HOTPLUG_LONG_DETECT;
+ intel_vgpu_trigger_virtual_event(vgpu, DP_B_HOTPLUG);
+ }
+ if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
+ if (connected) {
+ vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
+ GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
+ vgpu_vreg_t(vgpu, SFUSE_STRAP) |=
+ SFUSE_STRAP_DDIC_DETECTED;
+ } else {
vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &=
~GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
+ vgpu_vreg_t(vgpu, SFUSE_STRAP) &=
+ ~SFUSE_STRAP_DDIC_DETECTED;
}
+ vgpu_vreg_t(vgpu, GEN8_DE_PORT_IIR) |=
+ GEN8_DE_PORT_HOTPLUG(HPD_PORT_C);
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) &=
+ ~PORTC_HOTPLUG_STATUS_MASK;
+ vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
+ PORTC_HOTPLUG_LONG_DETECT;
+ intel_vgpu_trigger_virtual_event(vgpu, DP_C_HOTPLUG);
}
- vgpu_vreg_t(vgpu, PCH_PORT_HOTPLUG) |=
- PORTB_HOTPLUG_STATUS_MASK;
- intel_vgpu_trigger_virtual_event(vgpu, DP_B_HOTPLUG);
}
}
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index e49944fde333..cbe5931906e0 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -437,10 +437,9 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
if (ret)
goto out_clean_sched_policy;
- if (IS_BROADWELL(dev_priv))
+ if (IS_BROADWELL(dev_priv) || IS_BROXTON(dev_priv))
ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_B);
- /* FixMe: Re-enable APL/BXT once vfio_edid enabled */
- else if (!IS_BROXTON(dev_priv))
+ else
ret = intel_gvt_hypervisor_set_edid(vgpu, PORT_D);
if (ret)
goto out_clean_sched_policy;
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 88ad754962af..99eb0d7bbc44 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1047,6 +1047,8 @@ static void intel_shutdown_encoders(struct drm_i915_private *dev_priv)
void i915_driver_shutdown(struct drm_i915_private *i915)
{
+ disable_rpm_wakeref_asserts(&i915->runtime_pm);
+
i915_gem_suspend(i915);
drm_kms_helper_poll_disable(&i915->drm);
@@ -1060,6 +1062,8 @@ void i915_driver_shutdown(struct drm_i915_private *i915)
intel_suspend_encoders(i915);
intel_shutdown_encoders(i915);
+
+ enable_rpm_wakeref_asserts(&i915->runtime_pm);
}
static bool suspend_to_idle(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_mitigations.c b/drivers/gpu/drm/i915/i915_mitigations.c
new file mode 100644
index 000000000000..84f12598d145
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_mitigations.c
@@ -0,0 +1,146 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+#include "i915_drv.h"
+#include "i915_mitigations.h"
+
+static unsigned long mitigations __read_mostly = ~0UL;
+
+enum {
+ CLEAR_RESIDUALS = 0,
+};
+
+static const char * const names[] = {
+ [CLEAR_RESIDUALS] = "residuals",
+};
+
+bool i915_mitigate_clear_residuals(void)
+{
+ return READ_ONCE(mitigations) & BIT(CLEAR_RESIDUALS);
+}
+
+static int mitigations_set(const char *val, const struct kernel_param *kp)
+{
+ unsigned long new = ~0UL;
+ char *str, *sep, *tok;
+ bool first = true;
+ int err = 0;
+
+ BUILD_BUG_ON(ARRAY_SIZE(names) >= BITS_PER_TYPE(mitigations));
+
+ str = kstrdup(val, GFP_KERNEL);
+ if (!str)
+ return -ENOMEM;
+
+ for (sep = str; (tok = strsep(&sep, ","));) {
+ bool enable = true;
+ int i;
+
+ /* Be tolerant of leading/trailing whitespace */
+ tok = strim(tok);
+
+ if (first) {
+ first = false;
+
+ if (!strcmp(tok, "auto"))
+ continue;
+
+ new = 0;
+ if (!strcmp(tok, "off"))
+ continue;
+ }
+
+ if (*tok == '!') {
+ enable = !enable;
+ tok++;
+ }
+
+ if (!strncmp(tok, "no", 2)) {
+ enable = !enable;
+ tok += 2;
+ }
+
+ if (*tok == '\0')
+ continue;
+
+ for (i = 0; i < ARRAY_SIZE(names); i++) {
+ if (!strcmp(tok, names[i])) {
+ if (enable)
+ new |= BIT(i);
+ else
+ new &= ~BIT(i);
+ break;
+ }
+ }
+ if (i == ARRAY_SIZE(names)) {
+ pr_err("Bad \"%s.mitigations=%s\", '%s' is unknown\n",
+ DRIVER_NAME, val, tok);
+ err = -EINVAL;
+ break;
+ }
+ }
+ kfree(str);
+ if (err)
+ return err;
+
+ WRITE_ONCE(mitigations, new);
+ return 0;
+}
+
+static int mitigations_get(char *buffer, const struct kernel_param *kp)
+{
+ unsigned long local = READ_ONCE(mitigations);
+ int count, i;
+ bool enable;
+
+ if (!local)
+ return scnprintf(buffer, PAGE_SIZE, "%s\n", "off");
+
+ if (local & BIT(BITS_PER_LONG - 1)) {
+ count = scnprintf(buffer, PAGE_SIZE, "%s,", "auto");
+ enable = false;
+ } else {
+ enable = true;
+ count = 0;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(names); i++) {
+ if ((local & BIT(i)) != enable)
+ continue;
+
+ count += scnprintf(buffer + count, PAGE_SIZE - count,
+ "%s%s,", enable ? "" : "!", names[i]);
+ }
+
+ buffer[count - 1] = '\n';
+ return count;
+}
+
+static const struct kernel_param_ops ops = {
+ .set = mitigations_set,
+ .get = mitigations_get,
+};
+
+module_param_cb_unsafe(mitigations, &ops, NULL, 0600);
+MODULE_PARM_DESC(mitigations,
+"Selectively enable security mitigations for all Intel® GPUs in the system.\n"
+"\n"
+" auto -- enables all mitigations required for the platform [default]\n"
+" off -- disables all mitigations\n"
+"\n"
+"Individual mitigations can be enabled by passing a comma-separated string,\n"
+"e.g. mitigations=residuals to enable only clearing residuals or\n"
+"mitigations=auto,noresiduals to disable only the clear residual mitigation.\n"
+"Either '!' or 'no' may be used to switch from enabling the mitigation to\n"
+"disabling it.\n"
+"\n"
+"Active mitigations for Ivybridge, Baytrail, Haswell:\n"
+" residuals -- clear all thread-local registers between contexts"
+);
diff --git a/drivers/gpu/drm/i915/i915_mitigations.h b/drivers/gpu/drm/i915/i915_mitigations.h
new file mode 100644
index 000000000000..1359d8135287
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_mitigations.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef __I915_MITIGATIONS_H__
+#define __I915_MITIGATIONS_H__
+
+#include <linux/types.h>
+
+bool i915_mitigate_clear_residuals(void);
+
+#endif /* __I915_MITIGATIONS_H__ */
diff --git a/drivers/gpu/drm/nouveau/dispnv50/Kbuild b/drivers/gpu/drm/nouveau/dispnv50/Kbuild
index 6fdddb266fb1..4488e1c061b3 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/Kbuild
+++ b/drivers/gpu/drm/nouveau/dispnv50/Kbuild
@@ -37,6 +37,7 @@ nouveau-y += dispnv50/wimmc37b.o
nouveau-y += dispnv50/wndw.o
nouveau-y += dispnv50/wndwc37e.o
nouveau-y += dispnv50/wndwc57e.o
+nouveau-y += dispnv50/wndwc67e.o
nouveau-y += dispnv50/base.o
nouveau-y += dispnv50/base507c.o
diff --git a/drivers/gpu/drm/nouveau/dispnv50/core.c b/drivers/gpu/drm/nouveau/dispnv50/core.c
index 27ea3f34706d..abefc2343443 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/core.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/core.c
@@ -42,6 +42,7 @@ nv50_core_new(struct nouveau_drm *drm, struct nv50_core **pcore)
int version;
int (*new)(struct nouveau_drm *, s32, struct nv50_core **);
} cores[] = {
+ { GA102_DISP_CORE_CHANNEL_DMA, 0, corec57d_new },
{ TU102_DISP_CORE_CHANNEL_DMA, 0, corec57d_new },
{ GV100_DISP_CORE_CHANNEL_DMA, 0, corec37d_new },
{ GP102_DISP_CORE_CHANNEL_DMA, 0, core917d_new },
diff --git a/drivers/gpu/drm/nouveau/dispnv50/curs.c b/drivers/gpu/drm/nouveau/dispnv50/curs.c
index 121c24a18f11..31d8b2e4791d 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/curs.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/curs.c
@@ -31,6 +31,7 @@ nv50_curs_new(struct nouveau_drm *drm, int head, struct nv50_wndw **pwndw)
int version;
int (*new)(struct nouveau_drm *, int, s32, struct nv50_wndw **);
} curses[] = {
+ { GA102_DISP_CURSOR, 0, cursc37a_new },
{ TU102_DISP_CURSOR, 0, cursc37a_new },
{ GV100_DISP_CURSOR, 0, cursc37a_new },
{ GK104_DISP_CURSOR, 0, curs907a_new },
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 33fff388dd83..c6367035970e 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -222,7 +222,7 @@ nv50_dmac_wait(struct nvif_push *push, u32 size)
int
nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
- const s32 *oclass, u8 head, void *data, u32 size, u64 syncbuf,
+ const s32 *oclass, u8 head, void *data, u32 size, s64 syncbuf,
struct nv50_dmac *dmac)
{
struct nouveau_cli *cli = (void *)device->object.client;
@@ -271,7 +271,7 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
if (ret)
return ret;
- if (!syncbuf)
+ if (syncbuf < 0)
return 0;
ret = nvif_object_ctor(&dmac->base.user, "kmsSyncCtxDma", NV50_DISP_HANDLE_SYNCBUF,
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.h b/drivers/gpu/drm/nouveau/dispnv50/disp.h
index 92bddc083617..38dec11e7dda 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.h
@@ -95,7 +95,7 @@ struct nv50_outp_atom {
int nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
const s32 *oclass, u8 head, void *data, u32 size,
- u64 syncbuf, struct nv50_dmac *dmac);
+ s64 syncbuf, struct nv50_dmac *dmac);
void nv50_dmac_destroy(struct nv50_dmac *);
/*
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wimm.c b/drivers/gpu/drm/nouveau/dispnv50/wimm.c
index a1ac153d5e98..566fbddfc8d7 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wimm.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wimm.c
@@ -31,6 +31,7 @@ nv50_wimm_init(struct nouveau_drm *drm, struct nv50_wndw *wndw)
int version;
int (*init)(struct nouveau_drm *, s32, struct nv50_wndw *);
} wimms[] = {
+ { GA102_DISP_WINDOW_IMM_CHANNEL_DMA, 0, wimmc37b_init },
{ TU102_DISP_WINDOW_IMM_CHANNEL_DMA, 0, wimmc37b_init },
{ GV100_DISP_WINDOW_IMM_CHANNEL_DMA, 0, wimmc37b_init },
{}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c b/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
index 685b70871324..b390029c69ec 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wimmc37b.c
@@ -76,7 +76,7 @@ wimmc37b_init_(const struct nv50_wimm_func *func, struct nouveau_drm *drm,
int ret;
ret = nv50_dmac_create(&drm->client.device, &disp->disp->object,
- &oclass, 0, &args, sizeof(args), 0,
+ &oclass, 0, &args, sizeof(args), -1,
&wndw->wimm);
if (ret) {
NV_ERROR(drm, "wimm%04x allocation failed: %d\n", oclass, ret);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index 0356474ad6f6..ce451242f79e 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -784,6 +784,7 @@ nv50_wndw_new(struct nouveau_drm *drm, enum drm_plane_type type, int index,
int (*new)(struct nouveau_drm *, enum drm_plane_type,
int, s32, struct nv50_wndw **);
} wndws[] = {
+ { GA102_DISP_WINDOW_CHANNEL_DMA, 0, wndwc67e_new },
{ TU102_DISP_WINDOW_CHANNEL_DMA, 0, wndwc57e_new },
{ GV100_DISP_WINDOW_CHANNEL_DMA, 0, wndwc37e_new },
{}
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.h b/drivers/gpu/drm/nouveau/dispnv50/wndw.h
index 3278e2880034..f4e0c5080034 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.h
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.h
@@ -129,6 +129,14 @@ int wndwc37e_update(struct nv50_wndw *, u32 *);
int wndwc57e_new(struct nouveau_drm *, enum drm_plane_type, int, s32,
struct nv50_wndw **);
+bool wndwc57e_ilut(struct nv50_wndw *, struct nv50_wndw_atom *, int);
+int wndwc57e_ilut_set(struct nv50_wndw *, struct nv50_wndw_atom *);
+int wndwc57e_ilut_clr(struct nv50_wndw *);
+int wndwc57e_csc_set(struct nv50_wndw *, struct nv50_wndw_atom *);
+int wndwc57e_csc_clr(struct nv50_wndw *);
+
+int wndwc67e_new(struct nouveau_drm *, enum drm_plane_type, int, s32,
+ struct nv50_wndw **);
int nv50_wndw_new(struct nouveau_drm *, enum drm_plane_type, int index,
struct nv50_wndw **);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
index 429be0bb0222..abdd3bb658b3 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc57e.c
@@ -80,7 +80,7 @@ wndwc57e_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
return 0;
}
-static int
+int
wndwc57e_csc_clr(struct nv50_wndw *wndw)
{
struct nvif_push *push = wndw->wndw.push;
@@ -98,7 +98,7 @@ wndwc57e_csc_clr(struct nv50_wndw *wndw)
return 0;
}
-static int
+int
wndwc57e_csc_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
{
struct nvif_push *push = wndw->wndw.push;
@@ -111,7 +111,7 @@ wndwc57e_csc_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
return 0;
}
-static int
+int
wndwc57e_ilut_clr(struct nv50_wndw *wndw)
{
struct nvif_push *push = wndw->wndw.push;
@@ -124,7 +124,7 @@ wndwc57e_ilut_clr(struct nv50_wndw *wndw)
return 0;
}
-static int
+int
wndwc57e_ilut_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
{
struct nvif_push *push = wndw->wndw.push;
@@ -179,7 +179,7 @@ wndwc57e_ilut_load(struct drm_color_lut *in, int size, void __iomem *mem)
writew(readw(mem - 4), mem + 4);
}
-static bool
+bool
wndwc57e_ilut(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw, int size)
{
if (size = size ? size : 1024, size != 256 && size != 1024)
diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndwc67e.c b/drivers/gpu/drm/nouveau/dispnv50/wndwc67e.c
new file mode 100644
index 000000000000..7a370fa1df20
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndwc67e.c
@@ -0,0 +1,106 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "wndw.h"
+#include "atom.h"
+
+#include <nvif/pushc37b.h>
+
+#include <nvhw/class/clc57e.h>
+
+static int
+wndwc67e_image_set(struct nv50_wndw *wndw, struct nv50_wndw_atom *asyw)
+{
+ struct nvif_push *push = wndw->wndw.push;
+ int ret;
+
+ if ((ret = PUSH_WAIT(push, 17)))
+ return ret;
+
+ PUSH_MTHD(push, NVC57E, SET_PRESENT_CONTROL,
+ NVVAL(NVC57E, SET_PRESENT_CONTROL, MIN_PRESENT_INTERVAL, asyw->image.interval) |
+ NVVAL(NVC57E, SET_PRESENT_CONTROL, BEGIN_MODE, asyw->image.mode) |
+ NVDEF(NVC57E, SET_PRESENT_CONTROL, TIMESTAMP_MODE, DISABLE));
+
+ PUSH_MTHD(push, NVC57E, SET_SIZE,
+ NVVAL(NVC57E, SET_SIZE, WIDTH, asyw->image.w) |
+ NVVAL(NVC57E, SET_SIZE, HEIGHT, asyw->image.h),
+
+ SET_STORAGE,
+ NVVAL(NVC57E, SET_STORAGE, BLOCK_HEIGHT, asyw->image.blockh),
+
+ SET_PARAMS,
+ NVVAL(NVC57E, SET_PARAMS, FORMAT, asyw->image.format) |
+ NVDEF(NVC57E, SET_PARAMS, CLAMP_BEFORE_BLEND, DISABLE) |
+ NVDEF(NVC57E, SET_PARAMS, SWAP_UV, DISABLE) |
+ NVDEF(NVC57E, SET_PARAMS, FMT_ROUNDING_MODE, ROUND_TO_NEAREST),
+
+ SET_PLANAR_STORAGE(0),
+ NVVAL(NVC57E, SET_PLANAR_STORAGE, PITCH, asyw->image.blocks[0]) |
+ NVVAL(NVC57E, SET_PLANAR_STORAGE, PITCH, asyw->image.pitch[0] >> 6));
+
+ PUSH_MTHD(push, NVC57E, SET_CONTEXT_DMA_ISO(0), asyw->image.handle, 1);
+ PUSH_MTHD(push, NVC57E, SET_OFFSET(0), asyw->image.offset[0] >> 8);
+
+ PUSH_MTHD(push, NVC57E, SET_POINT_IN(0),
+ NVVAL(NVC57E, SET_POINT_IN, X, asyw->state.src_x >> 16) |
+ NVVAL(NVC57E, SET_POINT_IN, Y, asyw->state.src_y >> 16));
+
+ PUSH_MTHD(push, NVC57E, SET_SIZE_IN,
+ NVVAL(NVC57E, SET_SIZE_IN, WIDTH, asyw->state.src_w >> 16) |
+ NVVAL(NVC57E, SET_SIZE_IN, HEIGHT, asyw->state.src_h >> 16));
+
+ PUSH_MTHD(push, NVC57E, SET_SIZE_OUT,
+ NVVAL(NVC57E, SET_SIZE_OUT, WIDTH, asyw->state.crtc_w) |
+ NVVAL(NVC57E, SET_SIZE_OUT, HEIGHT, asyw->state.crtc_h));
+ return 0;
+}
+
+static const struct nv50_wndw_func
+wndwc67e = {
+ .acquire = wndwc37e_acquire,
+ .release = wndwc37e_release,
+ .sema_set = wndwc37e_sema_set,
+ .sema_clr = wndwc37e_sema_clr,
+ .ntfy_set = wndwc37e_ntfy_set,
+ .ntfy_clr = wndwc37e_ntfy_clr,
+ .ntfy_reset = corec37d_ntfy_init,
+ .ntfy_wait_begun = base507c_ntfy_wait_begun,
+ .ilut = wndwc57e_ilut,
+ .ilut_identity = true,
+ .ilut_size = 1024,
+ .xlut_set = wndwc57e_ilut_set,
+ .xlut_clr = wndwc57e_ilut_clr,
+ .csc = base907c_csc,
+ .csc_set = wndwc57e_csc_set,
+ .csc_clr = wndwc57e_csc_clr,
+ .image_set = wndwc67e_image_set,
+ .image_clr = wndwc37e_image_clr,
+ .blend_set = wndwc37e_blend_set,
+ .update = wndwc37e_update,
+};
+
+int
+wndwc67e_new(struct nouveau_drm *drm, enum drm_plane_type type, int index,
+ s32 oclass, struct nv50_wndw **pwndw)
+{
+ return wndwc37e_new_(&wndwc67e, drm, type, index, oclass, BIT(index >> 1), pwndw);
+}
diff --git a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
index cd9a2e687bb6..57d4f457a7d4 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/cl0080.h
@@ -33,6 +33,7 @@ struct nv_device_info_v0 {
#define NV_DEVICE_INFO_V0_PASCAL 0x0a
#define NV_DEVICE_INFO_V0_VOLTA 0x0b
#define NV_DEVICE_INFO_V0_TURING 0x0c
+#define NV_DEVICE_INFO_V0_AMPERE 0x0d
__u8 family;
__u8 pad06[2];
__u64 ram_size;
diff --git a/drivers/gpu/drm/nouveau/include/nvif/class.h b/drivers/gpu/drm/nouveau/include/nvif/class.h
index 2c79beb41126..ba2c28ea43d2 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/class.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/class.h
@@ -88,6 +88,7 @@
#define GP102_DISP /* cl5070.h */ 0x00009870
#define GV100_DISP /* cl5070.h */ 0x0000c370
#define TU102_DISP /* cl5070.h */ 0x0000c570
+#define GA102_DISP /* cl5070.h */ 0x0000c670
#define GV100_DISP_CAPS 0x0000c373
@@ -103,6 +104,7 @@
#define GK104_DISP_CURSOR /* cl507a.h */ 0x0000917a
#define GV100_DISP_CURSOR /* cl507a.h */ 0x0000c37a
#define TU102_DISP_CURSOR /* cl507a.h */ 0x0000c57a
+#define GA102_DISP_CURSOR /* cl507a.h */ 0x0000c67a
#define NV50_DISP_OVERLAY /* cl507b.h */ 0x0000507b
#define G82_DISP_OVERLAY /* cl507b.h */ 0x0000827b
@@ -112,6 +114,7 @@
#define GV100_DISP_WINDOW_IMM_CHANNEL_DMA /* clc37b.h */ 0x0000c37b
#define TU102_DISP_WINDOW_IMM_CHANNEL_DMA /* clc37b.h */ 0x0000c57b
+#define GA102_DISP_WINDOW_IMM_CHANNEL_DMA /* clc37b.h */ 0x0000c67b
#define NV50_DISP_BASE_CHANNEL_DMA /* cl507c.h */ 0x0000507c
#define G82_DISP_BASE_CHANNEL_DMA /* cl507c.h */ 0x0000827c
@@ -135,6 +138,7 @@
#define GP102_DISP_CORE_CHANNEL_DMA /* cl507d.h */ 0x0000987d
#define GV100_DISP_CORE_CHANNEL_DMA /* cl507d.h */ 0x0000c37d
#define TU102_DISP_CORE_CHANNEL_DMA /* cl507d.h */ 0x0000c57d
+#define GA102_DISP_CORE_CHANNEL_DMA /* cl507d.h */ 0x0000c67d
#define NV50_DISP_OVERLAY_CHANNEL_DMA /* cl507e.h */ 0x0000507e
#define G82_DISP_OVERLAY_CHANNEL_DMA /* cl507e.h */ 0x0000827e
@@ -145,6 +149,7 @@
#define GV100_DISP_WINDOW_CHANNEL_DMA /* clc37e.h */ 0x0000c37e
#define TU102_DISP_WINDOW_CHANNEL_DMA /* clc37e.h */ 0x0000c57e
+#define GA102_DISP_WINDOW_CHANNEL_DMA /* clc37e.h */ 0x0000c67e
#define NV50_TESLA 0x00005097
#define G82_TESLA 0x00008297
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
index 5c007ce62fc3..c920939a1467 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/core/device.h
@@ -120,6 +120,7 @@ struct nvkm_device {
GP100 = 0x130,
GV100 = 0x140,
TU100 = 0x160,
+ GA100 = 0x170,
} card_type;
u32 chipset;
u8 chiprev;
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
index 5a96c942d912..0f6fa6631a19 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/engine/disp.h
@@ -37,4 +37,5 @@ int gp100_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
int gp102_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
int gv100_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
int tu102_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
+int ga102_disp_new(struct nvkm_device *, int, struct nvkm_disp **);
#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h
index 1a39e52e09e3..50cc7c05eac4 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/devinit.h
@@ -32,4 +32,5 @@ int gm107_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
int gm200_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
int gv100_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
int tu102_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
+int ga100_devinit_new(struct nvkm_device *, int, struct nvkm_devinit **);
#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
index 34b56b10218a..2ecd52aec1d1 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/fb.h
@@ -86,6 +86,8 @@ int gp100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
int gp102_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
int gp10b_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
int gv100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
+int ga100_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
+int ga102_fb_new(struct nvkm_device *, int, struct nvkm_fb **);
#include <subdev/bios.h>
#include <subdev/bios/ramcfg.h>
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gpio.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gpio.h
index eaacf8d80527..cdcce5ece6ff 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gpio.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gpio.h
@@ -37,4 +37,5 @@ int nv50_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
int g94_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
int gf119_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
int gk104_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
+int ga102_gpio_new(struct nvkm_device *, int, struct nvkm_gpio **);
#endif
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/i2c.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/i2c.h
index 81b977319640..640f649ce497 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/i2c.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/i2c.h
@@ -92,6 +92,7 @@ int g94_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
int gf117_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
int gf119_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
int gk104_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
+int gk110_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
int gm200_i2c_new(struct nvkm_device *, int, struct nvkm_i2c **);
static inline int
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h
index 6641fe4c252c..e45ca4583967 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mc.h
@@ -32,4 +32,5 @@ int gk20a_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
int gp100_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
int gp10b_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
int tu102_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
+int ga100_mc_new(struct nvkm_device *, int, struct nvkm_mc **);
#endif
diff --git a/drivers/gpu/drm/nouveau/nouveau_backlight.c b/drivers/gpu/drm/nouveau/nouveau_backlight.c
index c7a94c94dbf3..72f35a2babcb 100644
--- a/drivers/gpu/drm/nouveau/nouveau_backlight.c
+++ b/drivers/gpu/drm/nouveau/nouveau_backlight.c
@@ -256,6 +256,7 @@ nouveau_backlight_init(struct drm_connector *connector)
case NV_DEVICE_INFO_V0_PASCAL:
case NV_DEVICE_INFO_V0_VOLTA:
case NV_DEVICE_INFO_V0_TURING:
+ case NV_DEVICE_INFO_V0_AMPERE: //XXX: not confirmed
ret = nv50_backlight_init(nv_encoder, &props, &ops);
break;
default:
diff --git a/drivers/gpu/drm/nouveau/nvif/disp.c b/drivers/gpu/drm/nouveau/nvif/disp.c
index 8d0d30e08f57..529cb60d5efb 100644
--- a/drivers/gpu/drm/nouveau/nvif/disp.c
+++ b/drivers/gpu/drm/nouveau/nvif/disp.c
@@ -35,6 +35,7 @@ nvif_disp_ctor(struct nvif_device *device, const char *name, s32 oclass,
struct nvif_disp *disp)
{
static const struct nvif_mclass disps[] = {
+ { GA102_DISP, -1 },
{ TU102_DISP, -1 },
{ GV100_DISP, -1 },
{ GP102_DISP, -1 },
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
index 7851bec5f0e5..cdcc851e06f9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/base.c
@@ -1815,7 +1815,7 @@ nvf0_chipset = {
.fb = gk110_fb_new,
.fuse = gf100_fuse_new,
.gpio = gk104_gpio_new,
- .i2c = gk104_i2c_new,
+ .i2c = gk110_i2c_new,
.ibus = gk104_ibus_new,
.iccsense = gf100_iccsense_new,
.imem = nv50_instmem_new,
@@ -1853,7 +1853,7 @@ nvf1_chipset = {
.fb = gk110_fb_new,
.fuse = gf100_fuse_new,
.gpio = gk104_gpio_new,
- .i2c = gk104_i2c_new,
+ .i2c = gk110_i2c_new,
.ibus = gk104_ibus_new,
.iccsense = gf100_iccsense_new,
.imem = nv50_instmem_new,
@@ -1891,7 +1891,7 @@ nv106_chipset = {
.fb = gk110_fb_new,
.fuse = gf100_fuse_new,
.gpio = gk104_gpio_new,
- .i2c = gk104_i2c_new,
+ .i2c = gk110_i2c_new,
.ibus = gk104_ibus_new,
.iccsense = gf100_iccsense_new,
.imem = nv50_instmem_new,
@@ -1929,7 +1929,7 @@ nv108_chipset = {
.fb = gk110_fb_new,
.fuse = gf100_fuse_new,
.gpio = gk104_gpio_new,
- .i2c = gk104_i2c_new,
+ .i2c = gk110_i2c_new,
.ibus = gk104_ibus_new,
.iccsense = gf100_iccsense_new,
.imem = nv50_instmem_new,
@@ -1967,7 +1967,7 @@ nv117_chipset = {
.fb = gm107_fb_new,
.fuse = gm107_fuse_new,
.gpio = gk104_gpio_new,
- .i2c = gk104_i2c_new,
+ .i2c = gk110_i2c_new,
.ibus = gk104_ibus_new,
.iccsense = gf100_iccsense_new,
.imem = nv50_instmem_new,
@@ -2003,7 +2003,7 @@ nv118_chipset = {
.fb = gm107_fb_new,
.fuse = gm107_fuse_new,
.gpio = gk104_gpio_new,
- .i2c = gk104_i2c_new,
+ .i2c = gk110_i2c_new,
.ibus = gk104_ibus_new,
.iccsense = gf100_iccsense_new,
.imem = nv50_instmem_new,
@@ -2652,6 +2652,61 @@ nv168_chipset = {
.sec2 = tu102_sec2_new,
};
+static const struct nvkm_device_chip
+nv170_chipset = {
+ .name = "GA100",
+ .bar = tu102_bar_new,
+ .bios = nvkm_bios_new,
+ .devinit = ga100_devinit_new,
+ .fb = ga100_fb_new,
+ .gpio = gk104_gpio_new,
+ .i2c = gm200_i2c_new,
+ .ibus = gm200_ibus_new,
+ .imem = nv50_instmem_new,
+ .mc = ga100_mc_new,
+ .mmu = tu102_mmu_new,
+ .pci = gp100_pci_new,
+ .timer = gk20a_timer_new,
+};
+
+static const struct nvkm_device_chip
+nv172_chipset = {
+ .name = "GA102",
+ .bar = tu102_bar_new,
+ .bios = nvkm_bios_new,
+ .devinit = ga100_devinit_new,
+ .fb = ga102_fb_new,
+ .gpio = ga102_gpio_new,
+ .i2c = gm200_i2c_new,
+ .ibus = gm200_ibus_new,
+ .imem = nv50_instmem_new,
+ .mc = ga100_mc_new,
+ .mmu = tu102_mmu_new,
+ .pci = gp100_pci_new,
+ .timer = gk20a_timer_new,
+ .disp = ga102_disp_new,
+ .dma = gv100_dma_new,
+};
+
+static const struct nvkm_device_chip
+nv174_chipset = {
+ .name = "GA104",
+ .bar = tu102_bar_new,
+ .bios = nvkm_bios_new,
+ .devinit = ga100_devinit_new,
+ .fb = ga102_fb_new,
+ .gpio = ga102_gpio_new,
+ .i2c = gm200_i2c_new,
+ .ibus = gm200_ibus_new,
+ .imem = nv50_instmem_new,
+ .mc = ga100_mc_new,
+ .mmu = tu102_mmu_new,
+ .pci = gp100_pci_new,
+ .timer = gk20a_timer_new,
+ .disp = ga102_disp_new,
+ .dma = gv100_dma_new,
+};
+
static int
nvkm_device_event_ctor(struct nvkm_object *object, void *data, u32 size,
struct nvkm_notify *notify)
@@ -3063,6 +3118,7 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
case 0x130: device->card_type = GP100; break;
case 0x140: device->card_type = GV100; break;
case 0x160: device->card_type = TU100; break;
+ case 0x170: device->card_type = GA100; break;
default:
break;
}
@@ -3160,10 +3216,23 @@ nvkm_device_ctor(const struct nvkm_device_func *func,
case 0x166: device->chip = &nv166_chipset; break;
case 0x167: device->chip = &nv167_chipset; break;
case 0x168: device->chip = &nv168_chipset; break;
+ case 0x172: device->chip = &nv172_chipset; break;
+ case 0x174: device->chip = &nv174_chipset; break;
default:
- nvdev_error(device, "unknown chipset (%08x)\n", boot0);
- ret = -ENODEV;
- goto done;
+ if (nvkm_boolopt(device->cfgopt, "NvEnableUnsupportedChipsets", false)) {
+ switch (device->chipset) {
+ case 0x170: device->chip = &nv170_chipset; break;
+ default:
+ break;
+ }
+ }
+
+ if (!device->chip) {
+ nvdev_error(device, "unknown chipset (%08x)\n", boot0);
+ ret = -ENODEV;
+ goto done;
+ }
+ break;
}
nvdev_info(device, "NVIDIA %s (%08x)\n",
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
index 03c6d9aef075..147894798786 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/user.c
@@ -176,6 +176,7 @@ nvkm_udevice_info(struct nvkm_udevice *udev, void *data, u32 size)
case GP100: args->v0.family = NV_DEVICE_INFO_V0_PASCAL; break;
case GV100: args->v0.family = NV_DEVICE_INFO_V0_VOLTA; break;
case TU100: args->v0.family = NV_DEVICE_INFO_V0_TURING; break;
+ case GA100: args->v0.family = NV_DEVICE_INFO_V0_AMPERE; break;
default:
args->v0.family = 0;
break;
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
index cf075311cdd2..b03f043efe26 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/Kbuild
@@ -17,6 +17,7 @@ nvkm-y += nvkm/engine/disp/gp100.o
nvkm-y += nvkm/engine/disp/gp102.o
nvkm-y += nvkm/engine/disp/gv100.o
nvkm-y += nvkm/engine/disp/tu102.o
+nvkm-y += nvkm/engine/disp/ga102.o
nvkm-y += nvkm/engine/disp/vga.o
nvkm-y += nvkm/engine/disp/head.o
@@ -42,6 +43,7 @@ nvkm-y += nvkm/engine/disp/sorgm200.o
nvkm-y += nvkm/engine/disp/sorgp100.o
nvkm-y += nvkm/engine/disp/sorgv100.o
nvkm-y += nvkm/engine/disp/sortu102.o
+nvkm-y += nvkm/engine/disp/sorga102.o
nvkm-y += nvkm/engine/disp/outp.o
nvkm-y += nvkm/engine/disp/dp.o
@@ -75,6 +77,7 @@ nvkm-y += nvkm/engine/disp/rootgp100.o
nvkm-y += nvkm/engine/disp/rootgp102.o
nvkm-y += nvkm/engine/disp/rootgv100.o
nvkm-y += nvkm/engine/disp/roottu102.o
+nvkm-y += nvkm/engine/disp/rootga102.o
nvkm-y += nvkm/engine/disp/capsgv100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
index 3800aeb507d0..55fbfe28c6dc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c
@@ -33,6 +33,12 @@
#include <nvif/event.h>
+/* IED scripts are no longer used by UEFI/RM from Ampere, but have been updated for
+ * the x86 option ROM. However, the relevant VBIOS table versions weren't modified,
+ * so we're unable to detect this in a nice way.
+ */
+#define AMPERE_IED_HACK(disp) ((disp)->engine.subdev.device->card_type >= GA100)
+
struct lt_state {
struct nvkm_dp *dp;
u8 stat[6];
@@ -238,6 +244,19 @@ nvkm_dp_train_links(struct nvkm_dp *dp)
dp->dpcd[DPCD_RC02] &= ~DPCD_RC02_TPS3_SUPPORTED;
lt.pc2 = dp->dpcd[DPCD_RC02] & DPCD_RC02_TPS3_SUPPORTED;
+ if (AMPERE_IED_HACK(disp) && (lnkcmp = lt.dp->info.script[0])) {
+ /* Execute BeforeLinkTraining script from DP Info table. */
+ while (ior->dp.bw < nvbios_rd08(bios, lnkcmp))
+ lnkcmp += 3;
+ lnkcmp = nvbios_rd16(bios, lnkcmp + 1);
+
+ nvbios_init(&dp->outp.disp->engine.subdev, lnkcmp,
+ init.outp = &dp->outp.info;
+ init.or = ior->id;
+ init.link = ior->asy.link;
+ );
+ }
+
/* Set desired link configuration on the source. */
if ((lnkcmp = lt.dp->info.lnkcmp)) {
if (dp->version < 0x30) {
@@ -316,12 +335,14 @@ nvkm_dp_train_init(struct nvkm_dp *dp)
);
}
- /* Execute BeforeLinkTraining script from DP Info table. */
- nvbios_init(&dp->outp.disp->engine.subdev, dp->info.script[0],
- init.outp = &dp->outp.info;
- init.or = dp->outp.ior->id;
- init.link = dp->outp.ior->asy.link;
- );
+ if (!AMPERE_IED_HACK(dp->outp.disp)) {
+ /* Execute BeforeLinkTraining script from DP Info table. */
+ nvbios_init(&dp->outp.disp->engine.subdev, dp->info.script[0],
+ init.outp = &dp->outp.info;
+ init.or = dp->outp.ior->id;
+ init.link = dp->outp.ior->asy.link;
+ );
+ }
}
static const struct dp_rates {
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c
new file mode 100644
index 000000000000..aa2e5645fe36
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ga102.c
@@ -0,0 +1,46 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "nv50.h"
+#include "head.h"
+#include "ior.h"
+#include "channv50.h"
+#include "rootnv50.h"
+
+static const struct nv50_disp_func
+ga102_disp = {
+ .init = tu102_disp_init,
+ .fini = gv100_disp_fini,
+ .intr = gv100_disp_intr,
+ .uevent = &gv100_disp_chan_uevent,
+ .super = gv100_disp_super,
+ .root = &ga102_disp_root_oclass,
+ .wndw = { .cnt = gv100_disp_wndw_cnt },
+ .head = { .cnt = gv100_head_cnt, .new = gv100_head_new },
+ .sor = { .cnt = gv100_sor_cnt, .new = ga102_sor_new },
+ .ramht_size = 0x2000,
+};
+
+int
+ga102_disp_new(struct nvkm_device *device, int index, struct nvkm_disp **pdisp)
+{
+ return nv50_disp_new_(&ga102_disp, device, index, pdisp);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h
index 09f3038eff26..9f0bb7c6b010 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h
@@ -150,6 +150,8 @@ void gv100_sor_dp_audio(struct nvkm_ior *, int, bool);
void gv100_sor_dp_audio_sym(struct nvkm_ior *, int, u16, u32);
void gv100_sor_dp_watermark(struct nvkm_ior *, int, u8);
+void tu102_sor_dp_vcpi(struct nvkm_ior *, int, u8, u8, u16, u16);
+
void g84_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
void gt215_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
void gf119_hdmi_ctrl(struct nvkm_ior *, int, bool, u8, u8, u8 *, u8 , u8 *, u8);
@@ -207,4 +209,6 @@ int gv100_sor_cnt(struct nvkm_disp *, unsigned long *);
int gv100_sor_new(struct nvkm_disp *, int);
int tu102_sor_new(struct nvkm_disp *, int);
+
+int ga102_sor_new(struct nvkm_disp *, int);
#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
index a677161c7f3a..db31b37752a2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.h
@@ -86,6 +86,8 @@ void gv100_disp_intr(struct nv50_disp *);
void gv100_disp_super(struct work_struct *);
int gv100_disp_wndw_cnt(struct nvkm_disp *, unsigned long *);
+int tu102_disp_init(struct nv50_disp *);
+
void nv50_disp_dptmds_war_2(struct nv50_disp *, struct dcb_output *);
void nv50_disp_dptmds_war_3(struct nv50_disp *, struct dcb_output *);
void nv50_disp_update_sppll1(struct nv50_disp *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootga102.c
new file mode 100644
index 000000000000..9af07c3cf9fc
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootga102.c
@@ -0,0 +1,52 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "rootnv50.h"
+#include "channv50.h"
+
+#include <nvif/class.h>
+
+static const struct nv50_disp_root_func
+ga102_disp_root = {
+ .user = {
+ {{-1,-1,GV100_DISP_CAPS }, gv100_disp_caps_new },
+ {{0,0,GA102_DISP_CURSOR }, gv100_disp_curs_new },
+ {{0,0,GA102_DISP_WINDOW_IMM_CHANNEL_DMA}, gv100_disp_wimm_new },
+ {{0,0,GA102_DISP_CORE_CHANNEL_DMA }, gv100_disp_core_new },
+ {{0,0,GA102_DISP_WINDOW_CHANNEL_DMA }, gv100_disp_wndw_new },
+ {}
+ },
+};
+
+static int
+ga102_disp_root_new(struct nvkm_disp *disp, const struct nvkm_oclass *oclass,
+ void *data, u32 size, struct nvkm_object **pobject)
+{
+ return nv50_disp_root_new_(&ga102_disp_root, disp, oclass, data, size, pobject);
+}
+
+const struct nvkm_disp_oclass
+ga102_disp_root_oclass = {
+ .base.oclass = GA102_DISP,
+ .base.minver = -1,
+ .base.maxver = -1,
+ .ctor = ga102_disp_root_new,
+};
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
index 7070f5408d92..27bb170d0293 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/rootnv50.h
@@ -41,4 +41,5 @@ extern const struct nvkm_disp_oclass gp100_disp_root_oclass;
extern const struct nvkm_disp_oclass gp102_disp_root_oclass;
extern const struct nvkm_disp_oclass gv100_disp_root_oclass;
extern const struct nvkm_disp_oclass tu102_disp_root_oclass;
+extern const struct nvkm_disp_oclass ga102_disp_root_oclass;
#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorga102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorga102.c
new file mode 100644
index 000000000000..033827de9116
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sorga102.c
@@ -0,0 +1,140 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ior.h"
+
+#include <subdev/timer.h>
+
+static int
+ga102_sor_dp_links(struct nvkm_ior *sor, struct nvkm_i2c_aux *aux)
+{
+ struct nvkm_device *device = sor->disp->engine.subdev.device;
+ const u32 soff = nv50_ior_base(sor);
+ const u32 loff = nv50_sor_link(sor);
+ u32 dpctrl = 0x00000000;
+ u32 clksor = 0x00000000;
+
+ switch (sor->dp.bw) {
+ case 0x06: clksor |= 0x00000000; break;
+ case 0x0a: clksor |= 0x00040000; break;
+ case 0x14: clksor |= 0x00080000; break;
+ case 0x1e: clksor |= 0x000c0000; break;
+ default:
+ WARN_ON(1);
+ return -EINVAL;
+ }
+
+ dpctrl |= ((1 << sor->dp.nr) - 1) << 16;
+ if (sor->dp.mst)
+ dpctrl |= 0x40000000;
+ if (sor->dp.ef)
+ dpctrl |= 0x00004000;
+
+ nvkm_mask(device, 0x612300 + soff, 0x007c0000, clksor);
+
+ /*XXX*/
+ nvkm_msec(device, 40, NVKM_DELAY);
+ nvkm_mask(device, 0x612300 + soff, 0x00030000, 0x00010000);
+ nvkm_mask(device, 0x61c10c + loff, 0x00000003, 0x00000001);
+
+ nvkm_mask(device, 0x61c10c + loff, 0x401f4000, dpctrl);
+ return 0;
+}
+
+static void
+ga102_sor_clock(struct nvkm_ior *sor)
+{
+ struct nvkm_device *device = sor->disp->engine.subdev.device;
+ u32 div2 = 0;
+ if (sor->asy.proto == TMDS) {
+ if (sor->tmds.high_speed)
+ div2 = 1;
+ }
+ nvkm_wr32(device, 0x00ec08 + (sor->id * 0x10), 0x00000000);
+ nvkm_wr32(device, 0x00ec04 + (sor->id * 0x10), div2);
+}
+
+static const struct nvkm_ior_func
+ga102_sor_hda = {
+ .route = {
+ .get = gm200_sor_route_get,
+ .set = gm200_sor_route_set,
+ },
+ .state = gv100_sor_state,
+ .power = nv50_sor_power,
+ .clock = ga102_sor_clock,
+ .hdmi = {
+ .ctrl = gv100_hdmi_ctrl,
+ .scdc = gm200_hdmi_scdc,
+ },
+ .dp = {
+ .lanes = { 0, 1, 2, 3 },
+ .links = ga102_sor_dp_links,
+ .power = g94_sor_dp_power,
+ .pattern = gm107_sor_dp_pattern,
+ .drive = gm200_sor_dp_drive,
+ .vcpi = tu102_sor_dp_vcpi,
+ .audio = gv100_sor_dp_audio,
+ .audio_sym = gv100_sor_dp_audio_sym,
+ .watermark = gv100_sor_dp_watermark,
+ },
+ .hda = {
+ .hpd = gf119_hda_hpd,
+ .eld = gf119_hda_eld,
+ .device_entry = gv100_hda_device_entry,
+ },
+};
+
+static const struct nvkm_ior_func
+ga102_sor = {
+ .route = {
+ .get = gm200_sor_route_get,
+ .set = gm200_sor_route_set,
+ },
+ .state = gv100_sor_state,
+ .power = nv50_sor_power,
+ .clock = ga102_sor_clock,
+ .hdmi = {
+ .ctrl = gv100_hdmi_ctrl,
+ .scdc = gm200_hdmi_scdc,
+ },
+ .dp = {
+ .lanes = { 0, 1, 2, 3 },
+ .links = ga102_sor_dp_links,
+ .power = g94_sor_dp_power,
+ .pattern = gm107_sor_dp_pattern,
+ .drive = gm200_sor_dp_drive,
+ .vcpi = tu102_sor_dp_vcpi,
+ .audio = gv100_sor_dp_audio,
+ .audio_sym = gv100_sor_dp_audio_sym,
+ .watermark = gv100_sor_dp_watermark,
+ },
+};
+
+int
+ga102_sor_new(struct nvkm_disp *disp, int id)
+{
+ struct nvkm_device *device = disp->engine.subdev.device;
+ u32 hda = nvkm_rd32(device, 0x08a15c);
+ if (hda & BIT(id))
+ return nvkm_ior_new_(&ga102_sor_hda, disp, SOR, id);
+ return nvkm_ior_new_(&ga102_sor, disp, SOR, id);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sortu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sortu102.c
index 59865a934c4b..0cf9e8752d25 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/sortu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/sortu102.c
@@ -23,7 +23,7 @@
#include <subdev/timer.h>
-static void
+void
tu102_sor_dp_vcpi(struct nvkm_ior *sor, int head,
u8 slot, u8 slot_nr, u16 pbn, u16 aligned)
{
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c
index 883ae4151ff8..4c85d1d4fbd4 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/tu102.c
@@ -28,7 +28,7 @@
#include <core/gpuobj.h>
#include <subdev/timer.h>
-static int
+int
tu102_disp_init(struct nv50_disp *disp)
{
struct nvkm_device *device = disp->base.engine.subdev.device;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
index 7deb81b6dbac..4b571cc6bc70 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadow.c
@@ -75,7 +75,7 @@ shadow_image(struct nvkm_bios *bios, int idx, u32 offset, struct shadow *mthd)
nvkm_debug(subdev, "%08x: type %02x, %d bytes\n",
image.base, image.type, image.size);
- if (!shadow_fetch(bios, mthd, image.size)) {
+ if (!shadow_fetch(bios, mthd, image.base + image.size)) {
nvkm_debug(subdev, "%08x: fetch failed\n", image.base);
return 0;
}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c
index 3634cd0630b8..023ddc7c5399 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowramin.c
@@ -64,6 +64,9 @@ pramin_init(struct nvkm_bios *bios, const char *name)
return NULL;
/* we can't get the bios image pointer without PDISP */
+ if (device->card_type >= GA100)
+ addr = device->chipset == 0x170; /*XXX: find the fuse reg for this */
+ else
if (device->card_type >= GM100)
addr = nvkm_rd32(device, 0x021c04);
else
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
index b3429371ed82..d1abb64841da 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/Kbuild
@@ -15,3 +15,4 @@ nvkm-y += nvkm/subdev/devinit/gm107.o
nvkm-y += nvkm/subdev/devinit/gm200.o
nvkm-y += nvkm/subdev/devinit/gv100.o
nvkm-y += nvkm/subdev/devinit/tu102.o
+nvkm-y += nvkm/subdev/devinit/ga100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/ga100.c
new file mode 100644
index 000000000000..636a92128f6c
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/ga100.c
@@ -0,0 +1,76 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "nv50.h"
+
+#include <subdev/bios.h>
+#include <subdev/bios/pll.h>
+#include <subdev/clk/pll.h>
+
+static int
+ga100_devinit_pll_set(struct nvkm_devinit *init, u32 type, u32 freq)
+{
+ struct nvkm_subdev *subdev = &init->subdev;
+ struct nvkm_device *device = subdev->device;
+ struct nvbios_pll info;
+ int head = type - PLL_VPLL0;
+ int N, fN, M, P;
+ int ret;
+
+ ret = nvbios_pll_parse(device->bios, type, &info);
+ if (ret)
+ return ret;
+
+ ret = gt215_pll_calc(subdev, &info, freq, &N, &fN, &M, &P);
+ if (ret < 0)
+ return ret;
+
+ switch (info.type) {
+ case PLL_VPLL0:
+ case PLL_VPLL1:
+ case PLL_VPLL2:
+ case PLL_VPLL3:
+ nvkm_wr32(device, 0x00ef00 + (head * 0x40), 0x02080004);
+ nvkm_wr32(device, 0x00ef18 + (head * 0x40), (N << 16) | fN);
+ nvkm_wr32(device, 0x00ef04 + (head * 0x40), (P << 16) | M);
+ nvkm_wr32(device, 0x00e9c0 + (head * 0x04), 0x00000001);
+ break;
+ default:
+ nvkm_warn(subdev, "%08x/%dKhz unimplemented\n", type, freq);
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+static const struct nvkm_devinit_func
+ga100_devinit = {
+ .init = nv50_devinit_init,
+ .post = tu102_devinit_post,
+ .pll_set = ga100_devinit_pll_set,
+};
+
+int
+ga100_devinit_new(struct nvkm_device *device, int index, struct nvkm_devinit **pinit)
+{
+ return nv50_devinit_new_(&ga100_devinit, device, index, pinit);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/priv.h
index 94723352137a..05961e624264 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/priv.h
@@ -19,4 +19,5 @@ void nvkm_devinit_ctor(const struct nvkm_devinit_func *, struct nvkm_device *,
int index, struct nvkm_devinit *);
int nv04_devinit_post(struct nvkm_devinit *, bool);
+int tu102_devinit_post(struct nvkm_devinit *, bool);
#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c
index 397670e72fff..9a469bf482f2 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/tu102.c
@@ -65,7 +65,7 @@ tu102_devinit_pll_set(struct nvkm_devinit *init, u32 type, u32 freq)
return ret;
}
-static int
+int
tu102_devinit_post(struct nvkm_devinit *base, bool post)
{
struct nv50_devinit *init = nv50_devinit(base);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
index 43a42159a3d0..5d0bab8ecb43 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/Kbuild
@@ -32,6 +32,8 @@ nvkm-y += nvkm/subdev/fb/gp100.o
nvkm-y += nvkm/subdev/fb/gp102.o
nvkm-y += nvkm/subdev/fb/gp10b.o
nvkm-y += nvkm/subdev/fb/gv100.o
+nvkm-y += nvkm/subdev/fb/ga100.o
+nvkm-y += nvkm/subdev/fb/ga102.o
nvkm-y += nvkm/subdev/fb/ram.o
nvkm-y += nvkm/subdev/fb/ramnv04.o
@@ -52,6 +54,7 @@ nvkm-y += nvkm/subdev/fb/ramgk104.o
nvkm-y += nvkm/subdev/fb/ramgm107.o
nvkm-y += nvkm/subdev/fb/ramgm200.o
nvkm-y += nvkm/subdev/fb/ramgp100.o
+nvkm-y += nvkm/subdev/fb/ramga102.o
nvkm-y += nvkm/subdev/fb/sddr2.o
nvkm-y += nvkm/subdev/fb/sddr3.o
nvkm-y += nvkm/subdev/fb/gddr3.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c
new file mode 100644
index 000000000000..bf82686851cd
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga100.c
@@ -0,0 +1,40 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gf100.h"
+#include "ram.h"
+
+static const struct nvkm_fb_func
+ga100_fb = {
+ .dtor = gf100_fb_dtor,
+ .oneinit = gf100_fb_oneinit,
+ .init = gp100_fb_init,
+ .init_page = gv100_fb_init_page,
+ .init_unkn = gp100_fb_init_unkn,
+ .ram_new = gp100_ram_new,
+ .default_bigpage = 16,
+};
+
+int
+ga100_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
+{
+ return gp102_fb_new_(&ga100_fb, device, index, pfb);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c
new file mode 100644
index 000000000000..bcecf84a6e67
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ga102.c
@@ -0,0 +1,40 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "gf100.h"
+#include "ram.h"
+
+static const struct nvkm_fb_func
+ga102_fb = {
+ .dtor = gf100_fb_dtor,
+ .oneinit = gf100_fb_oneinit,
+ .init = gp100_fb_init,
+ .init_page = gv100_fb_init_page,
+ .init_unkn = gp100_fb_init_unkn,
+ .ram_new = ga102_ram_new,
+ .default_bigpage = 16,
+};
+
+int
+ga102_fb_new(struct nvkm_device *device, int index, struct nvkm_fb **pfb)
+{
+ return gp102_fb_new_(&ga102_fb, device, index, pfb);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
index 10ff5d053f7e..feda86a5fba8 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/gv100.c
@@ -22,7 +22,7 @@
#include "gf100.h"
#include "ram.h"
-static int
+int
gv100_fb_init_page(struct nvkm_fb *fb)
{
return (fb->page == 16) ? 0 : -EINVAL;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
index 5be9c563350d..66932ac10d15 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/priv.h
@@ -82,4 +82,6 @@ int gp102_fb_new_(const struct nvkm_fb_func *, struct nvkm_device *, int,
struct nvkm_fb **);
bool gp102_fb_vpr_scrub_required(struct nvkm_fb *);
int gp102_fb_vpr_scrub(struct nvkm_fb *);
+
+int gv100_fb_init_page(struct nvkm_fb *);
#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
index d723a9b4e3c4..ea7d66f3dd82 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
@@ -70,4 +70,5 @@ int gk104_ram_new(struct nvkm_fb *, struct nvkm_ram **);
int gm107_ram_new(struct nvkm_fb *, struct nvkm_ram **);
int gm200_ram_new(struct nvkm_fb *, struct nvkm_ram **);
int gp100_ram_new(struct nvkm_fb *, struct nvkm_ram **);
+int ga102_ram_new(struct nvkm_fb *, struct nvkm_ram **);
#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramga102.c
new file mode 100644
index 000000000000..298c136cefe0
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramga102.c
@@ -0,0 +1,40 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "ram.h"
+
+#include <subdev/bios.h>
+#include <subdev/bios/init.h>
+#include <subdev/bios/rammap.h>
+
+static const struct nvkm_ram_func
+ga102_ram = {
+};
+
+int
+ga102_ram_new(struct nvkm_fb *fb, struct nvkm_ram **pram)
+{
+ struct nvkm_device *device = fb->subdev.device;
+ enum nvkm_ram_type type = nvkm_fb_bios_memtype(device->bios);
+ u32 size = nvkm_rd32(device, 0x1183a4);
+
+ return nvkm_ram_new_(&ga102_ram, fb, type, (u64)size << 20, pram);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild
index b2ad5922a1c2..efbbaa080de5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/Kbuild
@@ -5,3 +5,4 @@ nvkm-y += nvkm/subdev/gpio/nv50.o
nvkm-y += nvkm/subdev/gpio/g94.o
nvkm-y += nvkm/subdev/gpio/gf119.o
nvkm-y += nvkm/subdev/gpio/gk104.o
+nvkm-y += nvkm/subdev/gpio/ga102.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/ga102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/ga102.c
new file mode 100644
index 000000000000..62c791baf400
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gpio/ga102.c
@@ -0,0 +1,118 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+static void
+ga102_gpio_reset(struct nvkm_gpio *gpio, u8 match)
+{
+ struct nvkm_device *device = gpio->subdev.device;
+ struct nvkm_bios *bios = device->bios;
+ u8 ver, len;
+ u16 entry;
+ int ent = -1;
+
+ while ((entry = dcb_gpio_entry(bios, 0, ++ent, &ver, &len))) {
+ u32 data = nvbios_rd32(bios, entry);
+ u8 line = (data & 0x0000003f);
+ u8 defs = !!(data & 0x00000080);
+ u8 func = (data & 0x0000ff00) >> 8;
+ u8 unk0 = (data & 0x00ff0000) >> 16;
+ u8 unk1 = (data & 0x1f000000) >> 24;
+
+ if ( func == DCB_GPIO_UNUSED ||
+ (match != DCB_GPIO_UNUSED && match != func))
+ continue;
+
+ nvkm_gpio_set(gpio, 0, func, line, defs);
+
+ nvkm_mask(device, 0x021200 + (line * 4), 0xff, unk0);
+ if (unk1--)
+ nvkm_mask(device, 0x00d740 + (unk1 * 4), 0xff, line);
+ }
+}
+
+static int
+ga102_gpio_drive(struct nvkm_gpio *gpio, int line, int dir, int out)
+{
+ struct nvkm_device *device = gpio->subdev.device;
+ u32 data = ((dir ^ 1) << 13) | (out << 12);
+ nvkm_mask(device, 0x021200 + (line * 4), 0x00003000, data);
+ nvkm_mask(device, 0x00d604, 0x00000001, 0x00000001); /* update? */
+ return 0;
+}
+
+static int
+ga102_gpio_sense(struct nvkm_gpio *gpio, int line)
+{
+ struct nvkm_device *device = gpio->subdev.device;
+ return !!(nvkm_rd32(device, 0x021200 + (line * 4)) & 0x00004000);
+}
+
+static void
+ga102_gpio_intr_stat(struct nvkm_gpio *gpio, u32 *hi, u32 *lo)
+{
+ struct nvkm_device *device = gpio->subdev.device;
+ u32 intr0 = nvkm_rd32(device, 0x021640);
+ u32 intr1 = nvkm_rd32(device, 0x02164c);
+ u32 stat0 = nvkm_rd32(device, 0x021648) & intr0;
+ u32 stat1 = nvkm_rd32(device, 0x021654) & intr1;
+ *lo = (stat1 & 0xffff0000) | (stat0 >> 16);
+ *hi = (stat1 << 16) | (stat0 & 0x0000ffff);
+ nvkm_wr32(device, 0x021640, intr0);
+ nvkm_wr32(device, 0x02164c, intr1);
+}
+
+static void
+ga102_gpio_intr_mask(struct nvkm_gpio *gpio, u32 type, u32 mask, u32 data)
+{
+ struct nvkm_device *device = gpio->subdev.device;
+ u32 inte0 = nvkm_rd32(device, 0x021648);
+ u32 inte1 = nvkm_rd32(device, 0x021654);
+ if (type & NVKM_GPIO_LO)
+ inte0 = (inte0 & ~(mask << 16)) | (data << 16);
+ if (type & NVKM_GPIO_HI)
+ inte0 = (inte0 & ~(mask & 0xffff)) | (data & 0xffff);
+ mask >>= 16;
+ data >>= 16;
+ if (type & NVKM_GPIO_LO)
+ inte1 = (inte1 & ~(mask << 16)) | (data << 16);
+ if (type & NVKM_GPIO_HI)
+ inte1 = (inte1 & ~mask) | data;
+ nvkm_wr32(device, 0x021648, inte0);
+ nvkm_wr32(device, 0x021654, inte1);
+}
+
+static const struct nvkm_gpio_func
+ga102_gpio = {
+ .lines = 32,
+ .intr_stat = ga102_gpio_intr_stat,
+ .intr_mask = ga102_gpio_intr_mask,
+ .drive = ga102_gpio_drive,
+ .sense = ga102_gpio_sense,
+ .reset = ga102_gpio_reset,
+};
+
+int
+ga102_gpio_new(struct nvkm_device *device, int index, struct nvkm_gpio **pgpio)
+{
+ return nvkm_gpio_new_(&ga102_gpio, device, index, pgpio);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild
index 723d0284caef..819703913a00 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/Kbuild
@@ -7,6 +7,7 @@ nvkm-y += nvkm/subdev/i2c/g94.o
nvkm-y += nvkm/subdev/i2c/gf117.o
nvkm-y += nvkm/subdev/i2c/gf119.o
nvkm-y += nvkm/subdev/i2c/gk104.o
+nvkm-y += nvkm/subdev/i2c/gk110.o
nvkm-y += nvkm/subdev/i2c/gm200.o
nvkm-y += nvkm/subdev/i2c/pad.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.h b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.h
index 30b48896965e..f920eabf8628 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/aux.h
@@ -3,6 +3,13 @@
#define __NVKM_I2C_AUX_H__
#include "pad.h"
+static inline void
+nvkm_i2c_aux_autodpcd(struct nvkm_i2c *i2c, int aux, bool enable)
+{
+ if (i2c->func->aux_autodpcd)
+ i2c->func->aux_autodpcd(i2c, aux, false);
+}
+
struct nvkm_i2c_aux_func {
bool address_only;
int (*xfer)(struct nvkm_i2c_aux *, bool retry, u8 type,
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
index db7769cb33eb..47068f6f9c55 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxg94.c
@@ -77,7 +77,8 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
u8 type, u32 addr, u8 *data, u8 *size)
{
struct g94_i2c_aux *aux = g94_i2c_aux(obj);
- struct nvkm_device *device = aux->base.pad->i2c->subdev.device;
+ struct nvkm_i2c *i2c = aux->base.pad->i2c;
+ struct nvkm_device *device = i2c->subdev.device;
const u32 base = aux->ch * 0x50;
u32 ctrl, stat, timeout, retries = 0;
u32 xbuf[4] = {};
@@ -96,6 +97,8 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
goto out;
}
+ nvkm_i2c_aux_autodpcd(i2c, aux->ch, false);
+
if (!(type & 1)) {
memcpy(xbuf, data, *size);
for (i = 0; i < 16; i += 4) {
@@ -128,7 +131,7 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
if (!timeout--) {
AUX_ERR(&aux->base, "timeout %08x", ctrl);
ret = -EIO;
- goto out;
+ goto out_err;
}
} while (ctrl & 0x00010000);
ret = 0;
@@ -154,7 +157,8 @@ g94_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
memcpy(data, xbuf, *size);
*size = stat & 0x0000001f;
}
-
+out_err:
+ nvkm_i2c_aux_autodpcd(i2c, aux->ch, true);
out:
g94_i2c_aux_fini(aux);
return ret < 0 ? ret : (stat & 0x000f0000) >> 16;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
index edb6148cbca0..8bd1d442e465 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/auxgm200.c
@@ -33,7 +33,7 @@ static void
gm200_i2c_aux_fini(struct gm200_i2c_aux *aux)
{
struct nvkm_device *device = aux->base.pad->i2c->subdev.device;
- nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00310000, 0x00000000);
+ nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00710000, 0x00000000);
}
static int
@@ -54,10 +54,10 @@ gm200_i2c_aux_init(struct gm200_i2c_aux *aux)
AUX_ERR(&aux->base, "begin idle timeout %08x", ctrl);
return -EBUSY;
}
- } while (ctrl & 0x03010000);
+ } while (ctrl & 0x07010000);
/* set some magic, and wait up to 1ms for it to appear */
- nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00300000, ureq);
+ nvkm_mask(device, 0x00d954 + (aux->ch * 0x50), 0x00700000, ureq);
timeout = 1000;
do {
ctrl = nvkm_rd32(device, 0x00d954 + (aux->ch * 0x50));
@@ -67,7 +67,7 @@ gm200_i2c_aux_init(struct gm200_i2c_aux *aux)
gm200_i2c_aux_fini(aux);
return -EBUSY;
}
- } while ((ctrl & 0x03000000) != urep);
+ } while ((ctrl & 0x07000000) != urep);
return 0;
}
@@ -77,7 +77,8 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
u8 type, u32 addr, u8 *data, u8 *size)
{
struct gm200_i2c_aux *aux = gm200_i2c_aux(obj);
- struct nvkm_device *device = aux->base.pad->i2c->subdev.device;
+ struct nvkm_i2c *i2c = aux->base.pad->i2c;
+ struct nvkm_device *device = i2c->subdev.device;
const u32 base = aux->ch * 0x50;
u32 ctrl, stat, timeout, retries = 0;
u32 xbuf[4] = {};
@@ -96,6 +97,8 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
goto out;
}
+ nvkm_i2c_aux_autodpcd(i2c, aux->ch, false);
+
if (!(type & 1)) {
memcpy(xbuf, data, *size);
for (i = 0; i < 16; i += 4) {
@@ -128,7 +131,7 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
if (!timeout--) {
AUX_ERR(&aux->base, "timeout %08x", ctrl);
ret = -EIO;
- goto out;
+ goto out_err;
}
} while (ctrl & 0x00010000);
ret = 0;
@@ -155,6 +158,8 @@ gm200_i2c_aux_xfer(struct nvkm_i2c_aux *obj, bool retry,
*size = stat & 0x0000001f;
}
+out_err:
+ nvkm_i2c_aux_autodpcd(i2c, aux->ch, true);
out:
gm200_i2c_aux_fini(aux);
return ret < 0 ? ret : (stat & 0x000f0000) >> 16;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gk110.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gk110.c
new file mode 100644
index 000000000000..8e3bfa1af52a
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gk110.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+#include "pad.h"
+
+static void
+gk110_aux_autodpcd(struct nvkm_i2c *i2c, int aux, bool enable)
+{
+ nvkm_mask(i2c->subdev.device, 0x00e4f8 + (aux * 0x50), 0x00010000, enable << 16);
+}
+
+static const struct nvkm_i2c_func
+gk110_i2c = {
+ .pad_x_new = gf119_i2c_pad_x_new,
+ .pad_s_new = gf119_i2c_pad_s_new,
+ .aux = 4,
+ .aux_stat = gk104_aux_stat,
+ .aux_mask = gk104_aux_mask,
+ .aux_autodpcd = gk110_aux_autodpcd,
+};
+
+int
+gk110_i2c_new(struct nvkm_device *device, int index, struct nvkm_i2c **pi2c)
+{
+ return nvkm_i2c_new_(&gk110_i2c, device, index, pi2c);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gm200.c
index a23c5f315221..7b2375bff8a9 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gm200.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/gm200.c
@@ -24,6 +24,12 @@
#include "priv.h"
#include "pad.h"
+static void
+gm200_aux_autodpcd(struct nvkm_i2c *i2c, int aux, bool enable)
+{
+ nvkm_mask(i2c->subdev.device, 0x00d968 + (aux * 0x50), 0x00010000, enable << 16);
+}
+
static const struct nvkm_i2c_func
gm200_i2c = {
.pad_x_new = gf119_i2c_pad_x_new,
@@ -31,6 +37,7 @@ gm200_i2c = {
.aux = 8,
.aux_stat = gk104_aux_stat,
.aux_mask = gk104_aux_mask,
+ .aux_autodpcd = gm200_aux_autodpcd,
};
int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/pad.h b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/pad.h
index 461016814f4f..44b7bb7d4777 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/pad.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/pad.h
@@ -1,7 +1,7 @@
/* SPDX-License-Identifier: MIT */
#ifndef __NVKM_I2C_PAD_H__
#define __NVKM_I2C_PAD_H__
-#include <subdev/i2c.h>
+#include "priv.h"
struct nvkm_i2c_pad {
const struct nvkm_i2c_pad_func *func;
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/priv.h
index bd86bc298ebe..e35f6036fcfc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/i2c/priv.h
@@ -23,6 +23,10 @@ struct nvkm_i2c_func {
/* mask on/off interrupt types for a given set of auxch
*/
void (*aux_mask)(struct nvkm_i2c *, u32, u32, u32);
+
+ /* enable/disable HW-initiated DPCD reads
+ */
+ void (*aux_autodpcd)(struct nvkm_i2c *, int aux, bool enable);
};
void g94_aux_stat(struct nvkm_i2c *, u32 *, u32 *, u32 *, u32 *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c
index 2340040942c9..1115376bc85f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gf100.c
@@ -22,6 +22,7 @@
* Authors: Ben Skeggs
*/
#include "priv.h"
+#include <subdev/timer.h>
static void
gf100_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
@@ -31,7 +32,6 @@ gf100_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
u32 data = nvkm_rd32(device, 0x122124 + (i * 0x0400));
u32 stat = nvkm_rd32(device, 0x122128 + (i * 0x0400));
nvkm_debug(ibus, "HUB%d: %06x %08x (%08x)\n", i, addr, data, stat);
- nvkm_mask(device, 0x122128 + (i * 0x0400), 0x00000200, 0x00000000);
}
static void
@@ -42,7 +42,6 @@ gf100_ibus_intr_rop(struct nvkm_subdev *ibus, int i)
u32 data = nvkm_rd32(device, 0x124124 + (i * 0x0400));
u32 stat = nvkm_rd32(device, 0x124128 + (i * 0x0400));
nvkm_debug(ibus, "ROP%d: %06x %08x (%08x)\n", i, addr, data, stat);
- nvkm_mask(device, 0x124128 + (i * 0x0400), 0x00000200, 0x00000000);
}
static void
@@ -53,7 +52,6 @@ gf100_ibus_intr_gpc(struct nvkm_subdev *ibus, int i)
u32 data = nvkm_rd32(device, 0x128124 + (i * 0x0400));
u32 stat = nvkm_rd32(device, 0x128128 + (i * 0x0400));
nvkm_debug(ibus, "GPC%d: %06x %08x (%08x)\n", i, addr, data, stat);
- nvkm_mask(device, 0x128128 + (i * 0x0400), 0x00000200, 0x00000000);
}
void
@@ -90,6 +88,12 @@ gf100_ibus_intr(struct nvkm_subdev *ibus)
intr1 &= ~stat;
}
}
+
+ nvkm_mask(device, 0x121c4c, 0x0000003f, 0x00000002);
+ nvkm_msec(device, 2000,
+ if (!(nvkm_rd32(device, 0x121c4c) & 0x0000003f))
+ break;
+ );
}
static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c
index f3915f85838e..22e487b493ad 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk104.c
@@ -22,6 +22,7 @@
* Authors: Ben Skeggs
*/
#include "priv.h"
+#include <subdev/timer.h>
static void
gk104_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
@@ -31,7 +32,6 @@ gk104_ibus_intr_hub(struct nvkm_subdev *ibus, int i)
u32 data = nvkm_rd32(device, 0x122124 + (i * 0x0800));
u32 stat = nvkm_rd32(device, 0x122128 + (i * 0x0800));
nvkm_debug(ibus, "HUB%d: %06x %08x (%08x)\n", i, addr, data, stat);
- nvkm_mask(device, 0x122128 + (i * 0x0800), 0x00000200, 0x00000000);
}
static void
@@ -42,7 +42,6 @@ gk104_ibus_intr_rop(struct nvkm_subdev *ibus, int i)
u32 data = nvkm_rd32(device, 0x124124 + (i * 0x0800));
u32 stat = nvkm_rd32(device, 0x124128 + (i * 0x0800));
nvkm_debug(ibus, "ROP%d: %06x %08x (%08x)\n", i, addr, data, stat);
- nvkm_mask(device, 0x124128 + (i * 0x0800), 0x00000200, 0x00000000);
}
static void
@@ -53,7 +52,6 @@ gk104_ibus_intr_gpc(struct nvkm_subdev *ibus, int i)
u32 data = nvkm_rd32(device, 0x128124 + (i * 0x0800));
u32 stat = nvkm_rd32(device, 0x128128 + (i * 0x0800));
nvkm_debug(ibus, "GPC%d: %06x %08x (%08x)\n", i, addr, data, stat);
- nvkm_mask(device, 0x128128 + (i * 0x0800), 0x00000200, 0x00000000);
}
void
@@ -90,6 +88,12 @@ gk104_ibus_intr(struct nvkm_subdev *ibus)
intr1 &= ~stat;
}
}
+
+ nvkm_mask(device, 0x12004c, 0x0000003f, 0x00000002);
+ nvkm_msec(device, 2000,
+ if (!(nvkm_rd32(device, 0x12004c) & 0x0000003f))
+ break;
+ );
}
static int
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
index 2585ef07532a..ac2b34e9ac6a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/Kbuild
@@ -14,3 +14,4 @@ nvkm-y += nvkm/subdev/mc/gk20a.o
nvkm-y += nvkm/subdev/mc/gp100.o
nvkm-y += nvkm/subdev/mc/gp10b.o
nvkm-y += nvkm/subdev/mc/tu102.o
+nvkm-y += nvkm/subdev/mc/ga100.o
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mc/ga100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/ga100.c
new file mode 100644
index 000000000000..967eb3af11eb
--- /dev/null
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mc/ga100.c
@@ -0,0 +1,74 @@
+/*
+ * Copyright 2021 Red Hat Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#include "priv.h"
+
+static void
+ga100_mc_intr_unarm(struct nvkm_mc *mc)
+{
+ nvkm_wr32(mc->subdev.device, 0xb81610, 0x00000004);
+}
+
+static void
+ga100_mc_intr_rearm(struct nvkm_mc *mc)
+{
+ nvkm_wr32(mc->subdev.device, 0xb81608, 0x00000004);
+}
+
+static void
+ga100_mc_intr_mask(struct nvkm_mc *mc, u32 mask, u32 intr)
+{
+ nvkm_wr32(mc->subdev.device, 0xb81210, mask & intr );
+ nvkm_wr32(mc->subdev.device, 0xb81410, mask & ~(mask & intr));
+}
+
+static u32
+ga100_mc_intr_stat(struct nvkm_mc *mc)
+{
+ u32 intr_top = nvkm_rd32(mc->subdev.device, 0xb81600), intr = 0x00000000;
+ if (intr_top & 0x00000004)
+ intr = nvkm_mask(mc->subdev.device, 0xb81010, 0x00000000, 0x00000000);
+ return intr;
+}
+
+static void
+ga100_mc_init(struct nvkm_mc *mc)
+{
+ nv50_mc_init(mc);
+ nvkm_wr32(mc->subdev.device, 0xb81210, 0xffffffff);
+}
+
+static const struct nvkm_mc_func
+ga100_mc = {
+ .init = ga100_mc_init,
+ .intr = gp100_mc_intr,
+ .intr_unarm = ga100_mc_intr_unarm,
+ .intr_rearm = ga100_mc_intr_rearm,
+ .intr_mask = ga100_mc_intr_mask,
+ .intr_stat = ga100_mc_intr_stat,
+ .reset = gk104_mc_reset,
+};
+
+int
+ga100_mc_new(struct nvkm_device *device, int index, struct nvkm_mc **pmc)
+{
+ return nvkm_mc_new_(&ga100_mc, device, index, pmc);
+}
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
index de91e9a26172..6d5212ae2fd5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/base.c
@@ -316,9 +316,9 @@ nvkm_mmu_vram(struct nvkm_mmu *mmu)
{
struct nvkm_device *device = mmu->subdev.device;
struct nvkm_mm *mm = &device->fb->ram->vram;
- const u32 sizeN = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NORMAL);
- const u32 sizeU = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NOMAP);
- const u32 sizeM = nvkm_mm_heap_size(mm, NVKM_RAM_MM_MIXED);
+ const u64 sizeN = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NORMAL);
+ const u64 sizeU = nvkm_mm_heap_size(mm, NVKM_RAM_MM_NOMAP);
+ const u64 sizeM = nvkm_mm_heap_size(mm, NVKM_RAM_MM_MIXED);
u8 type = NVKM_MEM_KIND * !!mmu->func->kind;
u8 heap = NVKM_MEM_VRAM;
int heapM, heapN, heapU;
diff --git a/drivers/gpu/drm/ttm/ttm_pool.c b/drivers/gpu/drm/ttm/ttm_pool.c
index a00b7ab9c14c..8cd776adc592 100644
--- a/drivers/gpu/drm/ttm/ttm_pool.c
+++ b/drivers/gpu/drm/ttm/ttm_pool.c
@@ -66,7 +66,7 @@ static struct ttm_pool_type global_uncached[MAX_ORDER];
static struct ttm_pool_type global_dma32_write_combined[MAX_ORDER];
static struct ttm_pool_type global_dma32_uncached[MAX_ORDER];
-static spinlock_t shrinker_lock;
+static struct mutex shrinker_lock;
static struct list_head shrinker_list;
static struct shrinker mm_shrinker;
@@ -190,7 +190,7 @@ static int ttm_pool_map(struct ttm_pool *pool, unsigned int order,
size_t size = (1ULL << order) * PAGE_SIZE;
addr = dma_map_page(pool->dev, p, 0, size, DMA_BIDIRECTIONAL);
- if (dma_mapping_error(pool->dev, **dma_addr))
+ if (dma_mapping_error(pool->dev, addr))
return -EFAULT;
}
@@ -249,9 +249,9 @@ static void ttm_pool_type_init(struct ttm_pool_type *pt, struct ttm_pool *pool,
spin_lock_init(&pt->lock);
INIT_LIST_HEAD(&pt->pages);
- spin_lock(&shrinker_lock);
+ mutex_lock(&shrinker_lock);
list_add_tail(&pt->shrinker_list, &shrinker_list);
- spin_unlock(&shrinker_lock);
+ mutex_unlock(&shrinker_lock);
}
/* Remove a pool_type from the global shrinker list and free all pages */
@@ -259,9 +259,9 @@ static void ttm_pool_type_fini(struct ttm_pool_type *pt)
{
struct page *p, *tmp;
- spin_lock(&shrinker_lock);
+ mutex_lock(&shrinker_lock);
list_del(&pt->shrinker_list);
- spin_unlock(&shrinker_lock);
+ mutex_unlock(&shrinker_lock);
list_for_each_entry_safe(p, tmp, &pt->pages, lru)
ttm_pool_free_page(pt->pool, pt->caching, pt->order, p);
@@ -302,7 +302,7 @@ static unsigned int ttm_pool_shrink(void)
unsigned int num_freed;
struct page *p;
- spin_lock(&shrinker_lock);
+ mutex_lock(&shrinker_lock);
pt = list_first_entry(&shrinker_list, typeof(*pt), shrinker_list);
p = ttm_pool_type_take(pt);
@@ -314,7 +314,7 @@ static unsigned int ttm_pool_shrink(void)
}
list_move_tail(&pt->shrinker_list, &shrinker_list);
- spin_unlock(&shrinker_lock);
+ mutex_unlock(&shrinker_lock);
return num_freed;
}
@@ -564,7 +564,7 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
{
unsigned int i;
- spin_lock(&shrinker_lock);
+ mutex_lock(&shrinker_lock);
seq_puts(m, "\t ");
for (i = 0; i < MAX_ORDER; ++i)
@@ -600,7 +600,7 @@ int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m)
seq_printf(m, "\ntotal\t: %8lu of %8lu\n",
atomic_long_read(&allocated_pages), page_pool_size);
- spin_unlock(&shrinker_lock);
+ mutex_unlock(&shrinker_lock);
return 0;
}
@@ -644,7 +644,7 @@ int ttm_pool_mgr_init(unsigned long num_pages)
if (!page_pool_size)
page_pool_size = num_pages;
- spin_lock_init(&shrinker_lock);
+ mutex_init(&shrinker_lock);
INIT_LIST_HEAD(&shrinker_list);
for (i = 0; i < MAX_ORDER; ++i) {
diff --git a/drivers/infiniband/core/cma_configfs.c b/drivers/infiniband/core/cma_configfs.c
index 7f70e5a7de10..97a77ea8d3c9 100644
--- a/drivers/infiniband/core/cma_configfs.c
+++ b/drivers/infiniband/core/cma_configfs.c
@@ -131,8 +131,10 @@ static ssize_t default_roce_mode_store(struct config_item *item,
return ret;
gid_type = ib_cache_gid_parse_type_str(buf);
- if (gid_type < 0)
+ if (gid_type < 0) {
+ cma_configfs_params_put(cma_dev);
return -EINVAL;
+ }
ret = cma_set_default_gid_type(cma_dev, group->port_num, gid_type);
diff --git a/drivers/infiniband/core/restrack.c b/drivers/infiniband/core/restrack.c
index e0a41c867002..ff1551b3cf61 100644
--- a/drivers/infiniband/core/restrack.c
+++ b/drivers/infiniband/core/restrack.c
@@ -254,6 +254,7 @@ void rdma_restrack_add(struct rdma_restrack_entry *res)
} else {
ret = xa_alloc_cyclic(&rt->xa, &res->id, res, xa_limit_32b,
&rt->next_id, GFP_KERNEL);
+ ret = (ret < 0) ? ret : 0;
}
out:
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 7dab9a27a145..da2512c30ffd 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -95,8 +95,6 @@ struct ucma_context {
u64 uid;
struct list_head list;
- /* sync between removal event and id destroy, protected by file mut */
- int destroying;
struct work_struct close_work;
};
@@ -122,7 +120,7 @@ static DEFINE_XARRAY_ALLOC(ctx_table);
static DEFINE_XARRAY_ALLOC(multicast_table);
static const struct file_operations ucma_fops;
-static int __destroy_id(struct ucma_context *ctx);
+static int ucma_destroy_private_ctx(struct ucma_context *ctx);
static inline struct ucma_context *_ucma_find_context(int id,
struct ucma_file *file)
@@ -179,19 +177,14 @@ static void ucma_close_id(struct work_struct *work)
/* once all inflight tasks are finished, we close all underlying
* resources. The context is still alive till its explicit destryoing
- * by its creator.
+ * by its creator. This puts back the xarray's reference.
*/
ucma_put_ctx(ctx);
wait_for_completion(&ctx->comp);
/* No new events will be generated after destroying the id. */
rdma_destroy_id(ctx->cm_id);
- /*
- * At this point ctx->ref is zero so the only place the ctx can be is in
- * a uevent or in __destroy_id(). Since the former doesn't touch
- * ctx->cm_id and the latter sync cancels this, there is no races with
- * this store.
- */
+ /* Reading the cm_id without holding a positive ref is not allowed */
ctx->cm_id = NULL;
}
@@ -204,7 +197,6 @@ static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file)
return NULL;
INIT_WORK(&ctx->close_work, ucma_close_id);
- refcount_set(&ctx->ref, 1);
init_completion(&ctx->comp);
/* So list_del() will work if we don't do ucma_finish_ctx() */
INIT_LIST_HEAD(&ctx->list);
@@ -218,6 +210,13 @@ static struct ucma_context *ucma_alloc_ctx(struct ucma_file *file)
return ctx;
}
+static void ucma_set_ctx_cm_id(struct ucma_context *ctx,
+ struct rdma_cm_id *cm_id)
+{
+ refcount_set(&ctx->ref, 1);
+ ctx->cm_id = cm_id;
+}
+
static void ucma_finish_ctx(struct ucma_context *ctx)
{
lockdep_assert_held(&ctx->file->mut);
@@ -303,7 +302,7 @@ static int ucma_connect_event_handler(struct rdma_cm_id *cm_id,
ctx = ucma_alloc_ctx(listen_ctx->file);
if (!ctx)
goto err_backlog;
- ctx->cm_id = cm_id;
+ ucma_set_ctx_cm_id(ctx, cm_id);
uevent = ucma_create_uevent(listen_ctx, event);
if (!uevent)
@@ -321,8 +320,7 @@ static int ucma_connect_event_handler(struct rdma_cm_id *cm_id,
return 0;
err_alloc:
- xa_erase(&ctx_table, ctx->id);
- kfree(ctx);
+ ucma_destroy_private_ctx(ctx);
err_backlog:
atomic_inc(&listen_ctx->backlog);
/* Returning error causes the new ID to be destroyed */
@@ -356,8 +354,12 @@ static int ucma_event_handler(struct rdma_cm_id *cm_id,
wake_up_interruptible(&ctx->file->poll_wait);
}
- if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL && !ctx->destroying)
- queue_work(system_unbound_wq, &ctx->close_work);
+ if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) {
+ xa_lock(&ctx_table);
+ if (xa_load(&ctx_table, ctx->id) == ctx)
+ queue_work(system_unbound_wq, &ctx->close_work);
+ xa_unlock(&ctx_table);
+ }
return 0;
}
@@ -461,13 +463,12 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf,
ret = PTR_ERR(cm_id);
goto err1;
}
- ctx->cm_id = cm_id;
+ ucma_set_ctx_cm_id(ctx, cm_id);
resp.id = ctx->id;
if (copy_to_user(u64_to_user_ptr(cmd.response),
&resp, sizeof(resp))) {
- xa_erase(&ctx_table, ctx->id);
- __destroy_id(ctx);
+ ucma_destroy_private_ctx(ctx);
return -EFAULT;
}
@@ -477,8 +478,7 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf,
return 0;
err1:
- xa_erase(&ctx_table, ctx->id);
- kfree(ctx);
+ ucma_destroy_private_ctx(ctx);
return ret;
}
@@ -516,68 +516,73 @@ static void ucma_cleanup_mc_events(struct ucma_multicast *mc)
rdma_unlock_handler(mc->ctx->cm_id);
}
-/*
- * ucma_free_ctx is called after the underlying rdma CM-ID is destroyed. At
- * this point, no new events will be reported from the hardware. However, we
- * still need to cleanup the UCMA context for this ID. Specifically, there
- * might be events that have not yet been consumed by the user space software.
- * mutex. After that we release them as needed.
- */
-static int ucma_free_ctx(struct ucma_context *ctx)
+static int ucma_cleanup_ctx_events(struct ucma_context *ctx)
{
int events_reported;
struct ucma_event *uevent, *tmp;
LIST_HEAD(list);
- ucma_cleanup_multicast(ctx);
-
- /* Cleanup events not yet reported to the user. */
+ /* Cleanup events not yet reported to the user.*/
mutex_lock(&ctx->file->mut);
list_for_each_entry_safe(uevent, tmp, &ctx->file->event_list, list) {
- if (uevent->ctx == ctx || uevent->conn_req_ctx == ctx)
+ if (uevent->ctx != ctx)
+ continue;
+
+ if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST &&
+ xa_cmpxchg(&ctx_table, uevent->conn_req_ctx->id,
+ uevent->conn_req_ctx, XA_ZERO_ENTRY,
+ GFP_KERNEL) == uevent->conn_req_ctx) {
list_move_tail(&uevent->list, &list);
+ continue;
+ }
+ list_del(&uevent->list);
+ kfree(uevent);
}
list_del(&ctx->list);
events_reported = ctx->events_reported;
mutex_unlock(&ctx->file->mut);
/*
- * If this was a listening ID then any connections spawned from it
- * that have not been delivered to userspace are cleaned up too.
- * Must be done outside any locks.
+ * If this was a listening ID then any connections spawned from it that
+ * have not been delivered to userspace are cleaned up too. Must be done
+ * outside any locks.
*/
list_for_each_entry_safe(uevent, tmp, &list, list) {
- list_del(&uevent->list);
- if (uevent->resp.event == RDMA_CM_EVENT_CONNECT_REQUEST &&
- uevent->conn_req_ctx != ctx)
- __destroy_id(uevent->conn_req_ctx);
+ ucma_destroy_private_ctx(uevent->conn_req_ctx);
kfree(uevent);
}
-
- mutex_destroy(&ctx->mutex);
- kfree(ctx);
return events_reported;
}
-static int __destroy_id(struct ucma_context *ctx)
+/*
+ * When this is called the xarray must have a XA_ZERO_ENTRY in the ctx->id (ie
+ * the ctx is not public to the user). This either because:
+ * - ucma_finish_ctx() hasn't been called
+ * - xa_cmpxchg() succeed to remove the entry (only one thread can succeed)
+ */
+static int ucma_destroy_private_ctx(struct ucma_context *ctx)
{
+ int events_reported;
+
/*
- * If the refcount is already 0 then ucma_close_id() has already
- * destroyed the cm_id, otherwise holding the refcount keeps cm_id
- * valid. Prevent queue_work() from being called.
+ * Destroy the underlying cm_id. New work queuing is prevented now by
+ * the removal from the xarray. Once the work is cancled ref will either
+ * be 0 because the work ran to completion and consumed the ref from the
+ * xarray, or it will be positive because we still have the ref from the
+ * xarray. This can also be 0 in cases where cm_id was never set
*/
- if (refcount_inc_not_zero(&ctx->ref)) {
- rdma_lock_handler(ctx->cm_id);
- ctx->destroying = 1;
- rdma_unlock_handler(ctx->cm_id);
- ucma_put_ctx(ctx);
- }
-
cancel_work_sync(&ctx->close_work);
- /* At this point it's guaranteed that there is no inflight closing task */
- if (ctx->cm_id)
+ if (refcount_read(&ctx->ref))
ucma_close_id(&ctx->close_work);
- return ucma_free_ctx(ctx);
+
+ events_reported = ucma_cleanup_ctx_events(ctx);
+ ucma_cleanup_multicast(ctx);
+
+ WARN_ON(xa_cmpxchg(&ctx_table, ctx->id, XA_ZERO_ENTRY, NULL,
+ GFP_KERNEL) != NULL);
+ mutex_destroy(&ctx->mutex);
+ kfree(ctx);
+ return events_reported;
}
static ssize_t ucma_destroy_id(struct ucma_file *file, const char __user *inbuf,
@@ -596,14 +601,17 @@ static ssize_t ucma_destroy_id(struct ucma_file *file, const char __user *inbuf,
xa_lock(&ctx_table);
ctx = _ucma_find_context(cmd.id, file);
- if (!IS_ERR(ctx))
- __xa_erase(&ctx_table, ctx->id);
+ if (!IS_ERR(ctx)) {
+ if (__xa_cmpxchg(&ctx_table, ctx->id, ctx, XA_ZERO_ENTRY,
+ GFP_KERNEL) != ctx)
+ ctx = ERR_PTR(-ENOENT);
+ }
xa_unlock(&ctx_table);
if (IS_ERR(ctx))
return PTR_ERR(ctx);
- resp.events_reported = __destroy_id(ctx);
+ resp.events_reported = ucma_destroy_private_ctx(ctx);
if (copy_to_user(u64_to_user_ptr(cmd.response),
&resp, sizeof(resp)))
ret = -EFAULT;
@@ -1777,15 +1785,16 @@ static int ucma_close(struct inode *inode, struct file *filp)
* prevented by this being a FD release function. The list_add_tail() in
* ucma_connect_event_handler() can run concurrently, however it only
* adds to the list *after* a listening ID. By only reading the first of
- * the list, and relying on __destroy_id() to block
+ * the list, and relying on ucma_destroy_private_ctx() to block
* ucma_connect_event_handler(), no additional locking is needed.
*/
while (!list_empty(&file->ctx_list)) {
struct ucma_context *ctx = list_first_entry(
&file->ctx_list, struct ucma_context, list);
- xa_erase(&ctx_table, ctx->id);
- __destroy_id(ctx);
+ WARN_ON(xa_cmpxchg(&ctx_table, ctx->id, ctx, XA_ZERO_ENTRY,
+ GFP_KERNEL) != ctx);
+ ucma_destroy_private_ctx(ctx);
}
kfree(file);
return 0;
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 7ca4112e3e8f..917338db7ac1 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -135,7 +135,7 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
*/
if (mask)
pgsz_bitmap &= GENMASK(count_trailing_zeros(mask), 0);
- return rounddown_pow_of_two(pgsz_bitmap);
+ return pgsz_bitmap ? rounddown_pow_of_two(pgsz_bitmap) : 0;
}
EXPORT_SYMBOL(ib_umem_find_best_pgsz);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 3bae9ba0ead8..d26f3f3e0462 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3956,7 +3956,7 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
err = set_has_smi_cap(dev);
if (err)
- return err;
+ goto err_mp;
if (!mlx5_core_mp_enabled(mdev)) {
for (i = 1; i <= dev->num_ports; i++) {
@@ -4319,7 +4319,7 @@ static int mlx5_ib_stage_bfrag_init(struct mlx5_ib_dev *dev)
err = mlx5_alloc_bfreg(dev->mdev, &dev->fp_bfreg, false, true);
if (err)
- mlx5_free_bfreg(dev->mdev, &dev->fp_bfreg);
+ mlx5_free_bfreg(dev->mdev, &dev->bfreg);
return err;
}
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index bc98bd950d99..3acb5c10b155 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -434,9 +434,9 @@ static void ocrdma_dealloc_ucontext_pd(struct ocrdma_ucontext *uctx)
pr_err("%s(%d) Freeing in use pdid=0x%x.\n",
__func__, dev->id, pd->id);
}
- kfree(uctx->cntxt_pd);
uctx->cntxt_pd = NULL;
_ocrdma_dealloc_pd(dev, pd);
+ kfree(pd);
}
static struct ocrdma_pd *ocrdma_get_ucontext_pd(struct ocrdma_ucontext *uctx)
diff --git a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
index 38a37770c016..3705c6b8b223 100644
--- a/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
+++ b/drivers/infiniband/hw/usnic/usnic_ib_verbs.c
@@ -214,6 +214,7 @@ find_free_vf_and_create_qp_grp(struct usnic_ib_dev *us_ibdev,
}
usnic_uiom_free_dev_list(dev_list);
+ dev_list = NULL;
}
/* Try to find resources on an unused vf */
@@ -239,6 +240,8 @@ find_free_vf_and_create_qp_grp(struct usnic_ib_dev *us_ibdev,
qp_grp_check:
if (IS_ERR_OR_NULL(qp_grp)) {
usnic_err("Failed to allocate qp_grp\n");
+ if (usnic_ib_share_vf)
+ usnic_uiom_free_dev_list(dev_list);
return ERR_PTR(qp_grp ? PTR_ERR(qp_grp) : -ENOMEM);
}
return qp_grp;
diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
index 1b83d140742f..bcda17012aee 100644
--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
@@ -325,7 +325,9 @@ static struct arm_smmu_device *qcom_smmu_create(struct arm_smmu_device *smmu,
}
static const struct of_device_id __maybe_unused qcom_smmu_impl_of_match[] = {
+ { .compatible = "qcom,msm8998-smmu-v2" },
{ .compatible = "qcom,sc7180-smmu-500" },
+ { .compatible = "qcom,sdm630-smmu-v2" },
{ .compatible = "qcom,sdm845-smmu-500" },
{ .compatible = "qcom,sm8150-smmu-500" },
{ .compatible = "qcom,sm8250-smmu-500" },
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 65cf06d70bf4..f665322a0991 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -38,7 +38,6 @@
#include <linux/dmi.h>
#include <linux/pci-ats.h>
#include <linux/memblock.h>
-#include <linux/dma-map-ops.h>
#include <linux/dma-direct.h>
#include <linux/crash_dump.h>
#include <linux/numa.h>
diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index 790ef3497e7e..18a9f05df407 100644
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -118,8 +118,10 @@ void intel_svm_check(struct intel_iommu *iommu)
iommu->flags |= VTD_FLAG_SVM_CAPABLE;
}
-static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_dev *sdev,
- unsigned long address, unsigned long pages, int ih)
+static void __flush_svm_range_dev(struct intel_svm *svm,
+ struct intel_svm_dev *sdev,
+ unsigned long address,
+ unsigned long pages, int ih)
{
struct qi_desc desc;
@@ -170,6 +172,22 @@ static void intel_flush_svm_range_dev (struct intel_svm *svm, struct intel_svm_d
}
}
+static void intel_flush_svm_range_dev(struct intel_svm *svm,
+ struct intel_svm_dev *sdev,
+ unsigned long address,
+ unsigned long pages, int ih)
+{
+ unsigned long shift = ilog2(__roundup_pow_of_two(pages));
+ unsigned long align = (1ULL << (VTD_PAGE_SHIFT + shift));
+ unsigned long start = ALIGN_DOWN(address, align);
+ unsigned long end = ALIGN(address + (pages << VTD_PAGE_SHIFT), align);
+
+ while (start < end) {
+ __flush_svm_range_dev(svm, sdev, start, align >> VTD_PAGE_SHIFT, ih);
+ start += align;
+ }
+}
+
static void intel_flush_svm_range(struct intel_svm *svm, unsigned long address,
unsigned long pages, int ih)
{
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index b7e2d9666614..9e44c09f6410 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -605,6 +605,7 @@ config DM_INTEGRITY
select BLK_DEV_INTEGRITY
select DM_BUFIO
select CRYPTO
+ select CRYPTO_SKCIPHER
select ASYNC_XOR
help
This device-mapper target emulates a block device that has
@@ -622,6 +623,7 @@ config DM_ZONED
tristate "Drive-managed zoned block device target support"
depends on BLK_DEV_DM
depends on BLK_DEV_ZONED
+ select CRC32
help
This device-mapper target takes a host-managed or host-aware zoned
block device and exposes most of its capacity as a regular block
diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c
index 9c1a86bde658..fce4cbf9529d 100644
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -1534,6 +1534,12 @@ sector_t dm_bufio_get_device_size(struct dm_bufio_client *c)
}
EXPORT_SYMBOL_GPL(dm_bufio_get_device_size);
+struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c)
+{
+ return c->dm_io;
+}
+EXPORT_SYMBOL_GPL(dm_bufio_get_dm_io_client);
+
sector_t dm_bufio_get_block_number(struct dm_buffer *b)
{
return b->block;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 53791138d78b..8c874710f0bc 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1454,13 +1454,16 @@ static int crypt_convert_block_skcipher(struct crypt_config *cc,
static void kcryptd_async_done(struct crypto_async_request *async_req,
int error);
-static void crypt_alloc_req_skcipher(struct crypt_config *cc,
+static int crypt_alloc_req_skcipher(struct crypt_config *cc,
struct convert_context *ctx)
{
unsigned key_index = ctx->cc_sector & (cc->tfms_count - 1);
- if (!ctx->r.req)
- ctx->r.req = mempool_alloc(&cc->req_pool, GFP_NOIO);
+ if (!ctx->r.req) {
+ ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO);
+ if (!ctx->r.req)
+ return -ENOMEM;
+ }
skcipher_request_set_tfm(ctx->r.req, cc->cipher_tfm.tfms[key_index]);
@@ -1471,13 +1474,18 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc,
skcipher_request_set_callback(ctx->r.req,
CRYPTO_TFM_REQ_MAY_BACKLOG,
kcryptd_async_done, dmreq_of_req(cc, ctx->r.req));
+
+ return 0;
}
-static void crypt_alloc_req_aead(struct crypt_config *cc,
+static int crypt_alloc_req_aead(struct crypt_config *cc,
struct convert_context *ctx)
{
- if (!ctx->r.req_aead)
- ctx->r.req_aead = mempool_alloc(&cc->req_pool, GFP_NOIO);
+ if (!ctx->r.req) {
+ ctx->r.req = mempool_alloc(&cc->req_pool, in_interrupt() ? GFP_ATOMIC : GFP_NOIO);
+ if (!ctx->r.req)
+ return -ENOMEM;
+ }
aead_request_set_tfm(ctx->r.req_aead, cc->cipher_tfm.tfms_aead[0]);
@@ -1488,15 +1496,17 @@ static void crypt_alloc_req_aead(struct crypt_config *cc,
aead_request_set_callback(ctx->r.req_aead,
CRYPTO_TFM_REQ_MAY_BACKLOG,
kcryptd_async_done, dmreq_of_req(cc, ctx->r.req_aead));
+
+ return 0;
}
-static void crypt_alloc_req(struct crypt_config *cc,
+static int crypt_alloc_req(struct crypt_config *cc,
struct convert_context *ctx)
{
if (crypt_integrity_aead(cc))
- crypt_alloc_req_aead(cc, ctx);
+ return crypt_alloc_req_aead(cc, ctx);
else
- crypt_alloc_req_skcipher(cc, ctx);
+ return crypt_alloc_req_skcipher(cc, ctx);
}
static void crypt_free_req_skcipher(struct crypt_config *cc,
@@ -1529,17 +1539,28 @@ static void crypt_free_req(struct crypt_config *cc, void *req, struct bio *base_
* Encrypt / decrypt data from one bio to another one (can be the same one)
*/
static blk_status_t crypt_convert(struct crypt_config *cc,
- struct convert_context *ctx, bool atomic)
+ struct convert_context *ctx, bool atomic, bool reset_pending)
{
unsigned int tag_offset = 0;
unsigned int sector_step = cc->sector_size >> SECTOR_SHIFT;
int r;
- atomic_set(&ctx->cc_pending, 1);
+ /*
+ * if reset_pending is set we are dealing with the bio for the first time,
+ * else we're continuing to work on the previous bio, so don't mess with
+ * the cc_pending counter
+ */
+ if (reset_pending)
+ atomic_set(&ctx->cc_pending, 1);
while (ctx->iter_in.bi_size && ctx->iter_out.bi_size) {
- crypt_alloc_req(cc, ctx);
+ r = crypt_alloc_req(cc, ctx);
+ if (r) {
+ complete(&ctx->restart);
+ return BLK_STS_DEV_RESOURCE;
+ }
+
atomic_inc(&ctx->cc_pending);
if (crypt_integrity_aead(cc))
@@ -1553,7 +1574,25 @@ static blk_status_t crypt_convert(struct crypt_config *cc,
* but the driver request queue is full, let's wait.
*/
case -EBUSY:
- wait_for_completion(&ctx->restart);
+ if (in_interrupt()) {
+ if (try_wait_for_completion(&ctx->restart)) {
+ /*
+ * we don't have to block to wait for completion,
+ * so proceed
+ */
+ } else {
+ /*
+ * we can't wait for completion without blocking
+ * exit and continue processing in a workqueue
+ */
+ ctx->r.req = NULL;
+ ctx->cc_sector += sector_step;
+ tag_offset++;
+ return BLK_STS_DEV_RESOURCE;
+ }
+ } else {
+ wait_for_completion(&ctx->restart);
+ }
reinit_completion(&ctx->restart);
fallthrough;
/*
@@ -1691,6 +1730,12 @@ static void crypt_inc_pending(struct dm_crypt_io *io)
atomic_inc(&io->io_pending);
}
+static void kcryptd_io_bio_endio(struct work_struct *work)
+{
+ struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+ bio_endio(io->base_bio);
+}
+
/*
* One of the bios was finished. Check for completion of
* the whole request and correctly clean up the buffer.
@@ -1713,7 +1758,23 @@ static void crypt_dec_pending(struct dm_crypt_io *io)
kfree(io->integrity_metadata);
base_bio->bi_status = error;
- bio_endio(base_bio);
+
+ /*
+ * If we are running this function from our tasklet,
+ * we can't call bio_endio() here, because it will call
+ * clone_endio() from dm.c, which in turn will
+ * free the current struct dm_crypt_io structure with
+ * our tasklet. In this case we need to delay bio_endio()
+ * execution to after the tasklet is done and dequeued.
+ */
+ if (tasklet_trylock(&io->tasklet)) {
+ tasklet_unlock(&io->tasklet);
+ bio_endio(base_bio);
+ return;
+ }
+
+ INIT_WORK(&io->work, kcryptd_io_bio_endio);
+ queue_work(cc->io_queue, &io->work);
}
/*
@@ -1945,6 +2006,37 @@ static bool kcryptd_crypt_write_inline(struct crypt_config *cc,
}
}
+static void kcryptd_crypt_write_continue(struct work_struct *work)
+{
+ struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+ struct crypt_config *cc = io->cc;
+ struct convert_context *ctx = &io->ctx;
+ int crypt_finished;
+ sector_t sector = io->sector;
+ blk_status_t r;
+
+ wait_for_completion(&ctx->restart);
+ reinit_completion(&ctx->restart);
+
+ r = crypt_convert(cc, &io->ctx, true, false);
+ if (r)
+ io->error = r;
+ crypt_finished = atomic_dec_and_test(&ctx->cc_pending);
+ if (!crypt_finished && kcryptd_crypt_write_inline(cc, ctx)) {
+ /* Wait for completion signaled by kcryptd_async_done() */
+ wait_for_completion(&ctx->restart);
+ crypt_finished = 1;
+ }
+
+ /* Encryption was already finished, submit io now */
+ if (crypt_finished) {
+ kcryptd_crypt_write_io_submit(io, 0);
+ io->sector = sector;
+ }
+
+ crypt_dec_pending(io);
+}
+
static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
@@ -1973,7 +2065,17 @@ static void kcryptd_crypt_write_convert(struct dm_crypt_io *io)
crypt_inc_pending(io);
r = crypt_convert(cc, ctx,
- test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags));
+ test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags), true);
+ /*
+ * Crypto API backlogged the request, because its queue was full
+ * and we're in softirq context, so continue from a workqueue
+ * (TODO: is it actually possible to be in softirq in the write path?)
+ */
+ if (r == BLK_STS_DEV_RESOURCE) {
+ INIT_WORK(&io->work, kcryptd_crypt_write_continue);
+ queue_work(cc->crypt_queue, &io->work);
+ return;
+ }
if (r)
io->error = r;
crypt_finished = atomic_dec_and_test(&ctx->cc_pending);
@@ -1998,6 +2100,25 @@ static void kcryptd_crypt_read_done(struct dm_crypt_io *io)
crypt_dec_pending(io);
}
+static void kcryptd_crypt_read_continue(struct work_struct *work)
+{
+ struct dm_crypt_io *io = container_of(work, struct dm_crypt_io, work);
+ struct crypt_config *cc = io->cc;
+ blk_status_t r;
+
+ wait_for_completion(&io->ctx.restart);
+ reinit_completion(&io->ctx.restart);
+
+ r = crypt_convert(cc, &io->ctx, true, false);
+ if (r)
+ io->error = r;
+
+ if (atomic_dec_and_test(&io->ctx.cc_pending))
+ kcryptd_crypt_read_done(io);
+
+ crypt_dec_pending(io);
+}
+
static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
{
struct crypt_config *cc = io->cc;
@@ -2009,7 +2130,16 @@ static void kcryptd_crypt_read_convert(struct dm_crypt_io *io)
io->sector);
r = crypt_convert(cc, &io->ctx,
- test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags));
+ test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags), true);
+ /*
+ * Crypto API backlogged the request, because its queue was full
+ * and we're in softirq context, so continue from a workqueue
+ */
+ if (r == BLK_STS_DEV_RESOURCE) {
+ INIT_WORK(&io->work, kcryptd_crypt_read_continue);
+ queue_work(cc->crypt_queue, &io->work);
+ return;
+ }
if (r)
io->error = r;
@@ -2091,8 +2221,12 @@ static void kcryptd_queue_crypt(struct dm_crypt_io *io)
if ((bio_data_dir(io->base_bio) == READ && test_bit(DM_CRYPT_NO_READ_WORKQUEUE, &cc->flags)) ||
(bio_data_dir(io->base_bio) == WRITE && test_bit(DM_CRYPT_NO_WRITE_WORKQUEUE, &cc->flags))) {
- if (in_irq()) {
- /* Crypto API's "skcipher_walk_first() refuses to work in hard IRQ context */
+ /*
+ * in_irq(): Crypto API's skcipher_walk_first() refuses to work in hard IRQ context.
+ * irqs_disabled(): the kernel may run some IO completion from the idle thread, but
+ * it is being executed with irqs disabled.
+ */
+ if (in_irq() || irqs_disabled()) {
tasklet_init(&io->tasklet, kcryptd_crypt_tasklet, (unsigned long)&io->work);
tasklet_schedule(&io->tasklet);
return;
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 5a7a1b90e671..81df019ab284 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -1379,12 +1379,52 @@ thorough_test:
#undef MAY_BE_HASH
}
-static void dm_integrity_flush_buffers(struct dm_integrity_c *ic)
+struct flush_request {
+ struct dm_io_request io_req;
+ struct dm_io_region io_reg;
+ struct dm_integrity_c *ic;
+ struct completion comp;
+};
+
+static void flush_notify(unsigned long error, void *fr_)
+{
+ struct flush_request *fr = fr_;
+ if (unlikely(error != 0))
+ dm_integrity_io_error(fr->ic, "flusing disk cache", -EIO);
+ complete(&fr->comp);
+}
+
+static void dm_integrity_flush_buffers(struct dm_integrity_c *ic, bool flush_data)
{
int r;
+
+ struct flush_request fr;
+
+ if (!ic->meta_dev)
+ flush_data = false;
+ if (flush_data) {
+ fr.io_req.bi_op = REQ_OP_WRITE,
+ fr.io_req.bi_op_flags = REQ_PREFLUSH | REQ_SYNC,
+ fr.io_req.mem.type = DM_IO_KMEM,
+ fr.io_req.mem.ptr.addr = NULL,
+ fr.io_req.notify.fn = flush_notify,
+ fr.io_req.notify.context = &fr;
+ fr.io_req.client = dm_bufio_get_dm_io_client(ic->bufio),
+ fr.io_reg.bdev = ic->dev->bdev,
+ fr.io_reg.sector = 0,
+ fr.io_reg.count = 0,
+ fr.ic = ic;
+ init_completion(&fr.comp);
+ r = dm_io(&fr.io_req, 1, &fr.io_reg, NULL);
+ BUG_ON(r);
+ }
+
r = dm_bufio_write_dirty_buffers(ic->bufio);
if (unlikely(r))
dm_integrity_io_error(ic, "writing tags", r);
+
+ if (flush_data)
+ wait_for_completion(&fr.comp);
}
static void sleep_on_endio_wait(struct dm_integrity_c *ic)
@@ -2110,7 +2150,7 @@ offload_to_thread:
if (unlikely(dio->op == REQ_OP_DISCARD) && likely(ic->mode != 'D')) {
integrity_metadata(&dio->work);
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, false);
dio->in_flight = (atomic_t)ATOMIC_INIT(1);
dio->completion = NULL;
@@ -2195,7 +2235,7 @@ static void integrity_commit(struct work_struct *w)
flushes = bio_list_get(&ic->flush_bio_list);
if (unlikely(ic->mode != 'J')) {
spin_unlock_irq(&ic->endio_wait.lock);
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, true);
goto release_flush_bios;
}
@@ -2409,7 +2449,7 @@ skip_io:
complete_journal_op(&comp);
wait_for_completion_io(&comp.comp);
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, true);
}
static void integrity_writer(struct work_struct *w)
@@ -2451,7 +2491,7 @@ static void recalc_write_super(struct dm_integrity_c *ic)
{
int r;
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, false);
if (dm_integrity_failed(ic))
return;
@@ -2654,7 +2694,7 @@ static void bitmap_flush_work(struct work_struct *work)
unsigned long limit;
struct bio *bio;
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, false);
range.logical_sector = 0;
range.n_sectors = ic->provided_data_sectors;
@@ -2663,9 +2703,7 @@ static void bitmap_flush_work(struct work_struct *work)
add_new_range_and_wait(ic, &range);
spin_unlock_irq(&ic->endio_wait.lock);
- dm_integrity_flush_buffers(ic);
- if (ic->meta_dev)
- blkdev_issue_flush(ic->dev->bdev, GFP_NOIO);
+ dm_integrity_flush_buffers(ic, true);
limit = ic->provided_data_sectors;
if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING)) {
@@ -2934,11 +2972,11 @@ static void dm_integrity_postsuspend(struct dm_target *ti)
if (ic->meta_dev)
queue_work(ic->writer_wq, &ic->writer_work);
drain_workqueue(ic->writer_wq);
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, true);
}
if (ic->mode == 'B') {
- dm_integrity_flush_buffers(ic);
+ dm_integrity_flush_buffers(ic, true);
#if 1
/* set to 0 to test bitmap replay code */
init_journal(ic, 0, ic->journal_sections, 0);
@@ -3754,7 +3792,7 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv)
unsigned extra_args;
struct dm_arg_set as;
static const struct dm_arg _args[] = {
- {0, 9, "Invalid number of feature args"},
+ {0, 15, "Invalid number of feature args"},
};
unsigned journal_sectors, interleave_sectors, buffer_sectors, journal_watermark, sync_msec;
bool should_write_sb;
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 23c38777e8f6..cab12b2251ba 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -3729,10 +3729,10 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
blk_limits_io_opt(limits, chunk_size_bytes * mddev_data_stripes(rs));
/*
- * RAID1 and RAID10 personalities require bio splitting,
- * RAID0/4/5/6 don't and process large discard bios properly.
+ * RAID0 and RAID10 personalities require bio splitting,
+ * RAID1/4/5/6 don't and process large discard bios properly.
*/
- if (rs_is_raid1(rs) || rs_is_raid10(rs)) {
+ if (rs_is_raid0(rs) || rs_is_raid10(rs)) {
limits->discard_granularity = chunk_size_bytes;
limits->max_discard_sectors = rs->md.chunk_sectors;
}
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 4668b2cd98f4..11890db71f3f 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -141,6 +141,11 @@ struct dm_snapshot {
* for them to be committed.
*/
struct bio_list bios_queued_during_merge;
+
+ /*
+ * Flush data after merge.
+ */
+ struct bio flush_bio;
};
/*
@@ -1121,6 +1126,17 @@ shut:
static void error_bios(struct bio *bio);
+static int flush_data(struct dm_snapshot *s)
+{
+ struct bio *flush_bio = &s->flush_bio;
+
+ bio_reset(flush_bio);
+ bio_set_dev(flush_bio, s->origin->bdev);
+ flush_bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+
+ return submit_bio_wait(flush_bio);
+}
+
static void merge_callback(int read_err, unsigned long write_err, void *context)
{
struct dm_snapshot *s = context;
@@ -1134,6 +1150,11 @@ static void merge_callback(int read_err, unsigned long write_err, void *context)
goto shut;
}
+ if (flush_data(s) < 0) {
+ DMERR("Flush after merge failed: shutting down merge");
+ goto shut;
+ }
+
if (s->store->type->commit_merge(s->store,
s->num_merging_chunks) < 0) {
DMERR("Write error in exception store: shutting down merge");
@@ -1318,6 +1339,7 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
s->first_merging_chunk = 0;
s->num_merging_chunks = 0;
bio_list_init(&s->bios_queued_during_merge);
+ bio_init(&s->flush_bio, NULL, 0);
/* Allocate hash table for COW data */
if (init_hash_tables(s)) {
@@ -1504,6 +1526,8 @@ static void snapshot_dtr(struct dm_target *ti)
dm_exception_store_destroy(s->store);
+ bio_uninit(&s->flush_bio);
+
dm_put_device(ti, s->cow);
dm_put_device(ti, s->origin);
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b3c3c8b4cb42..7bac564f3faa 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -562,7 +562,7 @@ static int dm_blk_ioctl(struct block_device *bdev, fmode_t mode,
* subset of the parent bdev; require extra privileges.
*/
if (!capable(CAP_SYS_RAWIO)) {
- DMWARN_LIMIT(
+ DMDEBUG_LIMIT(
"%s: sending ioctl %x to DM device without required privilege.",
current->comm, cmd);
r = -ENOIOCTLCMD;
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f320273fc672..200bdd672c28 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2856,6 +2856,11 @@ static const struct attribute_group *nvme_subsys_attrs_groups[] = {
NULL,
};
+static inline bool nvme_discovery_ctrl(struct nvme_ctrl *ctrl)
+{
+ return ctrl->opts && ctrl->opts->discovery_nqn;
+}
+
static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
{
@@ -2875,7 +2880,7 @@ static bool nvme_validate_cntlid(struct nvme_subsystem *subsys,
}
if ((id->cmic & NVME_CTRL_CMIC_MULTI_CTRL) ||
- (ctrl->opts && ctrl->opts->discovery_nqn))
+ nvme_discovery_ctrl(ctrl))
continue;
dev_err(ctrl->device,
@@ -3144,7 +3149,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
goto out_free;
}
- if (!ctrl->opts->discovery_nqn && !ctrl->kas) {
+ if (!nvme_discovery_ctrl(ctrl) && !ctrl->kas) {
dev_err(ctrl->device,
"keep-alive support is mandatory for fabrics\n");
ret = -EINVAL;
@@ -3184,7 +3189,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
if (ret < 0)
return ret;
- if (!ctrl->identified) {
+ if (!ctrl->identified && !nvme_discovery_ctrl(ctrl)) {
ret = nvme_hwmon_init(ctrl);
if (ret < 0)
return ret;
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 979ee31b8dd1..216619926563 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -201,7 +201,7 @@ static inline size_t nvme_tcp_req_cur_offset(struct nvme_tcp_request *req)
static inline size_t nvme_tcp_req_cur_length(struct nvme_tcp_request *req)
{
- return min_t(size_t, req->iter.bvec->bv_len - req->iter.iov_offset,
+ return min_t(size_t, iov_iter_single_seg_count(&req->iter),
req->pdu_len - req->pdu_sent);
}
@@ -286,7 +286,7 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
* directly, otherwise queue io_work. Also, only do that if we
* are on the same cpu, so we don't introduce contention.
*/
- if (queue->io_cpu == smp_processor_id() &&
+ if (queue->io_cpu == __smp_processor_id() &&
sync && empty && mutex_trylock(&queue->send_mutex)) {
queue->more_requests = !last;
nvme_tcp_send_all(queue);
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index bdfc22eb2a10..06b6b742bb21 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -1220,6 +1220,14 @@ nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
}
ndev->inline_data_size = nport->inline_data_size;
ndev->inline_page_count = inline_page_count;
+
+ if (nport->pi_enable && !(cm_id->device->attrs.device_cap_flags &
+ IB_DEVICE_INTEGRITY_HANDOVER)) {
+ pr_warn("T10-PI is not supported by device %s. Disabling it\n",
+ cm_id->device->name);
+ nport->pi_enable = false;
+ }
+
ndev->device = cm_id->device;
kref_init(&ndev->ref);
@@ -1855,14 +1863,6 @@ static int nvmet_rdma_enable_port(struct nvmet_rdma_port *port)
goto out_destroy_id;
}
- if (port->nport->pi_enable &&
- !(cm_id->device->attrs.device_cap_flags &
- IB_DEVICE_INTEGRITY_HANDOVER)) {
- pr_err("T10-PI is not supported for %pISpcs\n", addr);
- ret = -EINVAL;
- goto out_destroy_id;
- }
-
port->cm_id = cm_id;
return 0;
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 794a37d50853..cb2f55f450e4 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -726,11 +726,6 @@ static int armpmu_get_cpu_irq(struct arm_pmu *pmu, int cpu)
return per_cpu(hw_events->irq, cpu);
}
-bool arm_pmu_irq_is_nmi(void)
-{
- return has_nmi;
-}
-
/*
* PMU hardware loses all context when a CPU goes offline.
* When a CPU is hotplugged back in, since some hardware registers are
diff --git a/drivers/scsi/mpt3sas/Kconfig b/drivers/scsi/mpt3sas/Kconfig
index 86209455172d..c299f7e078fb 100644
--- a/drivers/scsi/mpt3sas/Kconfig
+++ b/drivers/scsi/mpt3sas/Kconfig
@@ -79,5 +79,5 @@ config SCSI_MPT2SAS
select SCSI_MPT3SAS
depends on PCI && SCSI
help
- Dummy config option for backwards compatiblity: configure the MPT3SAS
+ Dummy config option for backwards compatibility: configure the MPT3SAS
driver instead.
diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index f5fc7f518f8a..47ad64b06623 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -2245,7 +2245,7 @@ qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type,
chap_name);
break;
case ISCSI_BOOT_TGT_CHAP_SECRET:
- rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN,
+ rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN,
chap_secret);
break;
case ISCSI_BOOT_TGT_REV_CHAP_NAME:
@@ -2253,7 +2253,7 @@ qedi_show_boot_tgt_info(struct qedi_ctx *qedi, int type,
mchap_name);
break;
case ISCSI_BOOT_TGT_REV_CHAP_SECRET:
- rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_NAME_MAX_LEN,
+ rc = sprintf(buf, "%.*s\n", NVM_ISCSI_CFG_CHAP_PWD_MAX_LEN,
mchap_secret);
break;
case ISCSI_BOOT_TGT_FLAGS:
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 24c0f7ec0351..4a08c450b756 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -6740,7 +6740,7 @@ static int __init scsi_debug_init(void)
k = sdeb_zbc_model_str(sdeb_zbc_model_s);
if (k < 0) {
ret = k;
- goto free_vm;
+ goto free_q_arr;
}
sdeb_zbc_model = k;
switch (sdeb_zbc_model) {
@@ -6753,7 +6753,8 @@ static int __init scsi_debug_init(void)
break;
default:
pr_err("Invalid ZBC model\n");
- return -EINVAL;
+ ret = -EINVAL;
+ goto free_q_arr;
}
}
if (sdeb_zbc_model != BLK_ZONED_NONE) {
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 679c2c025047..a3d2d4bc4a3d 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -984,8 +984,10 @@ static blk_status_t sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
}
}
- if (sdp->no_write_same)
+ if (sdp->no_write_same) {
+ rq->rq_flags |= RQF_QUIET;
return BLK_STS_TARGET;
+ }
if (sdkp->ws16 || lba > 0xffffffff || nr_blocks > 0xffff)
return sd_setup_write_same16_cmnd(cmd, false);
@@ -3510,10 +3512,8 @@ static int sd_probe(struct device *dev)
static int sd_remove(struct device *dev)
{
struct scsi_disk *sdkp;
- dev_t devt;
sdkp = dev_get_drvdata(dev);
- devt = disk_devt(sdkp->disk);
scsi_autopm_get_device(sdkp->device);
async_synchronize_full_domain(&scsi_sd_pm_domain);
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 82ad31781bc9..e31d2c5c7b23 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -289,7 +289,8 @@ static inline void ufshcd_wb_config(struct ufs_hba *hba)
if (ret)
dev_err(hba->dev, "%s: En WB flush during H8: failed: %d\n",
__func__, ret);
- ufshcd_wb_toggle_flush(hba, true);
+ if (!(hba->quirks & UFSHCI_QUIRK_SKIP_MANUAL_WB_FLUSH_CTRL))
+ ufshcd_wb_toggle_flush(hba, true);
}
static void ufshcd_scsi_unblock_requests(struct ufs_hba *hba)
@@ -5436,9 +5437,6 @@ static int ufshcd_wb_toggle_flush_during_h8(struct ufs_hba *hba, bool set)
static inline void ufshcd_wb_toggle_flush(struct ufs_hba *hba, bool enable)
{
- if (hba->quirks & UFSHCI_QUIRK_SKIP_MANUAL_WB_FLUSH_CTRL)
- return;
-
if (enable)
ufshcd_wb_buf_flush_enable(hba);
else
@@ -6661,19 +6659,16 @@ static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd)
{
struct Scsi_Host *host;
struct ufs_hba *hba;
- unsigned int tag;
u32 pos;
int err;
- u8 resp = 0xF;
- struct ufshcd_lrb *lrbp;
+ u8 resp = 0xF, lun;
unsigned long flags;
host = cmd->device->host;
hba = shost_priv(host);
- tag = cmd->request->tag;
- lrbp = &hba->lrb[tag];
- err = ufshcd_issue_tm_cmd(hba, lrbp->lun, 0, UFS_LOGICAL_RESET, &resp);
+ lun = ufshcd_scsi_to_upiu_lun(cmd->device->lun);
+ err = ufshcd_issue_tm_cmd(hba, lun, 0, UFS_LOGICAL_RESET, &resp);
if (err || resp != UPIU_TASK_MANAGEMENT_FUNC_COMPL) {
if (!err)
err = resp;
@@ -6682,7 +6677,7 @@ static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd)
/* clear the commands that were pending for corresponding LUN */
for_each_set_bit(pos, &hba->outstanding_reqs, hba->nutrs) {
- if (hba->lrb[pos].lun == lrbp->lun) {
+ if (hba->lrb[pos].lun == lun) {
err = ufshcd_clear_cmd(hba, pos);
if (err)
break;
@@ -8698,6 +8693,8 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
ufshcd_wb_need_flush(hba));
}
+ flush_work(&hba->eeh_work);
+
if (req_dev_pwr_mode != hba->curr_dev_pwr_mode) {
if (!ufshcd_is_runtime_pm(pm_op))
/* ensure that bkops is disabled */
@@ -8710,8 +8707,6 @@ static int ufshcd_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
}
}
- flush_work(&hba->eeh_work);
-
/*
* In the case of DeepSleep, the device is expected to remain powered
* with the link off, so do not check for bkops.
@@ -8938,7 +8933,8 @@ int ufshcd_system_suspend(struct ufs_hba *hba)
if ((ufs_get_pm_lvl_to_dev_pwr_mode(hba->spm_lvl) ==
hba->curr_dev_pwr_mode) &&
(ufs_get_pm_lvl_to_link_pwr_state(hba->spm_lvl) ==
- hba->uic_link_state))
+ hba->uic_link_state) &&
+ !hba->dev_info.b_rpm_dev_flush_capable)
goto out;
if (pm_runtime_suspended(hba->dev)) {
diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index 70467b9d61ba..a3afd1b9ac56 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -115,6 +115,7 @@ struct cdns_spi {
void __iomem *regs;
struct clk *ref_clk;
struct clk *pclk;
+ unsigned int clk_rate;
u32 speed_hz;
const u8 *txbuf;
u8 *rxbuf;
@@ -250,7 +251,7 @@ static void cdns_spi_config_clock_freq(struct spi_device *spi,
u32 ctrl_reg, baud_rate_val;
unsigned long frequency;
- frequency = clk_get_rate(xspi->ref_clk);
+ frequency = xspi->clk_rate;
ctrl_reg = cdns_spi_read(xspi, CDNS_SPI_CR);
@@ -558,8 +559,9 @@ static int cdns_spi_probe(struct platform_device *pdev)
master->auto_runtime_pm = true;
master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+ xspi->clk_rate = clk_get_rate(xspi->ref_clk);
/* Set to default valid value */
- master->max_speed_hz = clk_get_rate(xspi->ref_clk) / 4;
+ master->max_speed_hz = xspi->clk_rate / 4;
xspi->speed_hz = master->max_speed_hz;
master->bits_per_word_mask = SPI_BPW_MASK(8);
diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c
index 9494257e1c33..6d8e0a05a535 100644
--- a/drivers/spi/spi-fsl-spi.c
+++ b/drivers/spi/spi-fsl-spi.c
@@ -115,14 +115,13 @@ static void fsl_spi_chipselect(struct spi_device *spi, int value)
{
struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(spi->master);
struct fsl_spi_platform_data *pdata;
- bool pol = spi->mode & SPI_CS_HIGH;
struct spi_mpc8xxx_cs *cs = spi->controller_state;
pdata = spi->dev.parent->parent->platform_data;
if (value == BITBANG_CS_INACTIVE) {
if (pdata->cs_control)
- pdata->cs_control(spi, !pol);
+ pdata->cs_control(spi, false);
}
if (value == BITBANG_CS_ACTIVE) {
@@ -134,7 +133,7 @@ static void fsl_spi_chipselect(struct spi_device *spi, int value)
fsl_spi_change_mode(spi);
if (pdata->cs_control)
- pdata->cs_control(spi, pol);
+ pdata->cs_control(spi, true);
}
}
diff --git a/drivers/tty/serial/sifive.c b/drivers/tty/serial/sifive.c
index 1066eebe3b28..328d5a78792f 100644
--- a/drivers/tty/serial/sifive.c
+++ b/drivers/tty/serial/sifive.c
@@ -1000,6 +1000,7 @@ static int sifive_serial_probe(struct platform_device *pdev)
/* Set up clock divider */
ssp->clkin_rate = clk_get_rate(ssp->clk);
ssp->baud_rate = SIFIVE_DEFAULT_BAUD_RATE;
+ ssp->port.uartclk = ssp->baud_rate * 16;
__ssp_update_div(ssp);
platform_set_drvdata(pdev, ssp);
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index a8030332a191..e850f79351cb 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -2060,16 +2060,6 @@ static struct irq_chip xen_percpu_chip __read_mostly = {
.irq_ack = ack_dynirq,
};
-int xen_set_callback_via(uint64_t via)
-{
- struct xen_hvm_param a;
- a.domid = DOMID_SELF;
- a.index = HVM_PARAM_CALLBACK_IRQ;
- a.value = via;
- return HYPERVISOR_hvm_op(HVMOP_set_param, &a);
-}
-EXPORT_SYMBOL_GPL(xen_set_callback_via);
-
#ifdef CONFIG_XEN_PVHVM
/* Vector callbacks are better than PCI interrupts to receive event
* channel notifications because we can receive vector callbacks on any
diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c
index dd911e1ff782..18f0ed8b1f93 100644
--- a/drivers/xen/platform-pci.c
+++ b/drivers/xen/platform-pci.c
@@ -132,6 +132,13 @@ static int platform_pci_probe(struct pci_dev *pdev,
dev_warn(&pdev->dev, "request_irq failed err=%d\n", ret);
goto out;
}
+ /*
+ * It doesn't strictly *have* to run on CPU0 but it sure
+ * as hell better process the event channel ports delivered
+ * to CPU0.
+ */
+ irq_set_affinity(pdev->irq, cpumask_of(0));
+
callback_via = get_callback_via(pdev);
ret = xen_set_callback_via(callback_via);
if (ret) {
@@ -149,7 +156,6 @@ static int platform_pci_probe(struct pci_dev *pdev,
ret = gnttab_init();
if (ret)
goto grant_out;
- xenbus_probe(NULL);
return 0;
grant_out:
gnttab_free_auto_xlat_frames();
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index b0c73c58f987..720a7b7abd46 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -717,14 +717,15 @@ static long privcmd_ioctl_restrict(struct file *file, void __user *udata)
return 0;
}
-static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata)
+static long privcmd_ioctl_mmap_resource(struct file *file,
+ struct privcmd_mmap_resource __user *udata)
{
struct privcmd_data *data = file->private_data;
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
struct privcmd_mmap_resource kdata;
xen_pfn_t *pfns = NULL;
- struct xen_mem_acquire_resource xdata;
+ struct xen_mem_acquire_resource xdata = { };
int rc;
if (copy_from_user(&kdata, udata, sizeof(kdata)))
@@ -734,6 +735,22 @@ static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata)
if (data->domid != DOMID_INVALID && data->domid != kdata.dom)
return -EPERM;
+ /* Both fields must be set or unset */
+ if (!!kdata.addr != !!kdata.num)
+ return -EINVAL;
+
+ xdata.domid = kdata.dom;
+ xdata.type = kdata.type;
+ xdata.id = kdata.id;
+
+ if (!kdata.addr && !kdata.num) {
+ /* Query the size of the resource. */
+ rc = HYPERVISOR_memory_op(XENMEM_acquire_resource, &xdata);
+ if (rc)
+ return rc;
+ return __put_user(xdata.nr_frames, &udata->num);
+ }
+
mmap_write_lock(mm);
vma = find_vma(mm, kdata.addr);
@@ -768,10 +785,6 @@ static long privcmd_ioctl_mmap_resource(struct file *file, void __user *udata)
} else
vma->vm_private_data = PRIV_VMA_LOCKED;
- memset(&xdata, 0, sizeof(xdata));
- xdata.domid = kdata.dom;
- xdata.type = kdata.type;
- xdata.id = kdata.id;
xdata.frame = kdata.idx;
xdata.nr_frames = kdata.num;
set_xen_guest_handle(xdata.frame_list, pfns);
diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h
index 2a93b7c9c159..dc1537335414 100644
--- a/drivers/xen/xenbus/xenbus.h
+++ b/drivers/xen/xenbus/xenbus.h
@@ -115,6 +115,7 @@ int xenbus_probe_node(struct xen_bus_type *bus,
const char *type,
const char *nodename);
int xenbus_probe_devices(struct xen_bus_type *bus);
+void xenbus_probe(void);
void xenbus_dev_changed(const char *node, struct xen_bus_type *bus);
diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c
index eb5151fc8efa..e5fda0256feb 100644
--- a/drivers/xen/xenbus/xenbus_comms.c
+++ b/drivers/xen/xenbus/xenbus_comms.c
@@ -57,16 +57,8 @@ DEFINE_MUTEX(xs_response_mutex);
static int xenbus_irq;
static struct task_struct *xenbus_task;
-static DECLARE_WORK(probe_work, xenbus_probe);
-
-
static irqreturn_t wake_waiting(int irq, void *unused)
{
- if (unlikely(xenstored_ready == 0)) {
- xenstored_ready = 1;
- schedule_work(&probe_work);
- }
-
wake_up(&xb_waitq);
return IRQ_HANDLED;
}
diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c
index 44634d970a5c..c8f0282bb649 100644
--- a/drivers/xen/xenbus/xenbus_probe.c
+++ b/drivers/xen/xenbus/xenbus_probe.c
@@ -683,29 +683,76 @@ void unregister_xenstore_notifier(struct notifier_block *nb)
}
EXPORT_SYMBOL_GPL(unregister_xenstore_notifier);
-void xenbus_probe(struct work_struct *unused)
+void xenbus_probe(void)
{
xenstored_ready = 1;
+ /*
+ * In the HVM case, xenbus_init() deferred its call to
+ * xs_init() in case callbacks were not operational yet.
+ * So do it now.
+ */
+ if (xen_store_domain_type == XS_HVM)
+ xs_init();
+
/* Notify others that xenstore is up */
blocking_notifier_call_chain(&xenstore_chain, 0, NULL);
}
-EXPORT_SYMBOL_GPL(xenbus_probe);
-static int __init xenbus_probe_initcall(void)
+/*
+ * Returns true when XenStore init must be deferred in order to
+ * allow the PCI platform device to be initialised, before we
+ * can actually have event channel interrupts working.
+ */
+static bool xs_hvm_defer_init_for_callback(void)
{
- if (!xen_domain())
- return -ENODEV;
+#ifdef CONFIG_XEN_PVHVM
+ return xen_store_domain_type == XS_HVM &&
+ !xen_have_vector_callback;
+#else
+ return false;
+#endif
+}
- if (xen_initial_domain() || xen_hvm_domain())
- return 0;
+static int __init xenbus_probe_initcall(void)
+{
+ /*
+ * Probe XenBus here in the XS_PV case, and also XS_HVM unless we
+ * need to wait for the platform PCI device to come up.
+ */
+ if (xen_store_domain_type == XS_PV ||
+ (xen_store_domain_type == XS_HVM &&
+ !xs_hvm_defer_init_for_callback()))
+ xenbus_probe();
- xenbus_probe(NULL);
return 0;
}
-
device_initcall(xenbus_probe_initcall);
+int xen_set_callback_via(uint64_t via)
+{
+ struct xen_hvm_param a;
+ int ret;
+
+ a.domid = DOMID_SELF;
+ a.index = HVM_PARAM_CALLBACK_IRQ;
+ a.value = via;
+
+ ret = HYPERVISOR_hvm_op(HVMOP_set_param, &a);
+ if (ret)
+ return ret;
+
+ /*
+ * If xenbus_probe_initcall() deferred the xenbus_probe()
+ * due to the callback not functioning yet, we can do it now.
+ */
+ if (!xenstored_ready && xs_hvm_defer_init_for_callback())
+ xenbus_probe();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(xen_set_callback_via);
+
/* Set up event channel for xenstored which is run as a local process
* (this is normally used only in dom0)
*/
@@ -818,11 +865,17 @@ static int __init xenbus_init(void)
break;
}
- /* Initialize the interface to xenstore. */
- err = xs_init();
- if (err) {
- pr_warn("Error initializing xenstore comms: %i\n", err);
- goto out_error;
+ /*
+ * HVM domains may not have a functional callback yet. In that
+ * case let xs_init() be called from xenbus_probe(), which will
+ * get invoked at an appropriate time.
+ */
+ if (xen_store_domain_type != XS_HVM) {
+ err = xs_init();
+ if (err) {
+ pr_warn("Error initializing xenstore comms: %i\n", err);
+ goto out_error;
+ }
}
if ((xen_store_domain_type != XS_LOCAL) &&
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index 8bda092e60c5..e027c718ca01 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -413,7 +413,6 @@ int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
inode = d_backing_inode(object->backer);
ASSERT(S_ISREG(inode->i_mode));
- ASSERT(inode->i_mapping->a_ops->readpages);
/* calculate the shift required to use bmap */
shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
@@ -713,7 +712,6 @@ int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
inode = d_backing_inode(object->backer);
ASSERT(S_ISREG(inode->i_mode));
- ASSERT(inode->i_mapping->a_ops->readpages);
/* calculate the shift required to use bmap */
shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index b9df85506938..5d39129406ea 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -3740,7 +3740,7 @@ cifs_setup_session(const unsigned int xid, struct cifs_ses *ses,
if (!ses->binding) {
ses->capabilities = server->capabilities;
- if (linuxExtEnabled == 0)
+ if (!linuxExtEnabled)
ses->capabilities &= (~server->vals->cap_unix);
if (ses->auth_key.response) {
diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c
index 6ad6ba5f6ebe..0fdb0de7ff86 100644
--- a/fs/cifs/dfs_cache.c
+++ b/fs/cifs/dfs_cache.c
@@ -1260,7 +1260,8 @@ void dfs_cache_del_vol(const char *fullpath)
vi = find_vol(fullpath);
spin_unlock(&vol_list_lock);
- kref_put(&vi->refcnt, vol_release);
+ if (!IS_ERR(vi))
+ kref_put(&vi->refcnt, vol_release);
}
/**
diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c
index 0afccbbed2e6..076bcadc756a 100644
--- a/fs/cifs/fs_context.c
+++ b/fs/cifs/fs_context.c
@@ -303,8 +303,6 @@ do { \
int
smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx)
{
- int rc = 0;
-
memcpy(new_ctx, ctx, sizeof(*ctx));
new_ctx->prepath = NULL;
new_ctx->mount_options = NULL;
@@ -327,7 +325,7 @@ smb3_fs_context_dup(struct smb3_fs_context *new_ctx, struct smb3_fs_context *ctx
DUP_CTX_STR(nodename);
DUP_CTX_STR(iocharset);
- return rc;
+ return 0;
}
static int
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 067eb44c7baa..794fc3b68b4f 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -3248,7 +3248,7 @@ close_exit:
free_rsp_buf(resp_buftype, rsp);
/* retry close in a worker thread if this one is interrupted */
- if (rc == -EINTR) {
+ if (is_interrupt_error(rc)) {
int tmp_rc;
tmp_rc = smb2_handle_cancelled_close(tcon, persistent_fid,
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index 204a622b89ed..d85edf5d1429 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -424,7 +424,7 @@ struct smb2_rdma_transform_capabilities_context {
__le16 TransformCount;
__u16 Reserved1;
__u32 Reserved2;
- __le16 RDMATransformIds[1];
+ __le16 RDMATransformIds[];
} __packed;
/* Signing algorithms */
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 1a0a827a7f34..be799040a415 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -372,20 +372,3 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
}
return err;
}
-
-int __ext4_handle_dirty_super(const char *where, unsigned int line,
- handle_t *handle, struct super_block *sb)
-{
- struct buffer_head *bh = EXT4_SB(sb)->s_sbh;
- int err = 0;
-
- ext4_superblock_csum_set(sb);
- if (ext4_handle_valid(handle)) {
- err = jbd2_journal_dirty_metadata(handle, bh);
- if (err)
- ext4_journal_abort_handle(where, line, __func__,
- bh, handle, err);
- } else
- mark_buffer_dirty(bh);
- return err;
-}
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index a124c68b0c75..0d2fa423b7ad 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -244,9 +244,6 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
handle_t *handle, struct inode *inode,
struct buffer_head *bh);
-int __ext4_handle_dirty_super(const char *where, unsigned int line,
- handle_t *handle, struct super_block *sb);
-
#define ext4_journal_get_write_access(handle, bh) \
__ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh))
#define ext4_forget(handle, is_metadata, inode, bh, block_nr) \
@@ -257,8 +254,6 @@ int __ext4_handle_dirty_super(const char *where, unsigned int line,
#define ext4_handle_dirty_metadata(handle, inode, bh) \
__ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \
(bh))
-#define ext4_handle_dirty_super(handle, sb) \
- __ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
int type, int blocks, int rsv_blocks,
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 4fcc21c25e79..0a14a7c87bf8 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -604,13 +604,13 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star
trace_ext4_fc_track_range(inode, start, end, ret);
}
-static void ext4_fc_submit_bh(struct super_block *sb)
+static void ext4_fc_submit_bh(struct super_block *sb, bool is_tail)
{
int write_flags = REQ_SYNC;
struct buffer_head *bh = EXT4_SB(sb)->s_fc_bh;
- /* TODO: REQ_FUA | REQ_PREFLUSH is unnecessarily expensive. */
- if (test_opt(sb, BARRIER))
+ /* Add REQ_FUA | REQ_PREFLUSH only its tail */
+ if (test_opt(sb, BARRIER) && is_tail)
write_flags |= REQ_FUA | REQ_PREFLUSH;
lock_buffer(bh);
set_buffer_dirty(bh);
@@ -684,7 +684,7 @@ static u8 *ext4_fc_reserve_space(struct super_block *sb, int len, u32 *crc)
*crc = ext4_chksum(sbi, *crc, tl, sizeof(*tl));
if (pad_len > 0)
ext4_fc_memzero(sb, tl + 1, pad_len, crc);
- ext4_fc_submit_bh(sb);
+ ext4_fc_submit_bh(sb, false);
ret = jbd2_fc_get_buf(EXT4_SB(sb)->s_journal, &bh);
if (ret)
@@ -741,7 +741,7 @@ static int ext4_fc_write_tail(struct super_block *sb, u32 crc)
tail.fc_crc = cpu_to_le32(crc);
ext4_fc_memcpy(sb, dst, &tail.fc_crc, sizeof(tail.fc_crc), NULL);
- ext4_fc_submit_bh(sb);
+ ext4_fc_submit_bh(sb, true);
return 0;
}
@@ -1268,7 +1268,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full)
list_splice_init(&sbi->s_fc_dentry_q[FC_Q_STAGING],
&sbi->s_fc_dentry_q[FC_Q_MAIN]);
list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
- &sbi->s_fc_q[FC_Q_STAGING]);
+ &sbi->s_fc_q[FC_Q_MAIN]);
ext4_clear_mount_flag(sb, EXT4_MF_FC_COMMITTING);
ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
@@ -1318,14 +1318,14 @@ static int ext4_fc_replay_unlink(struct super_block *sb, struct ext4_fc_tl *tl)
entry.len = darg.dname_len;
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found", darg.ino);
return 0;
}
old_parent = ext4_iget(sb, darg.parent_ino,
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(old_parent)) {
+ if (IS_ERR(old_parent)) {
jbd_debug(1, "Dir with inode %d not found", darg.parent_ino);
iput(inode);
return 0;
@@ -1410,7 +1410,7 @@ static int ext4_fc_replay_link(struct super_block *sb, struct ext4_fc_tl *tl)
darg.parent_ino, darg.dname_len);
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return 0;
}
@@ -1466,10 +1466,11 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
trace_ext4_fc_replay(sb, tag, ino, 0, 0);
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
- if (!IS_ERR_OR_NULL(inode)) {
+ if (!IS_ERR(inode)) {
ext4_ext_clear_bb(inode);
iput(inode);
}
+ inode = NULL;
ext4_fc_record_modified_inode(sb, ino);
@@ -1512,7 +1513,7 @@ static int ext4_fc_replay_inode(struct super_block *sb, struct ext4_fc_tl *tl)
/* Given that we just wrote the inode on disk, this SHOULD succeed. */
inode = ext4_iget(sb, ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return -EFSCORRUPTED;
}
@@ -1564,7 +1565,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
goto out;
inode = ext4_iget(sb, darg.ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "inode %d not found.", darg.ino);
inode = NULL;
ret = -EINVAL;
@@ -1577,7 +1578,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl)
* dot and dot dot dirents are setup properly.
*/
dir = ext4_iget(sb, darg.parent_ino, EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(dir)) {
+ if (IS_ERR(dir)) {
jbd_debug(1, "Dir %d not found.", darg.ino);
goto out;
}
@@ -1653,7 +1654,7 @@ static int ext4_fc_replay_add_range(struct super_block *sb,
inode = ext4_iget(sb, le32_to_cpu(fc_add_ex->fc_ino),
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode not found.");
return 0;
}
@@ -1777,7 +1778,7 @@ ext4_fc_replay_del_range(struct super_block *sb, struct ext4_fc_tl *tl)
le32_to_cpu(lrange->fc_ino), cur, remaining);
inode = ext4_iget(sb, le32_to_cpu(lrange->fc_ino), EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found", le32_to_cpu(lrange->fc_ino));
return 0;
}
@@ -1832,7 +1833,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
for (i = 0; i < state->fc_modified_inodes_used; i++) {
inode = ext4_iget(sb, state->fc_modified_inodes[i],
EXT4_IGET_NORMAL);
- if (IS_ERR_OR_NULL(inode)) {
+ if (IS_ERR(inode)) {
jbd_debug(1, "Inode %d not found.",
state->fc_modified_inodes[i]);
continue;
@@ -1849,7 +1850,7 @@ static void ext4_fc_set_bitmaps_and_counters(struct super_block *sb)
if (ret > 0) {
path = ext4_find_extent(inode, map.m_lblk, NULL, 0);
- if (!IS_ERR_OR_NULL(path)) {
+ if (!IS_ERR(path)) {
for (j = 0; j < path->p_depth; j++)
ext4_mb_mark_bb(inode->i_sb,
path[j].p_block, 1, 1);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 3ed8c048fb12..349b27f0dda0 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -809,9 +809,12 @@ static int ext4_sample_last_mounted(struct super_block *sb,
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto out_journal;
- strlcpy(sbi->s_es->s_last_mounted, cp,
+ lock_buffer(sbi->s_sbh);
+ strncpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
- ext4_handle_dirty_super(handle, sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
out_journal:
ext4_journal_stop(handle);
out:
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 27946882d4ce..c173c8405856 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5150,9 +5150,13 @@ static int ext4_do_update_inode(handle_t *handle,
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (err)
goto out_brelse;
+ lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_set_feature_large_file(sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
ext4_handle_sync(handle);
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL,
+ EXT4_SB(sb)->s_sbh);
}
ext4_update_inode_fsync_trans(handle, inode, need_datasync);
out_brelse:
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 524e13432447..d9665d2f82db 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -1157,7 +1157,10 @@ resizefs_out:
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto pwsalt_err_journal;
+ lock_buffer(sbi->s_sbh);
generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
err = ext4_handle_dirty_metadata(handle, NULL,
sbi->s_sbh);
pwsalt_err_journal:
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index b17a082b7db1..cf652ba3e74d 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2976,14 +2976,17 @@ int ext4_orphan_add(handle_t *handle, struct inode *inode)
(le32_to_cpu(sbi->s_es->s_inodes_count))) {
/* Insert this inode at the head of the on-disk orphan list */
NEXT_ORPHAN(inode) = le32_to_cpu(sbi->s_es->s_last_orphan);
+ lock_buffer(sbi->s_sbh);
sbi->s_es->s_last_orphan = cpu_to_le32(inode->i_ino);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
dirty = true;
}
list_add(&EXT4_I(inode)->i_orphan, &sbi->s_orphan);
mutex_unlock(&sbi->s_orphan_lock);
if (dirty) {
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
rc = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (!err)
err = rc;
@@ -3059,9 +3062,12 @@ int ext4_orphan_del(handle_t *handle, struct inode *inode)
mutex_unlock(&sbi->s_orphan_lock);
goto out_brelse;
}
+ lock_buffer(sbi->s_sbh);
sbi->s_es->s_last_orphan = cpu_to_le32(ino_next);
+ ext4_superblock_csum_set(inode->i_sb);
+ unlock_buffer(sbi->s_sbh);
mutex_unlock(&sbi->s_orphan_lock);
- err = ext4_handle_dirty_super(handle, inode->i_sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
} else {
struct ext4_iloc iloc2;
struct inode *i_prev =
@@ -3593,9 +3599,6 @@ static int ext4_setent(handle_t *handle, struct ext4_renament *ent,
return retval2;
}
}
- brelse(ent->bh);
- ent->bh = NULL;
-
return retval;
}
@@ -3794,6 +3797,7 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
}
}
+ old_file_type = old.de->file_type;
if (IS_DIRSYNC(old.dir) || IS_DIRSYNC(new.dir))
ext4_handle_sync(handle);
@@ -3821,7 +3825,6 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
force_reread = (new.dir->i_ino == old.dir->i_ino &&
ext4_test_inode_flag(new.dir, EXT4_INODE_INLINE_DATA));
- old_file_type = old.de->file_type;
if (whiteout) {
/*
* Do this before adding a new entry, so the old entry is sure
@@ -3919,15 +3922,19 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
retval = 0;
end_rename:
- brelse(old.dir_bh);
- brelse(old.bh);
- brelse(new.bh);
if (whiteout) {
- if (retval)
+ if (retval) {
+ ext4_setent(handle, &old,
+ old.inode->i_ino, old_file_type);
drop_nlink(whiteout);
+ }
unlock_new_inode(whiteout);
iput(whiteout);
+
}
+ brelse(old.dir_bh);
+ brelse(old.bh);
+ brelse(new.bh);
if (handle)
ext4_journal_stop(handle);
return retval;
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 928700d57eb6..bd0d185654f3 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -899,8 +899,11 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
EXT4_SB(sb)->s_gdb_count++;
ext4_kvfree_array_rcu(o_group_desc);
+ lock_buffer(EXT4_SB(sb)->s_sbh);
le16_add_cpu(&es->s_reserved_gdt_blocks, -1);
- err = ext4_handle_dirty_super(handle, sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
+ err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
if (err)
ext4_std_error(sb, err);
return err;
@@ -1384,6 +1387,7 @@ static void ext4_update_super(struct super_block *sb,
reserved_blocks *= blocks_count;
do_div(reserved_blocks, 100);
+ lock_buffer(sbi->s_sbh);
ext4_blocks_count_set(es, ext4_blocks_count(es) + blocks_count);
ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + free_blocks);
le32_add_cpu(&es->s_inodes_count, EXT4_INODES_PER_GROUP(sb) *
@@ -1421,6 +1425,8 @@ static void ext4_update_super(struct super_block *sb,
* active. */
ext4_r_blocks_count_set(es, ext4_r_blocks_count(es) +
reserved_blocks);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
/* Update the free space counts */
percpu_counter_add(&sbi->s_freeclusters_counter,
@@ -1515,7 +1521,7 @@ static int ext4_flex_group_add(struct super_block *sb,
ext4_update_super(sb, flex_gd);
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
exit_journal:
err2 = ext4_journal_stop(handle);
@@ -1717,15 +1723,18 @@ static int ext4_group_extend_no_check(struct super_block *sb,
goto errout;
}
+ lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_blocks_count_set(es, o_blocks_count + add);
ext4_free_blocks_count_set(es, ext4_free_blocks_count(es) + add);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
/* We add the blocks to the bitmap and set the group need init bit */
err = ext4_group_add_blocks(handle, sb, o_blocks_count, add);
if (err)
goto errout;
- ext4_handle_dirty_super(handle, sb);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
o_blocks_count + add);
errout:
@@ -1874,12 +1883,15 @@ static int ext4_convert_meta_bg(struct super_block *sb, struct inode *inode)
if (err)
goto errout;
+ lock_buffer(sbi->s_sbh);
ext4_clear_feature_resize_inode(sb);
ext4_set_feature_meta_bg(sb);
sbi->s_es->s_first_meta_bg =
cpu_to_le32(num_desc_blocks(sb, sbi->s_groups_count));
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(sbi->s_sbh);
- err = ext4_handle_dirty_super(handle, sb);
+ err = ext4_handle_dirty_metadata(handle, NULL, sbi->s_sbh);
if (err) {
ext4_std_error(sb, err);
goto errout;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 21121787c874..9a6f9875aa34 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -65,7 +65,8 @@ static struct ratelimit_state ext4_mount_msg_ratelimit;
static int ext4_load_journal(struct super_block *, struct ext4_super_block *,
unsigned long journal_devnum);
static int ext4_show_options(struct seq_file *seq, struct dentry *root);
-static int ext4_commit_super(struct super_block *sb, int sync);
+static void ext4_update_super(struct super_block *sb);
+static int ext4_commit_super(struct super_block *sb);
static int ext4_mark_recovery_complete(struct super_block *sb,
struct ext4_super_block *es);
static int ext4_clear_journal_err(struct super_block *sb,
@@ -586,15 +587,12 @@ static int ext4_errno_to_code(int errno)
return EXT4_ERR_UNKNOWN;
}
-static void __save_error_info(struct super_block *sb, int error,
- __u32 ino, __u64 block,
- const char *func, unsigned int line)
+static void save_error_info(struct super_block *sb, int error,
+ __u32 ino, __u64 block,
+ const char *func, unsigned int line)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
- if (bdev_read_only(sb->s_bdev))
- return;
/* We default to EFSCORRUPTED error... */
if (error == 0)
error = EFSCORRUPTED;
@@ -618,15 +616,6 @@ static void __save_error_info(struct super_block *sb, int error,
spin_unlock(&sbi->s_error_lock);
}
-static void save_error_info(struct super_block *sb, int error,
- __u32 ino, __u64 block,
- const char *func, unsigned int line)
-{
- __save_error_info(sb, error, ino, block, func, line);
- if (!bdev_read_only(sb->s_bdev))
- ext4_commit_super(sb, 1);
-}
-
/* Deal with the reporting of failure conditions on a filesystem such as
* inconsistencies detected or read IO failures.
*
@@ -647,19 +636,40 @@ static void save_error_info(struct super_block *sb, int error,
* used to deal with unrecoverable failures such as journal IO errors or ENOMEM
* at a critical moment in log management.
*/
-static void ext4_handle_error(struct super_block *sb, bool force_ro)
+static void ext4_handle_error(struct super_block *sb, bool force_ro, int error,
+ __u32 ino, __u64 block,
+ const char *func, unsigned int line)
{
journal_t *journal = EXT4_SB(sb)->s_journal;
+ bool continue_fs = !force_ro && test_opt(sb, ERRORS_CONT);
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
if (test_opt(sb, WARN_ON_ERROR))
WARN_ON_ONCE(1);
- if (sb_rdonly(sb) || (!force_ro && test_opt(sb, ERRORS_CONT)))
+ if (!continue_fs && !sb_rdonly(sb)) {
+ ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
+ if (journal)
+ jbd2_journal_abort(journal, -EIO);
+ }
+
+ if (!bdev_read_only(sb->s_bdev)) {
+ save_error_info(sb, error, ino, block, func, line);
+ /*
+ * In case the fs should keep running, we need to writeout
+ * superblock through the journal. Due to lock ordering
+ * constraints, it may not be safe to do it right here so we
+ * defer superblock flushing to a workqueue.
+ */
+ if (continue_fs)
+ schedule_work(&EXT4_SB(sb)->s_error_work);
+ else
+ ext4_commit_super(sb);
+ }
+
+ if (sb_rdonly(sb) || continue_fs)
return;
- ext4_set_mount_flag(sb, EXT4_MF_FS_ABORTED);
- if (journal)
- jbd2_journal_abort(journal, -EIO);
/*
* We force ERRORS_RO behavior when system is rebooting. Otherwise we
* could panic during 'reboot -f' as the underlying device got already
@@ -682,8 +692,39 @@ static void flush_stashed_error_work(struct work_struct *work)
{
struct ext4_sb_info *sbi = container_of(work, struct ext4_sb_info,
s_error_work);
+ journal_t *journal = sbi->s_journal;
+ handle_t *handle;
- ext4_commit_super(sbi->s_sb, 1);
+ /*
+ * If the journal is still running, we have to write out superblock
+ * through the journal to avoid collisions of other journalled sb
+ * updates.
+ *
+ * We use directly jbd2 functions here to avoid recursing back into
+ * ext4 error handling code during handling of previous errors.
+ */
+ if (!sb_rdonly(sbi->s_sb) && journal) {
+ handle = jbd2_journal_start(journal, 1);
+ if (IS_ERR(handle))
+ goto write_directly;
+ if (jbd2_journal_get_write_access(handle, sbi->s_sbh)) {
+ jbd2_journal_stop(handle);
+ goto write_directly;
+ }
+ ext4_update_super(sbi->s_sb);
+ if (jbd2_journal_dirty_metadata(handle, sbi->s_sbh)) {
+ jbd2_journal_stop(handle);
+ goto write_directly;
+ }
+ jbd2_journal_stop(handle);
+ return;
+ }
+write_directly:
+ /*
+ * Write through journal failed. Write sb directly to get error info
+ * out and hope for the best.
+ */
+ ext4_commit_super(sbi->s_sb);
}
#define ext4_error_ratelimit(sb) \
@@ -710,8 +751,7 @@ void __ext4_error(struct super_block *sb, const char *function,
sb->s_id, function, line, current->comm, &vaf);
va_end(args);
}
- save_error_info(sb, error, 0, block, function, line);
- ext4_handle_error(sb, force_ro);
+ ext4_handle_error(sb, force_ro, error, 0, block, function, line);
}
void __ext4_error_inode(struct inode *inode, const char *function,
@@ -741,9 +781,8 @@ void __ext4_error_inode(struct inode *inode, const char *function,
current->comm, &vaf);
va_end(args);
}
- save_error_info(inode->i_sb, error, inode->i_ino, block,
- function, line);
- ext4_handle_error(inode->i_sb, false);
+ ext4_handle_error(inode->i_sb, false, error, inode->i_ino, block,
+ function, line);
}
void __ext4_error_file(struct file *file, const char *function,
@@ -780,9 +819,8 @@ void __ext4_error_file(struct file *file, const char *function,
current->comm, path, &vaf);
va_end(args);
}
- save_error_info(inode->i_sb, EFSCORRUPTED, inode->i_ino, block,
- function, line);
- ext4_handle_error(inode->i_sb, false);
+ ext4_handle_error(inode->i_sb, false, EFSCORRUPTED, inode->i_ino, block,
+ function, line);
}
const char *ext4_decode_error(struct super_block *sb, int errno,
@@ -849,8 +887,7 @@ void __ext4_std_error(struct super_block *sb, const char *function,
sb->s_id, function, line, errstr);
}
- save_error_info(sb, -errno, 0, 0, function, line);
- ext4_handle_error(sb, false);
+ ext4_handle_error(sb, false, -errno, 0, 0, function, line);
}
void __ext4_msg(struct super_block *sb,
@@ -944,13 +981,16 @@ __acquires(bitlock)
if (test_opt(sb, ERRORS_CONT)) {
if (test_opt(sb, WARN_ON_ERROR))
WARN_ON_ONCE(1);
- __save_error_info(sb, EFSCORRUPTED, ino, block, function, line);
- schedule_work(&EXT4_SB(sb)->s_error_work);
+ EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
+ if (!bdev_read_only(sb->s_bdev)) {
+ save_error_info(sb, EFSCORRUPTED, ino, block, function,
+ line);
+ schedule_work(&EXT4_SB(sb)->s_error_work);
+ }
return;
}
ext4_unlock_group(sb, grp);
- save_error_info(sb, EFSCORRUPTED, ino, block, function, line);
- ext4_handle_error(sb, false);
+ ext4_handle_error(sb, false, EFSCORRUPTED, ino, block, function, line);
/*
* We only get here in the ERRORS_RO case; relocking the group
* may be dangerous, but nothing bad will happen since the
@@ -1152,7 +1192,7 @@ static void ext4_put_super(struct super_block *sb)
es->s_state = cpu_to_le16(sbi->s_mount_state);
}
if (!sb_rdonly(sb))
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
rcu_read_lock();
group_desc = rcu_dereference(sbi->s_group_desc);
@@ -2642,7 +2682,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
if (sbi->s_journal)
ext4_set_feature_journal_needs_recovery(sb);
- err = ext4_commit_super(sb, 1);
+ err = ext4_commit_super(sb);
done:
if (test_opt(sb, DEBUG))
printk(KERN_INFO "[EXT4 FS bs=%lu, gc=%u, "
@@ -4868,7 +4908,7 @@ no_journal:
if (DUMMY_ENCRYPTION_ENABLED(sbi) && !sb_rdonly(sb) &&
!ext4_has_feature_encrypt(sb)) {
ext4_set_feature_encrypt(sb);
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
}
/*
@@ -5418,7 +5458,7 @@ static int ext4_load_journal(struct super_block *sb,
es->s_journal_dev = cpu_to_le32(journal_devnum);
/* Make sure we flush the recovery flag to disk. */
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
}
return 0;
@@ -5428,16 +5468,14 @@ err_out:
return err;
}
-static int ext4_commit_super(struct super_block *sb, int sync)
+/* Copy state of EXT4_SB(sb) into buffer for on-disk superblock */
+static void ext4_update_super(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- struct ext4_super_block *es = EXT4_SB(sb)->s_es;
- struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
- int error = 0;
-
- if (!sbh || block_device_ejected(sb))
- return error;
+ struct ext4_super_block *es = sbi->s_es;
+ struct buffer_head *sbh = sbi->s_sbh;
+ lock_buffer(sbh);
/*
* If the file system is mounted read-only, don't update the
* superblock write time. This avoids updating the superblock
@@ -5451,17 +5489,17 @@ static int ext4_commit_super(struct super_block *sb, int sync)
if (!(sb->s_flags & SB_RDONLY))
ext4_update_tstamp(es, s_wtime);
es->s_kbytes_written =
- cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
+ cpu_to_le64(sbi->s_kbytes_written +
((part_stat_read(sb->s_bdev, sectors[STAT_WRITE]) -
- EXT4_SB(sb)->s_sectors_written_start) >> 1));
- if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeclusters_counter))
+ sbi->s_sectors_written_start) >> 1));
+ if (percpu_counter_initialized(&sbi->s_freeclusters_counter))
ext4_free_blocks_count_set(es,
- EXT4_C2B(EXT4_SB(sb), percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeclusters_counter)));
- if (percpu_counter_initialized(&EXT4_SB(sb)->s_freeinodes_counter))
+ EXT4_C2B(sbi, percpu_counter_sum_positive(
+ &sbi->s_freeclusters_counter)));
+ if (percpu_counter_initialized(&sbi->s_freeinodes_counter))
es->s_free_inodes_count =
cpu_to_le32(percpu_counter_sum_positive(
- &EXT4_SB(sb)->s_freeinodes_counter));
+ &sbi->s_freeinodes_counter));
/* Copy error information to the on-disk superblock */
spin_lock(&sbi->s_error_lock);
if (sbi->s_add_error_count > 0) {
@@ -5502,10 +5540,20 @@ static int ext4_commit_super(struct super_block *sb, int sync)
}
spin_unlock(&sbi->s_error_lock);
- BUFFER_TRACE(sbh, "marking dirty");
ext4_superblock_csum_set(sb);
- if (sync)
- lock_buffer(sbh);
+ unlock_buffer(sbh);
+}
+
+static int ext4_commit_super(struct super_block *sb)
+{
+ struct buffer_head *sbh = EXT4_SB(sb)->s_sbh;
+ int error = 0;
+
+ if (!sbh || block_device_ejected(sb))
+ return error;
+
+ ext4_update_super(sb);
+
if (buffer_write_io_error(sbh) || !buffer_uptodate(sbh)) {
/*
* Oh, dear. A previous attempt to write the
@@ -5520,17 +5568,15 @@ static int ext4_commit_super(struct super_block *sb, int sync)
clear_buffer_write_io_error(sbh);
set_buffer_uptodate(sbh);
}
+ BUFFER_TRACE(sbh, "marking dirty");
mark_buffer_dirty(sbh);
- if (sync) {
- unlock_buffer(sbh);
- error = __sync_dirty_buffer(sbh,
- REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0));
- if (buffer_write_io_error(sbh)) {
- ext4_msg(sb, KERN_ERR, "I/O error while writing "
- "superblock");
- clear_buffer_write_io_error(sbh);
- set_buffer_uptodate(sbh);
- }
+ error = __sync_dirty_buffer(sbh,
+ REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0));
+ if (buffer_write_io_error(sbh)) {
+ ext4_msg(sb, KERN_ERR, "I/O error while writing "
+ "superblock");
+ clear_buffer_write_io_error(sbh);
+ set_buffer_uptodate(sbh);
}
return error;
}
@@ -5561,7 +5607,7 @@ static int ext4_mark_recovery_complete(struct super_block *sb,
if (ext4_has_feature_journal_needs_recovery(sb) && sb_rdonly(sb)) {
ext4_clear_feature_journal_needs_recovery(sb);
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
}
out:
jbd2_journal_unlock_updates(journal);
@@ -5603,7 +5649,7 @@ static int ext4_clear_journal_err(struct super_block *sb,
EXT4_SB(sb)->s_mount_state |= EXT4_ERROR_FS;
es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
jbd2_journal_clear_err(journal);
jbd2_journal_update_sb_errno(journal);
@@ -5705,7 +5751,7 @@ static int ext4_freeze(struct super_block *sb)
ext4_clear_feature_journal_needs_recovery(sb);
}
- error = ext4_commit_super(sb, 1);
+ error = ext4_commit_super(sb);
out:
if (journal)
/* we rely on upper layer to stop further updates */
@@ -5727,7 +5773,7 @@ static int ext4_unfreeze(struct super_block *sb)
ext4_set_feature_journal_needs_recovery(sb);
}
- ext4_commit_super(sb, 1);
+ ext4_commit_super(sb);
return 0;
}
@@ -5987,7 +6033,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
}
if (sbi->s_journal == NULL && !(old_sb_flags & SB_RDONLY)) {
- err = ext4_commit_super(sb, 1);
+ err = ext4_commit_super(sb);
if (err)
goto restore_opts;
}
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 4e3b1f8c2e81..372208500f4e 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -792,8 +792,11 @@ static void ext4_xattr_update_super_block(handle_t *handle,
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access");
if (ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh) == 0) {
+ lock_buffer(EXT4_SB(sb)->s_sbh);
ext4_set_feature_xattr(sb);
- ext4_handle_dirty_super(handle, sb);
+ ext4_superblock_csum_set(sb);
+ unlock_buffer(EXT4_SB(sb)->s_sbh);
+ ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh);
}
}
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 2f305c097bd5..985a9e3f976d 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -354,6 +354,7 @@ struct io_ring_ctx {
unsigned cq_entries;
unsigned cq_mask;
atomic_t cq_timeouts;
+ unsigned cq_last_tm_flush;
unsigned long cq_check_overflow;
struct wait_queue_head cq_wait;
struct fasync_struct *cq_fasync;
@@ -1106,6 +1107,9 @@ static void io_sq_thread_drop_mm_files(void)
static int __io_sq_thread_acquire_files(struct io_ring_ctx *ctx)
{
+ if (current->flags & PF_EXITING)
+ return -EFAULT;
+
if (!current->files) {
struct files_struct *files;
struct nsproxy *nsproxy;
@@ -1133,6 +1137,8 @@ static int __io_sq_thread_acquire_mm(struct io_ring_ctx *ctx)
{
struct mm_struct *mm;
+ if (current->flags & PF_EXITING)
+ return -EFAULT;
if (current->mm)
return 0;
@@ -1634,19 +1640,38 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx)
static void io_flush_timeouts(struct io_ring_ctx *ctx)
{
- while (!list_empty(&ctx->timeout_list)) {
+ u32 seq;
+
+ if (list_empty(&ctx->timeout_list))
+ return;
+
+ seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
+
+ do {
+ u32 events_needed, events_got;
struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
struct io_kiocb, timeout.list);
if (io_is_timeout_noseq(req))
break;
- if (req->timeout.target_seq != ctx->cached_cq_tail
- - atomic_read(&ctx->cq_timeouts))
+
+ /*
+ * Since seq can easily wrap around over time, subtract
+ * the last seq at which timeouts were flushed before comparing.
+ * Assuming not more than 2^31-1 events have happened since,
+ * these subtractions won't have wrapped, so we can check if
+ * target is in [last_seq, current_seq] by comparing the two.
+ */
+ events_needed = req->timeout.target_seq - ctx->cq_last_tm_flush;
+ events_got = seq - ctx->cq_last_tm_flush;
+ if (events_got < events_needed)
break;
list_del_init(&req->timeout.list);
io_kill_timeout(req);
- }
+ } while (!list_empty(&ctx->timeout_list));
+
+ ctx->cq_last_tm_flush = seq;
}
static void io_commit_cqring(struct io_ring_ctx *ctx)
@@ -5832,6 +5857,12 @@ static int io_timeout(struct io_kiocb *req)
tail = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
req->timeout.target_seq = tail + off;
+ /* Update the last seq here in case io_flush_timeouts() hasn't.
+ * This is safe because ->completion_lock is held, and submissions
+ * and completions are never mixed in the same ->completion_lock section.
+ */
+ ctx->cq_last_tm_flush = tail;
+
/*
* Insertion sort, ensuring the first entry in the list is always
* the one we need first.
@@ -7056,6 +7087,7 @@ static int io_sq_thread(void *data)
if (sqt_spin || !time_after(jiffies, timeout)) {
io_run_task_work();
+ io_sq_thread_drop_mm_files();
cond_resched();
if (sqt_spin)
timeout = jiffies + sqd->sq_thread_idle;
@@ -7093,6 +7125,7 @@ static int io_sq_thread(void *data)
}
io_run_task_work();
+ io_sq_thread_drop_mm_files();
if (cur_css)
io_sq_thread_unassociate_blkcg();
@@ -8888,7 +8921,8 @@ static void io_disable_sqo_submit(struct io_ring_ctx *ctx)
mutex_unlock(&ctx->uring_lock);
/* make sure callers enter the ring to get error */
- io_ring_set_wakeup_flag(ctx);
+ if (ctx->rings)
+ io_ring_set_wakeup_flag(ctx);
}
/*
@@ -9067,6 +9101,7 @@ void __io_uring_task_cancel(void)
finish_wait(&tctx->wait, &wait);
} while (1);
+ finish_wait(&tctx->wait, &wait);
atomic_dec(&tctx->in_idle);
io_uring_remove_task_files(tctx);
@@ -9700,6 +9735,7 @@ static int io_uring_create(unsigned entries, struct io_uring_params *p,
*/
ret = io_uring_install_fd(ctx, file);
if (ret < 0) {
+ io_disable_sqo_submit(ctx);
/* fput will clean it up */
fput(file);
return ret;
diff --git a/fs/namespace.c b/fs/namespace.c
index d2db7dfe232b..9d33909d0f9e 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1713,8 +1713,6 @@ static int can_umount(const struct path *path, int flags)
{
struct mount *mnt = real_mount(path->mnt);
- if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
- return -EINVAL;
if (!may_mount())
return -EPERM;
if (path->dentry != path->mnt->mnt_root)
@@ -1728,6 +1726,7 @@ static int can_umount(const struct path *path, int flags)
return 0;
}
+// caller is responsible for flags being sane
int path_umount(struct path *path, int flags)
{
struct mount *mnt = real_mount(path->mnt);
@@ -1749,6 +1748,10 @@ static int ksys_umount(char __user *name, int flags)
struct path path;
int ret;
+ // basic validity checks done first
+ if (flags & ~(MNT_FORCE | MNT_DETACH | MNT_EXPIRE | UMOUNT_NOFOLLOW))
+ return -EINVAL;
+
if (!(flags & UMOUNT_NOFOLLOW))
lookup_flags |= LOOKUP_FOLLOW;
ret = user_path_at(AT_FDCWD, name, lookup_flags, &path);
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 821db21ba072..34b880211e5e 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -865,9 +865,14 @@ compose_entry_fh(struct nfsd3_readdirres *cd, struct svc_fh *fhp,
if (isdotent(name, namlen)) {
if (namlen == 2) {
dchild = dget_parent(dparent);
- /* filesystem root - cannot return filehandle for ".." */
+ /*
+ * Don't return filehandle for ".." if we're at
+ * the filesystem or export root:
+ */
if (dchild == dparent)
goto out;
+ if (dparent == exp->ex_path.dentry)
+ goto out;
} else
dchild = dget(dparent);
} else
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index ee5a235b3056..602e3a52884d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1035,6 +1035,25 @@ struct clear_refs_private {
};
#ifdef CONFIG_MEM_SOFT_DIRTY
+
+#define is_cow_mapping(flags) (((flags) & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE)
+
+static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte)
+{
+ struct page *page;
+
+ if (!pte_write(pte))
+ return false;
+ if (!is_cow_mapping(vma->vm_flags))
+ return false;
+ if (likely(!atomic_read(&vma->vm_mm->has_pinned)))
+ return false;
+ page = vm_normal_page(vma, addr, pte);
+ if (!page)
+ return false;
+ return page_maybe_dma_pinned(page);
+}
+
static inline void clear_soft_dirty(struct vm_area_struct *vma,
unsigned long addr, pte_t *pte)
{
@@ -1049,6 +1068,8 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
if (pte_present(ptent)) {
pte_t old_pte;
+ if (pte_is_pinned(vma, addr, ptent))
+ return;
old_pte = ptep_modify_prot_start(vma, addr, pte);
ptent = pte_wrprotect(old_pte);
ptent = pte_clear_soft_dirty(ptent);
@@ -1215,41 +1236,26 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
.type = type,
};
+ if (mmap_write_lock_killable(mm)) {
+ count = -EINTR;
+ goto out_mm;
+ }
if (type == CLEAR_REFS_MM_HIWATER_RSS) {
- if (mmap_write_lock_killable(mm)) {
- count = -EINTR;
- goto out_mm;
- }
-
/*
* Writing 5 to /proc/pid/clear_refs resets the peak
* resident set size to this mm's current rss value.
*/
reset_mm_hiwater_rss(mm);
- mmap_write_unlock(mm);
- goto out_mm;
+ goto out_unlock;
}
- if (mmap_read_lock_killable(mm)) {
- count = -EINTR;
- goto out_mm;
- }
tlb_gather_mmu(&tlb, mm, 0, -1);
if (type == CLEAR_REFS_SOFT_DIRTY) {
for (vma = mm->mmap; vma; vma = vma->vm_next) {
if (!(vma->vm_flags & VM_SOFTDIRTY))
continue;
- mmap_read_unlock(mm);
- if (mmap_write_lock_killable(mm)) {
- count = -EINTR;
- goto out_mm;
- }
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
- vma->vm_flags &= ~VM_SOFTDIRTY;
- vma_set_page_prot(vma);
- }
- mmap_write_downgrade(mm);
- break;
+ vma->vm_flags &= ~VM_SOFTDIRTY;
+ vma_set_page_prot(vma);
}
mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY,
@@ -1261,7 +1267,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
if (type == CLEAR_REFS_SOFT_DIRTY)
mmu_notifier_invalidate_range_end(&range);
tlb_finish_mmu(&tlb, 0, -1);
- mmap_read_unlock(mm);
+out_unlock:
+ mmap_write_unlock(mm);
out_mm:
mmput(mm);
}
diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index dd90c9792909..0e7316a86240 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -11,19 +11,19 @@
* See Documentation/atomic_bitops.txt for details.
*/
-static inline void set_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void set_bit(unsigned int nr, volatile unsigned long *p)
{
p += BIT_WORD(nr);
atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
}
-static inline void clear_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void clear_bit(unsigned int nr, volatile unsigned long *p)
{
p += BIT_WORD(nr);
atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
}
-static inline void change_bit(unsigned int nr, volatile unsigned long *p)
+static __always_inline void change_bit(unsigned int nr, volatile unsigned long *p)
{
p += BIT_WORD(nr);
atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 74c6c0486eed..555ab0fddbef 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -13,6 +13,12 @@
/* https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 */
#if GCC_VERSION < 40900
# error Sorry, your version of GCC is too old - please use 4.9 or newer.
+#elif defined(CONFIG_ARM64) && GCC_VERSION < 50100
+/*
+ * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63293
+ * https://lore.kernel.org/r/20210107111841.GN1551@shell.armlinux.org.uk
+ */
+# error Sorry, your version of GCC is too old - please use 5.1 or newer.
#endif
/*
diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h
index 29d255fdd5d6..90bd558a17f5 100644
--- a/include/linux/dm-bufio.h
+++ b/include/linux/dm-bufio.h
@@ -150,6 +150,7 @@ void dm_bufio_set_minimum_buffers(struct dm_bufio_client *c, unsigned n);
unsigned dm_bufio_get_block_size(struct dm_bufio_client *c);
sector_t dm_bufio_get_device_size(struct dm_bufio_client *c);
+struct dm_io_client *dm_bufio_get_dm_io_client(struct dm_bufio_client *c);
sector_t dm_bufio_get_block_number(struct dm_buffer *b);
void *dm_bufio_get_block_data(struct dm_buffer *b);
void *dm_bufio_get_aux_data(struct dm_buffer *b);
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 5e0655fb2a6f..fe1ae73ff8b5 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -35,8 +35,12 @@ struct kunit_kasan_expectation {
#define KASAN_SHADOW_INIT 0
#endif
+#ifndef PTE_HWTABLE_PTRS
+#define PTE_HWTABLE_PTRS 0
+#endif
+
extern unsigned char kasan_early_shadow_page[PAGE_SIZE];
-extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE];
+extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS];
extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD];
extern pud_t kasan_early_shadow_pud[PTRS_PER_PUD];
extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D];
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d827bd7f3bfe..eeb0b52203e9 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -665,7 +665,7 @@ static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
{
struct mem_cgroup *memcg = page_memcg(page);
- VM_WARN_ON_ONCE_PAGE(!memcg, page);
+ VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page);
return mem_cgroup_lruvec(memcg, pgdat);
}
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index bf7966776c55..505480217cf1 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -163,8 +163,6 @@ int arm_pmu_acpi_probe(armpmu_init_fn init_fn);
static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; }
#endif
-bool arm_pmu_irq_is_nmi(void);
-
/* Internal functions only for core arm_pmu code */
struct arm_pmu *armpmu_alloc(void);
struct arm_pmu *armpmu_alloc_atomic(void);
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 58994e013022..6f89c27265f5 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1424,13 +1424,61 @@ TRACE_EVENT(rpcb_unregister,
)
);
+/* Record an xdr_buf containing a fully-formed RPC message */
+DECLARE_EVENT_CLASS(svc_xdr_msg_class,
+ TP_PROTO(
+ const struct xdr_buf *xdr
+ ),
+
+ TP_ARGS(xdr),
+
+ TP_STRUCT__entry(
+ __field(u32, xid)
+ __field(const void *, head_base)
+ __field(size_t, head_len)
+ __field(const void *, tail_base)
+ __field(size_t, tail_len)
+ __field(unsigned int, page_len)
+ __field(unsigned int, msg_len)
+ ),
+
+ TP_fast_assign(
+ __be32 *p = (__be32 *)xdr->head[0].iov_base;
+
+ __entry->xid = be32_to_cpu(*p);
+ __entry->head_base = p;
+ __entry->head_len = xdr->head[0].iov_len;
+ __entry->tail_base = xdr->tail[0].iov_base;
+ __entry->tail_len = xdr->tail[0].iov_len;
+ __entry->page_len = xdr->page_len;
+ __entry->msg_len = xdr->len;
+ ),
+
+ TP_printk("xid=0x%08x head=[%p,%zu] page=%u tail=[%p,%zu] len=%u",
+ __entry->xid,
+ __entry->head_base, __entry->head_len, __entry->page_len,
+ __entry->tail_base, __entry->tail_len, __entry->msg_len
+ )
+);
+
+#define DEFINE_SVCXDRMSG_EVENT(name) \
+ DEFINE_EVENT(svc_xdr_msg_class, \
+ svc_xdr_##name, \
+ TP_PROTO( \
+ const struct xdr_buf *xdr \
+ ), \
+ TP_ARGS(xdr))
+
+DEFINE_SVCXDRMSG_EVENT(recvfrom);
+
+/* Record an xdr_buf containing arbitrary data, tagged with an XID */
DECLARE_EVENT_CLASS(svc_xdr_buf_class,
TP_PROTO(
- const struct svc_rqst *rqst,
+ __be32 xid,
const struct xdr_buf *xdr
),
- TP_ARGS(rqst, xdr),
+ TP_ARGS(xid, xdr),
TP_STRUCT__entry(
__field(u32, xid)
@@ -1443,7 +1491,7 @@ DECLARE_EVENT_CLASS(svc_xdr_buf_class,
),
TP_fast_assign(
- __entry->xid = be32_to_cpu(rqst->rq_xid);
+ __entry->xid = be32_to_cpu(xid);
__entry->head_base = xdr->head[0].iov_base;
__entry->head_len = xdr->head[0].iov_len;
__entry->tail_base = xdr->tail[0].iov_base;
@@ -1463,12 +1511,11 @@ DECLARE_EVENT_CLASS(svc_xdr_buf_class,
DEFINE_EVENT(svc_xdr_buf_class, \
svc_xdr_##name, \
TP_PROTO( \
- const struct svc_rqst *rqst, \
+ __be32 xid, \
const struct xdr_buf *xdr \
), \
- TP_ARGS(rqst, xdr))
+ TP_ARGS(xid, xdr))
-DEFINE_SVCXDRBUF_EVENT(recvfrom);
DEFINE_SVCXDRBUF_EVENT(sendto);
/*
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index 00c7235ae93e..2c43b0ef1e4d 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -192,7 +192,7 @@ void xs_suspend_cancel(void);
struct work_struct;
-void xenbus_probe(struct work_struct *);
+void xenbus_probe(void);
#define XENBUS_IS_ERR_READ(str) ({ \
if (!IS_ERR(str) && strlen(str) == 0) { \
diff --git a/kernel/signal.c b/kernel/signal.c
index 5736c55aaa1a..6b9c431da08f 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2550,6 +2550,9 @@ bool get_signal(struct ksignal *ksig)
struct signal_struct *signal = current->signal;
int signr;
+ if (unlikely(current->task_works))
+ task_work_run();
+
/*
* For non-generic architectures, check for TIF_NOTIFY_SIGNAL so
* that the arch handlers don't all have to do it. If we get here
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 1635111c5bd2..a21e6a5792c5 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1658,7 +1658,7 @@ static int copy_compat_iovec_from_user(struct iovec *iov,
(const struct compat_iovec __user *)uvec;
int ret = -EFAULT, i;
- if (!user_access_begin(uvec, nr_segs * sizeof(*uvec)))
+ if (!user_access_begin(uiov, nr_segs * sizeof(*uiov)))
return -EFAULT;
for (i = 0; i < nr_segs; i++) {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a2602969873d..18f6ee317900 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4371,7 +4371,7 @@ retry:
* So we need to block hugepage fault by PG_hwpoison bit check.
*/
if (unlikely(PageHWPoison(page))) {
- ret = VM_FAULT_HWPOISON |
+ ret = VM_FAULT_HWPOISON_LARGE |
VM_FAULT_SET_HINDEX(hstate_index(h));
goto backout_unlocked;
}
diff --git a/mm/kasan/init.c b/mm/kasan/init.c
index bc0ad208b3a7..7ca0b92d5886 100644
--- a/mm/kasan/init.c
+++ b/mm/kasan/init.c
@@ -64,7 +64,8 @@ static inline bool kasan_pmd_table(pud_t pud)
return false;
}
#endif
-pte_t kasan_early_shadow_pte[PTRS_PER_PTE] __page_aligned_bss;
+pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS]
+ __page_aligned_bss;
static inline bool kasan_pte_table(pmd_t pmd)
{
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 5a38e9eade94..04d9f154a130 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1940,7 +1940,7 @@ retry:
goto retry;
}
} else if (ret == -EIO) {
- pr_info("%s: %#lx: unknown page type: %lx (%pGP)\n",
+ pr_info("%s: %#lx: unknown page type: %lx (%pGp)\n",
__func__, pfn, page->flags, &page->flags);
}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 8cf96bd21341..2c3a86502053 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1111,7 +1111,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
const nodemask_t *to, int flags)
{
int busy = 0;
- int err;
+ int err = 0;
nodemask_t tmp;
migrate_prep();
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index bdbec4c98173..027f6481ba59 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2862,20 +2862,20 @@ __rmqueue(struct zone *zone, unsigned int order, int migratetype,
{
struct page *page;
-#ifdef CONFIG_CMA
- /*
- * Balance movable allocations between regular and CMA areas by
- * allocating from CMA when over half of the zone's free memory
- * is in the CMA area.
- */
- if (alloc_flags & ALLOC_CMA &&
- zone_page_state(zone, NR_FREE_CMA_PAGES) >
- zone_page_state(zone, NR_FREE_PAGES) / 2) {
- page = __rmqueue_cma_fallback(zone, order);
- if (page)
- return page;
+ if (IS_ENABLED(CONFIG_CMA)) {
+ /*
+ * Balance movable allocations between regular and CMA areas by
+ * allocating from CMA when over half of the zone's free memory
+ * is in the CMA area.
+ */
+ if (alloc_flags & ALLOC_CMA &&
+ zone_page_state(zone, NR_FREE_CMA_PAGES) >
+ zone_page_state(zone, NR_FREE_PAGES) / 2) {
+ page = __rmqueue_cma_fallback(zone, order);
+ if (page)
+ goto out;
+ }
}
-#endif
retry:
page = __rmqueue_smallest(zone, order, migratetype);
if (unlikely(!page)) {
@@ -2886,8 +2886,9 @@ retry:
alloc_flags))
goto retry;
}
-
- trace_mm_page_alloc_zone_locked(page, order, migratetype);
+out:
+ if (page)
+ trace_mm_page_alloc_zone_locked(page, order, migratetype);
return page;
}
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 4bcc11958089..f5fee9cf90f8 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -9,6 +9,7 @@
#include <linux/mm.h>
#include <linux/uio.h>
#include <linux/sched.h>
+#include <linux/compat.h>
#include <linux/sched/mm.h>
#include <linux/highmem.h>
#include <linux/ptrace.h>
diff --git a/mm/slub.c b/mm/slub.c
index dc5b42e700b8..d9e4e10683cc 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1973,7 +1973,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
t = acquire_slab(s, n, page, object == NULL, &objects);
if (!t)
- break;
+ continue; /* cmpxchg raced */
available += objects;
if (!object) {
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 4d88fe5a277a..e6f352bf0498 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2420,8 +2420,10 @@ void *vmap(struct page **pages, unsigned int count,
return NULL;
}
- if (flags & VM_MAP_PUT_PAGES)
+ if (flags & VM_MAP_PUT_PAGES) {
area->pages = pages;
+ area->nr_pages = count;
+ }
return area->addr;
}
EXPORT_SYMBOL(vmap);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 257cba79a96d..b1b574ad199d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1238,6 +1238,8 @@ static unsigned int shrink_page_list(struct list_head *page_list,
if (!PageSwapCache(page)) {
if (!(sc->gfp_mask & __GFP_IO))
goto keep_locked;
+ if (page_maybe_dma_pinned(page))
+ goto keep_locked;
if (PageTransHuge(page)) {
/* cannot split THP, skip it */
if (!can_split_huge_page(page, NULL))
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 5fb9164aa690..dcc50ae54550 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -857,6 +857,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
err = -EAGAIN;
if (len <= 0)
goto out_release;
+ trace_svc_xdr_recvfrom(&rqstp->rq_arg);
clear_bit(XPT_OLD, &xprt->xpt_flags);
@@ -866,7 +867,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
if (serv->sv_stats)
serv->sv_stats->netcnt++;
- trace_svc_xdr_recvfrom(rqstp, &rqstp->rq_arg);
return len;
out_release:
rqstp->rq_res.len = 0;
@@ -904,7 +904,7 @@ int svc_send(struct svc_rqst *rqstp)
xb->len = xb->head[0].iov_len +
xb->page_len +
xb->tail[0].iov_len;
- trace_svc_xdr_sendto(rqstp, xb);
+ trace_svc_xdr_sendto(rqstp->rq_xid, xb);
trace_svc_stats_latency(rqstp);
len = xprt->xpt_ops->xpo_sendto(rqstp);
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 7d8026f3f377..a0cd28cd31a8 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -275,7 +275,9 @@ static void dump_common_audit_data(struct audit_buffer *ab,
struct inode *inode;
audit_log_format(ab, " name=");
+ spin_lock(&a->u.dentry->d_lock);
audit_log_untrustedstring(ab, a->u.dentry->d_name.name);
+ spin_unlock(&a->u.dentry->d_lock);
inode = d_backing_inode(a->u.dentry);
if (inode) {
@@ -293,8 +295,9 @@ static void dump_common_audit_data(struct audit_buffer *ab,
dentry = d_find_alias(inode);
if (dentry) {
audit_log_format(ab, " name=");
- audit_log_untrustedstring(ab,
- dentry->d_name.name);
+ spin_lock(&dentry->d_lock);
+ audit_log_untrustedstring(ab, dentry->d_name.name);
+ spin_unlock(&dentry->d_lock);
dput(dentry);
}
audit_log_format(ab, " dev=");
diff --git a/tools/bootconfig/scripts/bconf2ftrace.sh b/tools/bootconfig/scripts/bconf2ftrace.sh
index 595e164dc352..feb30c2c7881 100755
--- a/tools/bootconfig/scripts/bconf2ftrace.sh
+++ b/tools/bootconfig/scripts/bconf2ftrace.sh
@@ -152,6 +152,7 @@ setup_instance() { # [instance]
set_array_of ${instance}.options ${instancedir}/trace_options
set_value_of ${instance}.trace_clock ${instancedir}/trace_clock
set_value_of ${instance}.cpumask ${instancedir}/tracing_cpumask
+ set_value_of ${instance}.tracing_on ${instancedir}/tracing_on
set_value_of ${instance}.tracer ${instancedir}/current_tracer
set_array_of ${instance}.ftrace.filters \
${instancedir}/set_ftrace_filter
diff --git a/tools/bootconfig/scripts/ftrace2bconf.sh b/tools/bootconfig/scripts/ftrace2bconf.sh
index 6c0d4b61e0c2..a0c3bcc6da4f 100755
--- a/tools/bootconfig/scripts/ftrace2bconf.sh
+++ b/tools/bootconfig/scripts/ftrace2bconf.sh
@@ -221,6 +221,10 @@ instance_options() { # [instance-name]
if [ `echo $val | sed -e s/f//g`x != x ]; then
emit_kv $PREFIX.cpumask = $val
fi
+ val=`cat $INSTANCE/tracing_on`
+ if [ `echo $val | sed -e s/f//g`x != x ]; then
+ emit_kv $PREFIX.tracing_on = $val
+ fi
val=
for i in `cat $INSTANCE/set_event`; do
diff --git a/tools/include/linux/build_bug.h b/tools/include/linux/build_bug.h
index ce365d212768..cc7070c7439b 100644
--- a/tools/include/linux/build_bug.h
+++ b/tools/include/linux/build_bug.h
@@ -79,9 +79,4 @@
#define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
#endif // static_assert
-#ifdef __GENKSYMS__
-/* genksyms gets confused by _Static_assert */
-#define _Static_assert(expr, ...)
-#endif
-
#endif /* _LINUX_BUILD_BUG_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 886802b8ffba..374c67875cdb 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -251,6 +251,7 @@ struct kvm_hyperv_exit {
#define KVM_EXIT_X86_RDMSR 29
#define KVM_EXIT_X86_WRMSR 30
#define KVM_EXIT_DIRTY_RING_FULL 31
+#define KVM_EXIT_AP_RESET_HOLD 32
/* For KVM_EXIT_INTERNAL_ERROR */
/* Emulate instruction failed. */
@@ -573,6 +574,7 @@ struct kvm_vapic_addr {
#define KVM_MP_STATE_CHECK_STOP 6
#define KVM_MP_STATE_OPERATING 7
#define KVM_MP_STATE_LOAD 8
+#define KVM_MP_STATE_AP_RESET_HOLD 9
struct kvm_mp_state {
__u32 mp_state;
diff --git a/tools/lib/perf/tests/test-cpumap.c b/tools/lib/perf/tests/test-cpumap.c
index c8d45091e7c2..c70e9e03af3e 100644
--- a/tools/lib/perf/tests/test-cpumap.c
+++ b/tools/lib/perf/tests/test-cpumap.c
@@ -27,5 +27,5 @@ int main(int argc, char **argv)
perf_cpu_map__put(cpus);
__T_END;
- return 0;
+ return tests_failed == 0 ? 0 : -1;
}
diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c
index 6d8ebe0c2504..e2ac0b7f432e 100644
--- a/tools/lib/perf/tests/test-evlist.c
+++ b/tools/lib/perf/tests/test-evlist.c
@@ -208,13 +208,13 @@ static int test_mmap_thread(void)
char path[PATH_MAX];
int id, err, pid, go_pipe[2];
union perf_event *event;
- char bf;
int count = 0;
snprintf(path, PATH_MAX, "%s/kernel/debug/tracing/events/syscalls/sys_enter_prctl/id",
sysfs__mountpoint());
if (filename__read_int(path, &id)) {
+ tests_failed++;
fprintf(stderr, "error: failed to get tracepoint id: %s\n", path);
return -1;
}
@@ -229,6 +229,7 @@ static int test_mmap_thread(void)
pid = fork();
if (!pid) {
int i;
+ char bf;
read(go_pipe[0], &bf, 1);
@@ -266,7 +267,7 @@ static int test_mmap_thread(void)
perf_evlist__enable(evlist);
/* kick the child and wait for it to finish */
- write(go_pipe[1], &bf, 1);
+ write(go_pipe[1], "A", 1);
waitpid(pid, NULL, 0);
/*
@@ -409,5 +410,5 @@ int main(int argc, char **argv)
test_mmap_cpus();
__T_END;
- return 0;
+ return tests_failed == 0 ? 0 : -1;
}
diff --git a/tools/lib/perf/tests/test-evsel.c b/tools/lib/perf/tests/test-evsel.c
index 135722ac965b..0ad82d7a2a51 100644
--- a/tools/lib/perf/tests/test-evsel.c
+++ b/tools/lib/perf/tests/test-evsel.c
@@ -131,5 +131,5 @@ int main(int argc, char **argv)
test_stat_thread_enable();
__T_END;
- return 0;
+ return tests_failed == 0 ? 0 : -1;
}
diff --git a/tools/lib/perf/tests/test-threadmap.c b/tools/lib/perf/tests/test-threadmap.c
index 7dc4d6fbedde..384471441b48 100644
--- a/tools/lib/perf/tests/test-threadmap.c
+++ b/tools/lib/perf/tests/test-threadmap.c
@@ -27,5 +27,5 @@ int main(int argc, char **argv)
perf_thread_map__put(threads);
__T_END;
- return 0;
+ return tests_failed == 0 ? 0 : -1;
}
diff --git a/tools/perf/examples/bpf/5sec.c b/tools/perf/examples/bpf/5sec.c
index 65c4ff6892d9..e6b6181c6dc6 100644
--- a/tools/perf/examples/bpf/5sec.c
+++ b/tools/perf/examples/bpf/5sec.c
@@ -39,7 +39,7 @@
Copyright (C) 2018 Red Hat, Inc., Arnaldo Carvalho de Melo <acme@redhat.com>
*/
-#include <bpf/bpf.h>
+#include <bpf.h>
#define NSEC_PER_SEC 1000000000L
diff --git a/tools/perf/tests/shell/stat+shadow_stat.sh b/tools/perf/tests/shell/stat+shadow_stat.sh
index 249dfe48cf6a..ebebd3596cf9 100755
--- a/tools/perf/tests/shell/stat+shadow_stat.sh
+++ b/tools/perf/tests/shell/stat+shadow_stat.sh
@@ -9,31 +9,29 @@ perf stat -a true > /dev/null 2>&1 || exit 2
test_global_aggr()
{
- local cyc
-
perf stat -a --no-big-num -e cycles,instructions sleep 1 2>&1 | \
grep -e cycles -e instructions | \
while read num evt hash ipc rest
do
# skip not counted events
- if [[ $num == "<not" ]]; then
+ if [ "$num" = "<not" ]; then
continue
fi
# save cycles count
- if [[ $evt == "cycles" ]]; then
+ if [ "$evt" = "cycles" ]; then
cyc=$num
continue
fi
# skip if no cycles
- if [[ -z $cyc ]]; then
+ if [ -z "$cyc" ]; then
continue
fi
# use printf for rounding and a leading zero
- local res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
- if [[ $ipc != $res ]]; then
+ res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
+ if [ "$ipc" != "$res" ]; then
echo "IPC is different: $res != $ipc ($num / $cyc)"
exit 1
fi
@@ -42,32 +40,32 @@ test_global_aggr()
test_no_aggr()
{
- declare -A results
-
perf stat -a -A --no-big-num -e cycles,instructions sleep 1 2>&1 | \
grep ^CPU | \
while read cpu num evt hash ipc rest
do
# skip not counted events
- if [[ $num == "<not" ]]; then
+ if [ "$num" = "<not" ]; then
continue
fi
# save cycles count
- if [[ $evt == "cycles" ]]; then
- results[$cpu]=$num
+ if [ "$evt" = "cycles" ]; then
+ results="$results $cpu:$num"
continue
fi
+ cyc=${results##* $cpu:}
+ cyc=${cyc%% *}
+
# skip if no cycles
- local cyc=${results[$cpu]}
- if [[ -z $cyc ]]; then
+ if [ -z "$cyc" ]; then
continue
fi
# use printf for rounding and a leading zero
- local res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
- if [[ $ipc != $res ]]; then
+ res=`printf "%.2f" $(echo "scale=6; $num / $cyc" | bc -q)`
+ if [ "$ipc" != "$res" ]; then
echo "IPC is different for $cpu: $res != $ipc ($num / $cyc)"
exit 1
fi
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 062383e225a3..c4ed3dc2c8f4 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -3323,6 +3323,14 @@ int perf_session__write_header(struct perf_session *session,
attr_offset = lseek(ff.fd, 0, SEEK_CUR);
evlist__for_each_entry(evlist, evsel) {
+ if (evsel->core.attr.size < sizeof(evsel->core.attr)) {
+ /*
+ * We are likely in "perf inject" and have read
+ * from an older file. Update attr size so that
+ * reader gets the right offset to the ids.
+ */
+ evsel->core.attr.size = sizeof(evsel->core.attr);
+ }
f_attr = (struct perf_file_attr){
.attr = evsel->core.attr,
.ids = {
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index f841f3503cae..1e9d3f982b47 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2980,7 +2980,7 @@ int machines__for_each_thread(struct machines *machines,
pid_t machine__get_current_tid(struct machine *machine, int cpu)
{
- int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
+ int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS);
if (cpu < 0 || cpu >= nr_cpus || !machine->current_tid)
return -1;
@@ -2992,7 +2992,7 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
pid_t tid)
{
struct thread *thread;
- int nr_cpus = min(machine->env->nr_cpus_online, MAX_NR_CPUS);
+ int nr_cpus = min(machine->env->nr_cpus_avail, MAX_NR_CPUS);
if (cpu < 0)
return -EINVAL;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 50ff9795a4f1..25adbcce0281 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -2404,7 +2404,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
{
int i, err = -1;
struct perf_cpu_map *map;
- int nr_cpus = min(session->header.env.nr_cpus_online, MAX_NR_CPUS);
+ int nr_cpus = min(session->header.env.nr_cpus_avail, MAX_NR_CPUS);
for (i = 0; i < PERF_TYPE_MAX; ++i) {
struct evsel *evsel;
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 901265127e36..12eafd12a693 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -8,6 +8,7 @@
#include "evlist.h"
#include "expr.h"
#include "metricgroup.h"
+#include "cgroup.h"
#include <linux/zalloc.h>
/*
@@ -28,6 +29,7 @@ struct saved_value {
enum stat_type type;
int ctx;
int cpu;
+ struct cgroup *cgrp;
struct runtime_stat *stat;
struct stats stats;
u64 metric_total;
@@ -57,6 +59,9 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
if (a->ctx != b->ctx)
return a->ctx - b->ctx;
+ if (a->cgrp != b->cgrp)
+ return (char *)a->cgrp < (char *)b->cgrp ? -1 : +1;
+
if (a->evsel == NULL && b->evsel == NULL) {
if (a->stat == b->stat)
return 0;
@@ -100,7 +105,8 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel,
bool create,
enum stat_type type,
int ctx,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct cgroup *cgrp)
{
struct rblist *rblist;
struct rb_node *nd;
@@ -110,10 +116,15 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel,
.type = type,
.ctx = ctx,
.stat = st,
+ .cgrp = cgrp,
};
rblist = &st->value_list;
+ /* don't use context info for clock events */
+ if (type == STAT_NSECS)
+ dm.ctx = 0;
+
nd = rblist__find(rblist, &dm);
if (nd)
return container_of(nd, struct saved_value, rb_node);
@@ -191,12 +202,18 @@ void perf_stat__reset_shadow_per_stat(struct runtime_stat *st)
reset_stat(st);
}
+struct runtime_stat_data {
+ int ctx;
+ struct cgroup *cgrp;
+};
+
static void update_runtime_stat(struct runtime_stat *st,
enum stat_type type,
- int ctx, int cpu, u64 count)
+ int cpu, u64 count,
+ struct runtime_stat_data *rsd)
{
- struct saved_value *v = saved_value_lookup(NULL, cpu, true,
- type, ctx, st);
+ struct saved_value *v = saved_value_lookup(NULL, cpu, true, type,
+ rsd->ctx, st, rsd->cgrp);
if (v)
update_stats(&v->stats, count);
@@ -210,82 +227,86 @@ static void update_runtime_stat(struct runtime_stat *st,
void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
int cpu, struct runtime_stat *st)
{
- int ctx = evsel_context(counter);
u64 count_ns = count;
struct saved_value *v;
+ struct runtime_stat_data rsd = {
+ .ctx = evsel_context(counter),
+ .cgrp = counter->cgrp,
+ };
count *= counter->scale;
if (evsel__is_clock(counter))
- update_runtime_stat(st, STAT_NSECS, 0, cpu, count_ns);
+ update_runtime_stat(st, STAT_NSECS, cpu, count_ns, &rsd);
else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
- update_runtime_stat(st, STAT_CYCLES, ctx, cpu, count);
+ update_runtime_stat(st, STAT_CYCLES, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
- update_runtime_stat(st, STAT_CYCLES_IN_TX, ctx, cpu, count);
+ update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TRANSACTION_START))
- update_runtime_stat(st, STAT_TRANSACTION, ctx, cpu, count);
+ update_runtime_stat(st, STAT_TRANSACTION, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, ELISION_START))
- update_runtime_stat(st, STAT_ELISION, ctx, cpu, count);
+ update_runtime_stat(st, STAT_ELISION, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING))
update_runtime_stat(st, STAT_TOPDOWN_RETIRING,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC))
update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND))
update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND))
update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_BACK,
- ctx, cpu, count);
+ cpu, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
- update_runtime_stat(st, STAT_BRANCHES, ctx, cpu, count);
+ update_runtime_stat(st, STAT_BRANCHES, cpu, count, &rsd);
else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
- update_runtime_stat(st, STAT_CACHEREFS, ctx, cpu, count);
+ update_runtime_stat(st, STAT_CACHEREFS, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
- update_runtime_stat(st, STAT_L1_DCACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_L1_DCACHE, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
- update_runtime_stat(st, STAT_L1_ICACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_L1_ICACHE, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL))
- update_runtime_stat(st, STAT_LL_CACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_LL_CACHE, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
- update_runtime_stat(st, STAT_DTLB_CACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_DTLB_CACHE, cpu, count, &rsd);
else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
- update_runtime_stat(st, STAT_ITLB_CACHE, ctx, cpu, count);
+ update_runtime_stat(st, STAT_ITLB_CACHE, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, SMI_NUM))
- update_runtime_stat(st, STAT_SMI_NUM, ctx, cpu, count);
+ update_runtime_stat(st, STAT_SMI_NUM, cpu, count, &rsd);
else if (perf_stat_evsel__is(counter, APERF))
- update_runtime_stat(st, STAT_APERF, ctx, cpu, count);
+ update_runtime_stat(st, STAT_APERF, cpu, count, &rsd);
if (counter->collect_stat) {
- v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st);
+ v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st,
+ rsd.cgrp);
update_stats(&v->stats, count);
if (counter->metric_leader)
v->metric_total += count;
} else if (counter->metric_leader) {
v = saved_value_lookup(counter->metric_leader,
- cpu, true, STAT_NONE, 0, st);
+ cpu, true, STAT_NONE, 0, st, rsd.cgrp);
v->metric_total += count;
v->metric_other++;
}
@@ -422,11 +443,12 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
}
static double runtime_stat_avg(struct runtime_stat *st,
- enum stat_type type, int ctx, int cpu)
+ enum stat_type type, int cpu,
+ struct runtime_stat_data *rsd)
{
struct saved_value *v;
- v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+ v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
if (!v)
return 0.0;
@@ -434,11 +456,12 @@ static double runtime_stat_avg(struct runtime_stat *st,
}
static double runtime_stat_n(struct runtime_stat *st,
- enum stat_type type, int ctx, int cpu)
+ enum stat_type type, int cpu,
+ struct runtime_stat_data *rsd)
{
struct saved_value *v;
- v = saved_value_lookup(NULL, cpu, false, type, ctx, st);
+ v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
if (!v)
return 0.0;
@@ -446,16 +469,15 @@ static double runtime_stat_n(struct runtime_stat *st,
}
static void print_stalled_cycles_frontend(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel, double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -470,16 +492,15 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config,
}
static void print_stalled_cycles_backend(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel, double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -490,17 +511,15 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config,
}
static void print_branch_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_BRANCHES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_BRANCHES, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -511,18 +530,15 @@ static void print_branch_misses(struct perf_stat_config *config,
}
static void print_l1_dcache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
-
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_L1_DCACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -533,18 +549,15 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
}
static void print_l1_icache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
-
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_L1_ICACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -554,17 +567,15 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
}
static void print_dtlb_cache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_DTLB_CACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -574,17 +585,15 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
}
static void print_itlb_cache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_ITLB_CACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -594,17 +603,15 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
}
static void print_ll_cache_misses(struct perf_stat_config *config,
- int cpu,
- struct evsel *evsel,
- double avg,
+ int cpu, double avg,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double total, ratio = 0.0;
const char *color;
- int ctx = evsel_context(evsel);
- total = runtime_stat_avg(st, STAT_LL_CACHE, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_LL_CACHE, cpu, rsd);
if (total)
ratio = avg / total * 100.0;
@@ -662,56 +669,61 @@ static double sanitize_val(double x)
return x;
}
-static double td_total_slots(int ctx, int cpu, struct runtime_stat *st)
+static double td_total_slots(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
- return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, ctx, cpu);
+ return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu, rsd);
}
-static double td_bad_spec(int ctx, int cpu, struct runtime_stat *st)
+static double td_bad_spec(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double bad_spec = 0;
double total_slots;
double total;
- total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, ctx, cpu) -
- runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, ctx, cpu) +
- runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu, rsd) -
+ runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu, rsd) +
+ runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu, rsd);
- total_slots = td_total_slots(ctx, cpu, st);
+ total_slots = td_total_slots(cpu, st, rsd);
if (total_slots)
bad_spec = total / total_slots;
return sanitize_val(bad_spec);
}
-static double td_retiring(int ctx, int cpu, struct runtime_stat *st)
+static double td_retiring(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double retiring = 0;
- double total_slots = td_total_slots(ctx, cpu, st);
+ double total_slots = td_total_slots(cpu, st, rsd);
double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED,
- ctx, cpu);
+ cpu, rsd);
if (total_slots)
retiring = ret_slots / total_slots;
return retiring;
}
-static double td_fe_bound(int ctx, int cpu, struct runtime_stat *st)
+static double td_fe_bound(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double fe_bound = 0;
- double total_slots = td_total_slots(ctx, cpu, st);
+ double total_slots = td_total_slots(cpu, st, rsd);
double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES,
- ctx, cpu);
+ cpu, rsd);
if (total_slots)
fe_bound = fetch_bub / total_slots;
return fe_bound;
}
-static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
+static double td_be_bound(int cpu, struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
- double sum = (td_fe_bound(ctx, cpu, st) +
- td_bad_spec(ctx, cpu, st) +
- td_retiring(ctx, cpu, st));
+ double sum = (td_fe_bound(cpu, st, rsd) +
+ td_bad_spec(cpu, st, rsd) +
+ td_retiring(cpu, st, rsd));
if (sum == 0)
return 0;
return sanitize_val(1.0 - sum);
@@ -722,15 +734,15 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
* the ratios we need to recreate the sum.
*/
-static double td_metric_ratio(int ctx, int cpu,
- enum stat_type type,
- struct runtime_stat *stat)
+static double td_metric_ratio(int cpu, enum stat_type type,
+ struct runtime_stat *stat,
+ struct runtime_stat_data *rsd)
{
- double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) +
- runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) +
- runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) +
- runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu);
- double d = runtime_stat_avg(stat, type, ctx, cpu);
+ double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) +
+ runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd);
+ double d = runtime_stat_avg(stat, type, cpu, rsd);
if (sum)
return d / sum;
@@ -742,34 +754,33 @@ static double td_metric_ratio(int ctx, int cpu,
* We allow two missing.
*/
-static bool full_td(int ctx, int cpu,
- struct runtime_stat *stat)
+static bool full_td(int cpu, struct runtime_stat *stat,
+ struct runtime_stat_data *rsd)
{
int c = 0;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) > 0)
c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) > 0)
c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) > 0)
c++;
- if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu) > 0)
+ if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd) > 0)
c++;
return c >= 2;
}
-static void print_smi_cost(struct perf_stat_config *config,
- int cpu, struct evsel *evsel,
+static void print_smi_cost(struct perf_stat_config *config, int cpu,
struct perf_stat_output_ctx *out,
- struct runtime_stat *st)
+ struct runtime_stat *st,
+ struct runtime_stat_data *rsd)
{
double smi_num, aperf, cycles, cost = 0.0;
- int ctx = evsel_context(evsel);
const char *color = NULL;
- smi_num = runtime_stat_avg(st, STAT_SMI_NUM, ctx, cpu);
- aperf = runtime_stat_avg(st, STAT_APERF, ctx, cpu);
- cycles = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu, rsd);
+ aperf = runtime_stat_avg(st, STAT_APERF, cpu, rsd);
+ cycles = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
if ((cycles == 0) || (aperf == 0))
return;
@@ -804,7 +815,8 @@ static int prepare_metric(struct evsel **metric_events,
scale = 1e-9;
} else {
v = saved_value_lookup(metric_events[i], cpu, false,
- STAT_NONE, 0, st);
+ STAT_NONE, 0, st,
+ metric_events[i]->cgrp);
if (!v)
break;
stats = &v->stats;
@@ -930,12 +942,15 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric_t print_metric = out->print_metric;
double total, ratio = 0.0, total2;
const char *color = NULL;
- int ctx = evsel_context(evsel);
+ struct runtime_stat_data rsd = {
+ .ctx = evsel_context(evsel),
+ .cgrp = evsel->cgrp,
+ };
struct metric_event *me;
int num = 1;
if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
if (total) {
ratio = avg / total;
@@ -945,12 +960,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
}
- total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT,
- ctx, cpu);
+ total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu, &rsd);
total = max(total, runtime_stat_avg(st,
STAT_STALLED_CYCLES_BACK,
- ctx, cpu));
+ cpu, &rsd));
if (total && avg) {
out->new_line(config, ctxp);
@@ -960,8 +974,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
ratio);
}
} else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
- if (runtime_stat_n(st, STAT_BRANCHES, ctx, cpu) != 0)
- print_branch_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_BRANCHES, cpu, &rsd) != 0)
+ print_branch_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
} else if (
@@ -970,8 +984,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_L1_DCACHE, ctx, cpu) != 0)
- print_l1_dcache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_L1_DCACHE, cpu, &rsd) != 0)
+ print_l1_dcache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0);
} else if (
@@ -980,8 +994,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_L1_ICACHE, ctx, cpu) != 0)
- print_l1_icache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_L1_ICACHE, cpu, &rsd) != 0)
+ print_l1_icache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0);
} else if (
@@ -990,8 +1004,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_DTLB_CACHE, ctx, cpu) != 0)
- print_dtlb_cache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu, &rsd) != 0)
+ print_dtlb_cache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0);
} else if (
@@ -1000,8 +1014,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_ITLB_CACHE, ctx, cpu) != 0)
- print_itlb_cache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu, &rsd) != 0)
+ print_itlb_cache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0);
} else if (
@@ -1010,27 +1024,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
- if (runtime_stat_n(st, STAT_LL_CACHE, ctx, cpu) != 0)
- print_ll_cache_misses(config, cpu, evsel, avg, out, st);
+ if (runtime_stat_n(st, STAT_LL_CACHE, cpu, &rsd) != 0)
+ print_ll_cache_misses(config, cpu, avg, out, st, &rsd);
else
print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0);
} else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
- total = runtime_stat_avg(st, STAT_CACHEREFS, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CACHEREFS, cpu, &rsd);
if (total)
ratio = avg * 100 / total;
- if (runtime_stat_n(st, STAT_CACHEREFS, ctx, cpu) != 0)
+ if (runtime_stat_n(st, STAT_CACHEREFS, cpu, &rsd) != 0)
print_metric(config, ctxp, NULL, "%8.3f %%",
"of all cache refs", ratio);
else
print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
- print_stalled_cycles_frontend(config, cpu, evsel, avg, out, st);
+ print_stalled_cycles_frontend(config, cpu, avg, out, st, &rsd);
} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
- print_stalled_cycles_backend(config, cpu, evsel, avg, out, st);
+ print_stalled_cycles_backend(config, cpu, avg, out, st, &rsd);
} else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
- total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
+ total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
if (total) {
ratio = avg / total;
@@ -1039,7 +1053,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
}
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
if (total)
print_metric(config, ctxp, NULL,
@@ -1049,8 +1063,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
print_metric(config, ctxp, NULL, NULL, "transactional cycles",
0);
} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
- total = runtime_stat_avg(st, STAT_CYCLES, ctx, cpu);
- total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
+ total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
if (total2 < avg)
total2 = avg;
@@ -1060,21 +1074,19 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
else
print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
- total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
- ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
if (avg)
ratio = total / avg;
- if (runtime_stat_n(st, STAT_CYCLES_IN_TX, ctx, cpu) != 0)
+ if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu, &rsd) != 0)
print_metric(config, ctxp, NULL, "%8.0f",
"cycles / transaction", ratio);
else
print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
0);
} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
- total = runtime_stat_avg(st, STAT_CYCLES_IN_TX,
- ctx, cpu);
+ total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
if (avg)
ratio = total / avg;
@@ -1087,28 +1099,28 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
else
print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
- double fe_bound = td_fe_bound(ctx, cpu, st);
+ double fe_bound = td_fe_bound(cpu, st, &rsd);
if (fe_bound > 0.2)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
- double retiring = td_retiring(ctx, cpu, st);
+ double retiring = td_retiring(cpu, st, &rsd);
if (retiring > 0.7)
color = PERF_COLOR_GREEN;
print_metric(config, ctxp, color, "%8.1f%%", "retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
- double bad_spec = td_bad_spec(ctx, cpu, st);
+ double bad_spec = td_bad_spec(cpu, st, &rsd);
if (bad_spec > 0.1)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
bad_spec * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
- double be_bound = td_be_bound(ctx, cpu, st);
+ double be_bound = td_be_bound(cpu, st, &rsd);
const char *name = "backend bound";
static int have_recovery_bubbles = -1;
@@ -1121,43 +1133,43 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
if (be_bound > 0.2)
color = PERF_COLOR_RED;
- if (td_total_slots(ctx, cpu, st) > 0)
+ if (td_total_slots(cpu, st, &rsd) > 0)
print_metric(config, ctxp, color, "%8.1f%%", name,
be_bound * 100.);
else
print_metric(config, ctxp, NULL, NULL, name, 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) &&
- full_td(ctx, cpu, st)) {
- double retiring = td_metric_ratio(ctx, cpu,
- STAT_TOPDOWN_RETIRING, st);
-
+ full_td(cpu, st, &rsd)) {
+ double retiring = td_metric_ratio(cpu,
+ STAT_TOPDOWN_RETIRING, st,
+ &rsd);
if (retiring > 0.7)
color = PERF_COLOR_GREEN;
print_metric(config, ctxp, color, "%8.1f%%", "retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
- full_td(ctx, cpu, st)) {
- double fe_bound = td_metric_ratio(ctx, cpu,
- STAT_TOPDOWN_FE_BOUND, st);
-
+ full_td(cpu, st, &rsd)) {
+ double fe_bound = td_metric_ratio(cpu,
+ STAT_TOPDOWN_FE_BOUND, st,
+ &rsd);
if (fe_bound > 0.2)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
- full_td(ctx, cpu, st)) {
- double be_bound = td_metric_ratio(ctx, cpu,
- STAT_TOPDOWN_BE_BOUND, st);
-
+ full_td(cpu, st, &rsd)) {
+ double be_bound = td_metric_ratio(cpu,
+ STAT_TOPDOWN_BE_BOUND, st,
+ &rsd);
if (be_bound > 0.2)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
be_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
- full_td(ctx, cpu, st)) {
- double bad_spec = td_metric_ratio(ctx, cpu,
- STAT_TOPDOWN_BAD_SPEC, st);
-
+ full_td(cpu, st, &rsd)) {
+ double bad_spec = td_metric_ratio(cpu,
+ STAT_TOPDOWN_BAD_SPEC, st,
+ &rsd);
if (bad_spec > 0.1)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
@@ -1165,11 +1177,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
} else if (evsel->metric_expr) {
generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
evsel->name, evsel->metric_name, NULL, 1, cpu, out, st);
- } else if (runtime_stat_n(st, STAT_NSECS, 0, cpu) != 0) {
+ } else if (runtime_stat_n(st, STAT_NSECS, cpu, &rsd) != 0) {
char unit = 'M';
char unit_buf[10];
- total = runtime_stat_avg(st, STAT_NSECS, 0, cpu);
+ total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
if (total)
ratio = 1000.0 * avg / total;
@@ -1180,7 +1192,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
- print_smi_cost(config, cpu, evsel, out, st);
+ print_smi_cost(config, cpu, out, st, &rsd);
} else {
num = 0;
}
diff --git a/tools/testing/selftests/arm64/fp/fpsimd-test.S b/tools/testing/selftests/arm64/fp/fpsimd-test.S
index 1c5556bdd11d..0dbd594c2747 100644
--- a/tools/testing/selftests/arm64/fp/fpsimd-test.S
+++ b/tools/testing/selftests/arm64/fp/fpsimd-test.S
@@ -457,7 +457,7 @@ function barf
mov x11, x1 // actual data
mov x12, x2 // data size
- puts "Mistatch: PID="
+ puts "Mismatch: PID="
mov x0, x20
bl putdec
puts ", iteration="
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index f95074c9b48b..9210691aa998 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -625,7 +625,7 @@ function barf
mov x11, x1 // actual data
mov x12, x2 // data size
- puts "Mistatch: PID="
+ puts "Mismatch: PID="
mov x0, x20
bl putdec
puts ", iteration="