* Re: linux-next: manual merge of the swiotlb tree with the powerpc tree
From: Michael Ellerman @ 2019-02-22 3:17 UTC (permalink / raw)
To: Stephen Rothwell, Konrad Rzeszutek Wilk, Benjamin Herrenschmidt,
PowerPC
Cc: Dongli Zhang, Linux Next Mailing List, Linux Kernel Mailing List,
Christoph Hellwig
In-Reply-To: <20190222113624.2499244a@canb.auug.org.au>
Stephen Rothwell <sfr@canb.auug.org.au> writes:
> Hi all,
>
> Today's linux-next merge of the swiotlb tree got a conflict in:
>
> kernel/dma/swiotlb.c
>
> between commit:
>
> feee96440c9c ("swiotlb: remove swiotlb_dma_supported")
>
> from the powerpc tree and commit:
>
> 71602fe6d4e9 ("swiotlb: add debugfs to track swiotlb buffer usage")
>
> from the swiotlb tree.
>
> I fixed it up (see below) and can carry the fix as necessary. This
> is now fixed as far as linux-next is concerned, but any non trivial
> conflicts should be mentioned to your upstream maintainer when your tree
> is submitted for merging. You may also want to consider cooperating
> with the maintainer of the conflicting tree to minimise any particularly
> complex conflicts.
OK thanks. That looks pretty harmless as far as conflicts go.
cheers
^ permalink raw reply
* Re: [PATCH v3 2/2] powerpc: Enable kcov
From: Daniel Axtens @ 2019-02-22 2:29 UTC (permalink / raw)
To: Andrew Donnellan, linuxppc-dev; +Cc: npiggin, syzkaller, dvyukov
In-Reply-To: <20190222004046.14914-2-andrew.donnellan@au1.ibm.com>
Hi Andrew,
> kcov provides kernel coverage data that's useful for fuzzing tools like
> syzkaller.
>
> Wire up kcov support on powerpc. Disable kcov instrumentation on the same
> files where we currently disable gcov and UBSan instrumentation, plus some
> additional exclusions which appear necessary to boot on book3e machines.
>
> Signed-off-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
> Acked-by: Dmitry Vyukov <dvyukov@google.com>
> Tested-by: Daniel Axtens <dja@axtens.net> # e6500
Just confirming that this still works for me.
Regards,
Daniel
> ---
>
> v2->v3:
> - Add additional exclusions required to boot on book3e (dja)
> ---
> arch/powerpc/Kconfig | 1 +
> arch/powerpc/kernel/Makefile | 12 +++++++++++-
> arch/powerpc/kernel/trace/Makefile | 3 ++-
> arch/powerpc/kernel/vdso32/Makefile | 1 +
> arch/powerpc/kernel/vdso64/Makefile | 1 +
> arch/powerpc/mm/Makefile | 5 +++++
> arch/powerpc/xmon/Makefile | 1 +
> 7 files changed, 22 insertions(+), 2 deletions(-)
>
> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> index 2890d36eb531..d3698dae0e60 100644
> --- a/arch/powerpc/Kconfig
> +++ b/arch/powerpc/Kconfig
> @@ -134,6 +134,7 @@ config PPC
> select ARCH_HAS_ELF_RANDOMIZE
> select ARCH_HAS_FORTIFY_SOURCE
> select ARCH_HAS_GCOV_PROFILE_ALL
> + select ARCH_HAS_KCOV
> select ARCH_HAS_PHYS_TO_DMA
> select ARCH_HAS_PMEM_API if PPC64
> select ARCH_HAS_PTE_SPECIAL
> diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
> index cb7f0bb9ee71..3ae079014c04 100644
> --- a/arch/powerpc/kernel/Makefile
> +++ b/arch/powerpc/kernel/Makefile
> @@ -142,19 +142,29 @@ endif
> obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o
> obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o
>
> -# Disable GCOV & sanitizers in odd or sensitive code
> +# Disable GCOV, KCOV & sanitizers in odd or sensitive code
> GCOV_PROFILE_prom_init.o := n
> +KCOV_INSTRUMENT_prom_init.o := n
> UBSAN_SANITIZE_prom_init.o := n
> GCOV_PROFILE_machine_kexec_64.o := n
> +KCOV_INSTRUMENT_machine_kexec_64.o := n
> UBSAN_SANITIZE_machine_kexec_64.o := n
> GCOV_PROFILE_machine_kexec_32.o := n
> +KCOV_INSTRUMENT_machine_kexec_32.o := n
> UBSAN_SANITIZE_machine_kexec_32.o := n
> GCOV_PROFILE_kprobes.o := n
> +KCOV_INSTRUMENT_kprobes.o := n
> UBSAN_SANITIZE_kprobes.o := n
> GCOV_PROFILE_kprobes-ftrace.o := n
> +KCOV_INSTRUMENT_kprobes-ftrace.o := n
> UBSAN_SANITIZE_kprobes-ftrace.o := n
> UBSAN_SANITIZE_vdso.o := n
>
> +# Necessary for booting with kcov enabled on book3e machines
> +KCOV_INSTRUMENT_cputable.o := n
> +KCOV_INSTRUMENT_setup_64.o := n
> +KCOV_INSTRUMENT_paca.o := n
> +
> extra-$(CONFIG_PPC_FPU) += fpu.o
> extra-$(CONFIG_ALTIVEC) += vector.o
> extra-$(CONFIG_PPC64) += entry_64.o
> diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile
> index b1725ad3e13d..858503775c58 100644
> --- a/arch/powerpc/kernel/trace/Makefile
> +++ b/arch/powerpc/kernel/trace/Makefile
> @@ -23,6 +23,7 @@ obj-$(CONFIG_TRACING) += trace_clock.o
> obj-$(CONFIG_PPC64) += $(obj64-y)
> obj-$(CONFIG_PPC32) += $(obj32-y)
>
> -# Disable GCOV & sanitizers in odd or sensitive code
> +# Disable GCOV, KCOV & sanitizers in odd or sensitive code
> GCOV_PROFILE_ftrace.o := n
> +KCOV_INSTRUMENT_ftrace.o := n
> UBSAN_SANITIZE_ftrace.o := n
> diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
> index 50112d4473bb..ce199f6e4256 100644
> --- a/arch/powerpc/kernel/vdso32/Makefile
> +++ b/arch/powerpc/kernel/vdso32/Makefile
> @@ -23,6 +23,7 @@ targets := $(obj-vdso32) vdso32.so vdso32.so.dbg
> obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
>
> GCOV_PROFILE := n
> +KCOV_INSTRUMENT := n
> UBSAN_SANITIZE := n
>
> ccflags-y := -shared -fno-common -fno-builtin
> diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
> index 69cecb346269..28e7d112aa2f 100644
> --- a/arch/powerpc/kernel/vdso64/Makefile
> +++ b/arch/powerpc/kernel/vdso64/Makefile
> @@ -9,6 +9,7 @@ targets := $(obj-vdso64) vdso64.so vdso64.so.dbg
> obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
>
> GCOV_PROFILE := n
> +KCOV_INSTRUMENT := n
> UBSAN_SANITIZE := n
>
> ccflags-y := -shared -fno-common -fno-builtin
> diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
> index f965fc33a8b7..d4d32e229ace 100644
> --- a/arch/powerpc/mm/Makefile
> +++ b/arch/powerpc/mm/Makefile
> @@ -55,3 +55,8 @@ obj-$(CONFIG_PPC_BOOK3S_64) += dump_linuxpagetables-book3s64.o
> endif
> obj-$(CONFIG_PPC_HTDUMP) += dump_hashpagetable.o
> obj-$(CONFIG_PPC_MEM_KEYS) += pkeys.o
> +
> +# Disable kcov instrumentation on sensitive code
> +# This is necessary for booting with kcov enabled on book3e machines
> +KCOV_INSTRUMENT_tlb_nohash.o := n
> +KCOV_INSTRUMENT_fsl_booke_mmu.o := n
> diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
> index 878f9c1d3615..3050f9323254 100644
> --- a/arch/powerpc/xmon/Makefile
> +++ b/arch/powerpc/xmon/Makefile
> @@ -5,6 +5,7 @@
> subdir-ccflags-y := $(call cc-disable-warning, builtin-requires-header)
>
> GCOV_PROFILE := n
> +KCOV_INSTRUMENT := n
> UBSAN_SANITIZE := n
>
> # Disable ftrace for the entire directory
> --
> 2.11.0
^ permalink raw reply
* Re: [PATCH kernel] KVM: PPC: Improve KVM reference counting
From: Alexey Kardashevskiy @ 2019-02-22 1:33 UTC (permalink / raw)
To: Michael Ellerman, linuxppc-dev; +Cc: kvm-ppc, David Gibson
In-Reply-To: <87h8cxwtba.fsf@concordia.ellerman.id.au>
On 21/02/2019 17:26, Michael Ellerman wrote:
> Alexey Kardashevskiy <aik@ozlabs.ru> writes:
>
>> The anon fd's ops releases the KVM reference in the release hook.
>> However we reference the KVM object after we create the fd so there is
>> small window when the release function can be called and
>> dereferenced the KVM object which potentially may free it.
> dereference
>>
>> It is not a problem at the moment as the file is created and KVM is
>> referenced under the KVM lock and the release function obtains the same
>> lock before dereferencing the KVM (although the lock is not held when
>> calling kvm_put_kvm()) but it is a fragile against future changes.
>>
>> This references the KVM object before creating a file.
>>
>> Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
>> ---
>>
>> The original bug is described here:
>> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=cfa393811
>> But in this case kvm_put_kvm() is called straight away with no locks before/after/around.
>>
>> ---
>> arch/powerpc/kvm/book3s_64_vio.c | 7 ++++---
>> 1 file changed, 4 insertions(+), 3 deletions(-)
>>
>> diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
>> index 532ab797..d68c969 100644
>> --- a/arch/powerpc/kvm/book3s_64_vio.c
>> +++ b/arch/powerpc/kvm/book3s_64_vio.c
>> @@ -338,14 +338,15 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
>> }
>> }
>>
>> + kvm_get_kvm(kvm);
>> if (!ret)
>> ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
>> stt, O_RDWR | O_CLOEXEC);
>>
>> - if (ret >= 0) {
>> + if (ret >= 0)
>> list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
>> - kvm_get_kvm(kvm);
>> - }
>> + else
>> + kvm_put_kvm(kvm);
>>
>> mutex_unlock(&kvm->lock);
>
> This looks correct to me. But I feel like the logic could be cleaner,
> perhaps like this (patch below):
And I feel that 1) your patch tries to hide what it actually does 2)
having 2 unlocks for one lock is an invite for future bugs imho, I'd
think the whole point of adding new gotos is exactly to have 1 unlock.
>
> mutex_lock(&kvm->lock);
>
> /* Check this LIOBN hasn't been previously allocated */
> list_for_each_entry(siter, &kvm->arch.spapr_tce_tables, list) {
> if (siter->liobn == args->liobn) {
> ret = -EBUSY;
> goto fail_unlock;
> }
> }
>
> kvm_get_kvm(kvm);
> ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
> stt, O_RDWR | O_CLOEXEC);
>
> if (ret < 0) {
> kvm_put_kvm(kvm);
> goto fail_unlock;
> }
>
> list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
>
> mutex_unlock(&kvm->lock);
>
> return ret;
>
> fail_unlock:
> mutex_unlock(&kvm->lock);
> fail:
>
>
> cheers
>
> diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
> index 532ab79734c7..5d74602db0d0 100644
> --- a/arch/powerpc/kvm/book3s_64_vio.c
> +++ b/arch/powerpc/kvm/book3s_64_vio.c
> @@ -296,7 +296,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
> struct kvmppc_spapr_tce_table *stt = NULL;
> struct kvmppc_spapr_tce_table *siter;
> unsigned long npages, size = args->size;
> - int ret = -ENOMEM;
> + int ret;
> int i;
>
> if (!args->size || args->page_shift < 12 || args->page_shift > 34 ||
> @@ -330,28 +330,30 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
> mutex_lock(&kvm->lock);
>
> /* Check this LIOBN hasn't been previously allocated */
> - ret = 0;
> list_for_each_entry(siter, &kvm->arch.spapr_tce_tables, list) {
> if (siter->liobn == args->liobn) {
> ret = -EBUSY;
> - break;
> + goto fail_unlock;
> }
> }
>
> - if (!ret)
> - ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
> - stt, O_RDWR | O_CLOEXEC);
> + kvm_get_kvm(kvm);
> + ret = anon_inode_getfd("kvm-spapr-tce", &kvm_spapr_tce_fops,
> + stt, O_RDWR | O_CLOEXEC);
>
> - if (ret >= 0) {
> - list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
> - kvm_get_kvm(kvm);
> + if (ret < 0) {
> + kvm_put_kvm(kvm);
> + goto fail_unlock;
> }
>
> + list_add_rcu(&stt->list, &kvm->arch.spapr_tce_tables);
> +
> mutex_unlock(&kvm->lock);
>
> - if (ret >= 0)
> - return ret;
> + return ret;
>
> + fail_unlock:
> + mutex_unlock(&kvm->lock);
> fail:
> for (i = 0; i < npages; i++)
> if (stt->pages[i])
>
--
Alexey
^ permalink raw reply
* [PATCH v3 1/2] powerpc/64s: Fix logic when handling unknown CPU features
From: Andrew Donnellan @ 2019-02-22 0:40 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin, syzkaller, dvyukov, dja
From: Michael Ellerman <mpe@ellerman.id.au>
In cpufeatures_process_feature(), if a provided CPU feature is unknown and
enable_unknown is false, we erroneously print that the feature is being
enabled and return true, even though no feature has been enabled, and
may also set feature bits based on the last entry in the match table.
Fix this so that we only set feature bits from the match table if we have
actually enabled a feature from that table, and when failing to enable an
unknown feature, always print the "not enabling" message and return false.
Coincidentally, some older gccs (<GCC 7), when invoked with
-fsanitize-coverage=trace-pc, cause a spurious uninitialised variable
warning in this function:
arch/powerpc/kernel/dt_cpu_ftrs.c: In function ‘cpufeatures_process_feature’:
arch/powerpc/kernel/dt_cpu_ftrs.c:686:7: warning: ‘m’ may be used uninitialized in this function [-Wmaybe-uninitialized]
if (m->cpu_ftr_bit_mask)
An upcoming patch will enable support for kcov, which requires this option.
This patch avoids the warning.
Fixes: 5a61ef74f269 ("powerpc/64s: Support new device tree binding for discovering CPU features")
Reported-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
[ajd: add commit message]
Signed-off-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
---
arch/powerpc/kernel/dt_cpu_ftrs.c | 17 +++++++----------
1 file changed, 7 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 8be3721d9302..e49bd5efcfe6 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -666,8 +666,10 @@ static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f)
m = &dt_cpu_feature_match_table[i];
if (!strcmp(f->name, m->name)) {
known = true;
- if (m->enable(f))
+ if (m->enable(f)) {
+ cur_cpu_spec->cpu_features |= m->cpu_ftr_bit_mask;
break;
+ }
pr_info("not enabling: %s (disabled or unsupported by kernel)\n",
f->name);
@@ -675,17 +677,12 @@ static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f)
}
}
- if (!known && enable_unknown) {
- if (!feat_try_enable_unknown(f)) {
- pr_info("not enabling: %s (unknown and unsupported by kernel)\n",
- f->name);
- return false;
- }
+ if (!known && (!enable_unknown || !feat_try_enable_unknown(f))) {
+ pr_info("not enabling: %s (unknown and unsupported by kernel)\n",
+ f->name);
+ return false;
}
- if (m->cpu_ftr_bit_mask)
- cur_cpu_spec->cpu_features |= m->cpu_ftr_bit_mask;
-
if (known)
pr_debug("enabling: %s\n", f->name);
else
--
2.11.0
^ permalink raw reply related
* [PATCH v3 2/2] powerpc: Enable kcov
From: Andrew Donnellan @ 2019-02-22 0:40 UTC (permalink / raw)
To: linuxppc-dev; +Cc: npiggin, syzkaller, dvyukov, dja
In-Reply-To: <20190222004046.14914-1-andrew.donnellan@au1.ibm.com>
kcov provides kernel coverage data that's useful for fuzzing tools like
syzkaller.
Wire up kcov support on powerpc. Disable kcov instrumentation on the same
files where we currently disable gcov and UBSan instrumentation, plus some
additional exclusions which appear necessary to boot on book3e machines.
Signed-off-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
Acked-by: Dmitry Vyukov <dvyukov@google.com>
Tested-by: Daniel Axtens <dja@axtens.net> # e6500
---
v2->v3:
- Add additional exclusions required to boot on book3e (dja)
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/kernel/Makefile | 12 +++++++++++-
arch/powerpc/kernel/trace/Makefile | 3 ++-
arch/powerpc/kernel/vdso32/Makefile | 1 +
arch/powerpc/kernel/vdso64/Makefile | 1 +
arch/powerpc/mm/Makefile | 5 +++++
arch/powerpc/xmon/Makefile | 1 +
7 files changed, 22 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 2890d36eb531..d3698dae0e60 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -134,6 +134,7 @@ config PPC
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
+ select ARCH_HAS_KCOV
select ARCH_HAS_PHYS_TO_DMA
select ARCH_HAS_PMEM_API if PPC64
select ARCH_HAS_PTE_SPECIAL
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index cb7f0bb9ee71..3ae079014c04 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -142,19 +142,29 @@ endif
obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o
obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o
-# Disable GCOV & sanitizers in odd or sensitive code
+# Disable GCOV, KCOV & sanitizers in odd or sensitive code
GCOV_PROFILE_prom_init.o := n
+KCOV_INSTRUMENT_prom_init.o := n
UBSAN_SANITIZE_prom_init.o := n
GCOV_PROFILE_machine_kexec_64.o := n
+KCOV_INSTRUMENT_machine_kexec_64.o := n
UBSAN_SANITIZE_machine_kexec_64.o := n
GCOV_PROFILE_machine_kexec_32.o := n
+KCOV_INSTRUMENT_machine_kexec_32.o := n
UBSAN_SANITIZE_machine_kexec_32.o := n
GCOV_PROFILE_kprobes.o := n
+KCOV_INSTRUMENT_kprobes.o := n
UBSAN_SANITIZE_kprobes.o := n
GCOV_PROFILE_kprobes-ftrace.o := n
+KCOV_INSTRUMENT_kprobes-ftrace.o := n
UBSAN_SANITIZE_kprobes-ftrace.o := n
UBSAN_SANITIZE_vdso.o := n
+# Necessary for booting with kcov enabled on book3e machines
+KCOV_INSTRUMENT_cputable.o := n
+KCOV_INSTRUMENT_setup_64.o := n
+KCOV_INSTRUMENT_paca.o := n
+
extra-$(CONFIG_PPC_FPU) += fpu.o
extra-$(CONFIG_ALTIVEC) += vector.o
extra-$(CONFIG_PPC64) += entry_64.o
diff --git a/arch/powerpc/kernel/trace/Makefile b/arch/powerpc/kernel/trace/Makefile
index b1725ad3e13d..858503775c58 100644
--- a/arch/powerpc/kernel/trace/Makefile
+++ b/arch/powerpc/kernel/trace/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_TRACING) += trace_clock.o
obj-$(CONFIG_PPC64) += $(obj64-y)
obj-$(CONFIG_PPC32) += $(obj32-y)
-# Disable GCOV & sanitizers in odd or sensitive code
+# Disable GCOV, KCOV & sanitizers in odd or sensitive code
GCOV_PROFILE_ftrace.o := n
+KCOV_INSTRUMENT_ftrace.o := n
UBSAN_SANITIZE_ftrace.o := n
diff --git a/arch/powerpc/kernel/vdso32/Makefile b/arch/powerpc/kernel/vdso32/Makefile
index 50112d4473bb..ce199f6e4256 100644
--- a/arch/powerpc/kernel/vdso32/Makefile
+++ b/arch/powerpc/kernel/vdso32/Makefile
@@ -23,6 +23,7 @@ targets := $(obj-vdso32) vdso32.so vdso32.so.dbg
obj-vdso32 := $(addprefix $(obj)/, $(obj-vdso32))
GCOV_PROFILE := n
+KCOV_INSTRUMENT := n
UBSAN_SANITIZE := n
ccflags-y := -shared -fno-common -fno-builtin
diff --git a/arch/powerpc/kernel/vdso64/Makefile b/arch/powerpc/kernel/vdso64/Makefile
index 69cecb346269..28e7d112aa2f 100644
--- a/arch/powerpc/kernel/vdso64/Makefile
+++ b/arch/powerpc/kernel/vdso64/Makefile
@@ -9,6 +9,7 @@ targets := $(obj-vdso64) vdso64.so vdso64.so.dbg
obj-vdso64 := $(addprefix $(obj)/, $(obj-vdso64))
GCOV_PROFILE := n
+KCOV_INSTRUMENT := n
UBSAN_SANITIZE := n
ccflags-y := -shared -fno-common -fno-builtin
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index f965fc33a8b7..d4d32e229ace 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -55,3 +55,8 @@ obj-$(CONFIG_PPC_BOOK3S_64) += dump_linuxpagetables-book3s64.o
endif
obj-$(CONFIG_PPC_HTDUMP) += dump_hashpagetable.o
obj-$(CONFIG_PPC_MEM_KEYS) += pkeys.o
+
+# Disable kcov instrumentation on sensitive code
+# This is necessary for booting with kcov enabled on book3e machines
+KCOV_INSTRUMENT_tlb_nohash.o := n
+KCOV_INSTRUMENT_fsl_booke_mmu.o := n
diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
index 878f9c1d3615..3050f9323254 100644
--- a/arch/powerpc/xmon/Makefile
+++ b/arch/powerpc/xmon/Makefile
@@ -5,6 +5,7 @@
subdir-ccflags-y := $(call cc-disable-warning, builtin-requires-header)
GCOV_PROFILE := n
+KCOV_INSTRUMENT := n
UBSAN_SANITIZE := n
# Disable ftrace for the entire directory
--
2.11.0
^ permalink raw reply related
* linux-next: manual merge of the swiotlb tree with the powerpc tree
From: Stephen Rothwell @ 2019-02-22 0:36 UTC (permalink / raw)
To: Konrad Rzeszutek Wilk, Michael Ellerman, Benjamin Herrenschmidt,
PowerPC
Cc: Dongli Zhang, Linux Next Mailing List, Linux Kernel Mailing List,
Christoph Hellwig
[-- Attachment #1: Type: text/plain, Size: 2040 bytes --]
Hi all,
Today's linux-next merge of the swiotlb tree got a conflict in:
kernel/dma/swiotlb.c
between commit:
feee96440c9c ("swiotlb: remove swiotlb_dma_supported")
from the powerpc tree and commit:
71602fe6d4e9 ("swiotlb: add debugfs to track swiotlb buffer usage")
from the swiotlb tree.
I fixed it up (see below) and can carry the fix as necessary. This
is now fixed as far as linux-next is concerned, but any non trivial
conflicts should be mentioned to your upstream maintainer when your tree
is submitted for merging. You may also want to consider cooperating
with the maintainer of the conflicting tree to minimise any particularly
complex conflicts.
--
Cheers,
Stephen Rothwell
diff --cc kernel/dma/swiotlb.c
index 6d0236bd3929,2b0c8fd9658e..000000000000
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@@ -650,3 -665,48 +665,36 @@@ bool swiotlb_map(struct device *dev, ph
return true;
}
+
-/*
- * Return whether the given device DMA address mask can be supported
- * properly. For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask to
- * this function.
- */
-int
-swiotlb_dma_supported(struct device *hwdev, u64 mask)
-{
- return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
-}
-
+ #ifdef CONFIG_DEBUG_FS
+
+ static int __init swiotlb_create_debugfs(void)
+ {
+ struct dentry *d_swiotlb_usage;
+ struct dentry *ent;
+
+ d_swiotlb_usage = debugfs_create_dir("swiotlb", NULL);
+
+ if (!d_swiotlb_usage)
+ return -ENOMEM;
+
+ ent = debugfs_create_ulong("io_tlb_nslabs", 0400,
+ d_swiotlb_usage, &io_tlb_nslabs);
+ if (!ent)
+ goto fail;
+
+ ent = debugfs_create_ulong("io_tlb_used", 0400,
+ d_swiotlb_usage, &io_tlb_used);
+ if (!ent)
+ goto fail;
+
+ return 0;
+
+ fail:
+ debugfs_remove_recursive(d_swiotlb_usage);
+ return -ENOMEM;
+ }
+
+ late_initcall(swiotlb_create_debugfs);
+
+ #endif
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
* Re: [PATCH 0/7] Kernel Userspace Protection for radix
From: Kees Cook @ 2019-02-22 0:16 UTC (permalink / raw)
To: Russell Currey; +Cc: PowerPC, Nick Piggin, Kernel Hardening
In-Reply-To: <8ef1669cdfbcc6114eebc30c610c91c191c7cc7a.camel@russell.cc>
On Thu, Feb 21, 2019 at 4:09 PM Russell Currey <ruscur@russell.cc> wrote:
> On Thu, 2019-02-21 at 08:07 -0800, Kees Cook wrote:
> > On Thu, Feb 21, 2019 at 1:36 AM Russell Currey <ruscur@russell.cc>
> > wrote:
> > > The first three patches of these series are from Christophe's work
> > > and are
> > > the bare minimum framework needed to implement the support for
> > > radix.
> > >
> > > In patch 3, I have removed from Christophe's patch my
> > > implementation of
> > > the 64-bit exception handling code, since we don't have an answer
> > > for
> > > making nested exceptions work yet. This is mentioned in the final
> > > KUAP
> > > patch. Regardless, this is still a significant security
> > > improvement
> > > and greatly narrows the attack surface.
> >
> > Nice! Am I understanding correctly that with this series powerpc9 and
> > later, using radix, will pass the lkdtm tests for KUAP and KUEP (i.e.
> > EXEC_USERSPACE and ACCESS_USERSPACE)?
>
> Yes! We've had execution prevention for a while on radix (which is
> default on POWER9) since 3b10d0095a1e, the only functional thing this
> series does is allow disabling it with nosmep. This series adds access
> prevention.
Ah-ha; excellent. And CONFIG_PPC_RADIX_MMU is "default y" already. :)
--
Kees Cook
^ permalink raw reply
* Re: [PATCH 3/7] powerpc/mm: Add a framework for Kernel Userspace Access Protection
From: Russell Currey @ 2019-02-22 0:11 UTC (permalink / raw)
To: Mark Rutland, Christophe Leroy; +Cc: linuxppc-dev, npiggin, kernel-hardening
In-Reply-To: <20190221144818.GI33673@lakrids.cambridge.arm.com>
On Thu, 2019-02-21 at 14:48 +0000, Mark Rutland wrote:
> On Thu, Feb 21, 2019 at 11:46:06AM +0100, Christophe Leroy wrote:
> >
> > Le 21/02/2019 à 10:35, Russell Currey a écrit :
> > > From: Christophe Leroy <christophe.leroy@c-s.fr>
> > >
> > > This patch implements a framework for Kernel Userspace Access
> > > Protection.
> > >
> > > Then subarches will have to possibility to provide their own
> > > implementation by providing setup_kuap() and
> > > lock/unlock_user_access()
> > >
> > > Some platform will need to know the area accessed and whether it
> > > is
> > > accessed from read, write or both. Therefore source, destination
> > > and
> > > size and handed over to the two functions.
> >
> > Should we also consider adding user_access_begin() and the 3 other
> > associated macros ?
> >
> > See x86 for details.
>
> As a heads-up, there are some potential issues with
> user_access_{begin,end}() that may affect PPC. There's a long thread
> starting at:
>
> https://lkml.kernel.org/r/1547560709-56207-4-git-send-email-julien.thierry@arm.com/
I'd say we should look at adding those macros, but as follow-up work
after this series (and after we know what's going on with those issues)
- Russell
>
> Thanks,
> Mark.
^ permalink raw reply
* Re: [PATCH 0/7] Kernel Userspace Protection for radix
From: Russell Currey @ 2019-02-22 0:09 UTC (permalink / raw)
To: Kees Cook; +Cc: PowerPC, Nick Piggin, Kernel Hardening
In-Reply-To: <CAGXu5j+P1wh0uf1kfMywSTo4NYtwFPSnKXg6wbfyBRqwVRZVYA@mail.gmail.com>
On Thu, 2019-02-21 at 08:07 -0800, Kees Cook wrote:
> On Thu, Feb 21, 2019 at 1:36 AM Russell Currey <ruscur@russell.cc>
> wrote:
> > The first three patches of these series are from Christophe's work
> > and are
> > the bare minimum framework needed to implement the support for
> > radix.
> >
> > In patch 3, I have removed from Christophe's patch my
> > implementation of
> > the 64-bit exception handling code, since we don't have an answer
> > for
> > making nested exceptions work yet. This is mentioned in the final
> > KUAP
> > patch. Regardless, this is still a significant security
> > improvement
> > and greatly narrows the attack surface.
>
> Nice! Am I understanding correctly that with this series powerpc9 and
> later, using radix, will pass the lkdtm tests for KUAP and KUEP (i.e.
> EXEC_USERSPACE and ACCESS_USERSPACE)?
Yes! We've had execution prevention for a while on radix (which is
default on POWER9) since 3b10d0095a1e, the only functional thing this
series does is allow disabling it with nosmep. This series adds access
prevention.
^ permalink raw reply
* linux-next: manual merge of the powerpc tree with the dma-mapping tree
From: Stephen Rothwell @ 2019-02-21 22:27 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, PowerPC,
Christoph Hellwig
Cc: Linux Next Mailing List, Linux Kernel Mailing List
[-- Attachment #1: Type: text/plain, Size: 796 bytes --]
Hi all,
Today's linux-next merge of the powerpc tree got a conflict in:
arch/powerpc/kernel/dma.c
between commit:
cfced786969c ("dma-mapping: remove the default map_resource implementation")
from the dma-mapping tree and commit:
68005b67d15a ("powerpc/dma: use the generic direct mapping bypass")
from the powerpc tree.
I fixed it up (the latter removed the file, so I did that) and can
carry the fix as necessary. This is now fixed as far as linux-next is
concerned, but any non trivial conflicts should be mentioned to your
upstream maintainer when your tree is submitted for merging. You may
also want to consider cooperating with the maintainer of the conflicting
tree to minimise any particularly complex conflicts.
--
Cheers,
Stephen Rothwell
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
* linux-next: manual merge of the powerpc tree with the dma-mapping tree
From: Stephen Rothwell @ 2019-02-21 22:25 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, PowerPC,
Christoph Hellwig
Cc: Linux Next Mailing List, Linux Kernel Mailing List
[-- Attachment #1: Type: text/plain, Size: 1268 bytes --]
Hi all,
Today's linux-next merge of the powerpc tree got a conflict in:
kernel/dma/Kconfig
between commits:
ff4c25f26a71 ("dma-mapping: improve selection of dma_declare_coherent availability")
from the dma-mapping tree and commit:
11ddce15451e ("dma-mapping, powerpc: simplify the arch dma_set_mask override")
from the powerpc tree.
I fixed it up (see below) and can carry the fix as necessary. This
is now fixed as far as linux-next is concerned, but any non trivial
conflicts should be mentioned to your upstream maintainer when your tree
is submitted for merging. You may also want to consider cooperating
with the maintainer of the conflicting tree to minimise any particularly
complex conflicts.
--
Cheers,
Stephen Rothwell
diff --cc kernel/dma/Kconfig
index 212aac7c675f,0711d18645de..000000000000
--- a/kernel/dma/Kconfig
+++ b/kernel/dma/Kconfig
@@@ -16,13 -16,10 +16,16 @@@ config ARCH_DMA_ADDR_T_64BI
config ARCH_HAS_DMA_COHERENCE_H
bool
+ config ARCH_HAS_DMA_SET_MASK
+ bool
+
-config HAVE_GENERIC_DMA_COHERENT
+config DMA_DECLARE_COHERENT
+ bool
+
+config ARCH_HAS_SETUP_DMA_OPS
+ bool
+
+config ARCH_HAS_TEARDOWN_DMA_OPS
bool
config ARCH_HAS_SYNC_DMA_FOR_DEVICE
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
* Re: [RESEND PATCH 3/7] mm/gup: Change GUP fast to use flags rather than a write 'bool'
From: Ira Weiny @ 2019-02-21 22:24 UTC (permalink / raw)
To: Souptick Joarder
Cc: linux-fbdev, Michal Hocko, kvm, linux-sh, Peter Zijlstra,
James Hogan, linux-fpga, Heiko Carstens, dri-devel, linux-mips,
Linux-MM, Rich Felker, Paul Mackerras, sparclinux, ceph-devel,
open list:ANDROID DRIVERS, linux-s390, rds-devel, Yoshinori Sato,
linux-rdma, Jason Gunthorpe, Ingo Molnar, xen-devel, devel,
linux-media, John Hubbard, kvm-ppc, Borislav Petkov,
Thomas Gleixner, virtualization, linux-scsi, netdev, linux-kernel,
Ralf Baechle, Paul Burton, Martin Schwidefsky, Andrew Morton,
linuxppc-dev, David S. Miller, Kirill A. Shutemov
In-Reply-To: <CAFqt6zYvkhKw3GExRQB2e_c16KQqrKT=GoiqErA06txUQa2bMQ@mail.gmail.com>
On Thu, Feb 21, 2019 at 08:48:41AM +0530, Souptick Joarder wrote:
> Hi Ira,
>
> On Wed, Feb 20, 2019 at 11:01 AM <ira.weiny@intel.com> wrote:
> >
> > From: Ira Weiny <ira.weiny@intel.com>
> >
> > To facilitate additional options to get_user_pages_fast() change the
> > singular write parameter to be gup_flags.
> >
> > This patch does not change any functionality. New functionality will
> > follow in subsequent patches.
> >
> > Some of the get_user_pages_fast() call sites were unchanged because they
> > already passed FOLL_WRITE or 0 for the write parameter.
> >
> > Signed-off-by: Ira Weiny <ira.weiny@intel.com>
> > ---
[snip]
> > diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
> > index bd2dcfbf00cd..8fcb0a921e46 100644
> > --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
> > +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
> > @@ -582,7 +582,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
> > /* If writing != 0, then the HPTE must allow writing, if we get here */
> > write_ok = writing;
> > hva = gfn_to_hva_memslot(memslot, gfn);
> > - npages = get_user_pages_fast(hva, 1, writing, pages);
> > + npages = get_user_pages_fast(hva, 1, writing ? FOLL_WRITE : 0, pages);
>
> Just requesting for opinion,
> * writing ? FOLL_WRITE : 0 * is used in many places. How about placing it in a
> macro/ inline ?
I don't really think this would gain much. And I don't think it would be more
clear. In fact I can't even think of a macro name which would make sense. I'm
inclined to leave this as written.
Ira
>
> > if (npages < 1) {
> > /* Check if it's an I/O mapping */
> > down_read(¤t->mm->mmap_sem);
> > @@ -1175,7 +1175,7 @@ void *kvmppc_pin_guest_page(struct kvm *kvm, unsigned long gpa,
> > if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
> > goto err;
> > hva = gfn_to_hva_memslot(memslot, gfn);
> > - npages = get_user_pages_fast(hva, 1, 1, pages);
> > + npages = get_user_pages_fast(hva, 1, FOLL_WRITE, pages);
> > if (npages < 1)
> > goto err;
> > page = pages[0];
> > diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c
> > index 24296f4cadc6..e0af53fd78c5 100644
> > --- a/arch/powerpc/kvm/e500_mmu.c
> > +++ b/arch/powerpc/kvm/e500_mmu.c
> > @@ -783,7 +783,7 @@ int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
> > if (!pages)
> > return -ENOMEM;
> >
> > - ret = get_user_pages_fast(cfg->array, num_pages, 1, pages);
> > + ret = get_user_pages_fast(cfg->array, num_pages, FOLL_WRITE, pages);
> > if (ret < 0)
> > goto free_pages;
> >
> > diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
> > index a712a650a8b6..acb0990c8364 100644
> > --- a/arch/powerpc/mm/mmu_context_iommu.c
> > +++ b/arch/powerpc/mm/mmu_context_iommu.c
> > @@ -190,7 +190,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
> > for (i = 0; i < entries; ++i) {
> > cur_ua = ua + (i << PAGE_SHIFT);
> > if (1 != get_user_pages_fast(cur_ua,
> > - 1/* pages */, 1/* iswrite */, &page)) {
> > + 1/* pages */, FOLL_WRITE, &page)) {
> > ret = -EFAULT;
> > for (j = 0; j < i; ++j)
> > put_page(pfn_to_page(mem->hpas[j] >>
> > @@ -209,7 +209,7 @@ static long mm_iommu_do_alloc(struct mm_struct *mm, unsigned long ua,
> > if (mm_iommu_move_page_from_cma(page))
> > goto populate;
> > if (1 != get_user_pages_fast(cur_ua,
> > - 1/* pages */, 1/* iswrite */,
> > + 1/* pages */, FOLL_WRITE,
> > &page)) {
> > ret = -EFAULT;
> > for (j = 0; j < i; ++j)
> > diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
> > index fcb55b02990e..69d9366b966c 100644
> > --- a/arch/s390/kvm/interrupt.c
> > +++ b/arch/s390/kvm/interrupt.c
> > @@ -2278,7 +2278,7 @@ static int kvm_s390_adapter_map(struct kvm *kvm, unsigned int id, __u64 addr)
> > ret = -EFAULT;
> > goto out;
> > }
> > - ret = get_user_pages_fast(map->addr, 1, 1, &map->page);
> > + ret = get_user_pages_fast(map->addr, 1, FOLL_WRITE, &map->page);
> > if (ret < 0)
> > goto out;
> > BUG_ON(ret != 1);
> > diff --git a/arch/s390/mm/gup.c b/arch/s390/mm/gup.c
> > index 2809d11c7a28..0a6faf3d9960 100644
> > --- a/arch/s390/mm/gup.c
> > +++ b/arch/s390/mm/gup.c
> > @@ -265,7 +265,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > * get_user_pages_fast() - pin user pages in memory
> > * @start: starting user address
> > * @nr_pages: number of pages from start to pin
> > - * @write: whether pages will be written to
> > + * @gup_flags: flags modifying pin behaviour
> > * @pages: array that receives pointers to the pages pinned.
> > * Should be at least nr_pages long.
> > *
> > @@ -277,22 +277,22 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > * requested. If nr_pages is 0 or negative, returns 0. If no pages
> > * were pinned, returns -errno.
> > */
> > -int get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > - struct page **pages)
> > +int get_user_pages_fast(unsigned long start, int nr_pages,
> > + unsigned int gup_flags, struct page **pages)
> > {
> > int nr, ret;
> >
> > might_sleep();
> > start &= PAGE_MASK;
> > - nr = __get_user_pages_fast(start, nr_pages, write, pages);
> > + nr = __get_user_pages_fast(start, nr_pages, gup_flags & FOLL_WRITE,
> > + pages);
> > if (nr == nr_pages)
> > return nr;
> >
> > /* Try to get the remaining pages with get_user_pages */
> > start += nr << PAGE_SHIFT;
> > pages += nr;
> > - ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
> > - write ? FOLL_WRITE : 0);
> > + ret = get_user_pages_unlocked(start, nr_pages - nr, pages, gup_flags);
> > /* Have to be a bit careful with return values */
> > if (nr > 0)
> > ret = (ret < 0) ? nr : ret + nr;
> > diff --git a/arch/sh/mm/gup.c b/arch/sh/mm/gup.c
> > index 3e27f6d1f1ec..277c882f7489 100644
> > --- a/arch/sh/mm/gup.c
> > +++ b/arch/sh/mm/gup.c
> > @@ -204,7 +204,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > * get_user_pages_fast() - pin user pages in memory
> > * @start: starting user address
> > * @nr_pages: number of pages from start to pin
> > - * @write: whether pages will be written to
> > + * @gup_flags: flags modifying pin behaviour
> > * @pages: array that receives pointers to the pages pinned.
> > * Should be at least nr_pages long.
> > *
> > @@ -216,8 +216,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > * requested. If nr_pages is 0 or negative, returns 0. If no pages
> > * were pinned, returns -errno.
> > */
> > -int get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > - struct page **pages)
> > +int get_user_pages_fast(unsigned long start, int nr_pages,
> > + unsigned int gup_flags, struct page **pages)
> > {
> > struct mm_struct *mm = current->mm;
> > unsigned long addr, len, end;
> > @@ -241,7 +241,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > next = pgd_addr_end(addr, end);
> > if (pgd_none(pgd))
> > goto slow;
> > - if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
> > + if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE,
> > + pages, &nr))
> > goto slow;
> > } while (pgdp++, addr = next, addr != end);
> > local_irq_enable();
> > @@ -261,7 +262,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
> >
> > ret = get_user_pages_unlocked(start,
> > (end - start) >> PAGE_SHIFT, pages,
> > - write ? FOLL_WRITE : 0);
> > + gup_flags);
> >
> > /* Have to be a bit careful with return values */
> > if (nr > 0) {
> > diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
> > index aee6dba83d0e..1e770a517d4a 100644
> > --- a/arch/sparc/mm/gup.c
> > +++ b/arch/sparc/mm/gup.c
> > @@ -245,8 +245,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > return nr;
> > }
> >
> > -int get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > - struct page **pages)
> > +int get_user_pages_fast(unsigned long start, int nr_pages,
> > + unsigned int gup_flags, struct page **pages)
> > {
> > struct mm_struct *mm = current->mm;
> > unsigned long addr, len, end;
> > @@ -303,7 +303,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > next = pgd_addr_end(addr, end);
> > if (pgd_none(pgd))
> > goto slow;
> > - if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
> > + if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE,
> > + pages, &nr))
> > goto slow;
> > } while (pgdp++, addr = next, addr != end);
> >
> > @@ -324,7 +325,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
> >
> > ret = get_user_pages_unlocked(start,
> > (end - start) >> PAGE_SHIFT, pages,
> > - write ? FOLL_WRITE : 0);
> > + gup_flags);
> >
> > /* Have to be a bit careful with return values */
> > if (nr > 0) {
> > diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
> > index 6bdca39829bc..08715034e315 100644
> > --- a/arch/x86/kvm/paging_tmpl.h
> > +++ b/arch/x86/kvm/paging_tmpl.h
> > @@ -140,7 +140,7 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
> > pt_element_t *table;
> > struct page *page;
> >
> > - npages = get_user_pages_fast((unsigned long)ptep_user, 1, 1, &page);
> > + npages = get_user_pages_fast((unsigned long)ptep_user, 1, FOLL_WRITE, &page);
> > /* Check if the user is doing something meaningless. */
> > if (unlikely(npages != 1))
> > return -EFAULT;
> > diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
> > index f13a3a24d360..173596a020cb 100644
> > --- a/arch/x86/kvm/svm.c
> > +++ b/arch/x86/kvm/svm.c
> > @@ -1803,7 +1803,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr,
> > return NULL;
> >
> > /* Pin the user virtual address. */
> > - npinned = get_user_pages_fast(uaddr, npages, write ? FOLL_WRITE : 0, pages);
> > + npinned = get_user_pages_fast(uaddr, npages, FOLL_WRITE, pages);
> > if (npinned != npages) {
> > pr_err("SEV: Failure locking %lu pages.\n", npages);
> > goto err;
> > diff --git a/drivers/fpga/dfl-afu-dma-region.c b/drivers/fpga/dfl-afu-dma-region.c
> > index e18a786fc943..c438722bf4e1 100644
> > --- a/drivers/fpga/dfl-afu-dma-region.c
> > +++ b/drivers/fpga/dfl-afu-dma-region.c
> > @@ -102,7 +102,7 @@ static int afu_dma_pin_pages(struct dfl_feature_platform_data *pdata,
> > goto unlock_vm;
> > }
> >
> > - pinned = get_user_pages_fast(region->user_addr, npages, 1,
> > + pinned = get_user_pages_fast(region->user_addr, npages, FOLL_WRITE,
> > region->pages);
> > if (pinned < 0) {
> > ret = pinned;
> > diff --git a/drivers/gpu/drm/via/via_dmablit.c b/drivers/gpu/drm/via/via_dmablit.c
> > index 345bda4494e1..0c8b09602910 100644
> > --- a/drivers/gpu/drm/via/via_dmablit.c
> > +++ b/drivers/gpu/drm/via/via_dmablit.c
> > @@ -239,7 +239,8 @@ via_lock_all_dma_pages(drm_via_sg_info_t *vsg, drm_via_dmablit_t *xfer)
> > if (NULL == vsg->pages)
> > return -ENOMEM;
> > ret = get_user_pages_fast((unsigned long)xfer->mem_addr,
> > - vsg->num_pages, vsg->direction == DMA_FROM_DEVICE,
> > + vsg->num_pages,
> > + vsg->direction == DMA_FROM_DEVICE ? FOLL_WRITE : 0,
> > vsg->pages);
> > if (ret != vsg->num_pages) {
> > if (ret < 0)
> > diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c
> > index 24b592c6522e..78ccacaf97d0 100644
> > --- a/drivers/infiniband/hw/hfi1/user_pages.c
> > +++ b/drivers/infiniband/hw/hfi1/user_pages.c
> > @@ -105,7 +105,8 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np
> > {
> > int ret;
> >
> > - ret = get_user_pages_fast(vaddr, npages, writable, pages);
> > + ret = get_user_pages_fast(vaddr, npages, writable ? FOLL_WRITE : 0,
> > + pages);
> > if (ret < 0)
> > return ret;
> >
> > diff --git a/drivers/misc/genwqe/card_utils.c b/drivers/misc/genwqe/card_utils.c
> > index 25265fd0fd6e..89cff9d1012b 100644
> > --- a/drivers/misc/genwqe/card_utils.c
> > +++ b/drivers/misc/genwqe/card_utils.c
> > @@ -603,7 +603,7 @@ int genwqe_user_vmap(struct genwqe_dev *cd, struct dma_mapping *m, void *uaddr,
> > /* pin user pages in memory */
> > rc = get_user_pages_fast(data & PAGE_MASK, /* page aligned addr */
> > m->nr_pages,
> > - m->write, /* readable/writable */
> > + m->write ? FOLL_WRITE : 0, /* readable/writable */
> > m->page_list); /* ptrs to pages */
> > if (rc < 0)
> > goto fail_get_user_pages;
> > diff --git a/drivers/misc/vmw_vmci/vmci_host.c b/drivers/misc/vmw_vmci/vmci_host.c
> > index 997f92543dd4..422d08da3244 100644
> > --- a/drivers/misc/vmw_vmci/vmci_host.c
> > +++ b/drivers/misc/vmw_vmci/vmci_host.c
> > @@ -242,7 +242,7 @@ static int vmci_host_setup_notify(struct vmci_ctx *context,
> > /*
> > * Lock physical page backing a given user VA.
> > */
> > - retval = get_user_pages_fast(uva, 1, 1, &context->notify_page);
> > + retval = get_user_pages_fast(uva, 1, FOLL_WRITE, &context->notify_page);
> > if (retval != 1) {
> > context->notify_page = NULL;
> > return VMCI_ERROR_GENERIC;
> > diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c
> > index 264f4ed8eef2..c5396ee32e51 100644
> > --- a/drivers/misc/vmw_vmci/vmci_queue_pair.c
> > +++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c
> > @@ -666,7 +666,8 @@ static int qp_host_get_user_memory(u64 produce_uva,
> > int err = VMCI_SUCCESS;
> >
> > retval = get_user_pages_fast((uintptr_t) produce_uva,
> > - produce_q->kernel_if->num_pages, 1,
> > + produce_q->kernel_if->num_pages,
> > + FOLL_WRITE,
> > produce_q->kernel_if->u.h.header_page);
> > if (retval < (int)produce_q->kernel_if->num_pages) {
> > pr_debug("get_user_pages_fast(produce) failed (retval=%d)",
> > @@ -678,7 +679,8 @@ static int qp_host_get_user_memory(u64 produce_uva,
> > }
> >
> > retval = get_user_pages_fast((uintptr_t) consume_uva,
> > - consume_q->kernel_if->num_pages, 1,
> > + consume_q->kernel_if->num_pages,
> > + FOLL_WRITE,
> > consume_q->kernel_if->u.h.header_page);
> > if (retval < (int)consume_q->kernel_if->num_pages) {
> > pr_debug("get_user_pages_fast(consume) failed (retval=%d)",
> > diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c
> > index 321bc673c417..cef0133aa47a 100644
> > --- a/drivers/platform/goldfish/goldfish_pipe.c
> > +++ b/drivers/platform/goldfish/goldfish_pipe.c
> > @@ -274,7 +274,8 @@ static int pin_user_pages(unsigned long first_page,
> > *iter_last_page_size = last_page_size;
> > }
> >
> > - ret = get_user_pages_fast(first_page, requested_pages, !is_write,
> > + ret = get_user_pages_fast(first_page, requested_pages,
> > + !is_write ? FOLL_WRITE : 0,
> > pages);
> > if (ret <= 0)
> > return -EFAULT;
> > diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
> > index cbe467ff1aba..f681b3e9e970 100644
> > --- a/drivers/rapidio/devices/rio_mport_cdev.c
> > +++ b/drivers/rapidio/devices/rio_mport_cdev.c
> > @@ -868,7 +868,9 @@ rio_dma_transfer(struct file *filp, u32 transfer_mode,
> >
> > pinned = get_user_pages_fast(
> > (unsigned long)xfer->loc_addr & PAGE_MASK,
> > - nr_pages, dir == DMA_FROM_DEVICE, page_list);
> > + nr_pages,
> > + dir == DMA_FROM_DEVICE ? FOLL_WRITE : 0,
> > + page_list);
> >
> > if (pinned != nr_pages) {
> > if (pinned < 0) {
> > diff --git a/drivers/sbus/char/oradax.c b/drivers/sbus/char/oradax.c
> > index 6516bc3cb58b..790aa148670d 100644
> > --- a/drivers/sbus/char/oradax.c
> > +++ b/drivers/sbus/char/oradax.c
> > @@ -437,7 +437,7 @@ static int dax_lock_page(void *va, struct page **p)
> >
> > dax_dbg("uva %p", va);
> >
> > - ret = get_user_pages_fast((unsigned long)va, 1, 1, p);
> > + ret = get_user_pages_fast((unsigned long)va, 1, FOLL_WRITE, p);
> > if (ret == 1) {
> > dax_dbg("locked page %p, for VA %p", *p, va);
> > return 0;
> > diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
> > index 7ff22d3f03e3..871b25914c07 100644
> > --- a/drivers/scsi/st.c
> > +++ b/drivers/scsi/st.c
> > @@ -4918,7 +4918,8 @@ static int sgl_map_user_pages(struct st_buffer *STbp,
> >
> > /* Try to fault in all of the necessary pages */
> > /* rw==READ means read from drive, write into memory area */
> > - res = get_user_pages_fast(uaddr, nr_pages, rw == READ, pages);
> > + res = get_user_pages_fast(uaddr, nr_pages, rw == READ ? FOLL_WRITE : 0,
> > + pages);
> >
> > /* Errors and no page mapped should return here */
> > if (res < nr_pages)
> > diff --git a/drivers/staging/gasket/gasket_page_table.c b/drivers/staging/gasket/gasket_page_table.c
> > index 26755d9ca41d..f67fdf1d3817 100644
> > --- a/drivers/staging/gasket/gasket_page_table.c
> > +++ b/drivers/staging/gasket/gasket_page_table.c
> > @@ -486,8 +486,8 @@ static int gasket_perform_mapping(struct gasket_page_table *pg_tbl,
> > ptes[i].dma_addr = pg_tbl->coherent_pages[0].paddr +
> > off + i * PAGE_SIZE;
> > } else {
> > - ret = get_user_pages_fast(page_addr - offset, 1, 1,
> > - &page);
> > + ret = get_user_pages_fast(page_addr - offset, 1,
> > + FOLL_WRITE, &page);
> >
> > if (ret <= 0) {
> > dev_err(pg_tbl->device,
> > diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
> > index 0b9ab1d0dd45..49fd7312e2aa 100644
> > --- a/drivers/tee/tee_shm.c
> > +++ b/drivers/tee/tee_shm.c
> > @@ -273,7 +273,7 @@ struct tee_shm *tee_shm_register(struct tee_context *ctx, unsigned long addr,
> > goto err;
> > }
> >
> > - rc = get_user_pages_fast(start, num_pages, 1, shm->pages);
> > + rc = get_user_pages_fast(start, num_pages, FOLL_WRITE, shm->pages);
> > if (rc > 0)
> > shm->num_pages = rc;
> > if (rc != num_pages) {
> > diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
> > index c424913324e3..a4b10bb4086b 100644
> > --- a/drivers/vfio/vfio_iommu_spapr_tce.c
> > +++ b/drivers/vfio/vfio_iommu_spapr_tce.c
> > @@ -532,7 +532,8 @@ static int tce_iommu_use_page(unsigned long tce, unsigned long *hpa)
> > enum dma_data_direction direction = iommu_tce_direction(tce);
> >
> > if (get_user_pages_fast(tce & PAGE_MASK, 1,
> > - direction != DMA_TO_DEVICE, &page) != 1)
> > + direction != DMA_TO_DEVICE ? FOLL_WRITE : 0,
> > + &page) != 1)
> > return -EFAULT;
> >
> > *hpa = __pa((unsigned long) page_address(page));
> > diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> > index 24a129fcdd61..72685b1659ff 100644
> > --- a/drivers/vhost/vhost.c
> > +++ b/drivers/vhost/vhost.c
> > @@ -1700,7 +1700,7 @@ static int set_bit_to_user(int nr, void __user *addr)
> > int bit = nr + (log % PAGE_SIZE) * 8;
> > int r;
> >
> > - r = get_user_pages_fast(log, 1, 1, &page);
> > + r = get_user_pages_fast(log, 1, FOLL_WRITE, &page);
> > if (r < 0)
> > return r;
> > BUG_ON(r != 1);
> > diff --git a/drivers/video/fbdev/pvr2fb.c b/drivers/video/fbdev/pvr2fb.c
> > index 8a53d1de611d..41390c8e0f67 100644
> > --- a/drivers/video/fbdev/pvr2fb.c
> > +++ b/drivers/video/fbdev/pvr2fb.c
> > @@ -686,7 +686,7 @@ static ssize_t pvr2fb_write(struct fb_info *info, const char *buf,
> > if (!pages)
> > return -ENOMEM;
> >
> > - ret = get_user_pages_fast((unsigned long)buf, nr_pages, true, pages);
> > + ret = get_user_pages_fast((unsigned long)buf, nr_pages, FOLL_WRITE, pages);
> > if (ret < nr_pages) {
> > nr_pages = ret;
> > ret = -EINVAL;
> > diff --git a/drivers/virt/fsl_hypervisor.c b/drivers/virt/fsl_hypervisor.c
> > index 8ba726e600e9..6446bcab4185 100644
> > --- a/drivers/virt/fsl_hypervisor.c
> > +++ b/drivers/virt/fsl_hypervisor.c
> > @@ -244,7 +244,7 @@ static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p)
> >
> > /* Get the physical addresses of the source buffer */
> > num_pinned = get_user_pages_fast(param.local_vaddr - lb_offset,
> > - num_pages, param.source != -1, pages);
> > + num_pages, param.source != -1 ? FOLL_WRITE : 0, pages);
> >
> > if (num_pinned != num_pages) {
> > /* get_user_pages() failed */
> > diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
> > index 5efc5eee9544..7b47f1e6aab4 100644
> > --- a/drivers/xen/gntdev.c
> > +++ b/drivers/xen/gntdev.c
> > @@ -852,7 +852,7 @@ static int gntdev_get_page(struct gntdev_copy_batch *batch, void __user *virt,
> > unsigned long xen_pfn;
> > int ret;
> >
> > - ret = get_user_pages_fast(addr, 1, writeable, &page);
> > + ret = get_user_pages_fast(addr, 1, writeable ? FOLL_WRITE : 0, &page);
> > if (ret < 0)
> > return ret;
> >
> > diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c
> > index 443bcd8c3c19..5a7c4fda682f 100644
> > --- a/fs/orangefs/orangefs-bufmap.c
> > +++ b/fs/orangefs/orangefs-bufmap.c
> > @@ -269,7 +269,7 @@ orangefs_bufmap_map(struct orangefs_bufmap *bufmap,
> >
> > /* map the pages */
> > ret = get_user_pages_fast((unsigned long)user_desc->ptr,
> > - bufmap->page_count, 1, bufmap->page_array);
> > + bufmap->page_count, FOLL_WRITE, bufmap->page_array);
> >
> > if (ret < 0)
> > return ret;
> > diff --git a/include/linux/mm.h b/include/linux/mm.h
> > index 05a105d9d4c3..8e1f3cd7482a 100644
> > --- a/include/linux/mm.h
> > +++ b/include/linux/mm.h
> > @@ -1537,8 +1537,8 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
> > long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
> > struct page **pages, unsigned int gup_flags);
> >
> > -int get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > - struct page **pages);
> > +int get_user_pages_fast(unsigned long start, int nr_pages,
> > + unsigned int gup_flags, struct page **pages);
> >
> > /* Container for pinned pfns / pages */
> > struct frame_vector {
> > diff --git a/kernel/futex.c b/kernel/futex.c
> > index fdd312da0992..e10209946f8b 100644
> > --- a/kernel/futex.c
> > +++ b/kernel/futex.c
> > @@ -546,7 +546,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, enum futex_a
> > if (unlikely(should_fail_futex(fshared)))
> > return -EFAULT;
> >
> > - err = get_user_pages_fast(address, 1, 1, &page);
> > + err = get_user_pages_fast(address, 1, FOLL_WRITE, &page);
> > /*
> > * If write access is not required (eg. FUTEX_WAIT), try
> > * and get read-only access.
> > diff --git a/lib/iov_iter.c b/lib/iov_iter.c
> > index be4bd627caf0..6dbae0692719 100644
> > --- a/lib/iov_iter.c
> > +++ b/lib/iov_iter.c
> > @@ -1280,7 +1280,9 @@ ssize_t iov_iter_get_pages(struct iov_iter *i,
> > len = maxpages * PAGE_SIZE;
> > addr &= ~(PAGE_SIZE - 1);
> > n = DIV_ROUND_UP(len, PAGE_SIZE);
> > - res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, pages);
> > + res = get_user_pages_fast(addr, n,
> > + iov_iter_rw(i) != WRITE ? FOLL_WRITE : 0,
> > + pages);
> > if (unlikely(res < 0))
> > return res;
> > return (res == n ? len : res * PAGE_SIZE) - *start;
> > @@ -1361,7 +1363,8 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i,
> > p = get_pages_array(n);
> > if (!p)
> > return -ENOMEM;
> > - res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, p);
> > + res = get_user_pages_fast(addr, n,
> > + iov_iter_rw(i) != WRITE ? FOLL_WRITE : 0, p);
> > if (unlikely(res < 0)) {
> > kvfree(p);
> > return res;
> > diff --git a/mm/gup.c b/mm/gup.c
> > index 681388236106..6f32d36b3c5b 100644
> > --- a/mm/gup.c
> > +++ b/mm/gup.c
> > @@ -1863,7 +1863,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > * get_user_pages_fast() - pin user pages in memory
> > * @start: starting user address
> > * @nr_pages: number of pages from start to pin
> > - * @write: whether pages will be written to
> > + * @gup_flags: flags modifying pin behaviour
> > * @pages: array that receives pointers to the pages pinned.
> > * Should be at least nr_pages long.
> > *
> > @@ -1875,8 +1875,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > * requested. If nr_pages is 0 or negative, returns 0. If no pages
> > * were pinned, returns -errno.
> > */
> > -int get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > - struct page **pages)
> > +int get_user_pages_fast(unsigned long start, int nr_pages,
> > + unsigned int gup_flags, struct page **pages)
> > {
> > unsigned long addr, len, end;
> > int nr = 0, ret = 0;
> > @@ -1894,7 +1894,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
> >
> > if (gup_fast_permitted(start, nr_pages)) {
> > local_irq_disable();
> > - gup_pgd_range(addr, end, write ? FOLL_WRITE : 0, pages, &nr);
> > + gup_pgd_range(addr, end, gup_flags, pages, &nr);
> > local_irq_enable();
> > ret = nr;
> > }
> > @@ -1905,7 +1905,7 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
> > pages += nr;
> >
> > ret = get_user_pages_unlocked(start, nr_pages - nr, pages,
> > - write ? FOLL_WRITE : 0);
> > + gup_flags);
> >
> > /* Have to be a bit careful with return values */
> > if (nr > 0) {
> > diff --git a/mm/util.c b/mm/util.c
> > index 1ea055138043..01ffe145c62b 100644
> > --- a/mm/util.c
> > +++ b/mm/util.c
> > @@ -306,7 +306,7 @@ EXPORT_SYMBOL_GPL(__get_user_pages_fast);
> > * get_user_pages_fast() - pin user pages in memory
> > * @start: starting user address
> > * @nr_pages: number of pages from start to pin
> > - * @write: whether pages will be written to
> > + * @gup_flags: flags modifying pin behaviour
> > * @pages: array that receives pointers to the pages pinned.
> > * Should be at least nr_pages long.
> > *
> > @@ -327,10 +327,10 @@ EXPORT_SYMBOL_GPL(__get_user_pages_fast);
> > * get_user_pages_fast simply falls back to get_user_pages.
> > */
> > int __weak get_user_pages_fast(unsigned long start,
> > - int nr_pages, int write, struct page **pages)
> > + int nr_pages, unsigned int gup_flags,
> > + struct page **pages)
> > {
> > - return get_user_pages_unlocked(start, nr_pages, pages,
> > - write ? FOLL_WRITE : 0);
> > + return get_user_pages_unlocked(start, nr_pages, pages, gup_flags);
> > }
> > EXPORT_SYMBOL_GPL(get_user_pages_fast);
> >
> > diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
> > index d3736f5bffec..74cafc0142ea 100644
> > --- a/net/ceph/pagevec.c
> > +++ b/net/ceph/pagevec.c
> > @@ -27,7 +27,7 @@ struct page **ceph_get_direct_page_vector(const void __user *data,
> > while (got < num_pages) {
> > rc = get_user_pages_fast(
> > (unsigned long)data + ((unsigned long)got * PAGE_SIZE),
> > - num_pages - got, write_page, pages + got);
> > + num_pages - got, write_page ? FOLL_WRITE : 0, pages + got);
> > if (rc < 0)
> > break;
> > BUG_ON(rc == 0);
> > diff --git a/net/rds/info.c b/net/rds/info.c
> > index e367a97a18c8..03f6fd56d237 100644
> > --- a/net/rds/info.c
> > +++ b/net/rds/info.c
> > @@ -193,7 +193,7 @@ int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
> > ret = -ENOMEM;
> > goto out;
> > }
> > - ret = get_user_pages_fast(start, nr_pages, 1, pages);
> > + ret = get_user_pages_fast(start, nr_pages, FOLL_WRITE, pages);
> > if (ret != nr_pages) {
> > if (ret > 0)
> > nr_pages = ret;
> > diff --git a/net/rds/rdma.c b/net/rds/rdma.c
> > index 182ab8430594..b340ed4fc43a 100644
> > --- a/net/rds/rdma.c
> > +++ b/net/rds/rdma.c
> > @@ -158,7 +158,8 @@ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages,
> > {
> > int ret;
> >
> > - ret = get_user_pages_fast(user_addr, nr_pages, write, pages);
> > + ret = get_user_pages_fast(user_addr, nr_pages, write ? FOLL_WRITE : 0,
> > + pages);
> >
> > if (ret >= 0 && ret < nr_pages) {
> > while (ret--)
> > --
> > 2.20.1
> >
>
^ permalink raw reply
* linux-next: manual merge of the powerpc tree with the dma-mapping tree
From: Stephen Rothwell @ 2019-02-21 22:17 UTC (permalink / raw)
To: Michael Ellerman, Benjamin Herrenschmidt, PowerPC,
Christoph Hellwig
Cc: Linux Next Mailing List, Linux Kernel Mailing List
[-- Attachment #1: Type: text/plain, Size: 784 bytes --]
Hi all,
Today's linux-next merge of the powerpc tree got a conflict in:
arch/powerpc/kernel/dma-swiotlb.c
between commit:
cfced786969c ("dma-mapping: remove the default map_resource implementation")
from the dma-mapping tree and commit:
68005b67d15a ("powerpc/dma: use the generic direct mapping bypass")
from the powerpc tree.
I fixed it up (I just used the latter) and can carry the fix as
necessary. This is now fixed as far as linux-next is concerned, but any
non trivial conflicts should be mentioned to your upstream maintainer
when your tree is submitted for merging. You may also want to consider
cooperating with the maintainer of the conflicting tree to minimise any
particularly complex conflicts.
--
Cheers,
Stephen Rothwell
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply
* [PATCH] ASoC: fsl_ssi: remove unsupported formats in i2s master mode
From: Sven Van Asbroeck @ 2019-02-21 15:35 UTC (permalink / raw)
To: Timur Tabi, Nicolin Chen, Xiubo Li
Cc: alsa-devel, linuxppc-dev, Takashi Iwai, linux-kernel,
Liam Girdwood, Mark Brown, Jaroslav Kysela, Fabio Estevam
Quote from the ssi manual:
"The word length is fixed to 32 in I2S Master mode and
the WL bits determine the number of bits that will
contain valid data (out of the 32 transmitted/received
bits in each channel)."
(61.8.1.4, page 5138, IMX6DQRM Rev. 3, 07/2015)
In other words, in i2s master mode, we always get 32
physical bits/channel, no matter what.
However, the supported list of formats for this ssi
contains S8, S16_XX, S18_3XX, and S20_3XX, which have
8, 16, 24 and 24 physical bits/channel respectively.
If one of these is selected in i2s master mode, the
format generated by the ssi will be incorrect.
Fix by constraining the frame bits in i2s master mode
to 32 * channels. This will filter out those formats
that the ssi cannot support.
Tested on imx6 with tda998x and sgtl5k codecs.
Cc: Timur Tabi <timur@kernel.org>
Cc: Nicolin Chen <nicoleotsuka@gmail.com>
Cc: Xiubo Li <Xiubo.Lee@gmail.com>
Cc: Fabio Estevam <festevam@gmail.com>
Cc: Liam Girdwood <lgirdwood@gmail.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Jaroslav Kysela <perex@perex.cz>
Cc: Takashi Iwai <tiwai@suse.com>
Signed-off-by: Sven Van Asbroeck <TheSven73@gmail.com>
---
sound/soc/fsl/fsl_ssi.c | 28 ++++++++++++++++++++++++++++
1 file changed, 28 insertions(+)
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index 0a648229e643..3d375f60ecf4 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -627,6 +627,28 @@ static void fsl_ssi_setup_ac97(struct fsl_ssi *ssi)
regmap_write(regs, REG_SSI_SOR, SSI_SOR_WAIT(3));
}
+static int fsl_ssi_hw_rule_i2s_master(struct snd_pcm_hw_params *params,
+ struct snd_pcm_hw_rule *rule)
+{
+ struct snd_interval *it = hw_param_interval(params,
+ SNDRV_PCM_HW_PARAM_FRAME_BITS);
+ struct fsl_ssi *ssi = rule->private;
+ struct snd_interval t;
+
+ if (!fsl_ssi_is_i2s_master(ssi))
+ return 0;
+
+ /*
+ * In i2s master mode, the ssi always generates 32 physical
+ * bits/channel. Filter out formats that don't have 32 physical
+ * bits/channel, they are unsupported.
+ */
+ memset(&t, 0, sizeof(t));
+ t.min = t.max = params_channels(params) * 32;
+
+ return snd_interval_refine(it, &t);
+}
+
static int fsl_ssi_startup(struct snd_pcm_substream *substream,
struct snd_soc_dai *dai)
{
@@ -648,6 +670,12 @@ static int fsl_ssi_startup(struct snd_pcm_substream *substream,
snd_pcm_hw_constraint_step(substream->runtime, 0,
SNDRV_PCM_HW_PARAM_PERIOD_SIZE, 2);
+ snd_pcm_hw_rule_add(substream->runtime, 0,
+ SNDRV_PCM_HW_PARAM_FRAME_BITS,
+ fsl_ssi_hw_rule_i2s_master, ssi,
+ SNDRV_PCM_HW_PARAM_FORMAT, SNDRV_PCM_HW_PARAM_CHANNELS,
+ -1);
+
return 0;
}
--
2.17.1
^ permalink raw reply related
* Re: [PATCH v7 0/7] Add virtio-iommu driver
From: Thiago Jung Bauermann @ 2019-02-21 21:57 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: mark.rutland, devicetree, kevin.tian, tnowicki, virtio-dev,
Jean-Philippe Brucker, linux-pci, jasowang, linuxppc-dev,
will.deacon, frowand.list, virtualization, marc.zyngier, iommu,
robh+dt, bhelgaas, robin.murphy, kvmarm
In-Reply-To: <20190129135345-mutt-send-email-mst@kernel.org>
Michael S. Tsirkin <mst@redhat.com> writes:
> On Mon, Jan 21, 2019 at 11:29:05AM +0000, Jean-Philippe Brucker wrote:
>> Hi,
>>
>> On 18/01/2019 15:51, Michael S. Tsirkin wrote:
>> >
>> > On Tue, Jan 15, 2019 at 12:19:52PM +0000, Jean-Philippe Brucker wrote:
>> >> Implement the virtio-iommu driver, following specification v0.9 [1].
>> >>
>> >> This is a simple rebase onto Linux v5.0-rc2. We now use the
>> >> dev_iommu_fwspec_get() helper introduced in v5.0 instead of accessing
>> >> dev->iommu_fwspec, but there aren't any functional change from v6 [2].
>> >>
>> >> Our current goal for virtio-iommu is to get a paravirtual IOMMU working
>> >> on Arm, and enable device assignment to guest userspace. In this
>> >> use-case the mappings are static, and don't require optimal performance,
>> >> so this series tries to keep things simple. However there is plenty more
>> >> to do for features and optimizations, and having this base in v5.1 would
>> >> be good. Given that most of the changes are to drivers/iommu, I believe
>> >> the driver and future changes should go via the IOMMU tree.
>> >>
>> >> You can find Linux driver and kvmtool device on v0.9.2 branches [3],
>> >> module and x86 support on virtio-iommu/devel. Also tested with Eric's
>> >> QEMU device [4]. Please note that the series depends on Robin's
>> >> probe-deferral fix [5], which will hopefully land in v5.0.
>> >>
>> >> [1] Virtio-iommu specification v0.9, sources and pdf
>> >> git://linux-arm.org/virtio-iommu.git virtio-iommu/v0.9
>> >> http://jpbrucker.net/virtio-iommu/spec/v0.9/virtio-iommu-v0.9.pdf
>> >>
>> >> [2] [PATCH v6 0/7] Add virtio-iommu driver
>> >> https://lists.linuxfoundation.org/pipermail/iommu/2018-December/032127.html
>> >>
>> >> [3] git://linux-arm.org/linux-jpb.git virtio-iommu/v0.9.2
>> >> git://linux-arm.org/kvmtool-jpb.git virtio-iommu/v0.9.2
>> >>
>> >> [4] [RFC v9 00/17] VIRTIO-IOMMU device
>> >> https://www.mail-archive.com/qemu-devel@nongnu.org/msg575578.html
>> >>
>> >> [5] [PATCH] iommu/of: Fix probe-deferral
>> >> https://www.spinics.net/lists/arm-kernel/msg698371.html
>> >
>> > Thanks for the work!
>> > So really my only issue with this is that there's no
>> > way for the IOMMU to describe the devices that it
>> > covers.
>> >
>> > As a result that is then done in a platform-specific way.
>> >
>> > And this means that for example it does not solve the problem that e.g.
>> > some power people have in that their platform simply does not have a way
>> > to specify which devices are covered by the IOMMU.
>>
>> Isn't power using device tree? I haven't looked much at power because I
>> was told a while ago that they already paravirtualize their IOMMU and
>> don't need virtio-iommu, except perhaps for some legacy platforms. Or
>> something along those lines. But I would certainly be interested in
>> enabling the IOMMU for more architectures.
>
> I have CC'd the relevant ppc developers, let's see what do they think.
I'm far from being an expert, but what could be very useful for us is to
have a way for the guest to request IOMMU bypass for a device.
From what I understand, the pSeries platform used by POWER guests always
puts devices behind an IOMMU, so at least for current systems a
description of which devices are covered by the IOMMU would always say
"all of them".
>> As for the enumeration problem, I still don't think we can get much
>> better than DT and ACPI as solutions (and IMO they are necessary to make
>> this device portable). But I believe that getting DT and ACPI support is
>> just a one-off inconvenience. That is, once the required bindings are
>> accepted, any future extension can then be done at the virtio level with
>> feature bits and probe requests, without having to update ACPI or DT.
There is a device tree binding that can specify devices connected to a
given IOMMU in Documentation/devicetree/bindings/iommu/iommu.txt.
I don't believe POWER machines use it though.
>> Thanks,
>> Jean
>>
>> > Solving that problem would make me much more excited about
>> > this device.
>> >
>> > On the other hand I can see that while there have been some
>> > developments most of the code has been stable for quite a while now.
>> >
>> > So what I am trying to do right about now, is making a small module that
>> > loads early and pokes at the IOMMU sufficiently to get the data about
>> > which devices use the IOMMU out of it using standard virtio config
>> > space. IIUC it's claimed to be impossible without messy changes to the
>> > boot sequence.
>> >
>> > If I succeed at least on some platforms I'll ask that this design is
>> > worked into this device, minimizing info that goes through DT/ACPI. If
>> > I see I can't make it in time to meet the next merge window, I plan
>> > merging the existing patches using DT (barring surprises).
>> >
>> > As I only have a very small amount of time to spend on this attempt, If
>> > someone else wants to try doing that in parallel, that would be great!
--
Thiago Jung Bauermann
IBM Linux Technology Center
^ permalink raw reply
* [PATCH v5 16/16] powerpc/kconfig: make _etext and data areas alignment configurable on 8xx
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
On 8xx, large pages (512kb or 8M) are used to map kernel linear
memory. Aligning to 8M reduces TLB misses as only 8M pages are used
in that case. We make 8M the default for data.
This patchs allows the user to do it via Kconfig.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Kconfig | 18 +++++++++++++++---
arch/powerpc/kernel/head_8xx.S | 4 ++--
2 files changed, 17 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c4d6c97d7699..cf30a8f522b9 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -726,7 +726,8 @@ config THREAD_SHIFT
want. Only change this if you know what you are doing.
config ETEXT_SHIFT_BOOL
- bool "Set custom etext alignment" if STRICT_KERNEL_RWX && PPC_BOOK3S_32
+ bool "Set custom etext alignment" if STRICT_KERNEL_RWX && \
+ (PPC_BOOK3S_32 || PPC_8xx)
depends on ADVANCED_OPTIONS
help
This option allows you to set the kernel end of text alignment. When
@@ -738,6 +739,7 @@ config ETEXT_SHIFT_BOOL
config ETEXT_SHIFT
int "_etext shift" if ETEXT_SHIFT_BOOL
range 17 28 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
+ range 19 23 if STRICT_KERNEL_RWX && PPC_8xx
default 17 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
default 19 if STRICT_KERNEL_RWX && PPC_8xx
default PPC_PAGE_SHIFT
@@ -745,8 +747,13 @@ config ETEXT_SHIFT
On Book3S 32 (603+), IBATs are used to map kernel text.
Smaller is the alignment, greater is the number of necessary IBATs.
+ On 8xx, large pages (512kb or 8M) are used to map kernel linear
+ memory. Aligning to 8M reduces TLB misses as only 8M pages are used
+ in that case.
+
config DATA_SHIFT_BOOL
- bool "Set custom data alignment" if STRICT_KERNEL_RWX && PPC_BOOK3S_32
+ bool "Set custom data alignment" if STRICT_KERNEL_RWX && \
+ (PPC_BOOK3S_32 || PPC_8xx)
depends on ADVANCED_OPTIONS
help
This option allows you to set the kernel data alignment. When
@@ -759,13 +766,18 @@ config DATA_SHIFT
int "Data shift" if DATA_SHIFT_BOOL
default 24 if STRICT_KERNEL_RWX && PPC64
range 17 28 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
+ range 19 23 if STRICT_KERNEL_RWX && PPC_8xx
default 22 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
- default 19 if STRICT_KERNEL_RWX && PPC_8xx
+ default 23 if STRICT_KERNEL_RWX && PPC_8xx
default PPC_PAGE_SHIFT
help
On Book3S 32 (603+), DBATs are used to map kernel text and rodata RO.
Smaller is the alignment, greater is the number of necessary DBATs.
+ On 8xx, large pages (512kb or 8M) are used to map kernel linear
+ memory. Aligning to 8M reduces TLB misses as only 8M pages are used
+ in that case.
+
config FORCE_MAX_ZONEORDER
int "Maximum zone order"
range 8 9 if PPC64 && PPC_64K_PAGES
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 01ed8f3c95c8..63f1b7eec3f0 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -416,7 +416,7 @@ InstructionTLBMiss:
#ifndef CONFIG_PIN_TLB_TEXT
ITLBMissLinear:
mtcr r11
-#ifdef CONFIG_STRICT_KERNEL_RWX
+#if defined(CONFIG_STRICT_KERNEL_RWX) && CONFIG_ETEXT_SHIFT < 23
patch_site 0f, patch__itlbmiss_linmem_top8
mfspr r10, SPRN_SRR0
@@ -537,7 +537,7 @@ DTLBMissIMMR:
DTLBMissLinear:
mtcr r11
rlwinm r10, r10, 20, 0x0f800000 /* 8xx supports max 256Mb RAM */
-#ifdef CONFIG_STRICT_KERNEL_RWX
+#if defined(CONFIG_STRICT_KERNEL_RWX) && CONFIG_DATA_SHIFT < 23
patch_site 0f, patch__dtlbmiss_romem_top8
0: subis r11, r10, (PAGE_OFFSET - 0x80000000)@ha
--
2.13.3
^ permalink raw reply related
* [PATCH v5 15/16] powerpc/8xx: don't disable large TLBs with CONFIG_STRICT_KERNEL_RWX
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
This patch implements handling of STRICT_KERNEL_RWX with
large TLBs directly in the TLB miss handlers.
To do so, etext and sinittext are aligned on 512kB boundaries
and the miss handlers use 512kB pages instead of 8Mb pages for
addresses close to the boundaries.
It sets RO PP flags for addresses under sinittext.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Kconfig | 2 ++
arch/powerpc/include/asm/nohash/32/mmu-8xx.h | 3 +-
arch/powerpc/kernel/head_8xx.S | 54 +++++++++++++++++++++-------
arch/powerpc/mm/8xx_mmu.c | 31 +++++++++++++++-
arch/powerpc/mm/init_32.c | 2 +-
arch/powerpc/mm/mmu_decl.h | 2 +-
6 files changed, 78 insertions(+), 16 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 20c4e3a62b90..c4d6c97d7699 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -739,6 +739,7 @@ config ETEXT_SHIFT
int "_etext shift" if ETEXT_SHIFT_BOOL
range 17 28 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
default 17 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
+ default 19 if STRICT_KERNEL_RWX && PPC_8xx
default PPC_PAGE_SHIFT
help
On Book3S 32 (603+), IBATs are used to map kernel text.
@@ -759,6 +760,7 @@ config DATA_SHIFT
default 24 if STRICT_KERNEL_RWX && PPC64
range 17 28 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
default 22 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
+ default 19 if STRICT_KERNEL_RWX && PPC_8xx
default PPC_PAGE_SHIFT
help
On Book3S 32 (603+), DBATs are used to map kernel text and rodata RO.
diff --git a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
index b0f764c827c0..0a1a3fc54e54 100644
--- a/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
+++ b/arch/powerpc/include/asm/nohash/32/mmu-8xx.h
@@ -231,9 +231,10 @@ static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
}
/* patch sites */
-extern s32 patch__itlbmiss_linmem_top;
+extern s32 patch__itlbmiss_linmem_top, patch__itlbmiss_linmem_top8;
extern s32 patch__dtlbmiss_linmem_top, patch__dtlbmiss_immr_jmp;
extern s32 patch__fixupdar_linmem_top;
+extern s32 patch__dtlbmiss_romem_top, patch__dtlbmiss_romem_top8;
extern s32 patch__itlbmiss_exit_1, patch__itlbmiss_exit_2;
extern s32 patch__dtlbmiss_exit_1, patch__dtlbmiss_exit_2, patch__dtlbmiss_exit_3;
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 4a2e3ffdb5bb..01ed8f3c95c8 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -292,6 +292,17 @@ SystemCall:
*/
EXCEPTION(0x1000, SoftEmu, program_check_exception, EXC_XFER_STD)
+/* Called from DataStoreTLBMiss when perf TLB misses events are activated */
+#ifdef CONFIG_PERF_EVENTS
+ patch_site 0f, patch__dtlbmiss_perf
+0: lwz r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
+ addi r10, r10, 1
+ stw r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
+ mfspr r10, SPRN_SPRG_SCRATCH0
+ mfspr r11, SPRN_SPRG_SCRATCH1
+ rfi
+#endif
+
. = 0x1100
/*
* For the MPC8xx, this is a software tablewalk to load the instruction
@@ -405,10 +416,20 @@ InstructionTLBMiss:
#ifndef CONFIG_PIN_TLB_TEXT
ITLBMissLinear:
mtcr r11
+#ifdef CONFIG_STRICT_KERNEL_RWX
+ patch_site 0f, patch__itlbmiss_linmem_top8
+
+ mfspr r10, SPRN_SRR0
+0: subis r11, r10, (PAGE_OFFSET - 0x80000000)@ha
+ rlwinm r11, r11, 4, MI_PS8MEG ^ MI_PS512K
+ ori r11, r11, MI_PS512K | MI_SVALID
+ rlwinm r10, r10, 0, 0x0ff80000 /* 8xx supports max 256Mb RAM */
+#else
/* Set 8M byte page and mark it valid */
li r11, MI_PS8MEG | MI_SVALID
- mtspr SPRN_MI_TWC, r11
rlwinm r10, r10, 20, 0x0f800000 /* 8xx supports max 256Mb RAM */
+#endif
+ mtspr SPRN_MI_TWC, r11
ori r10, r10, 0xf0 | MI_SPS16K | _PAGE_SH | _PAGE_DIRTY | \
_PAGE_PRESENT
mtspr SPRN_MI_RPN, r10 /* Update TLB entry */
@@ -494,16 +515,6 @@ DataStoreTLBMiss:
rfi
patch_site 0b, patch__dtlbmiss_exit_1
-#ifdef CONFIG_PERF_EVENTS
- patch_site 0f, patch__dtlbmiss_perf
-0: lwz r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
- addi r10, r10, 1
- stw r10, (dtlb_miss_counter - PAGE_OFFSET)@l(0)
- mfspr r10, SPRN_SPRG_SCRATCH0
- mfspr r11, SPRN_SPRG_SCRATCH1
- rfi
-#endif
-
DTLBMissIMMR:
mtcr r11
/* Set 512k byte guarded page and mark it valid */
@@ -525,10 +536,29 @@ DTLBMissIMMR:
DTLBMissLinear:
mtcr r11
+ rlwinm r10, r10, 20, 0x0f800000 /* 8xx supports max 256Mb RAM */
+#ifdef CONFIG_STRICT_KERNEL_RWX
+ patch_site 0f, patch__dtlbmiss_romem_top8
+
+0: subis r11, r10, (PAGE_OFFSET - 0x80000000)@ha
+ rlwinm r11, r11, 0, 0xff800000
+ neg r10, r11
+ or r11, r11, r10
+ rlwinm r11, r11, 4, MI_PS8MEG ^ MI_PS512K
+ ori r11, r11, MI_PS512K | MI_SVALID
+ mfspr r10, SPRN_MD_EPN
+ rlwinm r10, r10, 0, 0x0ff80000 /* 8xx supports max 256Mb RAM */
+#else
/* Set 8M byte page and mark it valid */
li r11, MD_PS8MEG | MD_SVALID
+#endif
mtspr SPRN_MD_TWC, r11
- rlwinm r10, r10, 20, 0x0f800000 /* 8xx supports max 256Mb RAM */
+#ifdef CONFIG_STRICT_KERNEL_RWX
+ patch_site 0f, patch__dtlbmiss_romem_top
+
+0: subis r11, r10, 0
+ rlwimi r10, r11, 11, _PAGE_RO
+#endif
ori r10, r10, 0xf0 | MD_SPS16K | _PAGE_SH | _PAGE_DIRTY | \
_PAGE_PRESENT
mtspr SPRN_MD_RPN, r10 /* Update TLB entry */
diff --git a/arch/powerpc/mm/8xx_mmu.c b/arch/powerpc/mm/8xx_mmu.c
index 46bc26ef71e9..62d4e6d76cd7 100644
--- a/arch/powerpc/mm/8xx_mmu.c
+++ b/arch/powerpc/mm/8xx_mmu.c
@@ -94,11 +94,20 @@ static void __init mmu_mapin_immr(void)
map_kernel_page(v + offset, p + offset, PAGE_KERNEL_NCG);
}
-static void __init mmu_patch_cmp_limit(s32 *site, unsigned long mapped)
+static void mmu_patch_cmp_limit(s32 *site, unsigned long mapped)
{
modify_instruction_site(site, 0xffff, (unsigned long)__va(mapped) >> 16);
}
+static void mmu_patch_addis(s32 *site, long simm)
+{
+ unsigned int instr = *(unsigned int *)patch_site_addr(site);
+
+ instr &= 0xffff0000;
+ instr |= ((unsigned long)simm) >> 16;
+ patch_instruction_site(site, instr);
+}
+
unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
{
unsigned long mapped;
@@ -135,6 +144,26 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
return mapped;
}
+void mmu_mark_initmem_nx(void)
+{
+ if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX) && CONFIG_ETEXT_SHIFT < 23)
+ mmu_patch_addis(&patch__itlbmiss_linmem_top8,
+ -((long)_etext & ~(LARGE_PAGE_SIZE_8M - 1)));
+ if (!IS_ENABLED(CONFIG_PIN_TLB_TEXT))
+ mmu_patch_cmp_limit(&patch__itlbmiss_linmem_top, __pa(_etext));
+}
+
+#ifdef CONFIG_STRICT_KERNEL_RWX
+void mmu_mark_rodata_ro(void)
+{
+ if (CONFIG_DATA_SHIFT < 23)
+ mmu_patch_addis(&patch__dtlbmiss_romem_top8,
+ -__pa(((unsigned long)_sinittext) &
+ ~(LARGE_PAGE_SIZE_8M - 1)));
+ mmu_patch_addis(&patch__dtlbmiss_romem_top, -__pa(_sinittext));
+}
+#endif
+
void __init setup_initial_memory_limit(phys_addr_t first_memblock_base,
phys_addr_t first_memblock_size)
{
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index bc28995a37ea..41a3513cadc9 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -108,7 +108,7 @@ static void __init MMU_setup(void)
__map_without_bats = 1;
__map_without_ltlbs = 1;
}
- if (strict_kernel_rwx_enabled())
+ if (strict_kernel_rwx_enabled() && !IS_ENABLED(CONFIG_PPC_8xx))
__map_without_ltlbs = 1;
}
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 98fc94affc29..74ff61dabcb1 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -166,7 +166,7 @@ static inline phys_addr_t v_block_mapped(unsigned long va) { return 0; }
static inline unsigned long p_block_mapped(phys_addr_t pa) { return 0; }
#endif
-#if defined(CONFIG_PPC_BOOK3S_32)
+#if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_PPC_8xx)
void mmu_mark_initmem_nx(void);
void mmu_mark_rodata_ro(void);
#else
--
2.13.3
^ permalink raw reply related
* [PATCH v5 14/16] powerpc/kconfig: make _etext and data areas alignment configurable on Book3s 32
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
Depending on the number of available BATs for mapping the different
kernel areas, it might be needed to increase the alignment of _etext
and/or of data areas.
This patchs allows the user to do it via Kconfig.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Kconfig | 32 ++++++++++++++++++++++++++++++--
1 file changed, 30 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 640a7cfba9d0..20c4e3a62b90 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -725,16 +725,44 @@ config THREAD_SHIFT
Used to define the stack size. The default is almost always what you
want. Only change this if you know what you are doing.
+config ETEXT_SHIFT_BOOL
+ bool "Set custom etext alignment" if STRICT_KERNEL_RWX && PPC_BOOK3S_32
+ depends on ADVANCED_OPTIONS
+ help
+ This option allows you to set the kernel end of text alignment. When
+ RAM is mapped by blocks, the alignment needs to fit the size and
+ number of possible blocks. The default should be OK for most configs.
+
+ Say N here unless you know what you are doing.
+
config ETEXT_SHIFT
- int
+ int "_etext shift" if ETEXT_SHIFT_BOOL
+ range 17 28 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
default 17 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
default PPC_PAGE_SHIFT
+ help
+ On Book3S 32 (603+), IBATs are used to map kernel text.
+ Smaller is the alignment, greater is the number of necessary IBATs.
+
+config DATA_SHIFT_BOOL
+ bool "Set custom data alignment" if STRICT_KERNEL_RWX && PPC_BOOK3S_32
+ depends on ADVANCED_OPTIONS
+ help
+ This option allows you to set the kernel data alignment. When
+ RAM is mapped by blocks, the alignment needs to fit the size and
+ number of possible blocks. The default should be OK for most configs.
+
+ Say N here unless you know what you are doing.
config DATA_SHIFT
- int
+ int "Data shift" if DATA_SHIFT_BOOL
default 24 if STRICT_KERNEL_RWX && PPC64
+ range 17 28 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
default 22 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
default PPC_PAGE_SHIFT
+ help
+ On Book3S 32 (603+), DBATs are used to map kernel text and rodata RO.
+ Smaller is the alignment, greater is the number of necessary DBATs.
config FORCE_MAX_ZONEORDER
int "Maximum zone order"
--
2.13.3
^ permalink raw reply related
* [PATCH v5 13/16] powerpc/mm/32s: Use BATs for STRICT_KERNEL_RWX
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
Today, STRICT_KERNEL_RWX is based on the use of regular pages
to map kernel pages.
On Book3s 32, it has three consequences:
- Using pages instead of BAT for mapping kernel linear memory severely
impacts performance.
- Exec protection is not effective because no-execute cannot be set at
page level (except on 603 which doesn't have hash tables)
- Write protection is not effective because PP bits do not provide RO
mode for kernel-only pages (except on 603 which handles it in software
via PAGE_DIRTY)
On the 603+, we have:
- Independent IBAT and DBAT allowing limitation of exec parts.
- NX bit can be set in segment registers to forbit execution on memory
mapped by pages.
- RO mode on DBATs even for kernel-only blocks.
On the 601, there is nothing much we can do other than warn the user
about it, because:
- BATs are common to instructions and data.
- BAT do not provide RO mode for kernel-only blocks.
- segment registers don't have the NX bit.
In order to use IBAT for exec protection, this patch:
- Aligns _etext to BAT block sizes (128kb)
- Set NX bit in kernel segment register (Except on vmalloc area when
CONFIG_MODULES is selected)
- Maps kernel text with IBATs.
In order to use DBAT for exec protection, this patch:
- Aligns RW DATA to BAT block sizes (4M)
- Maps kernel RO area with write prohibited DBATs
- Maps remaining memory with remaining DBATs
Here is what we get with this patch on a 832x when activating
STRICT_KERNEL_RWX:
Symbols:
c0000000 T _stext
c0680000 R __start_rodata
c0680000 R _etext
c0800000 T __init_begin
c0800000 T _sinittext
~# cat /sys/kernel/debug/block_address_translation
---[ Instruction Block Address Translation ]---
0: 0xc0000000-0xc03fffff 0x00000000 Kernel EXEC coherent
1: 0xc0400000-0xc05fffff 0x00400000 Kernel EXEC coherent
2: 0xc0600000-0xc067ffff 0x00600000 Kernel EXEC coherent
3: -
4: -
5: -
6: -
7: -
---[ Data Block Address Translation ]---
0: 0xc0000000-0xc07fffff 0x00000000 Kernel RO coherent
1: 0xc0800000-0xc0ffffff 0x00800000 Kernel RW coherent
2: 0xc1000000-0xc1ffffff 0x01000000 Kernel RW coherent
3: 0xc2000000-0xc3ffffff 0x02000000 Kernel RW coherent
4: 0xc4000000-0xc7ffffff 0x04000000 Kernel RW coherent
5: 0xc8000000-0xcfffffff 0x08000000 Kernel RW coherent
6: 0xd0000000-0xdfffffff 0x10000000 Kernel RW coherent
7: -
~# cat /sys/kernel/debug/segment_registers
---[ User Segments ]---
0x00000000-0x0fffffff Kern key 1 User key 1 VSID 0xa085d0
0x10000000-0x1fffffff Kern key 1 User key 1 VSID 0xa086e1
0x20000000-0x2fffffff Kern key 1 User key 1 VSID 0xa087f2
0x30000000-0x3fffffff Kern key 1 User key 1 VSID 0xa08903
0x40000000-0x4fffffff Kern key 1 User key 1 VSID 0xa08a14
0x50000000-0x5fffffff Kern key 1 User key 1 VSID 0xa08b25
0x60000000-0x6fffffff Kern key 1 User key 1 VSID 0xa08c36
0x70000000-0x7fffffff Kern key 1 User key 1 VSID 0xa08d47
0x80000000-0x8fffffff Kern key 1 User key 1 VSID 0xa08e58
0x90000000-0x9fffffff Kern key 1 User key 1 VSID 0xa08f69
0xa0000000-0xafffffff Kern key 1 User key 1 VSID 0xa0907a
0xb0000000-0xbfffffff Kern key 1 User key 1 VSID 0xa0918b
---[ Kernel Segments ]---
0xc0000000-0xcfffffff Kern key 0 User key 1 No Exec VSID 0x000ccc
0xd0000000-0xdfffffff Kern key 0 User key 1 No Exec VSID 0x000ddd
0xe0000000-0xefffffff Kern key 0 User key 1 No Exec VSID 0x000eee
0xf0000000-0xffffffff Kern key 0 User key 1 No Exec VSID 0x000fff
Aligning _etext to 128kb allows to map up to 32Mb text with 8 IBATs:
16Mb + 8Mb + 4Mb + 2Mb + 1Mb + 512kb + 256kb + 128kb (+ 128kb) = 32Mb
(A 9th IBAT is unneeded as 32Mb would need only a single 32Mb block)
Aligning data to 4M allows to map up to 512Mb data with 8 DBATs:
16Mb + 8Mb + 4Mb + 4Mb + 32Mb + 64Mb + 128Mb + 256Mb = 512Mb
Because some processors only have 4 BATs and because some targets need
DBATs for mapping other areas, the following patch will allow to
modify _etext and data alignment.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Kconfig | 2 +
arch/powerpc/include/asm/book3s/32/pgtable.h | 11 ++++
arch/powerpc/mm/init_32.c | 4 +-
arch/powerpc/mm/mmu_decl.h | 8 +++
arch/powerpc/mm/pgtable_32.c | 10 +++-
arch/powerpc/mm/ppc_mmu_32.c | 87 ++++++++++++++++++++++++++--
6 files changed, 112 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index edef40a2b446..640a7cfba9d0 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -727,11 +727,13 @@ config THREAD_SHIFT
config ETEXT_SHIFT
int
+ default 17 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
default PPC_PAGE_SHIFT
config DATA_SHIFT
int
default 24 if STRICT_KERNEL_RWX && PPC64
+ default 22 if STRICT_KERNEL_RWX && PPC_BOOK3S_32
default PPC_PAGE_SHIFT
config FORCE_MAX_ZONEORDER
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 49d76adb9bc5..aa8406b8f7ba 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -174,7 +174,18 @@ static inline bool pte_user(pte_t pte)
* of RAM. -- Cort
*/
#define VMALLOC_OFFSET (0x1000000) /* 16M */
+
+/*
+ * With CONFIG_STRICT_KERNEL_RWX, kernel segments are set NX. But when modules
+ * are used, NX cannot be set on VMALLOC space. So vmalloc VM space and linear
+ * memory shall not share segments.
+ */
+#if defined(CONFIG_STRICT_KERNEL_RWX) && defined(CONFIG_MODULES)
+#define VMALLOC_START ((_ALIGN((long)high_memory, 256L << 20) + VMALLOC_OFFSET) & \
+ ~(VMALLOC_OFFSET - 1))
+#else
#define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
+#endif
#define VMALLOC_END ioremap_bot
#ifndef __ASSEMBLY__
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index ee5a430b9a18..bc28995a37ea 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -108,10 +108,8 @@ static void __init MMU_setup(void)
__map_without_bats = 1;
__map_without_ltlbs = 1;
}
- if (strict_kernel_rwx_enabled()) {
- __map_without_bats = 1;
+ if (strict_kernel_rwx_enabled())
__map_without_ltlbs = 1;
- }
}
/*
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 61730023dde3..98fc94affc29 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -165,3 +165,11 @@ unsigned long p_block_mapped(phys_addr_t pa);
static inline phys_addr_t v_block_mapped(unsigned long va) { return 0; }
static inline unsigned long p_block_mapped(phys_addr_t pa) { return 0; }
#endif
+
+#if defined(CONFIG_PPC_BOOK3S_32)
+void mmu_mark_initmem_nx(void);
+void mmu_mark_rodata_ro(void);
+#else
+static inline void mmu_mark_initmem_nx(void) { }
+static inline void mmu_mark_rodata_ro(void) { }
+#endif
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index a000768a5cc9..6e56a6240bfa 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -353,7 +353,10 @@ void mark_initmem_nx(void)
unsigned long numpages = PFN_UP((unsigned long)_einittext) -
PFN_DOWN((unsigned long)_sinittext);
- change_page_attr(page, numpages, PAGE_KERNEL);
+ if (v_block_mapped((unsigned long)_stext) + 1)
+ mmu_mark_initmem_nx();
+ else
+ change_page_attr(page, numpages, PAGE_KERNEL);
}
#ifdef CONFIG_STRICT_KERNEL_RWX
@@ -362,6 +365,11 @@ void mark_rodata_ro(void)
struct page *page;
unsigned long numpages;
+ if (v_block_mapped((unsigned long)_sinittext)) {
+ mmu_mark_rodata_ro();
+ return;
+ }
+
page = virt_to_page(_stext);
numpages = PFN_UP((unsigned long)_etext) -
PFN_DOWN((unsigned long)_stext);
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index 66f1319e8e20..d80622dccfa0 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -32,6 +32,7 @@
#include <asm/mmu.h>
#include <asm/machdep.h>
#include <asm/code-patching.h>
+#include <asm/sections.h>
#include "mmu_decl.h"
@@ -138,15 +139,10 @@ static void clearibat(int index)
bat[0].batl = 0;
}
-unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
+static unsigned long __init __mmu_mapin_ram(unsigned long base, unsigned long top)
{
int idx;
- if (__map_without_bats) {
- printk(KERN_DEBUG "RAM mapped without BATs\n");
- return base;
- }
-
while ((idx = find_free_bat()) != -1 && base != top) {
unsigned int size = block_size(base, top);
@@ -159,6 +155,85 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
return base;
}
+unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
+{
+ int done;
+ unsigned long border = (unsigned long)__init_begin - PAGE_OFFSET;
+
+ if (__map_without_bats) {
+ pr_debug("RAM mapped without BATs\n");
+ return base;
+ }
+
+ if (!strict_kernel_rwx_enabled() || base >= border || top <= border)
+ return __mmu_mapin_ram(base, top);
+
+ done = __mmu_mapin_ram(base, border);
+ if (done != border - base)
+ return done;
+
+ return done + __mmu_mapin_ram(border, top);
+}
+
+void mmu_mark_initmem_nx(void)
+{
+ int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
+ int i;
+ unsigned long base = (unsigned long)_stext - PAGE_OFFSET;
+ unsigned long top = (unsigned long)_etext - PAGE_OFFSET;
+ unsigned long size;
+
+ if (cpu_has_feature(CPU_FTR_601))
+ return;
+
+ for (i = 0; i < nb - 1 && base < top && top - base > (128 << 10);) {
+ size = block_size(base, top);
+ setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
+ base += size;
+ }
+ if (base < top) {
+ size = block_size(base, top);
+ size = max(size, 128UL << 10);
+ if ((top - base) > size) {
+ if (strict_kernel_rwx_enabled())
+ pr_warn("Kernel _etext not properly aligned\n");
+ size <<= 1;
+ }
+ setibat(i++, PAGE_OFFSET + base, base, size, PAGE_KERNEL_TEXT);
+ base += size;
+ }
+ for (; i < nb; i++)
+ clearibat(i);
+
+ update_bats();
+
+ for (i = TASK_SIZE >> 28; i < 16; i++) {
+ /* Do not set NX on VM space for modules */
+ if (IS_ENABLED(CONFIG_MODULES) &&
+ (VMALLOC_START & 0xf0000000) == i << 28)
+ break;
+ mtsrin(mfsrin(i << 28) | 0x10000000, i << 28);
+ }
+}
+
+void mmu_mark_rodata_ro(void)
+{
+ int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
+ int i;
+
+ if (cpu_has_feature(CPU_FTR_601))
+ return;
+
+ for (i = 0; i < nb; i++) {
+ struct ppc_bat *bat = BATS[i];
+
+ if (bat_addrs[i].start < (unsigned long)__init_begin)
+ bat[1].batl = (bat[1].batl & ~BPP_RW) | BPP_RX;
+ }
+
+ update_bats();
+}
+
/*
* Set up one of the I/D BAT (block address translation) register pairs.
* The parameters are not checked; in particular size must be a power
--
2.13.3
^ permalink raw reply related
* [PATCH v5 12/16] powerpc/mm/32s: add setibat() clearibat() and update_bats()
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
setibat() and clearibat() allows to manipulate IBATs independently
of DBATs.
update_bats() allows to update bats after init. This is done
with MMU off.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/book3s/32/mmu-hash.h | 2 ++
arch/powerpc/kernel/head_32.S | 35 +++++++++++++++++++++++++++
arch/powerpc/mm/ppc_mmu_32.c | 32 ++++++++++++++++++++++++
3 files changed, 69 insertions(+)
diff --git a/arch/powerpc/include/asm/book3s/32/mmu-hash.h b/arch/powerpc/include/asm/book3s/32/mmu-hash.h
index 0c261ba2c826..5cb588395fdc 100644
--- a/arch/powerpc/include/asm/book3s/32/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/32/mmu-hash.h
@@ -92,6 +92,8 @@ typedef struct {
unsigned long vdso_base;
} mm_context_t;
+void update_bats(void);
+
/* patch sites */
extern s32 patch__hash_page_A0, patch__hash_page_A1, patch__hash_page_A2;
extern s32 patch__hash_page_B, patch__hash_page_C;
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index c2f564690778..91b302b0797f 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -1104,6 +1104,41 @@ BEGIN_MMU_FTR_SECTION
END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
blr
+_ENTRY(update_bats)
+ lis r4, 1f@h
+ ori r4, r4, 1f@l
+ tophys(r4, r4)
+ mfmsr r6
+ mflr r7
+ li r3, MSR_KERNEL & ~(MSR_IR | MSR_DR)
+ rlwinm r0, r6, 0, ~MSR_RI
+ rlwinm r0, r0, 0, ~MSR_EE
+ mtmsr r0
+ mtspr SPRN_SRR0, r4
+ mtspr SPRN_SRR1, r3
+ SYNC
+ RFI
+1: bl clear_bats
+ lis r3, BATS@ha
+ addi r3, r3, BATS@l
+ tophys(r3, r3)
+ LOAD_BAT(0, r3, r4, r5)
+ LOAD_BAT(1, r3, r4, r5)
+ LOAD_BAT(2, r3, r4, r5)
+ LOAD_BAT(3, r3, r4, r5)
+BEGIN_MMU_FTR_SECTION
+ LOAD_BAT(4, r3, r4, r5)
+ LOAD_BAT(5, r3, r4, r5)
+ LOAD_BAT(6, r3, r4, r5)
+ LOAD_BAT(7, r3, r4, r5)
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_USE_HIGH_BATS)
+ li r3, MSR_KERNEL & ~(MSR_IR | MSR_DR | MSR_RI)
+ mtmsr r3
+ mtspr SPRN_SRR0, r7
+ mtspr SPRN_SRR1, r6
+ SYNC
+ RFI
+
flush_tlbs:
lis r10, 0x40
1: addic. r10, r10, -0x1000
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index ff8580c6ab11..66f1319e8e20 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -106,6 +106,38 @@ static unsigned int block_size(unsigned long base, unsigned long top)
return min3(max_size, 1U << base_shift, 1U << block_shift);
}
+/*
+ * Set up one of the IBAT (block address translation) register pairs.
+ * The parameters are not checked; in particular size must be a power
+ * of 2 between 128k and 256M.
+ * Only for 603+ ...
+ */
+static void setibat(int index, unsigned long virt, phys_addr_t phys,
+ unsigned int size, pgprot_t prot)
+{
+ unsigned int bl = (size >> 17) - 1;
+ int wimgxpp;
+ struct ppc_bat *bat = BATS[index];
+ unsigned long flags = pgprot_val(prot);
+
+ if (!cpu_has_feature(CPU_FTR_NEED_COHERENT))
+ flags &= ~_PAGE_COHERENT;
+
+ wimgxpp = (flags & _PAGE_COHERENT) | (_PAGE_EXEC ? BPP_RX : BPP_XX);
+ bat[0].batu = virt | (bl << 2) | 2; /* Vs=1, Vp=0 */
+ bat[0].batl = BAT_PHYS_ADDR(phys) | wimgxpp;
+ if (flags & _PAGE_USER)
+ bat[0].batu |= 1; /* Vp = 1 */
+}
+
+static void clearibat(int index)
+{
+ struct ppc_bat *bat = BATS[index];
+
+ bat[0].batu = 0;
+ bat[0].batl = 0;
+}
+
unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
{
int idx;
--
2.13.3
^ permalink raw reply related
* [PATCH v5 11/16] powerpc/kconfig: define CONFIG_DATA_SHIFT and CONFIG_ETEXT_SHIFT
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
CONFIG_STRICT_KERNEL_RWX requires a special alignment
for DATA for some subarches. Today it is just defined
as an #ifdef in vmlinux.lds.S
In order to get more flexibility, this patch moves the
definition of this alignment in Kconfig
On some subarches, CONFIG_STRICT_KERNEL_RWX will
require a special alignment of _etext.
This patch also adds a configuration item for it in Kconfig
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Kconfig | 9 +++++++++
arch/powerpc/kernel/vmlinux.lds.S | 9 +++------
2 files changed, 12 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 417e52a27f63..edef40a2b446 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -725,6 +725,15 @@ config THREAD_SHIFT
Used to define the stack size. The default is almost always what you
want. Only change this if you know what you are doing.
+config ETEXT_SHIFT
+ int
+ default PPC_PAGE_SHIFT
+
+config DATA_SHIFT
+ int
+ default 24 if STRICT_KERNEL_RWX && PPC64
+ default PPC_PAGE_SHIFT
+
config FORCE_MAX_ZONEORDER
int "Maximum zone order"
range 8 9 if PPC64 && PPC_64K_PAGES
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index c3efb972c8c1..060a1acd7c6d 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -12,11 +12,8 @@
#include <asm/cache.h>
#include <asm/thread_info.h>
-#if defined(CONFIG_STRICT_KERNEL_RWX) && !defined(CONFIG_PPC32)
-#define STRICT_ALIGN_SIZE (1 << 24)
-#else
-#define STRICT_ALIGN_SIZE PAGE_SIZE
-#endif
+#define STRICT_ALIGN_SIZE (1 << CONFIG_DATA_SHIFT)
+#define ETEXT_ALIGN_SIZE (1 << CONFIG_ETEXT_SHIFT)
ENTRY(_stext)
@@ -131,7 +128,7 @@ SECTIONS
} :kernel
- . = ALIGN(PAGE_SIZE);
+ . = ALIGN(ETEXT_ALIGN_SIZE);
_etext = .;
PROVIDE32 (etext = .);
--
2.13.3
^ permalink raw reply related
* [PATCH v5 10/16] powerpc/kconfig: define PAGE_SHIFT inside Kconfig
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
This patch defined CONFIG_PPC_PAGE_SHIFT in order
to be able to use PAGE_SHIFT value inside Kconfig.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Kconfig | 7 +++++++
arch/powerpc/include/asm/page.h | 13 ++-----------
2 files changed, 9 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 849b0d5ac3d1..417e52a27f63 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -708,6 +708,13 @@ config PPC_256K_PAGES
endchoice
+config PPC_PAGE_SHIFT
+ int
+ default 18 if PPC_256K_PAGES
+ default 16 if PPC_64K_PAGES
+ default 14 if PPC_16K_PAGES
+ default 12
+
config THREAD_SHIFT
int "Thread shift" if EXPERT
range 13 15
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index aa4497175bd3..ed870468ef6f 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -20,20 +20,11 @@
/*
* On regular PPC32 page size is 4K (but we support 4K/16K/64K/256K pages
- * on PPC44x). For PPC64 we support either 4K or 64K software
+ * on PPC44x and 4K/16K on 8xx). For PPC64 we support either 4K or 64K software
* page size. When using 64K pages however, whether we are really supporting
* 64K pages in HW or not is irrelevant to those definitions.
*/
-#if defined(CONFIG_PPC_256K_PAGES)
-#define PAGE_SHIFT 18
-#elif defined(CONFIG_PPC_64K_PAGES)
-#define PAGE_SHIFT 16
-#elif defined(CONFIG_PPC_16K_PAGES)
-#define PAGE_SHIFT 14
-#else
-#define PAGE_SHIFT 12
-#endif
-
+#define PAGE_SHIFT CONFIG_PPC_PAGE_SHIFT
#define PAGE_SIZE (ASM_CONST(1) << PAGE_SHIFT)
#ifndef __ASSEMBLY__
--
2.13.3
^ permalink raw reply related
* [PATCH v5 09/16] powerpc/mmu: add is_strict_kernel_rwx() helper
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
Add a helper to know whether STRICT_KERNEL_RWX is enabled.
This is based on rodata_enabled flag which is defined only
when CONFIG_STRICT_KERNEL_RWX is selected.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/mmu.h | 11 +++++++++++
arch/powerpc/mm/init_32.c | 4 +---
2 files changed, 12 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 6d22a8e78fe2..d34ad1657d7b 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -289,6 +289,17 @@ static inline u16 get_mm_addr_key(struct mm_struct *mm, unsigned long address)
}
#endif /* CONFIG_PPC_MEM_KEYS */
+#ifdef CONFIG_STRICT_KERNEL_RWX
+static inline bool strict_kernel_rwx_enabled(void)
+{
+ return rodata_enabled;
+}
+#else
+static inline bool strict_kernel_rwx_enabled(void)
+{
+ return false;
+}
+#endif
#endif /* !__ASSEMBLY__ */
/* The kernel use the constants below to index in the page sizes array.
diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c
index 3e59e5d64b01..ee5a430b9a18 100644
--- a/arch/powerpc/mm/init_32.c
+++ b/arch/powerpc/mm/init_32.c
@@ -108,12 +108,10 @@ static void __init MMU_setup(void)
__map_without_bats = 1;
__map_without_ltlbs = 1;
}
-#ifdef CONFIG_STRICT_KERNEL_RWX
- if (rodata_enabled) {
+ if (strict_kernel_rwx_enabled()) {
__map_without_bats = 1;
__map_without_ltlbs = 1;
}
-#endif
}
/*
--
2.13.3
^ permalink raw reply related
* [PATCH v5 08/16] powerpc/32: add helper to write into segment registers
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
This patch add an helper which wraps 'mtsrin' instruction
to write into segment registers.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/reg.h | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 1c98ef1f2d5b..a70cbaf5c26f 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1425,6 +1425,11 @@ static inline void msr_check_and_clear(unsigned long bits)
#define mfsrin(v) ({unsigned int rval; \
asm volatile("mfsrin %0,%1" : "=r" (rval) : "r" (v)); \
rval;})
+
+static inline void mtsrin(u32 val, u32 idx)
+{
+ asm volatile("mtsrin %0, %1" : : "r" (val), "r" (idx));
+}
#endif
#define proc_trap() asm volatile("trap")
--
2.13.3
^ permalink raw reply related
* [PATCH v5 07/16] powerpc/mm/32s: use _PAGE_EXEC in setbat()
From: Christophe Leroy @ 2019-02-21 19:08 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
j.neuschaefer
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1550775950.git.christophe.leroy@c-s.fr>
Do not set IBAT when setbat() is called without _PAGE_EXEC
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/mm/ppc_mmu_32.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index 5fc59b195fef..ff8580c6ab11 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -131,6 +131,7 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
* Set up one of the I/D BAT (block address translation) register pairs.
* The parameters are not checked; in particular size must be a power
* of 2 between 128k and 256M.
+ * On 603+, only set IBAT when _PAGE_EXEC is set
*/
void __init setbat(int index, unsigned long virt, phys_addr_t phys,
unsigned int size, pgprot_t prot)
@@ -157,11 +158,12 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys,
bat[1].batu |= 1; /* Vp = 1 */
if (flags & _PAGE_GUARDED) {
/* G bit must be zero in IBATs */
- bat[0].batu = bat[0].batl = 0;
- } else {
- /* make IBAT same as DBAT */
- bat[0] = bat[1];
+ flags &= ~_PAGE_EXEC;
}
+ if (flags & _PAGE_EXEC)
+ bat[0] = bat[1];
+ else
+ bat[0].batu = bat[0].batl = 0;
} else {
/* 601 cpu */
if (bl > BL_8M)
--
2.13.3
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox