* [PATCH v5 18/26] powerpc/book3s64/keys/kuap: Reset AMR/IAMR values on kexec
From: Aneesh Kumar K.V @ 2020-06-19 13:58 UTC (permalink / raw)
To: linuxppc-dev, mpe; +Cc: Aneesh Kumar K.V, linuxram, bauerman
In-Reply-To: <20200619135850.47155-1-aneesh.kumar@linux.ibm.com>
As we kexec across kernels that use AMR/IAMR for different purposes
we need to ensure that new kernels get kexec'd with a reset value
of AMR/IAMR. For ex: the new kernel can use key 0 for kernel mapping and the old
AMR value prevents access to key 0.
This patch also removes reset if IAMR and AMOR in kexec_sequence. Reset of AMOR
is not needed and the IAMR reset is partial (it doesn't do the reset
on secondary cpus) and is redundant with this patch.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
.../powerpc/include/asm/book3s/64/kup-radix.h | 20 +++++++++++++++++++
arch/powerpc/include/asm/kup.h | 14 +++++++++++++
arch/powerpc/kernel/misc_64.S | 14 -------------
arch/powerpc/kexec/core_64.c | 3 +++
arch/powerpc/mm/book3s64/pgtable.c | 3 +++
5 files changed, 40 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h
index 3ee1ec60be84..c57063c35833 100644
--- a/arch/powerpc/include/asm/book3s/64/kup-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h
@@ -180,6 +180,26 @@ static inline unsigned long kuap_get_and_check_amr(void)
}
#endif /* CONFIG_PPC_KUAP */
+#define reset_kuap reset_kuap
+static inline void reset_kuap(void)
+{
+ if (mmu_has_feature(MMU_FTR_RADIX_KUAP)) {
+ mtspr(SPRN_AMR, 0);
+ /* Do we need isync()? We are going via a kexec reset */
+ isync();
+ }
+}
+
+#define reset_kuep reset_kuep
+static inline void reset_kuep(void)
+{
+ if (mmu_has_feature(MMU_FTR_KUEP)) {
+ mtspr(SPRN_IAMR, 0);
+ /* Do we need isync()? We are going via a kexec reset */
+ isync();
+ }
+}
+
#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */
diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h
index c745ee41ad66..4dc23a706910 100644
--- a/arch/powerpc/include/asm/kup.h
+++ b/arch/powerpc/include/asm/kup.h
@@ -113,6 +113,20 @@ static inline void prevent_current_write_to_user(void)
prevent_user_access(NULL, NULL, ~0UL, KUAP_CURRENT_WRITE);
}
+#ifndef reset_kuap
+#define reset_kuap reset_kuap
+static inline void reset_kuap(void)
+{
+}
+#endif
+
+#ifndef reset_kuep
+#define reset_kuep reset_kuep
+static inline void reset_kuep(void)
+{
+}
+#endif
+
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_POWERPC_KUAP_H_ */
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 1864605eca29..7bb46ad98207 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -413,20 +413,6 @@ _GLOBAL(kexec_sequence)
li r0,0
std r0,16(r1)
-BEGIN_FTR_SECTION
- /*
- * This is the best time to turn AMR/IAMR off.
- * key 0 is used in radix for supervisor<->user
- * protection, but on hash key 0 is reserved
- * ideally we want to enter with a clean state.
- * NOTE, we rely on r0 being 0 from above.
- */
- mtspr SPRN_IAMR,r0
-BEGIN_FTR_SECTION_NESTED(42)
- mtspr SPRN_AMOR,r0
-END_FTR_SECTION_NESTED_IFSET(CPU_FTR_HVMODE, 42)
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-
/* save regs for local vars on new stack.
* yes, we won't go back, but ...
*/
diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
index b4184092172a..a124715f33ea 100644
--- a/arch/powerpc/kexec/core_64.c
+++ b/arch/powerpc/kexec/core_64.c
@@ -152,6 +152,9 @@ static void kexec_smp_down(void *arg)
if (ppc_md.kexec_cpu_down)
ppc_md.kexec_cpu_down(0, 1);
+ reset_kuap();
+ reset_kuep();
+
kexec_smp_wait();
/* NOTREACHED */
}
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index c58ad1049909..9673f4b74c9a 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -165,6 +165,9 @@ void mmu_cleanup_all(void)
radix__mmu_cleanup_all();
else if (mmu_hash_ops.hpte_clear_all)
mmu_hash_ops.hpte_clear_all();
+
+ reset_kuap();
+ reset_kuep();
}
#ifdef CONFIG_MEMORY_HOTPLUG
--
2.26.2
^ permalink raw reply related
* [PATCH v5 19/26] powerpc/book3s64/kuap: Move KUAP related function outside radix
From: Aneesh Kumar K.V @ 2020-06-19 13:58 UTC (permalink / raw)
To: linuxppc-dev, mpe; +Cc: Aneesh Kumar K.V, linuxram, bauerman
In-Reply-To: <20200619135850.47155-1-aneesh.kumar@linux.ibm.com>
The next set of patches adds support for kuap with hash translation.
In preparation for that rename/move kuap related functions to
non radix names.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
.../asm/book3s/64/{kup-radix.h => kup.h} | 6 +++---
arch/powerpc/include/asm/kup.h | 2 +-
arch/powerpc/kernel/syscall_64.c | 2 +-
arch/powerpc/mm/book3s64/pkeys.c | 19 +++++++++++++++++++
arch/powerpc/mm/book3s64/radix_pgtable.c | 18 ------------------
5 files changed, 24 insertions(+), 23 deletions(-)
rename arch/powerpc/include/asm/book3s/64/{kup-radix.h => kup.h} (97%)
diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup.h
similarity index 97%
rename from arch/powerpc/include/asm/book3s/64/kup-radix.h
rename to arch/powerpc/include/asm/book3s/64/kup.h
index c57063c35833..54e237c093da 100644
--- a/arch/powerpc/include/asm/book3s/64/kup-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/kup.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H
-#define _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H
+#ifndef _ASM_POWERPC_BOOK3S_64_KUP_H
+#define _ASM_POWERPC_BOOK3S_64_KUP_H
#include <linux/const.h>
#include <asm/reg.h>
@@ -202,4 +202,4 @@ static inline void reset_kuep(void)
#endif /* __ASSEMBLY__ */
-#endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */
+#endif /* _ASM_POWERPC_BOOK3S_64_KUP_H */
diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h
index 4dc23a706910..593707e112cc 100644
--- a/arch/powerpc/include/asm/kup.h
+++ b/arch/powerpc/include/asm/kup.h
@@ -15,7 +15,7 @@
#define KUAP_CURRENT (KUAP_CURRENT_READ | KUAP_CURRENT_WRITE)
#ifdef CONFIG_PPC64
-#include <asm/book3s/64/kup-radix.h>
+#include <asm/book3s/64/kup.h>
#endif
#ifdef CONFIG_PPC_8xx
#include <asm/nohash/32/kup-8xx.h>
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 79edba3ab312..7e560a01afa4 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -2,7 +2,7 @@
#include <linux/err.h>
#include <asm/asm-prototypes.h>
-#include <asm/book3s/64/kup-radix.h>
+#include <asm/book3s/64/kup.h>
#include <asm/cputime.h>
#include <asm/hw_irq.h>
#include <asm/kprobes.h>
diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
index 0d72c0246052..e93b65a0e6e7 100644
--- a/arch/powerpc/mm/book3s64/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -12,6 +12,7 @@
#include <linux/pkeys.h>
#include <linux/of_fdt.h>
+#include <asm/smp.h>
DEFINE_STATIC_KEY_FALSE(execute_pkey_disabled);
int max_pkey; /* Maximum key value supported */
@@ -199,6 +200,24 @@ void __init pkey_early_init_devtree(void)
return;
}
+#ifdef CONFIG_PPC_KUAP
+void __init setup_kuap(bool disabled)
+{
+ if (disabled || !early_radix_enabled())
+ return;
+
+ if (smp_processor_id() == boot_cpuid) {
+ pr_info("Activating Kernel Userspace Access Prevention\n");
+ cur_cpu_spec->mmu_features |= MMU_FTR_RADIX_KUAP;
+ }
+
+ /* Make sure userspace can't change the AMR */
+ mtspr(SPRN_UAMOR, 0);
+ mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
+ isync();
+}
+#endif
+
void pkey_mm_init(struct mm_struct *mm)
{
if (!mmu_has_feature(MMU_FTR_PKEY))
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 04fd749c6339..3959b7d4ad3c 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -534,24 +534,6 @@ void setup_kuep(bool disabled)
}
#endif
-#ifdef CONFIG_PPC_KUAP
-void setup_kuap(bool disabled)
-{
- if (disabled || !early_radix_enabled())
- return;
-
- if (smp_processor_id() == boot_cpuid) {
- pr_info("Activating Kernel Userspace Access Prevention\n");
- cur_cpu_spec->mmu_features |= MMU_FTR_RADIX_KUAP;
- }
-
- /* Make sure userspace can't change the AMR */
- mtspr(SPRN_UAMOR, 0);
- mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
- isync();
-}
-#endif
-
void __init radix__early_init_mmu(void)
{
unsigned long lpcr;
--
2.26.2
^ permalink raw reply related
* [PATCH v5 20/26] powerpc/book3s64/kuep: Move KUEP related function outside radix
From: Aneesh Kumar K.V @ 2020-06-19 13:58 UTC (permalink / raw)
To: linuxppc-dev, mpe; +Cc: Aneesh Kumar K.V, linuxram, bauerman
In-Reply-To: <20200619135850.47155-1-aneesh.kumar@linux.ibm.com>
The next set of patches adds support for kuep with hash translation.
In preparation for that rename/move kuap related functions to
non radix names.
Also set MMU_FTR_KUEP and add the missing isync().
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/powerpc/include/asm/book3s/64/kup.h | 1 +
arch/powerpc/mm/book3s64/pkeys.c | 21 +++++++++++++++++++++
arch/powerpc/mm/book3s64/radix_pgtable.c | 20 --------------------
3 files changed, 22 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/kup.h b/arch/powerpc/include/asm/book3s/64/kup.h
index 54e237c093da..c4cf9b1caa23 100644
--- a/arch/powerpc/include/asm/book3s/64/kup.h
+++ b/arch/powerpc/include/asm/book3s/64/kup.h
@@ -7,6 +7,7 @@
#define AMR_KUAP_BLOCK_READ UL(0x4000000000000000)
#define AMR_KUAP_BLOCK_WRITE UL(0x8000000000000000)
+#define AMR_KUEP_BLOCKED (1UL << 62)
#define AMR_KUAP_BLOCKED (AMR_KUAP_BLOCK_READ | AMR_KUAP_BLOCK_WRITE)
#define AMR_KUAP_SHIFT 62
diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
index e93b65a0e6e7..8ec677a91f80 100644
--- a/arch/powerpc/mm/book3s64/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -200,6 +200,27 @@ void __init pkey_early_init_devtree(void)
return;
}
+#ifdef CONFIG_PPC_KUEP
+void __init setup_kuep(bool disabled)
+{
+ if (disabled || !early_radix_enabled())
+ return;
+
+ if (smp_processor_id() == boot_cpuid) {
+ pr_info("Activating Kernel Userspace Execution Prevention\n");
+ cur_cpu_spec->mmu_features |= MMU_FTR_KUEP;
+ }
+
+ /*
+ * Radix always uses key0 of the IAMR to determine if an access is
+ * allowed. We set bit 0 (IBM bit 1) of key0, to prevent instruction
+ * fetch.
+ */
+ mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED);
+ isync();
+}
+#endif
+
#ifdef CONFIG_PPC_KUAP
void __init setup_kuap(bool disabled)
{
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 3959b7d4ad3c..2f641e1d7e82 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -514,26 +514,6 @@ static void radix_init_amor(void)
mtspr(SPRN_AMOR, (3ul << 62));
}
-#ifdef CONFIG_PPC_KUEP
-void setup_kuep(bool disabled)
-{
- if (disabled || !early_radix_enabled())
- return;
-
- if (smp_processor_id() == boot_cpuid) {
- pr_info("Activating Kernel Userspace Execution Prevention\n");
- cur_cpu_spec->mmu_features |= MMU_FTR_KUEP;
- }
-
- /*
- * Radix always uses key0 of the IAMR to determine if an access is
- * allowed. We set bit 0 (IBM bit 1) of key0, to prevent instruction
- * fetch.
- */
- mtspr(SPRN_IAMR, (1ul << 62));
-}
-#endif
-
void __init radix__early_init_mmu(void)
{
unsigned long lpcr;
--
2.26.2
^ permalink raw reply related
* [PATCH v5 21/26] powerpc/book3s64/kuap: Rename MMU_FTR_RADIX_KUAP to MMU_FTR_KUAP
From: Aneesh Kumar K.V @ 2020-06-19 13:58 UTC (permalink / raw)
To: linuxppc-dev, mpe; +Cc: Aneesh Kumar K.V, linuxram, bauerman
In-Reply-To: <20200619135850.47155-1-aneesh.kumar@linux.ibm.com>
The next set of patches adds support for kuap with hash translation.
In preparation for that rename/move kuap related functions to
non radix names.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/powerpc/include/asm/book3s/64/kup.h | 20 ++++++++++----------
arch/powerpc/include/asm/mmu.h | 6 +++---
arch/powerpc/mm/book3s64/pkeys.c | 2 +-
3 files changed, 14 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/kup.h b/arch/powerpc/include/asm/book3s/64/kup.h
index c4cf9b1caa23..3cecd964a63f 100644
--- a/arch/powerpc/include/asm/book3s/64/kup.h
+++ b/arch/powerpc/include/asm/book3s/64/kup.h
@@ -24,7 +24,7 @@
mtspr SPRN_AMR, \gpr2
/* No isync required, see kuap_restore_amr() */
998:
- END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67)
+ END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 67)
#endif
.endm
@@ -36,7 +36,7 @@
sldi \gpr2, \gpr2, AMR_KUAP_SHIFT
999: tdne \gpr1, \gpr2
EMIT_BUG_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE)
- END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67)
+ END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 67)
#endif
.endm
@@ -56,7 +56,7 @@
mtspr SPRN_AMR, \gpr2
isync
99:
- END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_RADIX_KUAP, 67)
+ END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 67)
#endif
.endm
@@ -69,7 +69,7 @@
static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr)
{
- if (mmu_has_feature(MMU_FTR_RADIX_KUAP) && unlikely(regs->kuap != amr)) {
+ if (mmu_has_feature(MMU_FTR_KUAP) && unlikely(regs->kuap != amr)) {
isync();
mtspr(SPRN_AMR, regs->kuap);
/*
@@ -82,7 +82,7 @@ static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr)
static inline unsigned long kuap_get_and_check_amr(void)
{
- if (mmu_has_feature(MMU_FTR_RADIX_KUAP)) {
+ if (mmu_has_feature(MMU_FTR_KUAP)) {
unsigned long amr = mfspr(SPRN_AMR);
if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG)) /* kuap_check_amr() */
WARN_ON_ONCE(amr != AMR_KUAP_BLOCKED);
@@ -93,7 +93,7 @@ static inline unsigned long kuap_get_and_check_amr(void)
static inline void kuap_check_amr(void)
{
- if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG) && mmu_has_feature(MMU_FTR_RADIX_KUAP))
+ if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG) && mmu_has_feature(MMU_FTR_KUAP))
WARN_ON_ONCE(mfspr(SPRN_AMR) != AMR_KUAP_BLOCKED);
}
@@ -104,7 +104,7 @@ static inline void kuap_check_amr(void)
static inline unsigned long get_kuap(void)
{
- if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP))
+ if (!early_mmu_has_feature(MMU_FTR_KUAP))
return 0;
return mfspr(SPRN_AMR);
@@ -112,7 +112,7 @@ static inline unsigned long get_kuap(void)
static inline void set_kuap(unsigned long value)
{
- if (!early_mmu_has_feature(MMU_FTR_RADIX_KUAP))
+ if (!early_mmu_has_feature(MMU_FTR_KUAP))
return;
/*
@@ -162,7 +162,7 @@ static inline void restore_user_access(unsigned long flags)
static inline bool
bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
{
- return WARN(mmu_has_feature(MMU_FTR_RADIX_KUAP) &&
+ return WARN(mmu_has_feature(MMU_FTR_KUAP) &&
(regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)),
"Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read");
}
@@ -184,7 +184,7 @@ static inline unsigned long kuap_get_and_check_amr(void)
#define reset_kuap reset_kuap
static inline void reset_kuap(void)
{
- if (mmu_has_feature(MMU_FTR_RADIX_KUAP)) {
+ if (mmu_has_feature(MMU_FTR_KUAP)) {
mtspr(SPRN_AMR, 0);
/* Do we need isync()? We are going via a kexec reset */
isync();
diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h
index 94435f85e3bc..14d7e6803453 100644
--- a/arch/powerpc/include/asm/mmu.h
+++ b/arch/powerpc/include/asm/mmu.h
@@ -112,7 +112,7 @@
/*
* Supports KUAP (key 0 controlling userspace addresses) on radix
*/
-#define MMU_FTR_RADIX_KUAP ASM_CONST(0x80000000)
+#define MMU_FTR_KUAP ASM_CONST(0x80000000)
/* MMU feature bit sets for various CPUs */
#define MMU_FTRS_DEFAULT_HPTE_ARCH_V2 \
@@ -175,10 +175,10 @@ enum {
#endif
#ifdef CONFIG_PPC_RADIX_MMU
MMU_FTR_TYPE_RADIX |
+#endif /* CONFIG_PPC_RADIX_MMU */
#ifdef CONFIG_PPC_KUAP
- MMU_FTR_RADIX_KUAP |
+ MMU_FTR_KUAP |
#endif /* CONFIG_PPC_KUAP */
-#endif /* CONFIG_PPC_RADIX_MMU */
#ifdef CONFIG_PPC_MEM_KEYS
MMU_FTR_PKEY |
#endif
diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
index 8ec677a91f80..aeecc8b8e11c 100644
--- a/arch/powerpc/mm/book3s64/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -229,7 +229,7 @@ void __init setup_kuap(bool disabled)
if (smp_processor_id() == boot_cpuid) {
pr_info("Activating Kernel Userspace Access Prevention\n");
- cur_cpu_spec->mmu_features |= MMU_FTR_RADIX_KUAP;
+ cur_cpu_spec->mmu_features |= MMU_FTR_KUAP;
}
/* Make sure userspace can't change the AMR */
--
2.26.2
^ permalink raw reply related
* [PATCH v5 22/26] powerpc/book3s64/kuap/kuep: Make KUAP and KUEP a subfeature of PPC_MEM_KEYS
From: Aneesh Kumar K.V @ 2020-06-19 13:58 UTC (permalink / raw)
To: linuxppc-dev, mpe; +Cc: Aneesh Kumar K.V, linuxram, bauerman
In-Reply-To: <20200619135850.47155-1-aneesh.kumar@linux.ibm.com>
The next set of patches adds support for kuap with hash translation.
Hence make KUAP a BOOK3S_64 feature. Also make it a subfeature of
PPC_MEM_KEYS. Hash translation is going to use pkeys to support
KUAP/KUEP. Adding this dependency reduces the code complexity and
enables us to move some of the initialization code to pkeys.c
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/powerpc/include/asm/book3s/64/kup.h | 33 ++++++++++++++----------
arch/powerpc/include/asm/ptrace.h | 2 +-
arch/powerpc/kernel/asm-offsets.c | 2 +-
arch/powerpc/platforms/Kconfig.cputype | 4 +--
4 files changed, 23 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/kup.h b/arch/powerpc/include/asm/book3s/64/kup.h
index 3cecd964a63f..3a0e138d2735 100644
--- a/arch/powerpc/include/asm/book3s/64/kup.h
+++ b/arch/powerpc/include/asm/book3s/64/kup.h
@@ -62,7 +62,7 @@
#else /* !__ASSEMBLY__ */
-#ifdef CONFIG_PPC_KUAP
+#ifdef CONFIG_PPC_MEM_KEYS
#include <asm/mmu.h>
#include <asm/ptrace.h>
@@ -97,6 +97,24 @@ static inline void kuap_check_amr(void)
WARN_ON_ONCE(mfspr(SPRN_AMR) != AMR_KUAP_BLOCKED);
}
+#else /* CONFIG_PPC_MEM_KEYS */
+
+static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr)
+{
+}
+
+static inline void kuap_check_amr(void)
+{
+}
+
+static inline unsigned long kuap_get_and_check_amr(void)
+{
+ return 0;
+}
+#endif /* CONFIG_PPC_MEM_KEYS */
+
+
+#ifdef CONFIG_PPC_KUAP
/*
* We support individually allowing read or write, but we don't support nesting
* because that would require an expensive read/modify write of the AMR.
@@ -166,19 +184,6 @@ bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
(regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)),
"Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read");
}
-#else /* CONFIG_PPC_KUAP */
-static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr)
-{
-}
-
-static inline void kuap_check_amr(void)
-{
-}
-
-static inline unsigned long kuap_get_and_check_amr(void)
-{
- return 0;
-}
#endif /* CONFIG_PPC_KUAP */
#define reset_kuap reset_kuap
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index ac3970fff0d5..1a6cadf63d14 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -53,7 +53,7 @@ struct pt_regs
#ifdef CONFIG_PPC64
unsigned long ppr;
#endif
-#ifdef CONFIG_PPC_KUAP
+#ifdef CONFIG_PPC_HAVE_KUAP
unsigned long kuap;
#endif
};
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 9b9cde07e396..1694c4f531b9 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -354,7 +354,7 @@ int main(void)
STACK_PT_REGS_OFFSET(_PPR, ppr);
#endif /* CONFIG_PPC64 */
-#ifdef CONFIG_PPC_KUAP
+#ifdef CONFIG_PPC_HAVE_KUAP
STACK_PT_REGS_OFFSET(STACK_REGS_KUAP, kuap);
#endif
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index d349603fb889..053c46aecf80 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -99,6 +99,8 @@ config PPC_BOOK3S_64
select ARCH_SUPPORTS_NUMA_BALANCING
select IRQ_WORK
select PPC_MM_SLICES
+ select PPC_HAVE_KUAP if PPC_MEM_KEYS
+ select PPC_HAVE_KUEP if PPC_MEM_KEYS
config PPC_BOOK3E_64
bool "Embedded processors"
@@ -350,8 +352,6 @@ config PPC_RADIX_MMU
bool "Radix MMU Support"
depends on PPC_BOOK3S_64
select ARCH_HAS_GIGANTIC_PAGE
- select PPC_HAVE_KUEP
- select PPC_HAVE_KUAP
default y
help
Enable support for the Power ISA 3.0 Radix style MMU. Currently this
--
2.26.2
^ permalink raw reply related
* [PATCH v5 23/26] powerpc/book3s64/kuap: Move UAMOR setup to key init function
From: Aneesh Kumar K.V @ 2020-06-19 13:58 UTC (permalink / raw)
To: linuxppc-dev, mpe; +Cc: Aneesh Kumar K.V, linuxram, bauerman
In-Reply-To: <20200619135850.47155-1-aneesh.kumar@linux.ibm.com>
UAMOR values are not application-specific. The kernel initializes
its value based on different reserved keys. Remove the thread-specific
UAMOR value and don't switch the UAMOR on context switch.
Move UAMOR initialization to key initialization code. Now that
KUAP/KUEP feature depends on PPC_MEM_KEYS, we can start to consolidate
all register initialization to keys init.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/powerpc/include/asm/book3s/64/kup.h | 2 ++
arch/powerpc/include/asm/processor.h | 1 -
arch/powerpc/kernel/ptrace/ptrace-view.c | 17 ++++++++----
arch/powerpc/kernel/smp.c | 5 ++++
arch/powerpc/mm/book3s64/pkeys.c | 35 ++++++++++++++----------
5 files changed, 39 insertions(+), 21 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/kup.h b/arch/powerpc/include/asm/book3s/64/kup.h
index 3a0e138d2735..942594745dfa 100644
--- a/arch/powerpc/include/asm/book3s/64/kup.h
+++ b/arch/powerpc/include/asm/book3s/64/kup.h
@@ -67,6 +67,8 @@
#include <asm/mmu.h>
#include <asm/ptrace.h>
+extern u64 default_uamor;
+
static inline void kuap_restore_amr(struct pt_regs *regs, unsigned long amr)
{
if (mmu_has_feature(MMU_FTR_KUAP) && unlikely(regs->kuap != amr)) {
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 52a67835057a..6ac12168f1fe 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -237,7 +237,6 @@ struct thread_struct {
#ifdef CONFIG_PPC_MEM_KEYS
unsigned long amr;
unsigned long iamr;
- unsigned long uamor;
#endif
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
void* kvm_shadow_vcpu; /* KVM internal data */
diff --git a/arch/powerpc/kernel/ptrace/ptrace-view.c b/arch/powerpc/kernel/ptrace/ptrace-view.c
index caeb5822a8f4..689711eb018a 100644
--- a/arch/powerpc/kernel/ptrace/ptrace-view.c
+++ b/arch/powerpc/kernel/ptrace/ptrace-view.c
@@ -488,14 +488,22 @@ static int pkey_active(struct task_struct *target, const struct user_regset *reg
static int pkey_get(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf)
{
+ int ret;
+
BUILD_BUG_ON(TSO(amr) + sizeof(unsigned long) != TSO(iamr));
- BUILD_BUG_ON(TSO(iamr) + sizeof(unsigned long) != TSO(uamor));
if (!arch_pkeys_enabled())
return -ENODEV;
- return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.amr,
- 0, ELF_NPKEY * sizeof(unsigned long));
+ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &target->thread.amr,
+ 0, 2 * sizeof(unsigned long));
+ if (ret)
+ goto err_out;
+
+ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, &default_uamor,
+ 2 * sizeof(unsigned long), 3 * sizeof(unsigned long));
+err_out:
+ return ret;
}
static int pkey_set(struct task_struct *target, const struct user_regset *regset,
@@ -518,8 +526,7 @@ static int pkey_set(struct task_struct *target, const struct user_regset *regset
return ret;
/* UAMOR determines which bits of the AMR can be set from userspace. */
- target->thread.amr = (new_amr & target->thread.uamor) |
- (target->thread.amr & ~target->thread.uamor);
+ target->thread.amr = (new_amr & default_uamor) | (target->thread.amr & ~default_uamor);
return 0;
}
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index c820c95162ff..eec40082599f 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -59,6 +59,7 @@
#include <asm/asm-prototypes.h>
#include <asm/cpu_has_feature.h>
#include <asm/ftrace.h>
+#include <asm/kup.h>
#ifdef DEBUG
#include <asm/udbg.h>
@@ -1256,6 +1257,10 @@ void start_secondary(void *unused)
mmgrab(&init_mm);
current->active_mm = &init_mm;
+#ifdef CONFIG_PPC_MEM_KEYS
+ mtspr(SPRN_UAMOR, default_uamor);
+#endif
+
smp_store_cpu_info(cpu);
set_dec(tb_ticks_per_jiffy);
preempt_disable();
diff --git a/arch/powerpc/mm/book3s64/pkeys.c b/arch/powerpc/mm/book3s64/pkeys.c
index aeecc8b8e11c..3f3593f85358 100644
--- a/arch/powerpc/mm/book3s64/pkeys.c
+++ b/arch/powerpc/mm/book3s64/pkeys.c
@@ -24,7 +24,7 @@ static u32 initial_allocation_mask; /* Bits set for the initially allocated k
static u64 default_amr;
static u64 default_iamr;
/* Allow all keys to be modified by default */
-static u64 default_uamor = ~0x0UL;
+u64 default_uamor = ~0x0UL;
/*
* Key used to implement PROT_EXEC mmap. Denies READ/WRITE
* We pick key 2 because 0 is special key and 1 is reserved as per ISA.
@@ -113,8 +113,16 @@ void __init pkey_early_init_devtree(void)
/* scan the device tree for pkey feature */
pkeys_total = scan_pkey_feature();
if (!pkeys_total) {
- /* No support for pkey. Mark it disabled */
- return;
+ /*
+ * No key support but on radix we can use key 0
+ * to implement kuap.
+ */
+ if (early_radix_enabled())
+ /*
+ * Make sure userspace can't change the AMR
+ */
+ default_uamor = 0;
+ goto err_out;
}
cur_cpu_spec->mmu_features |= MMU_FTR_PKEY;
@@ -197,6 +205,12 @@ void __init pkey_early_init_devtree(void)
initial_allocation_mask |= reserved_allocation_mask;
pr_info("Enabling Memory keys with max key count %d", max_pkey);
+err_out:
+ /*
+ * Setup uamor on boot cpu
+ */
+ mtspr(SPRN_UAMOR, default_uamor);
+
return;
}
@@ -232,8 +246,9 @@ void __init setup_kuap(bool disabled)
cur_cpu_spec->mmu_features |= MMU_FTR_KUAP;
}
- /* Make sure userspace can't change the AMR */
- mtspr(SPRN_UAMOR, 0);
+ /*
+ * Set the default kernel AMR values on all cpus.
+ */
mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
isync();
}
@@ -278,11 +293,6 @@ static inline u64 read_uamor(void)
return mfspr(SPRN_UAMOR);
}
-static inline void write_uamor(u64 value)
-{
- mtspr(SPRN_UAMOR, value);
-}
-
static bool is_pkey_enabled(int pkey)
{
u64 uamor = read_uamor();
@@ -353,7 +363,6 @@ void thread_pkey_regs_save(struct thread_struct *thread)
*/
thread->amr = read_amr();
thread->iamr = read_iamr();
- thread->uamor = read_uamor();
}
void thread_pkey_regs_restore(struct thread_struct *new_thread,
@@ -366,8 +375,6 @@ void thread_pkey_regs_restore(struct thread_struct *new_thread,
write_amr(new_thread->amr);
if (old_thread->iamr != new_thread->iamr)
write_iamr(new_thread->iamr);
- if (old_thread->uamor != new_thread->uamor)
- write_uamor(new_thread->uamor);
}
void thread_pkey_regs_init(struct thread_struct *thread)
@@ -377,11 +384,9 @@ void thread_pkey_regs_init(struct thread_struct *thread)
thread->amr = default_amr;
thread->iamr = default_iamr;
- thread->uamor = default_uamor;
write_amr(default_amr);
write_iamr(default_iamr);
- write_uamor(default_uamor);
}
int execute_only_pkey(struct mm_struct *mm)
--
2.26.2
^ permalink raw reply related
* [PATCH v5 24/26] powerpc/selftest/ptrave-pkey: Rename variables to make it easier to follow code
From: Aneesh Kumar K.V @ 2020-06-19 13:58 UTC (permalink / raw)
To: linuxppc-dev, mpe; +Cc: Aneesh Kumar K.V, linuxram, bauerman
In-Reply-To: <20200619135850.47155-1-aneesh.kumar@linux.ibm.com>
Rename variable to indicate that they are invalid values which we will use to
test ptrace update of pkeys.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
.../selftests/powerpc/ptrace/ptrace-pkey.c | 26 +++++++++----------
1 file changed, 13 insertions(+), 13 deletions(-)
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
index bdbbbe8431e0..f9216c7a1829 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
@@ -44,7 +44,7 @@ struct shared_info {
unsigned long amr2;
/* AMR value that ptrace should refuse to write to the child. */
- unsigned long amr3;
+ unsigned long invalid_amr;
/* IAMR value the parent expects to read from the child. */
unsigned long expected_iamr;
@@ -57,8 +57,8 @@ struct shared_info {
* (even though they're valid ones) because userspace doesn't have
* access to those registers.
*/
- unsigned long new_iamr;
- unsigned long new_uamor;
+ unsigned long invalid_iamr;
+ unsigned long invalid_uamor;
};
static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights)
@@ -100,7 +100,7 @@ static int child(struct shared_info *info)
info->amr1 |= 3ul << pkeyshift(pkey1);
info->amr2 |= 3ul << pkeyshift(pkey2);
- info->amr3 |= info->amr2 | 3ul << pkeyshift(pkey3);
+ info->invalid_amr |= info->amr2 | 3ul << pkeyshift(pkey3);
if (disable_execute)
info->expected_iamr |= 1ul << pkeyshift(pkey1);
@@ -111,8 +111,8 @@ static int child(struct shared_info *info)
info->expected_uamor |= 3ul << pkeyshift(pkey1) |
3ul << pkeyshift(pkey2);
- info->new_iamr |= 1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2);
- info->new_uamor |= 3ul << pkeyshift(pkey1);
+ info->invalid_iamr |= 1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2);
+ info->invalid_uamor |= 3ul << pkeyshift(pkey1);
/*
* We won't use pkey3. We just want a plausible but invalid key to test
@@ -196,9 +196,9 @@ static int parent(struct shared_info *info, pid_t pid)
PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync);
PARENT_FAIL_IF(ret, &info->child_sync);
- info->amr1 = info->amr2 = info->amr3 = regs[0];
- info->expected_iamr = info->new_iamr = regs[1];
- info->expected_uamor = info->new_uamor = regs[2];
+ info->amr1 = info->amr2 = info->invalid_amr = regs[0];
+ info->expected_iamr = info->invalid_iamr = regs[1];
+ info->expected_uamor = info->invalid_uamor = regs[2];
/* Wake up child so that it can set itself up. */
ret = prod_child(&info->child_sync);
@@ -234,10 +234,10 @@ static int parent(struct shared_info *info, pid_t pid)
return ret;
/* Write invalid AMR value in child. */
- ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->amr3, 1);
+ ret = ptrace_write_regs(pid, NT_PPC_PKEY, &info->invalid_amr, 1);
PARENT_FAIL_IF(ret, &info->child_sync);
- printf("%-30s AMR: %016lx\n", ptrace_write_running, info->amr3);
+ printf("%-30s AMR: %016lx\n", ptrace_write_running, info->invalid_amr);
/* Wake up child so that it can verify it didn't change. */
ret = prod_child(&info->child_sync);
@@ -249,7 +249,7 @@ static int parent(struct shared_info *info, pid_t pid)
/* Try to write to IAMR. */
regs[0] = info->amr1;
- regs[1] = info->new_iamr;
+ regs[1] = info->invalid_iamr;
ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 2);
PARENT_FAIL_IF(!ret, &info->child_sync);
@@ -257,7 +257,7 @@ static int parent(struct shared_info *info, pid_t pid)
ptrace_write_running, regs[0], regs[1]);
/* Try to write to IAMR and UAMOR. */
- regs[2] = info->new_uamor;
+ regs[2] = info->invalid_uamor;
ret = ptrace_write_regs(pid, NT_PPC_PKEY, regs, 3);
PARENT_FAIL_IF(!ret, &info->child_sync);
--
2.26.2
^ permalink raw reply related
* [PATCH v5 25/26] powerpc/selftest/ptrace-pkey: Update the test to mark an invalid pkey correctly
From: Aneesh Kumar K.V @ 2020-06-19 13:58 UTC (permalink / raw)
To: linuxppc-dev, mpe; +Cc: Aneesh Kumar K.V, linuxram, bauerman
In-Reply-To: <20200619135850.47155-1-aneesh.kumar@linux.ibm.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
.../selftests/powerpc/ptrace/ptrace-pkey.c | 30 ++++++++-----------
1 file changed, 12 insertions(+), 18 deletions(-)
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
index f9216c7a1829..bc33d748d95b 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
@@ -66,11 +66,6 @@ static int sys_pkey_alloc(unsigned long flags, unsigned long init_access_rights)
return syscall(__NR_pkey_alloc, flags, init_access_rights);
}
-static int sys_pkey_free(int pkey)
-{
- return syscall(__NR_pkey_free, pkey);
-}
-
static int child(struct shared_info *info)
{
unsigned long reg;
@@ -100,7 +95,11 @@ static int child(struct shared_info *info)
info->amr1 |= 3ul << pkeyshift(pkey1);
info->amr2 |= 3ul << pkeyshift(pkey2);
- info->invalid_amr |= info->amr2 | 3ul << pkeyshift(pkey3);
+ /*
+ * invalid amr value where we try to force write
+ * things which are deined by a uamor setting.
+ */
+ info->invalid_amr = info->amr2 | (~0x0UL & ~info->expected_uamor);
if (disable_execute)
info->expected_iamr |= 1ul << pkeyshift(pkey1);
@@ -111,17 +110,12 @@ static int child(struct shared_info *info)
info->expected_uamor |= 3ul << pkeyshift(pkey1) |
3ul << pkeyshift(pkey2);
- info->invalid_iamr |= 1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2);
- info->invalid_uamor |= 3ul << pkeyshift(pkey1);
-
/*
- * We won't use pkey3. We just want a plausible but invalid key to test
- * whether ptrace will let us write to AMR bits we are not supposed to.
- *
- * This also tests whether the kernel restores the UAMOR permissions
- * after a key is freed.
+ * Create an IAMR value different from expected value.
+ * Kernel will reject an IAMR and UAMOR change.
*/
- sys_pkey_free(pkey3);
+ info->invalid_iamr = info->expected_iamr | (1ul << pkeyshift(pkey1) | 1ul << pkeyshift(pkey2));
+ info->invalid_uamor = info->expected_uamor & ~(0x3ul << pkeyshift(pkey1));
printf("%-30s AMR: %016lx pkey1: %d pkey2: %d pkey3: %d\n",
user_write, info->amr1, pkey1, pkey2, pkey3);
@@ -196,9 +190,9 @@ static int parent(struct shared_info *info, pid_t pid)
PARENT_SKIP_IF_UNSUPPORTED(ret, &info->child_sync);
PARENT_FAIL_IF(ret, &info->child_sync);
- info->amr1 = info->amr2 = info->invalid_amr = regs[0];
- info->expected_iamr = info->invalid_iamr = regs[1];
- info->expected_uamor = info->invalid_uamor = regs[2];
+ info->amr1 = info->amr2 = regs[0];
+ info->expected_iamr = regs[1];
+ info->expected_uamor = regs[2];
/* Wake up child so that it can set itself up. */
ret = prod_child(&info->child_sync);
--
2.26.2
^ permalink raw reply related
* [PATCH v5 26/26] powerpc/selftest/ptrace-pkey: IAMR and uamor cannot be updated by ptrace
From: Aneesh Kumar K.V @ 2020-06-19 13:58 UTC (permalink / raw)
To: linuxppc-dev, mpe; +Cc: Aneesh Kumar K.V, linuxram, bauerman
In-Reply-To: <20200619135850.47155-1-aneesh.kumar@linux.ibm.com>
Both IAMR and uamor are privileged and cannot be updated by userspace. Hence
we also don't allow ptrace interface to update them. Don't update them in the
test. Also expected_iamr is only changed if we can allocate a DISABLE_EXECUTE
pkey.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
index bc33d748d95b..5c3c8222de46 100644
--- a/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
+++ b/tools/testing/selftests/powerpc/ptrace/ptrace-pkey.c
@@ -101,15 +101,12 @@ static int child(struct shared_info *info)
*/
info->invalid_amr = info->amr2 | (~0x0UL & ~info->expected_uamor);
+ /*
+ * if PKEY_DISABLE_EXECUTE succeeded we should update the expected_iamr
+ */
if (disable_execute)
info->expected_iamr |= 1ul << pkeyshift(pkey1);
- else
- info->expected_iamr &= ~(1ul << pkeyshift(pkey1));
-
- info->expected_iamr &= ~(1ul << pkeyshift(pkey2) | 1ul << pkeyshift(pkey3));
- info->expected_uamor |= 3ul << pkeyshift(pkey1) |
- 3ul << pkeyshift(pkey2);
/*
* Create an IAMR value different from expected value.
* Kernel will reject an IAMR and UAMOR change.
--
2.26.2
^ permalink raw reply related
* Re: linux-next: manual merge of the pidfd tree with the powerpc-fixes tree
From: Christian Brauner @ 2020-06-19 14:01 UTC (permalink / raw)
To: Michael Ellerman
Cc: Stephen Rothwell, Linux Next Mailing List, PowerPC,
Linux Kernel Mailing List, Christian Brauner
In-Reply-To: <878sgjcnjp.fsf@mpe.ellerman.id.au>
On Fri, Jun 19, 2020 at 09:17:30PM +1000, Michael Ellerman wrote:
> Stephen Rothwell <sfr@canb.auug.org.au> writes:
> > Hi all,
> >
> > Today's linux-next merge of the pidfd tree got a conflict in:
> >
> > arch/powerpc/kernel/syscalls/syscall.tbl
> >
> > between commit:
> >
> > 35e32a6cb5f6 ("powerpc/syscalls: Split SPU-ness out of ABI")
> >
> > from the powerpc-fixes tree and commit:
> >
> > 9b4feb630e8e ("arch: wire-up close_range()")
> >
> > from the pidfd 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.
>
> Thanks.
>
> I thought the week between rc1 and rc2 would be a safe time to do that
> conversion of the syscall table, but I guess I was wrong :)
:)
>
> I'm planning to send those changes to Linus for rc2, so the conflict
> will then be vs mainline. But I guess it's pretty trivial so it doesn't
> really matter.
close_range() is targeted for the v5.9 merge window. I always do
test-merges with mainline at the time I'm creating a pr and I'll just
mention to Linus that there's conflict with ppc. :)
Thanks!
Christian
^ permalink raw reply
* [PATCH v5] ocxl: control via sysfs whether the FPGA is reloaded on a link reset
From: Frederic Barrat @ 2020-06-19 14:04 UTC (permalink / raw)
To: linuxppc-dev, clombard, ajd, alastair
From: Philippe Bergheaud <felix@linux.ibm.com>
Some opencapi FPGA images allow to control if the FPGA should be reloaded
on the next adapter reset. If it is supported, the image specifies it
through a Vendor Specific DVSEC in the config space of function 0.
Signed-off-by: Philippe Bergheaud <felix@linux.ibm.com>
Signed-off-by: Frederic Barrat <fbarrat@linux.ibm.com>
---
Changelog:
v2:
- refine ResetReload debug message
- do not call get_function_0() if pci_dev is for function 0
v3:
- avoid get_function_0() in ocxl_config_set_reset_reload also
v4:
- simplify parsing of Vendor Specific DVSEC during AFU init
- only set/unset bit 0 of the config space register
- commonize code to fetch the right PCI function and DVSEC offset
- use kstrtoint() when parsing the sysfs buffer
v5:
- update documentation (Andrew)
Documentation/ABI/testing/sysfs-class-ocxl | 11 +++
drivers/misc/ocxl/config.c | 81 ++++++++++++++++++++--
drivers/misc/ocxl/ocxl_internal.h | 6 ++
drivers/misc/ocxl/sysfs.c | 35 ++++++++++
include/misc/ocxl-config.h | 1 +
5 files changed, 129 insertions(+), 5 deletions(-)
diff --git a/Documentation/ABI/testing/sysfs-class-ocxl b/Documentation/ABI/testing/sysfs-class-ocxl
index b5b1fa197592..ae1276efa45a 100644
--- a/Documentation/ABI/testing/sysfs-class-ocxl
+++ b/Documentation/ABI/testing/sysfs-class-ocxl
@@ -33,3 +33,14 @@ Date: January 2018
Contact: linuxppc-dev@lists.ozlabs.org
Description: read/write
Give access the global mmio area for the AFU
+
+What: /sys/class/ocxl/<afu name>/reload_on_reset
+Date: February 2020
+Contact: linuxppc-dev@lists.ozlabs.org
+Description: read/write
+ Control whether the FPGA is reloaded on a link reset. Enabled
+ through a vendor-specific logic block on the FPGA.
+ 0 Do not reload FPGA image from flash
+ 1 Reload FPGA image from flash
+ unavailable
+ The device does not support this capability
diff --git a/drivers/misc/ocxl/config.c b/drivers/misc/ocxl/config.c
index c8e19bfb5ef9..42f7a1298775 100644
--- a/drivers/misc/ocxl/config.c
+++ b/drivers/misc/ocxl/config.c
@@ -71,6 +71,20 @@ static int find_dvsec_afu_ctrl(struct pci_dev *dev, u8 afu_idx)
return 0;
}
+/**
+ * get_function_0() - Find a related PCI device (function 0)
+ * @device: PCI device to match
+ *
+ * Returns a pointer to the related device, or null if not found
+ */
+static struct pci_dev *get_function_0(struct pci_dev *dev)
+{
+ unsigned int devfn = PCI_DEVFN(PCI_SLOT(dev->devfn), 0);
+
+ return pci_get_domain_bus_and_slot(pci_domain_nr(dev->bus),
+ dev->bus->number, devfn);
+}
+
static void read_pasid(struct pci_dev *dev, struct ocxl_fn_config *fn)
{
u16 val;
@@ -159,14 +173,15 @@ static int read_dvsec_afu_info(struct pci_dev *dev, struct ocxl_fn_config *fn)
static int read_dvsec_vendor(struct pci_dev *dev)
{
int pos;
- u32 cfg, tlx, dlx;
+ u32 cfg, tlx, dlx, reset_reload;
/*
- * vendor specific DVSEC is optional
+ * vendor specific DVSEC, for IBM images only. Some older
+ * images may not have it
*
- * It's currently only used on function 0 to specify the
- * version of some logic blocks. Some older images may not
- * even have it so we ignore any errors
+ * It's only used on function 0 to specify the version of some
+ * logic blocks and to give access to special registers to
+ * enable host-based flashing.
*/
if (PCI_FUNC(dev->devfn) != 0)
return 0;
@@ -178,11 +193,67 @@ static int read_dvsec_vendor(struct pci_dev *dev)
pci_read_config_dword(dev, pos + OCXL_DVSEC_VENDOR_CFG_VERS, &cfg);
pci_read_config_dword(dev, pos + OCXL_DVSEC_VENDOR_TLX_VERS, &tlx);
pci_read_config_dword(dev, pos + OCXL_DVSEC_VENDOR_DLX_VERS, &dlx);
+ pci_read_config_dword(dev, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD,
+ &reset_reload);
dev_dbg(&dev->dev, "Vendor specific DVSEC:\n");
dev_dbg(&dev->dev, " CFG version = 0x%x\n", cfg);
dev_dbg(&dev->dev, " TLX version = 0x%x\n", tlx);
dev_dbg(&dev->dev, " DLX version = 0x%x\n", dlx);
+ dev_dbg(&dev->dev, " ResetReload = 0x%x\n", reset_reload);
+ return 0;
+}
+
+static int get_dvsec_vendor0(struct pci_dev *dev, struct pci_dev **dev0,
+ int *out_pos)
+{
+ int pos;
+
+ if (PCI_FUNC(dev->devfn) != 0) {
+ dev = get_function_0(dev);
+ if (!dev)
+ return -1;
+ }
+ pos = find_dvsec(dev, OCXL_DVSEC_VENDOR_ID);
+ if (!pos)
+ return -1;
+ *dev0 = dev;
+ *out_pos = pos;
+ return 0;
+}
+
+int ocxl_config_get_reset_reload(struct pci_dev *dev, int *val)
+{
+ struct pci_dev *dev0;
+ u32 reset_reload;
+ int pos;
+
+ if (get_dvsec_vendor0(dev, &dev0, &pos))
+ return -1;
+
+ pci_read_config_dword(dev0, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD,
+ &reset_reload);
+ *val = !!(reset_reload & BIT(0));
+ return 0;
+}
+
+int ocxl_config_set_reset_reload(struct pci_dev *dev, int val)
+{
+ struct pci_dev *dev0;
+ u32 reset_reload;
+ int pos;
+
+ if (get_dvsec_vendor0(dev, &dev0, &pos))
+ return -1;
+
+ pci_read_config_dword(dev0, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD,
+ &reset_reload);
+ if (val)
+ reset_reload |= BIT(0);
+ else
+ reset_reload &= ~BIT(0);
+ pci_write_config_dword(dev0, pos + OCXL_DVSEC_VENDOR_RESET_RELOAD,
+ reset_reload);
return 0;
}
diff --git a/drivers/misc/ocxl/ocxl_internal.h b/drivers/misc/ocxl/ocxl_internal.h
index 345bf843a38e..af9a84aeee6f 100644
--- a/drivers/misc/ocxl/ocxl_internal.h
+++ b/drivers/misc/ocxl/ocxl_internal.h
@@ -112,6 +112,12 @@ void ocxl_actag_afu_free(struct ocxl_fn *fn, u32 start, u32 size);
*/
int ocxl_config_get_pasid_info(struct pci_dev *dev, int *count);
+/*
+ * Control whether the FPGA is reloaded on a link reset
+ */
+int ocxl_config_get_reset_reload(struct pci_dev *dev, int *val);
+int ocxl_config_set_reset_reload(struct pci_dev *dev, int val);
+
/*
* Check if an AFU index is valid for the given function.
*
diff --git a/drivers/misc/ocxl/sysfs.c b/drivers/misc/ocxl/sysfs.c
index 58f1ba264206..25c78df8055d 100644
--- a/drivers/misc/ocxl/sysfs.c
+++ b/drivers/misc/ocxl/sysfs.c
@@ -51,11 +51,46 @@ static ssize_t contexts_show(struct device *device,
afu->pasid_count, afu->pasid_max);
}
+static ssize_t reload_on_reset_show(struct device *device,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct ocxl_afu *afu = to_afu(device);
+ struct ocxl_fn *fn = afu->fn;
+ struct pci_dev *pci_dev = to_pci_dev(fn->dev.parent);
+ int val;
+
+ if (ocxl_config_get_reset_reload(pci_dev, &val))
+ return scnprintf(buf, PAGE_SIZE, "unavailable\n");
+
+ return scnprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+
+static ssize_t reload_on_reset_store(struct device *device,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct ocxl_afu *afu = to_afu(device);
+ struct ocxl_fn *fn = afu->fn;
+ struct pci_dev *pci_dev = to_pci_dev(fn->dev.parent);
+ int rc, val;
+
+ rc = kstrtoint(buf, 0, &val);
+ if (rc || (val != 0 && val != 1))
+ return -EINVAL;
+
+ if (ocxl_config_set_reset_reload(pci_dev, val))
+ return -ENODEV;
+
+ return count;
+}
+
static struct device_attribute afu_attrs[] = {
__ATTR_RO(global_mmio_size),
__ATTR_RO(pp_mmio_size),
__ATTR_RO(afu_version),
__ATTR_RO(contexts),
+ __ATTR_RW(reload_on_reset),
};
static ssize_t global_mmio_read(struct file *filp, struct kobject *kobj,
diff --git a/include/misc/ocxl-config.h b/include/misc/ocxl-config.h
index 3526fa996a22..ccfd3b463517 100644
--- a/include/misc/ocxl-config.h
+++ b/include/misc/ocxl-config.h
@@ -41,5 +41,6 @@
#define OCXL_DVSEC_VENDOR_CFG_VERS 0x0C
#define OCXL_DVSEC_VENDOR_TLX_VERS 0x10
#define OCXL_DVSEC_VENDOR_DLX_VERS 0x20
+#define OCXL_DVSEC_VENDOR_RESET_RELOAD 0x38
#endif /* _OCXL_CONFIG_H_ */
--
2.26.2
^ permalink raw reply related
* [PATCH v1 3/8] powerpc: Set user/kernel boundary at TASK_SIZE instead of PAGE_OFFSET
From: Christophe Leroy @ 2020-06-19 15:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1592578278.git.christophe.leroy@csgroup.eu>
User space stops at TASK_SIZE. At the moment, kernel space starts
at PAGE_OFFSET.
In order to use space between TASK_SIZE and PAGE_OFFSET for modules,
make TASK_SIZE the limit between user and kernel space.
Note that fault.c already considers TASK_SIZE as the boundary between
user and kernel space.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/page.h | 2 +-
arch/powerpc/mm/ptdump/ptdump.c | 6 +++---
2 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index a63fe6f3a0ff..352a2b80d505 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -256,7 +256,7 @@ static inline bool pfn_valid(unsigned long pfn)
#ifdef CONFIG_PPC_BOOK3E_64
#define is_kernel_addr(x) ((x) >= 0x8000000000000000ul)
#else
-#define is_kernel_addr(x) ((x) >= PAGE_OFFSET)
+#define is_kernel_addr(x) ((x) >= TASK_SIZE)
#endif
#ifndef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index b71cc628facd..e995f2e9e9f7 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -351,7 +351,7 @@ static void populate_markers(void)
{
int i = 0;
- address_markers[i++].start_address = PAGE_OFFSET;
+ address_markers[i++].start_address = TASK_SIZE;
address_markers[i++].start_address = VMALLOC_START;
address_markers[i++].start_address = VMALLOC_END;
#ifdef CONFIG_PPC64
@@ -388,7 +388,7 @@ static int ptdump_show(struct seq_file *m, void *v)
struct pg_state st = {
.seq = m,
.marker = address_markers,
- .start_address = PAGE_OFFSET,
+ .start_address = TASK_SIZE,
};
#ifdef CONFIG_PPC64
@@ -432,7 +432,7 @@ void ptdump_check_wx(void)
.seq = NULL,
.marker = address_markers,
.check_wx = true,
- .start_address = PAGE_OFFSET,
+ .start_address = TASK_SIZE,
};
#ifdef CONFIG_PPC64
--
2.25.0
^ permalink raw reply related
* [PATCH v1 1/8] powerpc/ptdump: Refactor update of st->last_pa
From: Christophe Leroy @ 2020-06-19 15:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1592578278.git.christophe.leroy@csgroup.eu>
st->last_pa is always updated in note_page() so it can
be done outside the if/elseif/else block.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/ptdump/ptdump.c | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index de6e05ef871c..d5e42b958e86 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -207,7 +207,6 @@ static void note_page(struct pg_state *st, unsigned long addr,
st->current_flags = flag;
st->start_address = addr;
st->start_pa = pa;
- st->last_pa = pa;
st->page_size = page_size;
pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
/*
@@ -247,13 +246,11 @@ static void note_page(struct pg_state *st, unsigned long addr,
}
st->start_address = addr;
st->start_pa = pa;
- st->last_pa = pa;
st->page_size = page_size;
st->current_flags = flag;
st->level = level;
- } else {
- st->last_pa = pa;
}
+ st->last_pa = pa;
}
static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
--
2.25.0
^ permalink raw reply related
* [PATCH v1 0/8] powerpc/32s: Allocate modules outside of vmalloc space for STRICT_KERNEL_RWX
From: Christophe Leroy @ 2020-06-19 15:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
On book3s32 (hash), exec protection is set per 256Mb segments with NX bit.
Instead of clearing NX bit on vmalloc space when CONFIG_MODULES is selected,
allocate modules in a dedicated segment (0xb0000000-0xbfffffff by default).
This allows to keep exec protection on vmalloc space while allowing exec
on modules.
Christophe Leroy (8):
powerpc/ptdump: Refactor update of st->last_pa
powerpc/ptdump: Refactor update of pg_state
powerpc: Set user/kernel boundary at TASK_SIZE instead of PAGE_OFFSET
powerpc/lib: Prepare code-patching for modules allocated outside
vmalloc space
powerpc: Use MODULES_VADDR if defined
powerpc/32s: Only leave NX unset on segments used for modules
powerpc/32s: Kernel space starts at TASK_SIZE
powerpc/32s: Use dedicated segment for modules with STRICT_KERNEL_RWX
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/book3s/32/pgtable.h | 15 ++----
arch/powerpc/include/asm/page.h | 2 +-
arch/powerpc/kernel/head_32.S | 12 ++---
arch/powerpc/kernel/module.c | 11 ++++
arch/powerpc/lib/code-patching.c | 2 +-
arch/powerpc/mm/book3s32/hash_low.S | 2 +-
arch/powerpc/mm/book3s32/mmu.c | 17 +++++--
arch/powerpc/mm/kasan/kasan_init_32.c | 6 +++
arch/powerpc/mm/ptdump/ptdump.c | 53 ++++++++++++--------
10 files changed, 78 insertions(+), 43 deletions(-)
--
2.25.0
^ permalink raw reply
* [PATCH v1 4/8] powerpc/lib: Prepare code-patching for modules allocated outside vmalloc space
From: Christophe Leroy @ 2020-06-19 15:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1592578278.git.christophe.leroy@csgroup.eu>
Use is_vmalloc_or_module_addr() instead of is_vmalloc_addr()
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/lib/code-patching.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index 0a051dfeb177..8c3934ea6220 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -93,7 +93,7 @@ static int map_patch_area(void *addr, unsigned long text_poke_addr)
unsigned long pfn;
int err;
- if (is_vmalloc_addr(addr))
+ if (is_vmalloc_or_module_addr(addr))
pfn = vmalloc_to_pfn(addr);
else
pfn = __pa_symbol(addr) >> PAGE_SHIFT;
--
2.25.0
^ permalink raw reply related
* [PATCH v1 2/8] powerpc/ptdump: Refactor update of pg_state
From: Christophe Leroy @ 2020-06-19 15:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1592578278.git.christophe.leroy@csgroup.eu>
In note_page(), the pg_state is updated the same way in two places.
Add note_page_update_state() to do it.
Also include the display of boundary markers there as it is missing
"no level" leg, leading to a mismatch when the first two markers
are at the same address and the first displayed area uses that
address.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/ptdump/ptdump.c | 34 +++++++++++++++++++--------------
1 file changed, 20 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index d5e42b958e86..b71cc628facd 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -195,6 +195,24 @@ static void note_prot_wx(struct pg_state *st, unsigned long addr)
st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
}
+static void note_page_update_state(struct pg_state *st, unsigned long addr,
+ unsigned int level, u64 val, unsigned long page_size)
+{
+ u64 flag = val & pg_level[level].mask;
+ u64 pa = val & PTE_RPN_MASK;
+
+ st->level = level;
+ st->current_flags = flag;
+ st->start_address = addr;
+ st->start_pa = pa;
+ st->page_size = page_size;
+
+ while (addr >= st->marker[1].start_address) {
+ st->marker++;
+ pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+ }
+}
+
static void note_page(struct pg_state *st, unsigned long addr,
unsigned int level, u64 val, unsigned long page_size)
{
@@ -203,12 +221,8 @@ static void note_page(struct pg_state *st, unsigned long addr,
/* At first no level is set */
if (!st->level) {
- st->level = level;
- st->current_flags = flag;
- st->start_address = addr;
- st->start_pa = pa;
- st->page_size = page_size;
pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+ note_page_update_state(st, addr, level, val, page_size);
/*
* Dump the section of virtual memory when:
* - the PTE flags from one entry to the next differs.
@@ -240,15 +254,7 @@ static void note_page(struct pg_state *st, unsigned long addr,
* Address indicates we have passed the end of the
* current section of virtual memory
*/
- while (addr >= st->marker[1].start_address) {
- st->marker++;
- pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
- }
- st->start_address = addr;
- st->start_pa = pa;
- st->page_size = page_size;
- st->current_flags = flag;
- st->level = level;
+ note_page_update_state(st, addr, level, val, page_size);
}
st->last_pa = pa;
}
--
2.25.0
^ permalink raw reply related
* [PATCH v1 8/8] powerpc/32s: Use dedicated segment for modules with STRICT_KERNEL_RWX
From: Christophe Leroy @ 2020-06-19 15:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1592578278.git.christophe.leroy@csgroup.eu>
When STRICT_KERNEL_RWX is set, we want to set NX bit on vmalloc
segments. But modules require exec.
Use a dedicated segment for modules. There is not much space
above kernel, and we don't waste vmalloc space to do alignment.
Therefore, we take the segment before PAGE_OFFSET for modules.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/book3s/32/pgtable.h | 15 +++++----------
arch/powerpc/mm/ptdump/ptdump.c | 8 ++++++++
3 files changed, 14 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 9fa23eb320ff..2ba6ac9da46f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -1198,6 +1198,7 @@ config TASK_SIZE_BOOL
config TASK_SIZE
hex "Size of user task space" if TASK_SIZE_BOOL
default "0x80000000" if PPC_8xx
+ default "0xb0000000" if PPC_BOOK3S_32 && STRICT_KERNEL_RWX
default "0xc0000000"
endmenu
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 224912432821..36443cda8dcf 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -184,17 +184,7 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
*/
#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
#ifdef CONFIG_KASAN_VMALLOC
#define VMALLOC_END ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
@@ -202,6 +192,11 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
#define VMALLOC_END ioremap_bot
#endif
+#ifdef CONFIG_STRICT_KERNEL_RWX
+#define MODULES_END ALIGN_DOWN(PAGE_OFFSET, SZ_256M)
+#define MODULES_VADDR (MODULES_END - SZ_256M)
+#endif
+
#ifndef __ASSEMBLY__
#include <linux/sched.h>
#include <linux/threads.h>
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index e995f2e9e9f7..51aab1b7be31 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -74,6 +74,10 @@ struct addr_marker {
static struct addr_marker address_markers[] = {
{ 0, "Start of kernel VM" },
+#ifdef MODULES_VADDR
+ { 0, "modules start" },
+ { 0, "modules end" },
+#endif
{ 0, "vmalloc() Area" },
{ 0, "vmalloc() End" },
#ifdef CONFIG_PPC64
@@ -352,6 +356,10 @@ static void populate_markers(void)
int i = 0;
address_markers[i++].start_address = TASK_SIZE;
+#ifdef MODULES_VADDR
+ address_markers[i++].start_address = MODULES_VADDR;
+ address_markers[i++].start_address = MODULES_END;
+#endif
address_markers[i++].start_address = VMALLOC_START;
address_markers[i++].start_address = VMALLOC_END;
#ifdef CONFIG_PPC64
--
2.25.0
^ permalink raw reply related
* [PATCH v1 7/8] powerpc/32s: Kernel space starts at TASK_SIZE
From: Christophe Leroy @ 2020-06-19 15:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1592578278.git.christophe.leroy@csgroup.eu>
Kernel space starts at TASK_SIZE. Select kernel page table
when address is over TASK_SIZE.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/kernel/head_32.S | 12 ++++++------
arch/powerpc/mm/book3s32/hash_low.S | 2 +-
2 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 705c042309d8..bbef6ce8322b 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -474,7 +474,7 @@ InstructionTLBMiss:
/* Get PTE (linux-style) and check access */
mfspr r3,SPRN_IMISS
#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC)
- lis r1,PAGE_OFFSET@h /* check if kernel address */
+ lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
#endif
mfspr r2, SPRN_SPRG_PGDIR
@@ -484,7 +484,7 @@ InstructionTLBMiss:
li r1,_PAGE_PRESENT | _PAGE_EXEC
#endif
#if defined(CONFIG_MODULES) || defined(CONFIG_DEBUG_PAGEALLOC)
- bge- 112f
+ bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
#endif
@@ -541,7 +541,7 @@ DataLoadTLBMiss:
*/
/* Get PTE (linux-style) and check access */
mfspr r3,SPRN_DMISS
- lis r1,PAGE_OFFSET@h /* check if kernel address */
+ lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2, SPRN_SPRG_PGDIR
#ifdef CONFIG_SWAP
@@ -549,7 +549,7 @@ DataLoadTLBMiss:
#else
li r1, _PAGE_PRESENT
#endif
- bge- 112f
+ bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
@@ -621,7 +621,7 @@ DataStoreTLBMiss:
*/
/* Get PTE (linux-style) and check access */
mfspr r3,SPRN_DMISS
- lis r1,PAGE_OFFSET@h /* check if kernel address */
+ lis r1, TASK_SIZE@h /* check if kernel address */
cmplw 0,r1,r3
mfspr r2, SPRN_SPRG_PGDIR
#ifdef CONFIG_SWAP
@@ -629,7 +629,7 @@ DataStoreTLBMiss:
#else
li r1, _PAGE_RW | _PAGE_DIRTY | _PAGE_PRESENT
#endif
- bge- 112f
+ bgt- 112f
lis r2, (swapper_pg_dir - PAGE_OFFSET)@ha /* if kernel address, use */
addi r2, r2, (swapper_pg_dir - PAGE_OFFSET)@l /* kernel page table */
112: rlwimi r2,r3,12,20,29 /* insert top 10 bits of address */
diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S
index 923ad8f374eb..1690d369688b 100644
--- a/arch/powerpc/mm/book3s32/hash_low.S
+++ b/arch/powerpc/mm/book3s32/hash_low.S
@@ -62,7 +62,7 @@ _GLOBAL(hash_page)
isync
#endif
/* Get PTE (linux-style) and check access */
- lis r0,KERNELBASE@h /* check if kernel address */
+ lis r0, TASK_SIZE@h /* check if kernel address */
cmplw 0,r4,r0
ori r3,r3,_PAGE_USER|_PAGE_PRESENT /* test low addresses as user */
mfspr r5, SPRN_SPRG_PGDIR /* phys page-table root */
--
2.25.0
^ permalink raw reply related
* [PATCH v1 5/8] powerpc: Use MODULES_VADDR if defined
From: Christophe Leroy @ 2020-06-19 15:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1592578278.git.christophe.leroy@csgroup.eu>
In order to allow allocation of modules outside of vmalloc space,
use MODULES_VADDR and MODULES_END when MODULES_VADDR is defined.
Redefine module_alloc() when MODULES_VADDR defined.
Unmap corresponding KASAN shadow memory.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/kernel/module.c | 11 +++++++++++
arch/powerpc/mm/kasan/kasan_init_32.c | 6 ++++++
2 files changed, 17 insertions(+)
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index df649acb5631..a211b0253cdb 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -86,3 +86,14 @@ int module_finalize(const Elf_Ehdr *hdr,
return 0;
}
+
+#ifdef MODULES_VADDR
+void *module_alloc(unsigned long size)
+{
+ BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
+
+ return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, GFP_KERNEL,
+ PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
+ __builtin_return_address(0));
+}
+#endif
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
index 0760e1e754e4..f1bc267d42af 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -115,6 +115,12 @@ static void __init kasan_unmap_early_shadow_vmalloc(void)
unsigned long k_end = (unsigned long)kasan_mem_to_shadow((void *)VMALLOC_END);
kasan_update_early_region(k_start, k_end, __pte(0));
+
+#ifdef MODULES_VADDR
+ k_start = (unsigned long)kasan_mem_to_shadow((void *)MODULES_VADDR);
+ k_end = (unsigned long)kasan_mem_to_shadow((void *)MODULES_END);
+ kasan_update_early_region(k_start, k_end, __pte(0));
+#endif
}
static void __init kasan_mmu_init(void)
--
2.25.0
^ permalink raw reply related
* [PATCH v1 6/8] powerpc/32s: Only leave NX unset on segments used for modules
From: Christophe Leroy @ 2020-06-19 15:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1592578278.git.christophe.leroy@csgroup.eu>
Instead of leaving NX unset on all segments above the start
of vmalloc space, only leave NX unset on segments used for
modules.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/book3s32/mmu.c | 17 ++++++++++++++---
1 file changed, 14 insertions(+), 3 deletions(-)
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 03b6ba54460e..c0162911f6cb 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -187,6 +187,17 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
return __mmu_mapin_ram(border, top);
}
+static bool is_module_segment(unsigned long addr)
+{
+ if (!IS_ENABLED(CONFIG_MODULES))
+ return false;
+ if (addr < ALIGN_DOWN(VMALLOC_START, SZ_256M))
+ return false;
+ if (addr >= ALIGN(VMALLOC_END, SZ_256M))
+ return false;
+ return true;
+}
+
void mmu_mark_initmem_nx(void)
{
int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
@@ -223,9 +234,9 @@ void mmu_mark_initmem_nx(void)
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;
+ if (is_module_segment(i << 28))
+ continue;
+
mtsrin(mfsrin(i << 28) | 0x10000000, i << 28);
}
}
--
2.25.0
^ permalink raw reply related
* [PATCH] powerpc/pseries: new lparcfg key/value pair: partition_affinity_score
From: Scott Cheloha @ 2020-06-19 15:34 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Nathan Lynch, Tyrel Datwyler
The H_GetPerformanceCounterInfo PHYP hypercall has a subcall,
Affinity_Domain_Info_By_Partition, which returns, among other things,
a "partition affinity score" for a given LPAR. This score, a value on
[0-100], represents the processor-memory affinity for the LPAR in
question. A score of 0 indicates the worst possible affinity while a
score of 100 indicates perfect affinity. The score can be used to
reason about performance.
This patch adds the score for the local LPAR to the lparcfg procfile
under a new 'partition_affinity_score' key.
The H_GetPerformanceCounterInfo hypercall is already used elsewhere in
the kernel, in powerpc/perf/hv-gpci.c. Refactoring that code and this
code into a more general API might be worthwhile if additional modules
require the hypercall in the future.
Signed-off-by: Scott Cheloha <cheloha@linux.ibm.com>
---
arch/powerpc/platforms/pseries/lparcfg.c | 53 ++++++++++++++++++++++++
1 file changed, 53 insertions(+)
diff --git a/arch/powerpc/platforms/pseries/lparcfg.c b/arch/powerpc/platforms/pseries/lparcfg.c
index b8d28ab88178..b75151eee0f0 100644
--- a/arch/powerpc/platforms/pseries/lparcfg.c
+++ b/arch/powerpc/platforms/pseries/lparcfg.c
@@ -136,6 +136,57 @@ static unsigned int h_get_ppp(struct hvcall_ppp_data *ppp_data)
return rc;
}
+/*
+ * Based on H_GetPerformanceCounterInfo v1.10.
+ */
+static void show_gpci_data(struct seq_file *m)
+{
+ struct perf_counter_info_params {
+ __be32 counter_request;
+ __be32 starting_index;
+ __be16 secondary_index;
+ __be16 returned_values;
+ __be32 detail_rc;
+ __be16 counter_value_element_size;
+ u8 counter_info_version_in;
+ u8 counter_info_version_out;
+ u8 reserved[0xC];
+ } __packed;
+ struct hv_gpci_request_buffer {
+ struct perf_counter_info_params params;
+ u8 output[4096 - sizeof(struct perf_counter_info_params)];
+ } __packed;
+ struct hv_gpci_request_buffer *buf;
+ long ret;
+ unsigned int affinity_score;
+
+ buf = kmalloc(sizeof(*buf), GFP_KERNEL);
+ if (buf == NULL)
+ return;
+
+ /*
+ * Show the local LPAR's affinity score.
+ *
+ * 0xB1 selects the Affinity_Domain_Info_By_Partition subcall.
+ * The score is at byte 0xB in the output buffer.
+ */
+ memset(&buf->params, 0, sizeof(buf->params));
+ buf->params.counter_request = cpu_to_be32(0xB1);
+ buf->params.starting_index = cpu_to_be32(-1); /* local LPAR */
+ buf->params.counter_info_version_in = 0x5; /* v5+ for score */
+ ret = plpar_hcall_norets(H_GET_PERF_COUNTER_INFO, virt_to_phys(buf),
+ sizeof(*buf));
+ if (ret != H_SUCCESS) {
+ pr_debug("hcall failed: H_GET_PERF_COUNTER_INFO: %ld, %x\n",
+ ret, be32_to_cpu(buf->params.detail_rc));
+ goto out;
+ }
+ affinity_score = buf->output[0xB];
+ seq_printf(m, "partition_affinity_score=%u\n", affinity_score);
+out:
+ kfree(buf);
+}
+
static unsigned h_pic(unsigned long *pool_idle_time,
unsigned long *num_procs)
{
@@ -487,6 +538,8 @@ static int pseries_lparcfg_data(struct seq_file *m, void *v)
partition_active_processors * 100);
}
+ show_gpci_data(m);
+
seq_printf(m, "partition_active_processors=%d\n",
partition_active_processors);
--
2.24.1
^ permalink raw reply related
* [PATCH 16/26] mm/powerpc: Use general page fault accounting
From: Peter Xu @ 2020-06-19 16:13 UTC (permalink / raw)
To: linux-kernel, linux-mm
Cc: Andrea Arcangeli, linuxppc-dev, Peter Xu, Linus Torvalds,
Paul Mackerras, Andrew Morton, Will Deacon, Gerald Schaefer
In-Reply-To: <20200619160538.8641-1-peterx@redhat.com>
Use the general page fault accounting by passing regs into handle_mm_fault().
CC: Michael Ellerman <mpe@ellerman.id.au>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
CC: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Peter Xu <peterx@redhat.com>
---
arch/powerpc/mm/fault.c | 11 +++--------
1 file changed, 3 insertions(+), 8 deletions(-)
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 992b10c3761c..e325d13efaf5 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -563,7 +563,7 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
- fault = handle_mm_fault(vma, address, flags, NULL);
+ fault = handle_mm_fault(vma, address, flags, regs);
#ifdef CONFIG_PPC_MEM_KEYS
/*
@@ -604,14 +604,9 @@ static int __do_page_fault(struct pt_regs *regs, unsigned long address,
/*
* Major/minor page fault accounting.
*/
- if (major) {
- current->maj_flt++;
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
+ if (major)
cmo_account_page_fault();
- } else {
- current->min_flt++;
- perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
- }
+
return 0;
}
NOKPROBE_SYMBOL(__do_page_fault);
--
2.26.2
^ permalink raw reply related
* Re: [PATCH] pci: pcie: AER: Fix logging of Correctable errors
From: Sinan Kaya @ 2020-06-19 17:17 UTC (permalink / raw)
To: Matt Jolly, Russell Currey, Sam Bobroff, Oliver O'Halloran,
Bjorn Helgaas, linuxppc-dev, linux-pci, linux-kernel
In-Reply-To: <20200618155511.16009-1-Kangie@footclan.ninja>
On 6/18/2020 11:55 AM, Matt Jolly wrote:
> + pci_warn(dev, " device [%04x:%04x] error status/mask=%08x/%08x\n",
> + dev->vendor, dev->device,
> + info->status, info->mask);
> + } else {
<snip>
> + pci_err(dev, " device [%04x:%04x] error status/mask=%08x/%08x\n",
> + dev->vendor, dev->device,
> + info->status, info->mask);
Function pointers for pci_warn vs. pci_err ?
This looks like a lot of copy/paste.
^ permalink raw reply
* [PATCH] hvc: unify console setup naming
From: Sergey Senozhatsky @ 2020-06-19 17:22 UTC (permalink / raw)
To: Petr Mladek
Cc: Greg Kroah-Hartman, linux-kernel, Steven Rostedt,
Sergey Senozhatsky, Jiri Slaby, Andy Shevchenko, linuxppc-dev
Use the 'common' foo_console_setup() naming scheme. There are 71
foo_console_setup() callbacks and only one foo_setup_console().
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jiri Slaby <jslaby@suse.com>
---
drivers/tty/hvc/hvc_xen.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/tty/hvc/hvc_xen.c b/drivers/tty/hvc/hvc_xen.c
index 5ef08905fe05..2a0e51a20e34 100644
--- a/drivers/tty/hvc/hvc_xen.c
+++ b/drivers/tty/hvc/hvc_xen.c
@@ -603,7 +603,7 @@ static void xen_hvm_early_write(uint32_t vtermno, const char *str, int len) { }
#endif
#ifdef CONFIG_EARLY_PRINTK
-static int __init xenboot_setup_console(struct console *console, char *string)
+static int __init xenboot_console_setup(struct console *console, char *string)
{
static struct xencons_info xenboot;
@@ -647,7 +647,7 @@ static void xenboot_write_console(struct console *console, const char *string,
struct console xenboot_console = {
.name = "xenboot",
.write = xenboot_write_console,
- .setup = xenboot_setup_console,
+ .setup = xenboot_console_setup,
.flags = CON_PRINTBUFFER | CON_BOOT | CON_ANYTIME,
.index = -1,
};
--
2.27.0
^ permalink raw reply related
* Re: [PATCH] pci: pcie: AER: Fix logging of Correctable errors
From: Joe Perches @ 2020-06-19 18:09 UTC (permalink / raw)
To: Sinan Kaya, Matt Jolly, Russell Currey, Sam Bobroff,
Oliver O'Halloran, Bjorn Helgaas, linuxppc-dev, linux-pci,
linux-kernel
In-Reply-To: <d611dabd-b943-8492-a29e-0b7fb1980de8@kernel.org>
On Fri, 2020-06-19 at 13:17 -0400, Sinan Kaya wrote:
> On 6/18/2020 11:55 AM, Matt Jolly wrote:
>
> > + pci_warn(dev, " device [%04x:%04x] error status/mask=%08x/%08x\n",
> > + dev->vendor, dev->device,
> > + info->status, info->mask);
> > + } else {
>
> <snip>
>
> > + pci_err(dev, " device [%04x:%04x] error status/mask=%08x/%08x\n",
> > + dev->vendor, dev->device,
> > + info->status, info->mask);
>
> Function pointers for pci_warn vs. pci_err ?
Not really possible as both are function-like macros.
^ permalink raw reply
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