* [PATCH 4.4 01/15] powerpc/64s: Define MASKABLE_RELON_EXCEPTION_PSERIES_OOL
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
@ 2020-11-20 11:02 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 02/15] powerpc/64s: move some exception handlers out of line Greg Kroah-Hartman
` (17 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:02 UTC (permalink / raw)
To: linux-kernel, stable; +Cc: Greg Kroah-Hartman, dja
From: Daniel Axtens <dja@axtens.net>
Add a definition provided by mpe and fixed up for 4.4. It doesn't exist
for 4.4 and we'd quite like to use it.
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/powerpc/include/asm/exception-64s.h | 6 ++++++
1 file changed, 6 insertions(+)
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -597,6 +597,12 @@ label##_relon_hv: \
EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_HV, vec); \
EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_HV);
+#define MASKABLE_RELON_EXCEPTION_PSERIES_OOL(vec, label) \
+ .globl label##_relon_pSeries; \
+label##_relon_pSeries: \
+ EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_PR, vec); \
+ EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_STD)
+
/*
* Our exception common code can be passed various "additions"
* to specify the behaviour of interrupts, whether to kick the
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 02/15] powerpc/64s: move some exception handlers out of line
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
2020-11-20 11:02 ` [PATCH 4.4 01/15] powerpc/64s: Define MASKABLE_RELON_EXCEPTION_PSERIES_OOL Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 03/15] powerpc/64s: flush L1D on kernel entry Greg Kroah-Hartman
` (16 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel, stable; +Cc: Greg Kroah-Hartman, dja
From: Daniel Axtens <dja@axtens.net>
(backport only)
We're about to grow the exception handlers, which will make a bunch of them
no longer fit within the space available. We move them out of line.
This is a fiddly and error-prone business, so in the interests of reviewability
I haven't merged this in with the addition of the entry flush.
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/powerpc/kernel/exceptions-64s.S | 138 ++++++++++++++++++++++-------------
1 file changed, 90 insertions(+), 48 deletions(-)
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -202,8 +202,8 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE
data_access_pSeries:
HMT_MEDIUM_PPR_DISCARD
SET_SCRATCH0(r13)
- EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD,
- KVMTEST, 0x300)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b data_access_pSeries_ool
. = 0x380
.globl data_access_slb_pSeries
@@ -211,31 +211,15 @@ data_access_slb_pSeries:
HMT_MEDIUM_PPR_DISCARD
SET_SCRATCH0(r13)
EXCEPTION_PROLOG_0(PACA_EXSLB)
- EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
- std r3,PACA_EXSLB+EX_R3(r13)
- mfspr r3,SPRN_DAR
-#ifdef __DISABLED__
- /* Keep that around for when we re-implement dynamic VSIDs */
- cmpdi r3,0
- bge slb_miss_user_pseries
-#endif /* __DISABLED__ */
- mfspr r12,SPRN_SRR1
-#ifndef CONFIG_RELOCATABLE
- b slb_miss_realmode
-#else
- /*
- * We can't just use a direct branch to slb_miss_realmode
- * because the distance from here to there depends on where
- * the kernel ends up being put.
- */
- mfctr r11
- ld r10,PACAKBASE(r13)
- LOAD_HANDLER(r10, slb_miss_realmode)
- mtctr r10
- bctr
-#endif
+ b data_access_slb_pSeries_ool
- STD_EXCEPTION_PSERIES(0x400, 0x400, instruction_access)
+ . = 0x400
+ .globl instruction_access_pSeries
+instruction_access_pSeries:
+ HMT_MEDIUM_PPR_DISCARD
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b instruction_access_pSeries_ool
. = 0x480
.globl instruction_access_slb_pSeries
@@ -243,24 +227,7 @@ instruction_access_slb_pSeries:
HMT_MEDIUM_PPR_DISCARD
SET_SCRATCH0(r13)
EXCEPTION_PROLOG_0(PACA_EXSLB)
- EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480)
- std r3,PACA_EXSLB+EX_R3(r13)
- mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */
-#ifdef __DISABLED__
- /* Keep that around for when we re-implement dynamic VSIDs */
- cmpdi r3,0
- bge slb_miss_user_pseries
-#endif /* __DISABLED__ */
- mfspr r12,SPRN_SRR1
-#ifndef CONFIG_RELOCATABLE
- b slb_miss_realmode
-#else
- mfctr r11
- ld r10,PACAKBASE(r13)
- LOAD_HANDLER(r10, slb_miss_realmode)
- mtctr r10
- bctr
-#endif
+ b instruction_access_slb_pSeries_ool
/* We open code these as we can't have a ". = x" (even with
* x = "." within a feature section
@@ -291,13 +258,19 @@ hardware_interrupt_hv:
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800)
. = 0x900
- .globl decrementer_pSeries
-decrementer_pSeries:
+ .globl decrementer_trampoline
+decrementer_trampoline:
SET_SCRATCH0(r13)
EXCEPTION_PROLOG_0(PACA_EXGEN)
b decrementer_ool
- STD_EXCEPTION_HV(0x980, 0x982, hdecrementer)
+ . = 0x980
+ .globl hdecrementer_trampoline
+hdecrementer_trampoline:
+ HMT_MEDIUM_PPR_DISCARD;
+ SET_SCRATCH0(r13);
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b hdecrementer_hv
MASKABLE_EXCEPTION_PSERIES(0xa00, 0xa00, doorbell_super)
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00)
@@ -545,6 +518,64 @@ machine_check_pSeries_0:
KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900)
KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982)
+/* moved from 0x300 */
+ .globl data_access_pSeries_ool
+data_access_pSeries_ool:
+ EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, 0x300)
+ EXCEPTION_PROLOG_PSERIES_1(data_access_common, EXC_STD)
+
+ .globl data_access_slb_pSeries_ool
+data_access_slb_pSeries_ool:
+ EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
+ std r3,PACA_EXSLB+EX_R3(r13)
+ mfspr r3,SPRN_DAR
+#ifdef __DISABLED__
+ /* Keep that around for when we re-implement dynamic VSIDs */
+ cmpdi r3,0
+ bge slb_miss_user_pseries
+#endif /* __DISABLED__ */
+ mfspr r12,SPRN_SRR1
+#ifndef CONFIG_RELOCATABLE
+ b slb_miss_realmode
+#else
+ /*
+ * We can't just use a direct branch to slb_miss_realmode
+ * because the distance from here to there depends on where
+ * the kernel ends up being put.
+ */
+ mfctr r11
+ ld r10,PACAKBASE(r13)
+ LOAD_HANDLER(r10, slb_miss_realmode)
+ mtctr r10
+ bctr
+#endif
+
+ .globl instruction_access_pSeries_ool
+instruction_access_pSeries_ool:
+ EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, 0x400)
+ EXCEPTION_PROLOG_PSERIES_1(instruction_access_common, EXC_STD)
+
+ .globl instruction_access_slb_pSeries_ool
+instruction_access_slb_pSeries_ool:
+ EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480)
+ std r3,PACA_EXSLB+EX_R3(r13)
+ mfspr r3,SPRN_SRR0 /* SRR0 is faulting address */
+#ifdef __DISABLED__
+ /* Keep that around for when we re-implement dynamic VSIDs */
+ cmpdi r3,0
+ bge slb_miss_user_pseries
+#endif /* __DISABLED__ */
+ mfspr r12,SPRN_SRR1
+#ifndef CONFIG_RELOCATABLE
+ b slb_miss_realmode
+#else
+ mfctr r11
+ ld r10,PACAKBASE(r13)
+ LOAD_HANDLER(r10, slb_miss_realmode)
+ mtctr r10
+ bctr
+#endif
+
#ifdef CONFIG_PPC_DENORMALISATION
denorm_assist:
BEGIN_FTR_SECTION
@@ -612,6 +643,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
.align 7
/* moved from 0xe00 */
MASKABLE_EXCEPTION_OOL(0x900, decrementer)
+ STD_EXCEPTION_HV_OOL(0x982, hdecrementer)
STD_EXCEPTION_HV_OOL(0xe02, h_data_storage)
KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0xe02)
STD_EXCEPTION_HV_OOL(0xe22, h_instr_storage)
@@ -894,7 +926,15 @@ hardware_interrupt_relon_hv:
STD_RELON_EXCEPTION_PSERIES(0x4600, 0x600, alignment)
STD_RELON_EXCEPTION_PSERIES(0x4700, 0x700, program_check)
STD_RELON_EXCEPTION_PSERIES(0x4800, 0x800, fp_unavailable)
- MASKABLE_RELON_EXCEPTION_PSERIES(0x4900, 0x900, decrementer)
+
+ . = 0x4900
+ .globl decrementer_relon_trampoline
+decrementer_relon_trampoline:
+ HMT_MEDIUM_PPR_DISCARD
+ SET_SCRATCH0(r13)
+ EXCEPTION_PROLOG_0(PACA_EXGEN)
+ b decrementer_relon_pSeries
+
STD_RELON_EXCEPTION_HV(0x4980, 0x982, hdecrementer)
MASKABLE_RELON_EXCEPTION_PSERIES(0x4a00, 0xa00, doorbell_super)
STD_RELON_EXCEPTION_PSERIES(0x4b00, 0xb00, trap_0b)
@@ -1244,6 +1284,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
__end_handlers:
/* Equivalents to the above handlers for relocation-on interrupt vectors */
+ MASKABLE_RELON_EXCEPTION_PSERIES_OOL(0x900, decrementer)
+
STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist)
MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell)
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 03/15] powerpc/64s: flush L1D on kernel entry
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
2020-11-20 11:02 ` [PATCH 4.4 01/15] powerpc/64s: Define MASKABLE_RELON_EXCEPTION_PSERIES_OOL Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 02/15] powerpc/64s: move some exception handlers out of line Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 04/15] powerpc: Add a framework for user access tracking Greg Kroah-Hartman
` (15 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel, stable; +Cc: Greg Kroah-Hartman, dja, Nicholas Piggin
From: Nicholas Piggin <npiggin@gmail.com>
commit f79643787e0a0762d2409b7b8334e83f22d85695 upstream.
IBM Power9 processors can speculatively operate on data in the L1 cache before
it has been completely validated, via a way-prediction mechanism. It is not possible
for an attacker to determine the contents of impermissible memory using this method,
since these systems implement a combination of hardware and software security measures
to prevent scenarios where protected data could be leaked.
However these measures don't address the scenario where an attacker induces
the operating system to speculatively execute instructions using data that the
attacker controls. This can be used for example to speculatively bypass "kernel
user access prevention" techniques, as discovered by Anthony Steinhauser of
Google's Safeside Project. This is not an attack by itself, but there is a possibility
it could be used in conjunction with side-channels or other weaknesses in the
privileged code to construct an attack.
This issue can be mitigated by flushing the L1 cache between privilege boundaries
of concern. This patch flushes the L1 cache on kernel entry.
This is part of the fix for CVE-2020-4788.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
Documentation/kernel-parameters.txt | 3 +
arch/powerpc/include/asm/exception-64s.h | 9 +++-
arch/powerpc/include/asm/feature-fixups.h | 10 ++++
arch/powerpc/include/asm/security_features.h | 4 +
arch/powerpc/include/asm/setup.h | 3 +
arch/powerpc/kernel/exceptions-64s.S | 38 +++++++++++++++++
arch/powerpc/kernel/setup_64.c | 58 +++++++++++++++++++++++++++
arch/powerpc/kernel/vmlinux.lds.S | 7 +++
arch/powerpc/lib/feature-fixups.c | 54 +++++++++++++++++++++++++
arch/powerpc/platforms/powernv/setup.c | 10 ++++
arch/powerpc/platforms/pseries/setup.c | 4 +
11 files changed, 199 insertions(+), 1 deletion(-)
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2196,6 +2196,7 @@ bytes respectively. Such letter suffixes
spec_store_bypass_disable=off [X86]
mds=off [X86]
tsx_async_abort=off [X86]
+ no_entry_flush [PPC]
auto (default)
Mitigate all CPU vulnerabilities, but leave SMT
@@ -2476,6 +2477,8 @@ bytes respectively. Such letter suffixes
noefi Disable EFI runtime services support.
+ no_entry_flush [PPC] Don't flush the L1-D cache when entering the kernel.
+
noexec [IA-64]
noexec [X86]
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -65,11 +65,18 @@
nop; \
nop
+#define ENTRY_FLUSH_SLOT \
+ ENTRY_FLUSH_FIXUP_SECTION; \
+ nop; \
+ nop; \
+ nop;
+
/*
* r10 must be free to use, r13 must be paca
*/
#define INTERRUPT_TO_KERNEL \
- STF_ENTRY_BARRIER_SLOT
+ STF_ENTRY_BARRIER_SLOT; \
+ ENTRY_FLUSH_SLOT
/*
* Macros for annotating the expected destination of (h)rfid
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -200,6 +200,14 @@ label##3: \
FTR_ENTRY_OFFSET 955b-956b; \
.popsection;
+#define ENTRY_FLUSH_FIXUP_SECTION \
+957: \
+ .pushsection __entry_flush_fixup,"a"; \
+ .align 2; \
+958: \
+ FTR_ENTRY_OFFSET 957b-958b; \
+ .popsection;
+
#define RFI_FLUSH_FIXUP_SECTION \
951: \
.pushsection __rfi_flush_fixup,"a"; \
@@ -231,8 +239,10 @@ label##3: \
#ifndef __ASSEMBLY__
extern long stf_barrier_fallback;
+extern long entry_flush_fallback;
extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup;
extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup;
+extern long __start___entry_flush_fixup, __stop___entry_flush_fixup;
extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup;
extern long __start__btb_flush_fixup, __stop__btb_flush_fixup;
--- a/arch/powerpc/include/asm/security_features.h
+++ b/arch/powerpc/include/asm/security_features.h
@@ -84,12 +84,16 @@ static inline bool security_ftr_enabled(
// Software required to flush link stack on context switch
#define SEC_FTR_FLUSH_LINK_STACK 0x0000000000001000ull
+// The L1-D cache should be flushed when entering the kernel
+#define SEC_FTR_L1D_FLUSH_ENTRY 0x0000000000004000ull
+
// Features enabled by default
#define SEC_FTR_DEFAULT \
(SEC_FTR_L1D_FLUSH_HV | \
SEC_FTR_L1D_FLUSH_PR | \
SEC_FTR_BNDS_CHK_SPEC_BAR | \
+ SEC_FTR_L1D_FLUSH_ENTRY | \
SEC_FTR_FAVOUR_SECURITY)
#endif /* _ASM_POWERPC_SECURITY_FEATURES_H */
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -38,12 +38,15 @@ enum l1d_flush_type {
};
void setup_rfi_flush(enum l1d_flush_type, bool enable);
+void setup_entry_flush(bool enable);
+void setup_uaccess_flush(bool enable);
void do_rfi_flush_fixups(enum l1d_flush_type types);
#ifdef CONFIG_PPC_BARRIER_NOSPEC
void setup_barrier_nospec(void);
#else
static inline void setup_barrier_nospec(void) { };
#endif
+void do_entry_flush_fixups(enum l1d_flush_type types);
void do_barrier_nospec_fixups(bool enable);
extern bool barrier_nospec_enabled;
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1712,6 +1712,44 @@ hrfi_flush_fallback:
GET_SCRATCH0(r13);
hrfid
+ .globl entry_flush_fallback
+entry_flush_fallback:
+ std r9,PACA_EXRFI+EX_R9(r13)
+ std r10,PACA_EXRFI+EX_R10(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ mfctr r9
+ ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
+ ld r11,PACA_L1D_FLUSH_SIZE(r13)
+ srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
+ mtctr r11
+ DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
+
+ /* order ld/st prior to dcbt stop all streams with flushing */
+ sync
+
+ /*
+ * The load addresses are at staggered offsets within cachelines,
+ * which suits some pipelines better (on others it should not
+ * hurt).
+ */
+1:
+ ld r11,(0x80 + 8)*0(r10)
+ ld r11,(0x80 + 8)*1(r10)
+ ld r11,(0x80 + 8)*2(r10)
+ ld r11,(0x80 + 8)*3(r10)
+ ld r11,(0x80 + 8)*4(r10)
+ ld r11,(0x80 + 8)*5(r10)
+ ld r11,(0x80 + 8)*6(r10)
+ ld r11,(0x80 + 8)*7(r10)
+ addi r10,r10,0x80*8
+ bdnz 1b
+
+ mtctr r9
+ ld r9,PACA_EXRFI+EX_R9(r13)
+ ld r10,PACA_EXRFI+EX_R10(r13)
+ ld r11,PACA_EXRFI+EX_R11(r13)
+ blr
+
/*
* Hash table stuff
*/
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -844,7 +844,9 @@ early_initcall(disable_hardlockup_detect
static enum l1d_flush_type enabled_flush_types;
static void *l1d_flush_fallback_area;
static bool no_rfi_flush;
+static bool no_entry_flush;
bool rfi_flush;
+bool entry_flush;
static int __init handle_no_rfi_flush(char *p)
{
@@ -854,6 +856,14 @@ static int __init handle_no_rfi_flush(ch
}
early_param("no_rfi_flush", handle_no_rfi_flush);
+static int __init handle_no_entry_flush(char *p)
+{
+ pr_info("entry-flush: disabled on command line.");
+ no_entry_flush = true;
+ return 0;
+}
+early_param("no_entry_flush", handle_no_entry_flush);
+
/*
* The RFI flush is not KPTI, but because users will see doco that says to use
* nopti we hijack that option here to also disable the RFI flush.
@@ -885,6 +895,18 @@ void rfi_flush_enable(bool enable)
rfi_flush = enable;
}
+void entry_flush_enable(bool enable)
+{
+ if (enable) {
+ do_entry_flush_fixups(enabled_flush_types);
+ on_each_cpu(do_nothing, NULL, 1);
+ } else {
+ do_entry_flush_fixups(L1D_FLUSH_NONE);
+ }
+
+ entry_flush = enable;
+}
+
static void __ref init_fallback_flush(void)
{
u64 l1d_size, limit;
@@ -930,6 +952,15 @@ void setup_rfi_flush(enum l1d_flush_type
rfi_flush_enable(enable);
}
+void setup_entry_flush(bool enable)
+{
+ if (cpu_mitigations_off())
+ return;
+
+ if (!no_entry_flush)
+ entry_flush_enable(enable);
+}
+
#ifdef CONFIG_DEBUG_FS
static int rfi_flush_set(void *data, u64 val)
{
@@ -957,9 +988,36 @@ static int rfi_flush_get(void *data, u64
DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n");
+static int entry_flush_set(void *data, u64 val)
+{
+ bool enable;
+
+ if (val == 1)
+ enable = true;
+ else if (val == 0)
+ enable = false;
+ else
+ return -EINVAL;
+
+ /* Only do anything if we're changing state */
+ if (enable != entry_flush)
+ entry_flush_enable(enable);
+
+ return 0;
+}
+
+static int entry_flush_get(void *data, u64 *val)
+{
+ *val = entry_flush ? 1 : 0;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n");
+
static __init int rfi_flush_debugfs_init(void)
{
debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
+ debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush);
return 0;
}
device_initcall(rfi_flush_debugfs_init);
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -81,6 +81,13 @@ SECTIONS
}
. = ALIGN(8);
+ __entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) {
+ __start___entry_flush_fixup = .;
+ *(__entry_flush_fixup)
+ __stop___entry_flush_fixup = .;
+ }
+
+ . = ALIGN(8);
__stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) {
__start___stf_exit_barrier_fixup = .;
*(__stf_exit_barrier_fixup)
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -229,6 +229,60 @@ void do_stf_barrier_fixups(enum stf_barr
do_stf_exit_barrier_fixups(types);
}
+void do_entry_flush_fixups(enum l1d_flush_type types)
+{
+ unsigned int instrs[3], *dest;
+ long *start, *end;
+ int i;
+
+ start = PTRRELOC(&__start___entry_flush_fixup);
+ end = PTRRELOC(&__stop___entry_flush_fixup);
+
+ instrs[0] = 0x60000000; /* nop */
+ instrs[1] = 0x60000000; /* nop */
+ instrs[2] = 0x60000000; /* nop */
+
+ i = 0;
+ if (types == L1D_FLUSH_FALLBACK) {
+ instrs[i++] = 0x7d4802a6; /* mflr r10 */
+ instrs[i++] = 0x60000000; /* branch patched below */
+ instrs[i++] = 0x7d4803a6; /* mtlr r10 */
+ }
+
+ if (types & L1D_FLUSH_ORI) {
+ instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+ instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+ }
+
+ if (types & L1D_FLUSH_MTTRIG)
+ instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+ for (i = 0; start < end; start++, i++) {
+ dest = (void *)start + *start;
+
+ pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+ patch_instruction(dest, instrs[0]);
+
+ if (types == L1D_FLUSH_FALLBACK)
+ patch_branch((dest + 1), (unsigned long)&entry_flush_fallback,
+ BRANCH_SET_LINK);
+ else
+ patch_instruction((dest + 1), instrs[1]);
+
+ patch_instruction((dest + 2), instrs[2]);
+ }
+
+ printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i,
+ (types == L1D_FLUSH_NONE) ? "no" :
+ (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" :
+ (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG)
+ ? "ori+mttrig type"
+ : "ori type" :
+ (types & L1D_FLUSH_MTTRIG) ? "mttrig type"
+ : "unknown");
+}
+
void do_rfi_flush_fixups(enum l1d_flush_type types)
{
unsigned int instrs[3], *dest;
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -124,12 +124,22 @@ static void pnv_setup_rfi_flush(void)
type = L1D_FLUSH_ORI;
}
+ /*
+ * 4.4 doesn't support Power9 bare metal, so we don't need to flush
+ * here - the flush fixes a P9 specific vulnerability.
+ */
+ security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY);
+
enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \
(security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR) || \
security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV));
setup_rfi_flush(type, enable);
setup_count_cache_flush();
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
+ setup_entry_flush(enable);
}
static void __init pnv_setup_arch(void)
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -584,6 +584,10 @@ void pseries_setup_rfi_flush(void)
setup_rfi_flush(types, enable);
setup_count_cache_flush();
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
+ setup_entry_flush(enable);
}
static void __init pSeries_setup_arch(void)
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 04/15] powerpc: Add a framework for user access tracking
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (2 preceding siblings ...)
2020-11-20 11:03 ` [PATCH 4.4 03/15] powerpc/64s: flush L1D on kernel entry Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 05/15] powerpc: Implement user_access_begin and friends Greg Kroah-Hartman
` (14 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Greg Kroah-Hartman, dja, Christophe Leroy, Russell Currey,
Michael Ellerman
From: Christophe Leroy <christophe.leroy@c-s.fr>
Backported from commit de78a9c42a79 ("powerpc: Add a framework
for Kernel Userspace Access Protection"). Here we don't try to
add the KUAP framework, we just want the helper functions
because we want to put uaccess flush helpers in them.
In terms of fixes, we don't need commit 1d8f739b07bd ("powerpc/kuap:
Fix set direction in allow/prevent_user_access()") as we don't have
real KUAP. Likewise as all our allows are noops and all our prevents
are just flushes, we don't need commit 9dc086f1e9ef ("powerpc/futex:
Fix incorrect user access blocking") The other 2 fixes we do need.
The original description is:
This patch implements a framework for Kernel Userspace Access
Protection.
Then subarches will have the possibility to provide their own
implementation by providing setup_kuap() and
allow/prevent_user_access().
Some platforms 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.
mpe: Rename to allow/prevent rather than unlock/lock, and add
read/write wrappers. Drop the 32-bit code for now until we have an
implementation for it. Add kuap to pt_regs for 64-bit as well as
32-bit. Don't split strings, use pr_crit_ratelimited().
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Russell Currey <ruscur@russell.cc>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/powerpc/include/asm/futex.h | 4 +++
arch/powerpc/include/asm/kup.h | 36 ++++++++++++++++++++++++++++++
arch/powerpc/include/asm/uaccess.h | 38 +++++++++++++++++++++++++-------
arch/powerpc/lib/checksum_wrappers_64.c | 4 +++
4 files changed, 74 insertions(+), 8 deletions(-)
create mode 100644 arch/powerpc/include/asm/kup.h
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -36,6 +36,7 @@ static inline int arch_futex_atomic_op_i
{
int oldval = 0, ret;
+ allow_write_to_user(uaddr, sizeof(*uaddr));
pagefault_disable();
switch (op) {
@@ -62,6 +63,7 @@ static inline int arch_futex_atomic_op_i
*oval = oldval;
+ prevent_write_to_user(uaddr, sizeof(*uaddr));
return ret;
}
@@ -75,6 +77,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval,
if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
return -EFAULT;
+ allow_write_to_user(uaddr, sizeof(*uaddr));
__asm__ __volatile__ (
PPC_ATOMIC_ENTRY_BARRIER
"1: lwarx %1,0,%3 # futex_atomic_cmpxchg_inatomic\n\
@@ -97,6 +100,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval,
: "cc", "memory");
*uval = prev;
+ prevent_write_to_user(uaddr, sizeof(*uaddr));
return ret;
}
--- /dev/null
+++ b/arch/powerpc/include/asm/kup.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_KUP_H_
+#define _ASM_POWERPC_KUP_H_
+
+#ifndef __ASSEMBLY__
+
+#include <asm/pgtable.h>
+
+static inline void allow_user_access(void __user *to, const void __user *from,
+ unsigned long size) { }
+static inline void prevent_user_access(void __user *to, const void __user *from,
+ unsigned long size) { }
+
+static inline void allow_read_from_user(const void __user *from, unsigned long size)
+{
+ allow_user_access(NULL, from, size);
+}
+
+static inline void allow_write_to_user(void __user *to, unsigned long size)
+{
+ allow_user_access(to, NULL, size);
+}
+
+static inline void prevent_read_from_user(const void __user *from, unsigned long size)
+{
+ prevent_user_access(NULL, from, size);
+}
+
+static inline void prevent_write_to_user(void __user *to, unsigned long size)
+{
+ prevent_user_access(to, NULL, size);
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_KUP_H_ */
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -9,6 +9,7 @@
#include <asm/asm-compat.h>
#include <asm/processor.h>
#include <asm/page.h>
+#include <asm/kup.h>
#define VERIFY_READ 0
#define VERIFY_WRITE 1
@@ -164,6 +165,7 @@ extern long __put_user_bad(void);
#define __put_user_size(x, ptr, size, retval) \
do { \
retval = 0; \
+ allow_write_to_user(ptr, size); \
switch (size) { \
case 1: __put_user_asm(x, ptr, retval, "stb"); break; \
case 2: __put_user_asm(x, ptr, retval, "sth"); break; \
@@ -171,6 +173,7 @@ do { \
case 8: __put_user_asm2(x, ptr, retval); break; \
default: __put_user_bad(); \
} \
+ prevent_write_to_user(ptr, size); \
} while (0)
#define __put_user_nocheck(x, ptr, size) \
@@ -252,6 +255,7 @@ do { \
__chk_user_ptr(ptr); \
if (size > sizeof(x)) \
(x) = __get_user_bad(); \
+ allow_read_from_user(ptr, size); \
switch (size) { \
case 1: __get_user_asm(x, ptr, retval, "lbz"); break; \
case 2: __get_user_asm(x, ptr, retval, "lhz"); break; \
@@ -259,6 +263,7 @@ do { \
case 8: __get_user_asm2(x, ptr, retval); break; \
default: (x) = __get_user_bad(); \
} \
+ prevent_read_from_user(ptr, size); \
} while (0)
#define __get_user_nocheck(x, ptr, size) \
@@ -328,9 +333,14 @@ extern unsigned long __copy_tofrom_user(
static inline unsigned long copy_from_user(void *to,
const void __user *from, unsigned long n)
{
+ unsigned long ret;
+
if (likely(access_ok(VERIFY_READ, from, n))) {
+ allow_user_access(to, from, n);
barrier_nospec();
- return __copy_tofrom_user((__force void __user *)to, from, n);
+ ret = __copy_tofrom_user((__force void __user *)to, from, n);
+ prevent_user_access(to, from, n);
+ return ret;
}
memset(to, 0, n);
return n;
@@ -361,8 +371,9 @@ extern unsigned long copy_in_user(void _
static inline unsigned long __copy_from_user_inatomic(void *to,
const void __user *from, unsigned long n)
{
+ unsigned long ret;
if (__builtin_constant_p(n) && (n <= 8)) {
- unsigned long ret = 1;
+ ret = 1;
switch (n) {
case 1:
@@ -387,14 +398,18 @@ static inline unsigned long __copy_from_
}
barrier_nospec();
- return __copy_tofrom_user((__force void __user *)to, from, n);
+ allow_read_from_user(from, n);
+ ret = __copy_tofrom_user((__force void __user *)to, from, n);
+ prevent_read_from_user(from, n);
+ return ret;
}
static inline unsigned long __copy_to_user_inatomic(void __user *to,
const void *from, unsigned long n)
{
+ unsigned long ret;
if (__builtin_constant_p(n) && (n <= 8)) {
- unsigned long ret = 1;
+ ret = 1;
switch (n) {
case 1:
@@ -414,7 +429,10 @@ static inline unsigned long __copy_to_us
return 0;
}
- return __copy_tofrom_user(to, (__force const void __user *)from, n);
+ allow_write_to_user(to, n);
+ ret = __copy_tofrom_user(to, (__force const void __user *)from, n);
+ prevent_write_to_user(to, n);
+ return ret;
}
static inline unsigned long __copy_from_user(void *to,
@@ -435,10 +453,14 @@ extern unsigned long __clear_user(void _
static inline unsigned long clear_user(void __user *addr, unsigned long size)
{
+ unsigned long ret = size;
might_fault();
- if (likely(access_ok(VERIFY_WRITE, addr, size)))
- return __clear_user(addr, size);
- return size;
+ if (likely(access_ok(VERIFY_WRITE, addr, size))) {
+ allow_write_to_user(addr, size);
+ ret = __clear_user(addr, size);
+ prevent_write_to_user(addr, size);
+ }
+ return ret;
}
extern long strncpy_from_user(char *dst, const char __user *src, long count);
--- a/arch/powerpc/lib/checksum_wrappers_64.c
+++ b/arch/powerpc/lib/checksum_wrappers_64.c
@@ -29,6 +29,7 @@ __wsum csum_and_copy_from_user(const voi
unsigned int csum;
might_sleep();
+ allow_read_from_user(src, len);
*err_ptr = 0;
@@ -60,6 +61,7 @@ __wsum csum_and_copy_from_user(const voi
}
out:
+ prevent_read_from_user(src, len);
return (__force __wsum)csum;
}
EXPORT_SYMBOL(csum_and_copy_from_user);
@@ -70,6 +72,7 @@ __wsum csum_and_copy_to_user(const void
unsigned int csum;
might_sleep();
+ allow_write_to_user(dst, len);
*err_ptr = 0;
@@ -97,6 +100,7 @@ __wsum csum_and_copy_to_user(const void
}
out:
+ prevent_write_to_user(dst, len);
return (__force __wsum)csum;
}
EXPORT_SYMBOL(csum_and_copy_to_user);
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 05/15] powerpc: Implement user_access_begin and friends
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (3 preceding siblings ...)
2020-11-20 11:03 ` [PATCH 4.4 04/15] powerpc: Add a framework for user access tracking Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 06/15] powerpc: Fix __clear_user() with KUAP enabled Greg Kroah-Hartman
` (13 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Greg Kroah-Hartman, dja, Christophe Leroy, Michael Ellerman
From: Christophe Leroy <christophe.leroy@c-s.fr>
commit 5cd623333e7cf4e3a334c70529268b65f2a6c2c7 upstream.
Today, when a function like strncpy_from_user() is called,
the userspace access protection is de-activated and re-activated
for every word read.
By implementing user_access_begin and friends, the protection
is de-activated at the beginning of the copy and re-activated at the
end.
Implement user_access_begin(), user_access_end() and
unsafe_get_user(), unsafe_put_user() and unsafe_copy_to_user()
For the time being, we keep user_access_save() and
user_access_restore() as nops.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/36d4fbf9e56a75994aca4ee2214c77b26a5a8d35.1579866752.git.christophe.leroy@c-s.fr
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/powerpc/include/asm/uaccess.h | 60 ++++++++++++++++++++++++++++---------
1 file changed, 46 insertions(+), 14 deletions(-)
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -106,9 +106,14 @@ struct exception_table_entry {
__put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
#define __get_user(x, ptr) \
- __get_user_nocheck((x), (ptr), sizeof(*(ptr)))
+ __get_user_nocheck((x), (ptr), sizeof(*(ptr)), true)
#define __put_user(x, ptr) \
- __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
+ __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), true)
+
+#define __get_user_allowed(x, ptr) \
+ __get_user_nocheck((x), (ptr), sizeof(*(ptr)), false)
+#define __put_user_allowed(x, ptr) \
+ __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), false)
#define __get_user_inatomic(x, ptr) \
__get_user_nosleep((x), (ptr), sizeof(*(ptr)))
@@ -162,10 +167,9 @@ extern long __put_user_bad(void);
: "r" (x), "b" (addr), "i" (-EFAULT), "0" (err))
#endif /* __powerpc64__ */
-#define __put_user_size(x, ptr, size, retval) \
+#define __put_user_size_allowed(x, ptr, size, retval) \
do { \
retval = 0; \
- allow_write_to_user(ptr, size); \
switch (size) { \
case 1: __put_user_asm(x, ptr, retval, "stb"); break; \
case 2: __put_user_asm(x, ptr, retval, "sth"); break; \
@@ -173,17 +177,26 @@ do { \
case 8: __put_user_asm2(x, ptr, retval); break; \
default: __put_user_bad(); \
} \
+} while (0)
+
+#define __put_user_size(x, ptr, size, retval) \
+do { \
+ allow_write_to_user(ptr, size); \
+ __put_user_size_allowed(x, ptr, size, retval); \
prevent_write_to_user(ptr, size); \
} while (0)
-#define __put_user_nocheck(x, ptr, size) \
+#define __put_user_nocheck(x, ptr, size, do_allow) \
({ \
long __pu_err; \
__typeof__(*(ptr)) __user *__pu_addr = (ptr); \
if (!is_kernel_addr((unsigned long)__pu_addr)) \
might_fault(); \
__chk_user_ptr(ptr); \
- __put_user_size((x), __pu_addr, (size), __pu_err); \
+ if (do_allow) \
+ __put_user_size((x), __pu_addr, (size), __pu_err); \
+ else \
+ __put_user_size_allowed((x), __pu_addr, (size), __pu_err); \
__pu_err; \
})
@@ -249,13 +262,12 @@ extern long __get_user_bad(void);
: "b" (addr), "i" (-EFAULT), "0" (err))
#endif /* __powerpc64__ */
-#define __get_user_size(x, ptr, size, retval) \
+#define __get_user_size_allowed(x, ptr, size, retval) \
do { \
retval = 0; \
__chk_user_ptr(ptr); \
if (size > sizeof(x)) \
(x) = __get_user_bad(); \
- allow_read_from_user(ptr, size); \
switch (size) { \
case 1: __get_user_asm(x, ptr, retval, "lbz"); break; \
case 2: __get_user_asm(x, ptr, retval, "lhz"); break; \
@@ -263,10 +275,16 @@ do { \
case 8: __get_user_asm2(x, ptr, retval); break; \
default: (x) = __get_user_bad(); \
} \
+} while (0)
+
+#define __get_user_size(x, ptr, size, retval) \
+do { \
+ allow_read_from_user(ptr, size); \
+ __get_user_size_allowed(x, ptr, size, retval); \
prevent_read_from_user(ptr, size); \
} while (0)
-#define __get_user_nocheck(x, ptr, size) \
+#define __get_user_nocheck(x, ptr, size, do_allow) \
({ \
long __gu_err; \
unsigned long __gu_val; \
@@ -275,7 +293,10 @@ do { \
if (!is_kernel_addr((unsigned long)__gu_addr)) \
might_fault(); \
barrier_nospec(); \
- __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \
+ if (do_allow) \
+ __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \
+ else \
+ __get_user_size_allowed(__gu_val, __gu_addr, (size), __gu_err); \
(x) = (__typeof__(*(ptr)))__gu_val; \
__gu_err; \
})
@@ -408,21 +429,22 @@ static inline unsigned long __copy_to_us
const void *from, unsigned long n)
{
unsigned long ret;
+
if (__builtin_constant_p(n) && (n <= 8)) {
ret = 1;
switch (n) {
case 1:
- __put_user_size(*(u8 *)from, (u8 __user *)to, 1, ret);
+ __put_user_size_allowed(*(u8 *)from, (u8 __user *)to, 1, ret);
break;
case 2:
- __put_user_size(*(u16 *)from, (u16 __user *)to, 2, ret);
+ __put_user_size_allowed(*(u16 *)from, (u16 __user *)to, 2, ret);
break;
case 4:
- __put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret);
+ __put_user_size_allowed(*(u32 *)from, (u32 __user *)to, 4, ret);
break;
case 8:
- __put_user_size(*(u64 *)from, (u64 __user *)to, 8, ret);
+ __put_user_size_allowed(*(u64 *)from, (u64 __user *)to, 8, ret);
break;
}
if (ret == 0)
@@ -467,6 +489,16 @@ extern long strncpy_from_user(char *dst,
extern __must_check long strlen_user(const char __user *str);
extern __must_check long strnlen_user(const char __user *str, long n);
+
+#define user_access_begin() do { } while (0)
+#define user_access_end() prevent_user_access(NULL, NULL, ~0ul)
+
+#define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0)
+#define unsafe_get_user(x, p, e) unsafe_op_wrap(__get_user_allowed(x, p), e)
+#define unsafe_put_user(x, p, e) unsafe_op_wrap(__put_user_allowed(x, p), e)
+#define unsafe_copy_to_user(d, s, l, e) \
+ unsafe_op_wrap(__copy_to_user_inatomic(d, s, l), e)
+
#endif /* __ASSEMBLY__ */
#endif /* __KERNEL__ */
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 06/15] powerpc: Fix __clear_user() with KUAP enabled
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (4 preceding siblings ...)
2020-11-20 11:03 ` [PATCH 4.4 05/15] powerpc: Implement user_access_begin and friends Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 07/15] powerpc/uaccess: Evaluate macro arguments once, before user access is allowed Greg Kroah-Hartman
` (12 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Greg Kroah-Hartman, dja, syzbot+f25ecf4b2982d8c7a640,
Michael Ellerman, Andrew Donnellan
From: Andrew Donnellan <ajd@linux.ibm.com>
commit 61e3acd8c693a14fc69b824cb5b08d02cb90a6e7 upstream.
The KUAP implementation adds calls in clear_user() to enable and
disable access to userspace memory. However, it doesn't add these to
__clear_user(), which is used in the ptrace regset code.
As there's only one direct user of __clear_user() (the regset code),
and the time taken to set the AMR for KUAP purposes is going to
dominate the cost of a quick access_ok(), there's not much point
having a separate path.
Rename __clear_user() to __arch_clear_user(), and make __clear_user()
just call clear_user().
Reported-by: syzbot+f25ecf4b2982d8c7a640@syzkaller-ppc64.appspotmail.com
Reported-by: Daniel Axtens <dja@axtens.net>
Suggested-by: Michael Ellerman <mpe@ellerman.id.au>
Fixes: de78a9c42a79 ("powerpc: Add a framework for Kernel Userspace Access Protection")
Signed-off-by: Andrew Donnellan <ajd@linux.ibm.com>
[mpe: Use __arch_clear_user() for the asm version like arm64 & nds32]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191209132221.15328-1-ajd@linux.ibm.com
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/powerpc/include/asm/uaccess.h | 9 +++++++--
arch/powerpc/kernel/ppc_ksyms.c | 3 +++
arch/powerpc/lib/string.S | 2 +-
arch/powerpc/lib/string_64.S | 4 ++--
4 files changed, 13 insertions(+), 5 deletions(-)
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -471,7 +471,7 @@ static inline unsigned long __copy_to_us
return __copy_to_user_inatomic(to, from, size);
}
-extern unsigned long __clear_user(void __user *addr, unsigned long size);
+unsigned long __arch_clear_user(void __user *addr, unsigned long size);
static inline unsigned long clear_user(void __user *addr, unsigned long size)
{
@@ -479,12 +479,17 @@ static inline unsigned long clear_user(v
might_fault();
if (likely(access_ok(VERIFY_WRITE, addr, size))) {
allow_write_to_user(addr, size);
- ret = __clear_user(addr, size);
+ ret = __arch_clear_user(addr, size);
prevent_write_to_user(addr, size);
}
return ret;
}
+static inline unsigned long __clear_user(void __user *addr, unsigned long size)
+{
+ return clear_user(addr, size);
+}
+
extern long strncpy_from_user(char *dst, const char __user *src, long count);
extern __must_check long strlen_user(const char __user *str);
extern __must_check long strnlen_user(const char __user *str, long n);
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -5,6 +5,7 @@
#include <asm/switch_to.h>
#include <asm/cacheflush.h>
#include <asm/epapr_hcalls.h>
+#include <asm/uaccess.h>
EXPORT_SYMBOL(flush_dcache_range);
EXPORT_SYMBOL(flush_icache_range);
@@ -43,3 +44,5 @@ EXPORT_SYMBOL(epapr_hypercall_start);
#endif
EXPORT_SYMBOL(current_stack_pointer);
+
+EXPORT_SYMBOL(__arch_clear_user);
--- a/arch/powerpc/lib/string.S
+++ b/arch/powerpc/lib/string.S
@@ -122,7 +122,7 @@ _GLOBAL(memchr)
blr
#ifdef CONFIG_PPC32
-_GLOBAL(__clear_user)
+_GLOBAL(__arch_clear_user)
addi r6,r3,-4
li r3,0
li r5,0
--- a/arch/powerpc/lib/string_64.S
+++ b/arch/powerpc/lib/string_64.S
@@ -27,7 +27,7 @@ PPC64_CACHES:
.section ".text"
/**
- * __clear_user: - Zero a block of memory in user space, with less checking.
+ * __arch_clear_user: - Zero a block of memory in user space, with less checking.
* @to: Destination address, in user space.
* @n: Number of bytes to zero.
*
@@ -77,7 +77,7 @@ err3; stb r0,0(r3)
mr r3,r4
blr
-_GLOBAL_TOC(__clear_user)
+_GLOBAL_TOC(__arch_clear_user)
cmpdi r4,32
neg r6,r3
li r0,0
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 07/15] powerpc/uaccess: Evaluate macro arguments once, before user access is allowed
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (5 preceding siblings ...)
2020-11-20 11:03 ` [PATCH 4.4 06/15] powerpc: Fix __clear_user() with KUAP enabled Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 08/15] powerpc/64s: flush L1D after user accesses Greg Kroah-Hartman
` (11 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Greg Kroah-Hartman, dja, Nicholas Piggin, Michael Ellerman
From: Nicholas Piggin <npiggin@gmail.com>
commit d02f6b7dab8228487268298ea1f21081c0b4b3eb upstream.
get/put_user() can be called with nontrivial arguments. fs/proc/page.c
has a good example:
if (put_user(stable_page_flags(ppage), out)) {
stable_page_flags() is quite a lot of code, including spin locks in
the page allocator.
Ensure these arguments are evaluated before user access is allowed.
This improves security by reducing code with access to userspace, but
it also fixes a PREEMPT bug with KUAP on powerpc/64s:
stable_page_flags() is currently called with AMR set to allow writes,
it ends up calling spin_unlock(), which can call preempt_schedule. But
the task switch code can not be called with AMR set (it relies on
interrupts saving the register), so this blows up.
It's fine if the code inside allow_user_access() is preemptible,
because a timer or IPI will save the AMR, but it's not okay to
explicitly cause a reschedule.
Fixes: de78a9c42a79 ("powerpc: Add a framework for Kernel Userspace Access Protection")
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200407041245.600651-1-npiggin@gmail.com
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/powerpc/include/asm/uaccess.h | 49 ++++++++++++++++++++++++++-----------
1 file changed, 35 insertions(+), 14 deletions(-)
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -190,13 +190,17 @@ do { \
({ \
long __pu_err; \
__typeof__(*(ptr)) __user *__pu_addr = (ptr); \
+ __typeof__(*(ptr)) __pu_val = (x); \
+ __typeof__(size) __pu_size = (size); \
+ \
if (!is_kernel_addr((unsigned long)__pu_addr)) \
might_fault(); \
- __chk_user_ptr(ptr); \
+ __chk_user_ptr(__pu_addr); \
if (do_allow) \
- __put_user_size((x), __pu_addr, (size), __pu_err); \
+ __put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \
else \
- __put_user_size_allowed((x), __pu_addr, (size), __pu_err); \
+ __put_user_size_allowed(__pu_val, __pu_addr, __pu_size, __pu_err); \
+ \
__pu_err; \
})
@@ -204,9 +208,13 @@ do { \
({ \
long __pu_err = -EFAULT; \
__typeof__(*(ptr)) __user *__pu_addr = (ptr); \
+ __typeof__(*(ptr)) __pu_val = (x); \
+ __typeof__(size) __pu_size = (size); \
+ \
might_fault(); \
- if (access_ok(VERIFY_WRITE, __pu_addr, size)) \
- __put_user_size((x), __pu_addr, (size), __pu_err); \
+ if (access_ok(VERIFY_WRITE, __pu_addr, __pu_size)) \
+ __put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \
+ \
__pu_err; \
})
@@ -214,8 +222,12 @@ do { \
({ \
long __pu_err; \
__typeof__(*(ptr)) __user *__pu_addr = (ptr); \
- __chk_user_ptr(ptr); \
- __put_user_size((x), __pu_addr, (size), __pu_err); \
+ __typeof__(*(ptr)) __pu_val = (x); \
+ __typeof__(size) __pu_size = (size); \
+ \
+ __chk_user_ptr(__pu_addr); \
+ __put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \
+ \
__pu_err; \
})
@@ -289,15 +301,18 @@ do { \
long __gu_err; \
unsigned long __gu_val; \
__typeof__(*(ptr)) __user *__gu_addr = (ptr); \
- __chk_user_ptr(ptr); \
+ __typeof__(size) __gu_size = (size); \
+ \
+ __chk_user_ptr(__gu_addr); \
if (!is_kernel_addr((unsigned long)__gu_addr)) \
might_fault(); \
barrier_nospec(); \
if (do_allow) \
- __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \
+ __get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \
else \
- __get_user_size_allowed(__gu_val, __gu_addr, (size), __gu_err); \
+ __get_user_size_allowed(__gu_val, __gu_addr, __gu_size, __gu_err); \
(x) = (__typeof__(*(ptr)))__gu_val; \
+ \
__gu_err; \
})
@@ -322,12 +337,15 @@ do { \
long __gu_err = -EFAULT; \
unsigned long __gu_val = 0; \
__typeof__(*(ptr)) __user *__gu_addr = (ptr); \
+ __typeof__(size) __gu_size = (size); \
+ \
might_fault(); \
- if (access_ok(VERIFY_READ, __gu_addr, (size))) { \
+ if (access_ok(VERIFY_READ, __gu_addr, __gu_size)) { \
barrier_nospec(); \
- __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \
+ __get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \
} \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
+ \
__gu_err; \
})
@@ -336,10 +354,13 @@ do { \
long __gu_err; \
unsigned long __gu_val; \
__typeof__(*(ptr)) __user *__gu_addr = (ptr); \
- __chk_user_ptr(ptr); \
+ __typeof__(size) __gu_size = (size); \
+ \
+ __chk_user_ptr(__gu_addr); \
barrier_nospec(); \
- __get_user_size(__gu_val, __gu_addr, (size), __gu_err); \
+ __get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \
(x) = (__force __typeof__(*(ptr)))__gu_val; \
+ \
__gu_err; \
})
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 08/15] powerpc/64s: flush L1D after user accesses
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (6 preceding siblings ...)
2020-11-20 11:03 ` [PATCH 4.4 07/15] powerpc/uaccess: Evaluate macro arguments once, before user access is allowed Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 09/15] i2c: imx: Fix external abort on interrupt in exit paths Greg Kroah-Hartman
` (10 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel, stable; +Cc: Greg Kroah-Hartman, dja, Nicholas Piggin
From: Nicholas Piggin <npiggin@gmail.com>
commit 9a32a7e78bd0cd9a9b6332cbdc345ee5ffd0c5de upstream.
IBM Power9 processors can speculatively operate on data in the L1 cache before
it has been completely validated, via a way-prediction mechanism. It is not possible
for an attacker to determine the contents of impermissible memory using this method,
since these systems implement a combination of hardware and software security measures
to prevent scenarios where protected data could be leaked.
However these measures don't address the scenario where an attacker induces
the operating system to speculatively execute instructions using data that the
attacker controls. This can be used for example to speculatively bypass "kernel
user access prevention" techniques, as discovered by Anthony Steinhauser of
Google's Safeside Project. This is not an attack by itself, but there is a possibility
it could be used in conjunction with side-channels or other weaknesses in the
privileged code to construct an attack.
This issue can be mitigated by flushing the L1 cache between privilege boundaries
of concern. This patch flushes the L1 cache after user accesses.
This is part of the fix for CVE-2020-4788.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
Documentation/kernel-parameters.txt | 4 +
arch/powerpc/include/asm/book3s/64/kup-radix.h | 23 ++++++
arch/powerpc/include/asm/feature-fixups.h | 9 ++
arch/powerpc/include/asm/kup.h | 4 +
arch/powerpc/include/asm/security_features.h | 3
arch/powerpc/include/asm/setup.h | 1
arch/powerpc/kernel/exceptions-64s.S | 86 +++++++------------------
arch/powerpc/kernel/ppc_ksyms.c | 7 ++
arch/powerpc/kernel/setup_64.c | 80 +++++++++++++++++++++++
arch/powerpc/kernel/vmlinux.lds.S | 7 ++
arch/powerpc/lib/feature-fixups.c | 50 ++++++++++++++
arch/powerpc/platforms/powernv/setup.c | 7 +-
arch/powerpc/platforms/pseries/setup.c | 4 +
13 files changed, 224 insertions(+), 61 deletions(-)
create mode 100644 arch/powerpc/include/asm/book3s/64/kup-radix.h
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2197,6 +2197,7 @@ bytes respectively. Such letter suffixes
mds=off [X86]
tsx_async_abort=off [X86]
no_entry_flush [PPC]
+ no_uaccess_flush [PPC]
auto (default)
Mitigate all CPU vulnerabilities, but leave SMT
@@ -2521,6 +2522,9 @@ bytes respectively. Such letter suffixes
nospec_store_bypass_disable
[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
+ no_uaccess_flush
+ [PPC] Don't flush the L1-D cache after accessing user data.
+
noxsave [BUGS=X86] Disables x86 extended register state save
and restore using xsave. The kernel will fallback to
enabling legacy floating-point and sse state.
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H
+#define _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H
+#include <linux/jump_label.h>
+
+DECLARE_STATIC_KEY_FALSE(uaccess_flush_key);
+
+/* Prototype for function defined in exceptions-64s.S */
+void do_uaccess_flush(void);
+
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+ unsigned long size)
+{
+}
+
+static inline void prevent_user_access(void __user *to, const void __user *from,
+ unsigned long size)
+{
+ if (static_branch_unlikely(&uaccess_flush_key))
+ do_uaccess_flush();
+}
+
+#endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -200,6 +200,14 @@ label##3: \
FTR_ENTRY_OFFSET 955b-956b; \
.popsection;
+#define UACCESS_FLUSH_FIXUP_SECTION \
+959: \
+ .pushsection __uaccess_flush_fixup,"a"; \
+ .align 2; \
+960: \
+ FTR_ENTRY_OFFSET 959b-960b; \
+ .popsection;
+
#define ENTRY_FLUSH_FIXUP_SECTION \
957: \
.pushsection __entry_flush_fixup,"a"; \
@@ -242,6 +250,7 @@ extern long stf_barrier_fallback;
extern long entry_flush_fallback;
extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup;
extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup;
+extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup;
extern long __start___entry_flush_fixup, __stop___entry_flush_fixup;
extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup;
--- a/arch/powerpc/include/asm/kup.h
+++ b/arch/powerpc/include/asm/kup.h
@@ -6,10 +6,14 @@
#include <asm/pgtable.h>
+#ifdef CONFIG_PPC_BOOK3S_64
+#include <asm/book3s/64/kup-radix.h>
+#else
static inline void allow_user_access(void __user *to, const void __user *from,
unsigned long size) { }
static inline void prevent_user_access(void __user *to, const void __user *from,
unsigned long size) { }
+#endif /* CONFIG_PPC_BOOK3S_64 */
static inline void allow_read_from_user(const void __user *from, unsigned long size)
{
--- a/arch/powerpc/include/asm/security_features.h
+++ b/arch/powerpc/include/asm/security_features.h
@@ -87,6 +87,8 @@ static inline bool security_ftr_enabled(
// The L1-D cache should be flushed when entering the kernel
#define SEC_FTR_L1D_FLUSH_ENTRY 0x0000000000004000ull
+// The L1-D cache should be flushed after user accesses from the kernel
+#define SEC_FTR_L1D_FLUSH_UACCESS 0x0000000000008000ull
// Features enabled by default
#define SEC_FTR_DEFAULT \
@@ -94,6 +96,7 @@ static inline bool security_ftr_enabled(
SEC_FTR_L1D_FLUSH_PR | \
SEC_FTR_BNDS_CHK_SPEC_BAR | \
SEC_FTR_L1D_FLUSH_ENTRY | \
+ SEC_FTR_L1D_FLUSH_UACCESS | \
SEC_FTR_FAVOUR_SECURITY)
#endif /* _ASM_POWERPC_SECURITY_FEATURES_H */
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -46,6 +46,7 @@ void setup_barrier_nospec(void);
#else
static inline void setup_barrier_nospec(void) { };
#endif
+void do_uaccess_flush_fixups(enum l1d_flush_type types);
void do_entry_flush_fixups(enum l1d_flush_type types);
void do_barrier_nospec_fixups(bool enable);
extern bool barrier_nospec_enabled;
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1630,14 +1630,9 @@ stf_barrier_fallback:
.endr
blr
- .globl rfi_flush_fallback
-rfi_flush_fallback:
- SET_SCRATCH0(r13);
- GET_PACA(r13);
- std r9,PACA_EXRFI+EX_R9(r13)
- std r10,PACA_EXRFI+EX_R10(r13)
- std r11,PACA_EXRFI+EX_R11(r13)
- mfctr r9
+
+/* Clobbers r10, r11, ctr */
+.macro L1D_DISPLACEMENT_FLUSH
ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
ld r11,PACA_L1D_FLUSH_SIZE(r13)
srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
@@ -1663,7 +1658,18 @@ rfi_flush_fallback:
ld r11,(0x80 + 8)*7(r10)
addi r10,r10,0x80*8
bdnz 1b
+.endm
+
+ .globl rfi_flush_fallback
+rfi_flush_fallback:
+ SET_SCRATCH0(r13);
+ GET_PACA(r13);
+ std r9,PACA_EXRFI+EX_R9(r13)
+ std r10,PACA_EXRFI+EX_R10(r13)
+ std r11,PACA_EXRFI+EX_R11(r13)
+ mfctr r9
+ L1D_DISPLACEMENT_FLUSH
mtctr r9
ld r9,PACA_EXRFI+EX_R9(r13)
ld r10,PACA_EXRFI+EX_R10(r13)
@@ -1679,32 +1685,7 @@ hrfi_flush_fallback:
std r10,PACA_EXRFI+EX_R10(r13)
std r11,PACA_EXRFI+EX_R11(r13)
mfctr r9
- ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
- ld r11,PACA_L1D_FLUSH_SIZE(r13)
- srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
- mtctr r11
- DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
-
- /* order ld/st prior to dcbt stop all streams with flushing */
- sync
-
- /*
- * The load adresses are at staggered offsets within cachelines,
- * which suits some pipelines better (on others it should not
- * hurt).
- */
-1:
- ld r11,(0x80 + 8)*0(r10)
- ld r11,(0x80 + 8)*1(r10)
- ld r11,(0x80 + 8)*2(r10)
- ld r11,(0x80 + 8)*3(r10)
- ld r11,(0x80 + 8)*4(r10)
- ld r11,(0x80 + 8)*5(r10)
- ld r11,(0x80 + 8)*6(r10)
- ld r11,(0x80 + 8)*7(r10)
- addi r10,r10,0x80*8
- bdnz 1b
-
+ L1D_DISPLACEMENT_FLUSH
mtctr r9
ld r9,PACA_EXRFI+EX_R9(r13)
ld r10,PACA_EXRFI+EX_R10(r13)
@@ -1718,38 +1699,14 @@ entry_flush_fallback:
std r10,PACA_EXRFI+EX_R10(r13)
std r11,PACA_EXRFI+EX_R11(r13)
mfctr r9
- ld r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
- ld r11,PACA_L1D_FLUSH_SIZE(r13)
- srdi r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
- mtctr r11
- DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
-
- /* order ld/st prior to dcbt stop all streams with flushing */
- sync
-
- /*
- * The load addresses are at staggered offsets within cachelines,
- * which suits some pipelines better (on others it should not
- * hurt).
- */
-1:
- ld r11,(0x80 + 8)*0(r10)
- ld r11,(0x80 + 8)*1(r10)
- ld r11,(0x80 + 8)*2(r10)
- ld r11,(0x80 + 8)*3(r10)
- ld r11,(0x80 + 8)*4(r10)
- ld r11,(0x80 + 8)*5(r10)
- ld r11,(0x80 + 8)*6(r10)
- ld r11,(0x80 + 8)*7(r10)
- addi r10,r10,0x80*8
- bdnz 1b
-
+ L1D_DISPLACEMENT_FLUSH
mtctr r9
ld r9,PACA_EXRFI+EX_R9(r13)
ld r10,PACA_EXRFI+EX_R10(r13)
ld r11,PACA_EXRFI+EX_R11(r13)
blr
+
/*
* Hash table stuff
*/
@@ -1909,3 +1866,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
1: addi r3,r1,STACK_FRAME_OVERHEAD
bl kernel_bad_stack
b 1b
+
+_KPROBE(do_uaccess_flush)
+ UACCESS_FLUSH_FIXUP_SECTION
+ nop
+ nop
+ nop
+ blr
+ L1D_DISPLACEMENT_FLUSH
+ blr
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -6,6 +6,9 @@
#include <asm/cacheflush.h>
#include <asm/epapr_hcalls.h>
#include <asm/uaccess.h>
+#ifdef CONFIG_PPC64
+#include <asm/book3s/64/kup-radix.h>
+#endif
EXPORT_SYMBOL(flush_dcache_range);
EXPORT_SYMBOL(flush_icache_range);
@@ -46,3 +49,7 @@ EXPORT_SYMBOL(epapr_hypercall_start);
EXPORT_SYMBOL(current_stack_pointer);
EXPORT_SYMBOL(__arch_clear_user);
+
+#ifdef CONFIG_PPC64
+EXPORT_SYMBOL(do_uaccess_flush);
+#endif
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -845,8 +845,12 @@ static enum l1d_flush_type enabled_flush
static void *l1d_flush_fallback_area;
static bool no_rfi_flush;
static bool no_entry_flush;
+static bool no_uaccess_flush;
bool rfi_flush;
bool entry_flush;
+bool uaccess_flush;
+DEFINE_STATIC_KEY_FALSE(uaccess_flush_key);
+EXPORT_SYMBOL(uaccess_flush_key);
static int __init handle_no_rfi_flush(char *p)
{
@@ -864,6 +868,14 @@ static int __init handle_no_entry_flush(
}
early_param("no_entry_flush", handle_no_entry_flush);
+static int __init handle_no_uaccess_flush(char *p)
+{
+ pr_info("uaccess-flush: disabled on command line.");
+ no_uaccess_flush = true;
+ return 0;
+}
+early_param("no_uaccess_flush", handle_no_uaccess_flush);
+
/*
* The RFI flush is not KPTI, but because users will see doco that says to use
* nopti we hijack that option here to also disable the RFI flush.
@@ -907,6 +919,23 @@ void entry_flush_enable(bool enable)
entry_flush = enable;
}
+void uaccess_flush_enable(bool enable)
+{
+ if (enable) {
+ do_uaccess_flush_fixups(enabled_flush_types);
+ if (static_key_initialized)
+ static_branch_enable(&uaccess_flush_key);
+ else
+ printk(KERN_DEBUG "uaccess-flush: deferring static key until after static key initialization\n");
+ on_each_cpu(do_nothing, NULL, 1);
+ } else {
+ static_branch_disable(&uaccess_flush_key);
+ do_uaccess_flush_fixups(L1D_FLUSH_NONE);
+ }
+
+ uaccess_flush = enable;
+}
+
static void __ref init_fallback_flush(void)
{
u64 l1d_size, limit;
@@ -961,6 +990,15 @@ void setup_entry_flush(bool enable)
entry_flush_enable(enable);
}
+void setup_uaccess_flush(bool enable)
+{
+ if (cpu_mitigations_off())
+ return;
+
+ if (!no_uaccess_flush)
+ uaccess_flush_enable(enable);
+}
+
#ifdef CONFIG_DEBUG_FS
static int rfi_flush_set(void *data, u64 val)
{
@@ -1014,12 +1052,54 @@ static int entry_flush_get(void *data, u
DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n");
+static int uaccess_flush_set(void *data, u64 val)
+{
+ bool enable;
+
+ if (val == 1)
+ enable = true;
+ else if (val == 0)
+ enable = false;
+ else
+ return -EINVAL;
+
+ /* Only do anything if we're changing state */
+ if (enable != uaccess_flush)
+ uaccess_flush_enable(enable);
+
+ return 0;
+}
+
+static int uaccess_flush_get(void *data, u64 *val)
+{
+ *val = uaccess_flush ? 1 : 0;
+ return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set, "%llu\n");
+
+
static __init int rfi_flush_debugfs_init(void)
{
debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush);
+ debugfs_create_file("uaccess_flush", 0600, powerpc_debugfs_root, NULL, &fops_uaccess_flush);
return 0;
}
device_initcall(rfi_flush_debugfs_init);
#endif
+
+/*
+ * setup_uaccess_flush runs before jump_label_init, so we can't do the setup
+ * there. Do it now instead.
+ */
+static __init int uaccess_flush_static_key_init(void)
+{
+ if (uaccess_flush) {
+ printk(KERN_DEBUG "uaccess-flush: switching on static key\n");
+ static_branch_enable(&uaccess_flush_key);
+ }
+ return 0;
+}
+early_initcall(uaccess_flush_static_key_init);
#endif /* CONFIG_PPC_BOOK3S_64 */
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -81,6 +81,13 @@ SECTIONS
}
. = ALIGN(8);
+ __uaccess_flush_fixup : AT(ADDR(__uaccess_flush_fixup) - LOAD_OFFSET) {
+ __start___uaccess_flush_fixup = .;
+ *(__uaccess_flush_fixup)
+ __stop___uaccess_flush_fixup = .;
+ }
+
+ . = ALIGN(8);
__entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) {
__start___entry_flush_fixup = .;
*(__entry_flush_fixup)
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -229,6 +229,56 @@ void do_stf_barrier_fixups(enum stf_barr
do_stf_exit_barrier_fixups(types);
}
+void do_uaccess_flush_fixups(enum l1d_flush_type types)
+{
+ unsigned int instrs[4], *dest;
+ long *start, *end;
+ int i;
+
+ start = PTRRELOC(&__start___uaccess_flush_fixup);
+ end = PTRRELOC(&__stop___uaccess_flush_fixup);
+
+ instrs[0] = 0x60000000; /* nop */
+ instrs[1] = 0x60000000; /* nop */
+ instrs[2] = 0x60000000; /* nop */
+ instrs[3] = 0x4e800020; /* blr */
+
+ i = 0;
+ if (types == L1D_FLUSH_FALLBACK) {
+ instrs[3] = 0x60000000; /* nop */
+ /* fallthrough to fallback flush */
+ }
+
+ if (types & L1D_FLUSH_ORI) {
+ instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+ instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+ }
+
+ if (types & L1D_FLUSH_MTTRIG)
+ instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+ for (i = 0; start < end; start++, i++) {
+ dest = (void *)start + *start;
+
+ pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+ patch_instruction(dest, instrs[0]);
+
+ patch_instruction((dest + 1), instrs[1]);
+ patch_instruction((dest + 2), instrs[2]);
+ patch_instruction((dest + 3), instrs[3]);
+ }
+
+ printk(KERN_DEBUG "uaccess-flush: patched %d locations (%s flush)\n", i,
+ (types == L1D_FLUSH_NONE) ? "no" :
+ (types == L1D_FLUSH_FALLBACK) ? "fallback displacement" :
+ (types & L1D_FLUSH_ORI) ? (types & L1D_FLUSH_MTTRIG)
+ ? "ori+mttrig type"
+ : "ori type" :
+ (types & L1D_FLUSH_MTTRIG) ? "mttrig type"
+ : "unknown");
+}
+
void do_entry_flush_fixups(enum l1d_flush_type types)
{
unsigned int instrs[3], *dest;
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -126,9 +126,10 @@ static void pnv_setup_rfi_flush(void)
/*
* 4.4 doesn't support Power9 bare metal, so we don't need to flush
- * here - the flush fixes a P9 specific vulnerability.
+ * here - the flushes fix a P9 specific vulnerability.
*/
security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY);
+ security_ftr_clear(SEC_FTR_L1D_FLUSH_UACCESS);
enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \
(security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR) || \
@@ -140,6 +141,10 @@ static void pnv_setup_rfi_flush(void)
enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
setup_entry_flush(enable);
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS);
+ setup_uaccess_flush(enable);
}
static void __init pnv_setup_arch(void)
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -588,6 +588,10 @@ void pseries_setup_rfi_flush(void)
enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
setup_entry_flush(enable);
+
+ enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+ security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS);
+ setup_uaccess_flush(enable);
}
static void __init pSeries_setup_arch(void)
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 09/15] i2c: imx: Fix external abort on interrupt in exit paths
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (7 preceding siblings ...)
2020-11-20 11:03 ` [PATCH 4.4 08/15] powerpc/64s: flush L1D after user accesses Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 10/15] xfs: catch inode allocation state mismatch corruption Greg Kroah-Hartman
` (9 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Krzysztof Kozlowski, Oleksij Rempel,
Wolfram Sang, Sudip Mukherjee
From: Krzysztof Kozlowski <krzk@kernel.org>
commit e50e4f0b85be308a01b830c5fbdffc657e1a6dd0 upstream
If interrupt comes late, during probe error path or device remove (could
be triggered with CONFIG_DEBUG_SHIRQ), the interrupt handler
i2c_imx_isr() will access registers with the clock being disabled. This
leads to external abort on non-linefetch on Toradex Colibri VF50 module
(with Vybrid VF5xx):
Unhandled fault: external abort on non-linefetch (0x1008) at 0x8882d003
Internal error: : 1008 [#1] ARM
Modules linked in:
CPU: 0 PID: 1 Comm: swapper Not tainted 5.7.0 #607
Hardware name: Freescale Vybrid VF5xx/VF6xx (Device Tree)
(i2c_imx_isr) from [<8017009c>] (free_irq+0x25c/0x3b0)
(free_irq) from [<805844ec>] (release_nodes+0x178/0x284)
(release_nodes) from [<80580030>] (really_probe+0x10c/0x348)
(really_probe) from [<80580380>] (driver_probe_device+0x60/0x170)
(driver_probe_device) from [<80580630>] (device_driver_attach+0x58/0x60)
(device_driver_attach) from [<805806bc>] (__driver_attach+0x84/0xc0)
(__driver_attach) from [<8057e228>] (bus_for_each_dev+0x68/0xb4)
(bus_for_each_dev) from [<8057f3ec>] (bus_add_driver+0x144/0x1ec)
(bus_add_driver) from [<80581320>] (driver_register+0x78/0x110)
(driver_register) from [<8010213c>] (do_one_initcall+0xa8/0x2f4)
(do_one_initcall) from [<80c0100c>] (kernel_init_freeable+0x178/0x1dc)
(kernel_init_freeable) from [<80807048>] (kernel_init+0x8/0x110)
(kernel_init) from [<80100114>] (ret_from_fork+0x14/0x20)
Additionally, the i2c_imx_isr() could wake up the wait queue
(imx_i2c_struct->queue) before its initialization happens.
The resource-managed framework should not be used for interrupt handling,
because the resource will be released too late - after disabling clocks.
The interrupt handler is not prepared for such case.
Fixes: 1c4b6c3bcf30 ("i2c: imx: implement bus recovery")
Cc: <stable@vger.kernel.org>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Wolfram Sang <wsa@kernel.org>
[sudip: manual backport with extra label for goto]
Signed-off-by: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/i2c/busses/i2c-imx.c | 25 ++++++++++++++++---------
1 file changed, 16 insertions(+), 9 deletions(-)
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1093,20 +1093,20 @@ static int i2c_imx_probe(struct platform
goto clk_disable;
}
- /* Request IRQ */
- ret = devm_request_irq(&pdev->dev, irq, i2c_imx_isr, 0,
- pdev->name, i2c_imx);
- if (ret) {
- dev_err(&pdev->dev, "can't claim irq %d\n", irq);
- goto clk_disable;
- }
-
/* Init queue */
init_waitqueue_head(&i2c_imx->queue);
/* Set up adapter data */
i2c_set_adapdata(&i2c_imx->adapter, i2c_imx);
+ /* Request IRQ */
+ ret = request_threaded_irq(irq, i2c_imx_isr, NULL, 0,
+ pdev->name, i2c_imx);
+ if (ret) {
+ dev_err(&pdev->dev, "can't claim irq %d\n", irq);
+ goto clk_disable;
+ }
+
/* Set up clock divider */
i2c_imx->bitrate = IMX_I2C_BIT_RATE;
ret = of_property_read_u32(pdev->dev.of_node,
@@ -1125,7 +1125,7 @@ static int i2c_imx_probe(struct platform
ret = i2c_add_numbered_adapter(&i2c_imx->adapter);
if (ret < 0) {
dev_err(&pdev->dev, "registration failed\n");
- goto clk_disable;
+ goto clk_free_irq;
}
/* Set up platform driver data */
@@ -1143,6 +1143,8 @@ static int i2c_imx_probe(struct platform
return 0; /* Return OK */
+clk_free_irq:
+ free_irq(irq, i2c_imx);
clk_disable:
clk_disable_unprepare(i2c_imx->clk);
return ret;
@@ -1151,6 +1153,7 @@ clk_disable:
static int i2c_imx_remove(struct platform_device *pdev)
{
struct imx_i2c_struct *i2c_imx = platform_get_drvdata(pdev);
+ int irq;
/* remove adapter */
dev_dbg(&i2c_imx->adapter.dev, "adapter removed\n");
@@ -1165,6 +1168,10 @@ static int i2c_imx_remove(struct platfor
imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2CR);
imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2SR);
+ irq = platform_get_irq(pdev, 0);
+ if (irq >= 0)
+ free_irq(irq, i2c_imx);
+
return 0;
}
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 10/15] xfs: catch inode allocation state mismatch corruption
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (8 preceding siblings ...)
2020-11-20 11:03 ` [PATCH 4.4 09/15] i2c: imx: Fix external abort on interrupt in exit paths Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 11/15] xfs: validate cached inodes are free when allocated Greg Kroah-Hartman
` (8 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Dave Chinner, Carlos Maiolino,
Darrick J. Wong, Sudip Mukherjee
From: Dave Chinner <dchinner@redhat.com>
commit ee457001ed6c6f31ddad69c24c1da8f377d8472d upstream
We recently came across a V4 filesystem causing memory corruption
due to a newly allocated inode being setup twice and being added to
the superblock inode list twice. From code inspection, the only way
this could happen is if a newly allocated inode was not marked as
free on disk (i.e. di_mode wasn't zero).
Running the metadump on an upstream debug kernel fails during inode
allocation like so:
XFS: Assertion failed: ip->i_d.di_nblocks == 0, file: fs/xfs/xfs_inod=
e.c, line: 838
------------[ cut here ]------------
kernel BUG at fs/xfs/xfs_message.c:114!
invalid opcode: 0000 [#1] PREEMPT SMP
CPU: 11 PID: 3496 Comm: mkdir Not tainted 4.16.0-rc5-dgc #442
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/0=
1/2014
RIP: 0010:assfail+0x28/0x30
RSP: 0018:ffffc9000236fc80 EFLAGS: 00010202
RAX: 00000000ffffffea RBX: 0000000000004000 RCX: 0000000000000000
RDX: 00000000ffffffc0 RSI: 000000000000000a RDI: ffffffff8227211b
RBP: ffffc9000236fce8 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000bec R11: f000000000000000 R12: ffffc9000236fd30
R13: ffff8805c76bab80 R14: ffff8805c77ac800 R15: ffff88083fb12e10
FS: 00007fac8cbff040(0000) GS:ffff88083fd00000(0000) knlGS:0000000000000=
000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fffa6783ff8 CR3: 00000005c6e2b003 CR4: 00000000000606e0
Call Trace:
xfs_ialloc+0x383/0x570
xfs_dir_ialloc+0x6a/0x2a0
xfs_create+0x412/0x670
xfs_generic_create+0x1f7/0x2c0
? capable_wrt_inode_uidgid+0x3f/0x50
vfs_mkdir+0xfb/0x1b0
SyS_mkdir+0xcf/0xf0
do_syscall_64+0x73/0x1a0
entry_SYSCALL_64_after_hwframe+0x42/0xb7
Extracting the inode number we crashed on from an event trace and
looking at it with xfs_db:
xfs_db> inode 184452204
xfs_db> p
core.magic = 0x494e
core.mode = 0100644
core.version = 2
core.format = 2 (extents)
core.nlinkv2 = 1
core.onlink = 0
.....
Confirms that it is not a free inode on disk. xfs_repair
also trips over this inode:
.....
zero length extent (off = 0, fsbno = 0) in ino 184452204
correcting nextents for inode 184452204
bad attribute fork in inode 184452204, would clear attr fork
bad nblocks 1 for inode 184452204, would reset to 0
bad anextents 1 for inode 184452204, would reset to 0
imap claims in-use inode 184452204 is free, would correct imap
would have cleared inode 184452204
.....
disconnected inode 184452204, would move to lost+found
And so we have a situation where the directory structure and the
inobt thinks the inode is free, but the inode on disk thinks it is
still in use. Where this corruption came from is not possible to
diagnose, but we can detect it and prevent the kernel from oopsing
on lookup. The reproducer now results in:
$ sudo mkdir /mnt/scratch/{0,1,2,3,4,5}{0,1,2,3,4,5}
mkdir: cannot create directory =E2=80=98/mnt/scratch/00=E2=80=99: File ex=
ists
mkdir: cannot create directory =E2=80=98/mnt/scratch/01=E2=80=99: File ex=
ists
mkdir: cannot create directory =E2=80=98/mnt/scratch/03=E2=80=99: Structu=
re needs cleaning
mkdir: cannot create directory =E2=80=98/mnt/scratch/04=E2=80=99: Input/o=
utput error
mkdir: cannot create directory =E2=80=98/mnt/scratch/05=E2=80=99: Input/o=
utput error
....
And this corruption shutdown:
[ 54.843517] XFS (loop0): Corruption detected! Free inode 0xafe846c not=
marked free on disk
[ 54.845885] XFS (loop0): Internal error xfs_trans_cancel at line 1023 =
of file fs/xfs/xfs_trans.c. Caller xfs_create+0x425/0x670
[ 54.848994] CPU: 10 PID: 3541 Comm: mkdir Not tainted 4.16.0-rc5-dgc #=
443
[ 54.850753] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIO=
S 1.10.2-1 04/01/2014
[ 54.852859] Call Trace:
[ 54.853531] dump_stack+0x85/0xc5
[ 54.854385] xfs_trans_cancel+0x197/0x1c0
[ 54.855421] xfs_create+0x425/0x670
[ 54.856314] xfs_generic_create+0x1f7/0x2c0
[ 54.857390] ? capable_wrt_inode_uidgid+0x3f/0x50
[ 54.858586] vfs_mkdir+0xfb/0x1b0
[ 54.859458] SyS_mkdir+0xcf/0xf0
[ 54.860254] do_syscall_64+0x73/0x1a0
[ 54.861193] entry_SYSCALL_64_after_hwframe+0x42/0xb7
[ 54.862492] RIP: 0033:0x7fb73bddf547
[ 54.863358] RSP: 002b:00007ffdaa553338 EFLAGS: 00000246 ORIG_RAX: 0000=
000000000053
[ 54.865133] RAX: ffffffffffffffda RBX: 00007ffdaa55449a RCX: 00007fb73=
bddf547
[ 54.866766] RDX: 0000000000000001 RSI: 00000000000001ff RDI: 00007ffda=
a55449a
[ 54.868432] RBP: 00007ffdaa55449a R08: 00000000000001ff R09: 00005623a=
8670dd0
[ 54.870110] R10: 00007fb73be72d5b R11: 0000000000000246 R12: 000000000=
00001ff
[ 54.871752] R13: 00007ffdaa5534b0 R14: 0000000000000000 R15: 00007ffda=
a553500
[ 54.873429] XFS (loop0): xfs_do_force_shutdown(0x8) called from line 1=
024 of file fs/xfs/xfs_trans.c. Return address = ffffffff814cd050
[ 54.882790] XFS (loop0): Corruption of in-memory data detected. Shutt=
ing down filesystem
[ 54.884597] XFS (loop0): Please umount the filesystem and rectify the =
problem(s)
Note that this crash is only possible on v4 filesystemsi or v5
filesystems mounted with the ikeep mount option. For all other V5
filesystems, this problem cannot occur because we don't read inodes
we are allocating from disk - we simply overwrite them with the new
inode information.
Signed-Off-By: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Tested-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
[sudip: use ip->i_d.di_mode instead of VFS_I(ip)->i_mode]
Signed-off-by: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
fs/xfs/xfs_icache.c | 23 ++++++++++++++++++++++-
1 file changed, 22 insertions(+), 1 deletion(-)
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -298,7 +298,28 @@ xfs_iget_cache_miss(
trace_xfs_iget_miss(ip);
- if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
+
+ /*
+ * If we are allocating a new inode, then check what was returned is
+ * actually a free, empty inode. If we are not allocating an inode,
+ * the check we didn't find a free inode.
+ */
+ if (flags & XFS_IGET_CREATE) {
+ if (ip->i_d.di_mode != 0) {
+ xfs_warn(mp,
+"Corruption detected! Free inode 0x%llx not marked free on disk",
+ ino);
+ error = -EFSCORRUPTED;
+ goto out_destroy;
+ }
+ if (ip->i_d.di_nblocks != 0) {
+ xfs_warn(mp,
+"Corruption detected! Free inode 0x%llx has blocks allocated!",
+ ino);
+ error = -EFSCORRUPTED;
+ goto out_destroy;
+ }
+ } else if (ip->i_d.di_mode == 0) {
error = -ENOENT;
goto out_destroy;
}
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 11/15] xfs: validate cached inodes are free when allocated
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (9 preceding siblings ...)
2020-11-20 11:03 ` [PATCH 4.4 10/15] xfs: catch inode allocation state mismatch corruption Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 12/15] powerpc/8xx: Always fault when _PAGE_ACCESSED is not set Greg Kroah-Hartman
` (7 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Wen Xu, Dave Chinner,
Christoph Hellwig, Carlos Maiolino, Darrick J. Wong,
Sudip Mukherjee
From: Dave Chinner <dchinner@redhat.com>
commit afca6c5b2595fc44383919fba740c194b0b76aff upstream
A recent fuzzed filesystem image cached random dcache corruption
when the reproducer was run. This often showed up as panics in
lookup_slow() on a null inode->i_ops pointer when doing pathwalks.
BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
....
Call Trace:
lookup_slow+0x44/0x60
walk_component+0x3dd/0x9f0
link_path_walk+0x4a7/0x830
path_lookupat+0xc1/0x470
filename_lookup+0x129/0x270
user_path_at_empty+0x36/0x40
path_listxattr+0x98/0x110
SyS_listxattr+0x13/0x20
do_syscall_64+0xf5/0x280
entry_SYSCALL_64_after_hwframe+0x42/0xb7
but had many different failure modes including deadlocks trying to
lock the inode that was just allocated or KASAN reports of
use-after-free violations.
The cause of the problem was a corrupt INOBT on a v4 fs where the
root inode was marked as free in the inobt record. Hence when we
allocated an inode, it chose the root inode to allocate, found it in
the cache and re-initialised it.
We recently fixed a similar inode allocation issue caused by inobt
record corruption problem in xfs_iget_cache_miss() in commit
ee457001ed6c ("xfs: catch inode allocation state mismatch
corruption"). This change adds similar checks to the cache-hit path
to catch it, and turns the reproducer into a corruption shutdown
situation.
Reported-by: Wen Xu <wen.xu@gatech.edu>
Signed-Off-By: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
[darrick: fix typos in comment]
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
[sudip: use ip->i_d.di_mode instead of VFS_I(ip)->i_mode]
Signed-off-by: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
fs/xfs/xfs_icache.c | 73 ++++++++++++++++++++++++++++++++++------------------
1 file changed, 48 insertions(+), 25 deletions(-)
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -135,6 +135,46 @@ xfs_inode_free(
}
/*
+ * If we are allocating a new inode, then check what was returned is
+ * actually a free, empty inode. If we are not allocating an inode,
+ * then check we didn't find a free inode.
+ *
+ * Returns:
+ * 0 if the inode free state matches the lookup context
+ * -ENOENT if the inode is free and we are not allocating
+ * -EFSCORRUPTED if there is any state mismatch at all
+ */
+static int
+xfs_iget_check_free_state(
+ struct xfs_inode *ip,
+ int flags)
+{
+ if (flags & XFS_IGET_CREATE) {
+ /* should be a free inode */
+ if (ip->i_d.di_mode != 0) {
+ xfs_warn(ip->i_mount,
+"Corruption detected! Free inode 0x%llx not marked free! (mode 0x%x)",
+ ip->i_ino, ip->i_d.di_mode);
+ return -EFSCORRUPTED;
+ }
+
+ if (ip->i_d.di_nblocks != 0) {
+ xfs_warn(ip->i_mount,
+"Corruption detected! Free inode 0x%llx has blocks allocated!",
+ ip->i_ino);
+ return -EFSCORRUPTED;
+ }
+ return 0;
+ }
+
+ /* should be an allocated inode */
+ if (ip->i_d.di_mode == 0)
+ return -ENOENT;
+
+ return 0;
+}
+
+/*
* Check the validity of the inode we just found it the cache
*/
static int
@@ -183,12 +223,12 @@ xfs_iget_cache_hit(
}
/*
- * If lookup is racing with unlink return an error immediately.
+ * Check the inode free state is valid. This also detects lookup
+ * racing with unlinks.
*/
- if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
- error = -ENOENT;
+ error = xfs_iget_check_free_state(ip, flags);
+ if (error)
goto out_error;
- }
/*
* If IRECLAIMABLE is set, we've torn down the VFS inode already.
@@ -300,29 +340,12 @@ xfs_iget_cache_miss(
/*
- * If we are allocating a new inode, then check what was returned is
- * actually a free, empty inode. If we are not allocating an inode,
- * the check we didn't find a free inode.
+ * Check the inode free state is valid. This also detects lookup
+ * racing with unlinks.
*/
- if (flags & XFS_IGET_CREATE) {
- if (ip->i_d.di_mode != 0) {
- xfs_warn(mp,
-"Corruption detected! Free inode 0x%llx not marked free on disk",
- ino);
- error = -EFSCORRUPTED;
- goto out_destroy;
- }
- if (ip->i_d.di_nblocks != 0) {
- xfs_warn(mp,
-"Corruption detected! Free inode 0x%llx has blocks allocated!",
- ino);
- error = -EFSCORRUPTED;
- goto out_destroy;
- }
- } else if (ip->i_d.di_mode == 0) {
- error = -ENOENT;
+ error = xfs_iget_check_free_state(ip, flags);
+ if (error)
goto out_destroy;
- }
/*
* Preload the radix tree so we can insert safely under the
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 12/15] powerpc/8xx: Always fault when _PAGE_ACCESSED is not set
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (10 preceding siblings ...)
2020-11-20 11:03 ` [PATCH 4.4 11/15] xfs: validate cached inodes are free when allocated Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 13/15] Input: sunkbd - avoid use-after-free in teardown paths Greg Kroah-Hartman
` (6 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Christophe Leroy, Michael Ellerman
From: Christophe Leroy <christophe.leroy@csgroup.eu>
commit 29daf869cbab69088fe1755d9dd224e99ba78b56 upstream.
The kernel expects pte_young() to work regardless of CONFIG_SWAP.
Make sure a minor fault is taken to set _PAGE_ACCESSED when it
is not already set, regardless of the selection of CONFIG_SWAP.
This adds at least 3 instructions to the TLB miss exception
handlers fast path. Following patch will reduce this overhead.
Also update the rotation instruction to the correct number of bits
to reflect all changes done to _PAGE_ACCESSED over time.
Fixes: d069cb4373fe ("powerpc/8xx: Don't touch ACCESSED when no SWAP.")
Fixes: 5f356497c384 ("powerpc/8xx: remove unused _PAGE_WRITETHRU")
Fixes: e0a8e0d90a9f ("powerpc/8xx: Handle PAGE_USER via APG bits")
Fixes: 5b2753fc3e8a ("powerpc/8xx: Implementation of PAGE_EXEC")
Fixes: a891c43b97d3 ("powerpc/8xx: Prepare handlers for _PAGE_HUGE for 512k pages.")
Cc: stable@vger.kernel.org
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/af834e8a0f1fa97bfae65664950f0984a70c4750.1602492856.git.christophe.leroy@csgroup.eu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/powerpc/kernel/head_8xx.S | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -361,11 +361,9 @@ InstructionTLBMiss:
/* Load the MI_TWC with the attributes for this "segment." */
MTSPR_CPU6(SPRN_MI_TWC, r11, r3) /* Set segment attributes */
-#ifdef CONFIG_SWAP
- rlwinm r11, r10, 32-5, _PAGE_PRESENT
+ rlwinm r11, r10, 32-11, _PAGE_PRESENT
and r11, r11, r10
rlwimi r10, r11, 0, _PAGE_PRESENT
-#endif
li r11, RPN_PATTERN
/* The Linux PTE won't go exactly into the MMU TLB.
* Software indicator bits 20-23 and 28 must be clear.
@@ -436,11 +434,9 @@ DataStoreTLBMiss:
* r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5));
* r10 = (r10 & ~PRESENT) | r11;
*/
-#ifdef CONFIG_SWAP
- rlwinm r11, r10, 32-5, _PAGE_PRESENT
+ rlwinm r11, r10, 32-11, _PAGE_PRESENT
and r11, r11, r10
rlwimi r10, r11, 0, _PAGE_PRESENT
-#endif
/* The Linux PTE won't go exactly into the MMU TLB.
* Software indicator bits 22 and 28 must be clear.
* Software indicator bits 24, 25, 26, and 27 must be
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 13/15] Input: sunkbd - avoid use-after-free in teardown paths
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (11 preceding siblings ...)
2020-11-20 11:03 ` [PATCH 4.4 12/15] powerpc/8xx: Always fault when _PAGE_ACCESSED is not set Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 14/15] mac80211: always wind down STA state Greg Kroah-Hartman
` (5 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel; +Cc: Greg Kroah-Hartman, stable, Bodong Zhao, Dmitry Torokhov
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
commit 77e70d351db7de07a46ac49b87a6c3c7a60fca7e upstream.
We need to make sure we cancel the reinit work before we tear down the
driver structures.
Reported-by: Bodong Zhao <nopitydays@gmail.com>
Tested-by: Bodong Zhao <nopitydays@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
drivers/input/keyboard/sunkbd.c | 41 ++++++++++++++++++++++++++++++++--------
1 file changed, 33 insertions(+), 8 deletions(-)
--- a/drivers/input/keyboard/sunkbd.c
+++ b/drivers/input/keyboard/sunkbd.c
@@ -115,7 +115,8 @@ static irqreturn_t sunkbd_interrupt(stru
switch (data) {
case SUNKBD_RET_RESET:
- schedule_work(&sunkbd->tq);
+ if (sunkbd->enabled)
+ schedule_work(&sunkbd->tq);
sunkbd->reset = -1;
break;
@@ -216,16 +217,12 @@ static int sunkbd_initialize(struct sunk
}
/*
- * sunkbd_reinit() sets leds and beeps to a state the computer remembers they
- * were in.
+ * sunkbd_set_leds_beeps() sets leds and beeps to a state the computer remembers
+ * they were in.
*/
-static void sunkbd_reinit(struct work_struct *work)
+static void sunkbd_set_leds_beeps(struct sunkbd *sunkbd)
{
- struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq);
-
- wait_event_interruptible_timeout(sunkbd->wait, sunkbd->reset >= 0, HZ);
-
serio_write(sunkbd->serio, SUNKBD_CMD_SETLED);
serio_write(sunkbd->serio,
(!!test_bit(LED_CAPSL, sunkbd->dev->led) << 3) |
@@ -238,11 +235,39 @@ static void sunkbd_reinit(struct work_st
SUNKBD_CMD_BELLOFF - !!test_bit(SND_BELL, sunkbd->dev->snd));
}
+
+/*
+ * sunkbd_reinit() wait for the keyboard reset to complete and restores state
+ * of leds and beeps.
+ */
+
+static void sunkbd_reinit(struct work_struct *work)
+{
+ struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq);
+
+ /*
+ * It is OK that we check sunkbd->enabled without pausing serio,
+ * as we only want to catch true->false transition that will
+ * happen once and we will be woken up for it.
+ */
+ wait_event_interruptible_timeout(sunkbd->wait,
+ sunkbd->reset >= 0 || !sunkbd->enabled,
+ HZ);
+
+ if (sunkbd->reset >= 0 && sunkbd->enabled)
+ sunkbd_set_leds_beeps(sunkbd);
+}
+
static void sunkbd_enable(struct sunkbd *sunkbd, bool enable)
{
serio_pause_rx(sunkbd->serio);
sunkbd->enabled = enable;
serio_continue_rx(sunkbd->serio);
+
+ if (!enable) {
+ wake_up_interruptible(&sunkbd->wait);
+ cancel_work_sync(&sunkbd->tq);
+ }
}
/*
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 14/15] mac80211: always wind down STA state
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (12 preceding siblings ...)
2020-11-20 11:03 ` [PATCH 4.4 13/15] Input: sunkbd - avoid use-after-free in teardown paths Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:03 ` [PATCH 4.4 15/15] KVM: x86: clflushopt should be treated as a no-op by emulation Greg Kroah-Hartman
` (4 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, syzbot+2e293dbd67de2836ba42, Johannes Berg
From: Johannes Berg <johannes.berg@intel.com>
commit dcd479e10a0510522a5d88b29b8f79ea3467d501 upstream.
When (for example) an IBSS station is pre-moved to AUTHORIZED
before it's inserted, and then the insertion fails, we don't
clean up the fast RX/TX states that might already have been
created, since we don't go through all the state transitions
again on the way down.
Do that, if it hasn't been done already, when the station is
freed. I considered only freeing the fast TX/RX state there,
but we might add more state so it's more robust to wind down
the state properly.
Note that we warn if the station was ever inserted, it should
have been properly cleaned up in that case, and the driver
will probably not like things happening out of order.
Reported-by: syzbot+2e293dbd67de2836ba42@syzkaller.appspotmail.com
Link: https://lore.kernel.org/r/20201009141710.7223b322a955.I95bd08b9ad0e039c034927cce0b75beea38e059b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
net/mac80211/sta_info.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -242,6 +242,24 @@ struct sta_info *sta_info_get_by_idx(str
*/
void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
{
+ /*
+ * If we had used sta_info_pre_move_state() then we might not
+ * have gone through the state transitions down again, so do
+ * it here now (and warn if it's inserted).
+ *
+ * This will clear state such as fast TX/RX that may have been
+ * allocated during state transitions.
+ */
+ while (sta->sta_state > IEEE80211_STA_NONE) {
+ int ret;
+
+ WARN_ON_ONCE(test_sta_flag(sta, WLAN_STA_INSERTED));
+
+ ret = sta_info_move_state(sta, sta->sta_state - 1);
+ if (WARN_ONCE(ret, "sta_info_move_state() returned %d\n", ret))
+ break;
+ }
+
if (sta->rate_ctrl)
rate_control_free_sta(sta);
^ permalink raw reply [flat|nested] 22+ messages in thread* [PATCH 4.4 15/15] KVM: x86: clflushopt should be treated as a no-op by emulation
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (13 preceding siblings ...)
2020-11-20 11:03 ` [PATCH 4.4 14/15] mac80211: always wind down STA state Greg Kroah-Hartman
@ 2020-11-20 11:03 ` Greg Kroah-Hartman
2020-11-20 11:40 ` [PATCH 4.4 00/15] 4.4.245-rc1 review Pavel Machek
` (3 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-20 11:03 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, David Edmondson, Joao Martins, Paolo Bonzini
From: David Edmondson <david.edmondson@oracle.com>
commit 51b958e5aeb1e18c00332e0b37c5d4e95a3eff84 upstream.
The instruction emulator ignores clflush instructions, yet fails to
support clflushopt. Treat both similarly.
Fixes: 13e457e0eebf ("KVM: x86: Emulator does not decode clflush well")
Signed-off-by: David Edmondson <david.edmondson@oracle.com>
Message-Id: <20201103120400.240882-1-david.edmondson@oracle.com>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/x86/kvm/emulate.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3922,6 +3922,12 @@ static int em_clflush(struct x86_emulate
return X86EMUL_CONTINUE;
}
+static int em_clflushopt(struct x86_emulate_ctxt *ctxt)
+{
+ /* emulating clflushopt regardless of cpuid */
+ return X86EMUL_CONTINUE;
+}
+
static int em_movsxd(struct x86_emulate_ctxt *ctxt)
{
ctxt->dst.val = (s32) ctxt->src.val;
@@ -4411,7 +4417,7 @@ static const struct opcode group11[] = {
};
static const struct gprefix pfx_0f_ae_7 = {
- I(SrcMem | ByteOp, em_clflush), N, N, N,
+ I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N,
};
static const struct group_dual group15 = { {
^ permalink raw reply [flat|nested] 22+ messages in thread* Re: [PATCH 4.4 00/15] 4.4.245-rc1 review
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (14 preceding siblings ...)
2020-11-20 11:03 ` [PATCH 4.4 15/15] KVM: x86: clflushopt should be treated as a no-op by emulation Greg Kroah-Hartman
@ 2020-11-20 11:40 ` Pavel Machek
2020-11-20 22:40 ` Shuah Khan
` (2 subsequent siblings)
18 siblings, 0 replies; 22+ messages in thread
From: Pavel Machek @ 2020-11-20 11:40 UTC (permalink / raw)
To: Greg Kroah-Hartman
Cc: linux-kernel, torvalds, akpm, linux, shuah, patches, lkft-triage,
pavel, stable
[-- Attachment #1: Type: text/plain, Size: 728 bytes --]
Hi!
> This is the start of the stable review cycle for the 4.4.245 release.
> There are 15 patches in this series, all will be posted as a response
> to this one. If anyone has any issues with these being applied, please
> let me know.
>
> Responses should be made by Sun, 22 Nov 2020 10:45:32 +0000.
> Anything received after that time might be too late.
CIP testing did not find any problems here:
https://gitlab.com/cip-project/cip-testing/linux-stable-rc-ci/-/tree/linux-4.4.y
Tested-by: Pavel Machek (CIP) <pavel@denx.de>
Best regards,
Pavel
--
DENX Software Engineering GmbH, Managing Director: Wolfgang Denk
HRB 165235 Munich, Office: Kirchenstr.5, D-82194 Groebenzell, Germany
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 195 bytes --]
^ permalink raw reply [flat|nested] 22+ messages in thread* Re: [PATCH 4.4 00/15] 4.4.245-rc1 review
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (15 preceding siblings ...)
2020-11-20 11:40 ` [PATCH 4.4 00/15] 4.4.245-rc1 review Pavel Machek
@ 2020-11-20 22:40 ` Shuah Khan
2020-11-21 18:29 ` Guenter Roeck
2020-11-22 10:07 ` Naresh Kamboju
18 siblings, 0 replies; 22+ messages in thread
From: Shuah Khan @ 2020-11-20 22:40 UTC (permalink / raw)
To: Greg Kroah-Hartman, linux-kernel
Cc: torvalds, akpm, linux, shuah, patches, lkft-triage, pavel, stable, skhan
On 11/20/20 4:02 AM, Greg Kroah-Hartman wrote:
> This is the start of the stable review cycle for the 4.4.245 release.
> There are 15 patches in this series, all will be posted as a response
> to this one. If anyone has any issues with these being applied, please
> let me know.
>
> Responses should be made by Sun, 22 Nov 2020 10:45:32 +0000.
> Anything received after that time might be too late.
>
> The whole patch series can be found in one patch at:
> https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.4.245-rc1.gz
> or in the git tree and branch at:
> git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.4.y
> and the diffstat can be found below.
>
> thanks,
>
> greg k-h
>
Compiled and booted on my test system. No dmesg regressions.
Tested-by: Shuah Khan <skhan@linuxfoundation.org>
thanks,
-- Shuah
^ permalink raw reply [flat|nested] 22+ messages in thread* Re: [PATCH 4.4 00/15] 4.4.245-rc1 review
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (16 preceding siblings ...)
2020-11-20 22:40 ` Shuah Khan
@ 2020-11-21 18:29 ` Guenter Roeck
2020-11-22 8:00 ` Greg Kroah-Hartman
2020-11-22 10:07 ` Naresh Kamboju
18 siblings, 1 reply; 22+ messages in thread
From: Guenter Roeck @ 2020-11-21 18:29 UTC (permalink / raw)
To: Greg Kroah-Hartman
Cc: linux-kernel, torvalds, akpm, shuah, patches, lkft-triage, pavel, stable
On Fri, Nov 20, 2020 at 12:02:58PM +0100, Greg Kroah-Hartman wrote:
> This is the start of the stable review cycle for the 4.4.245 release.
> There are 15 patches in this series, all will be posted as a response
> to this one. If anyone has any issues with these being applied, please
> let me know.
>
> Responses should be made by Sun, 22 Nov 2020 10:45:32 +0000.
> Anything received after that time might be too late.
>
Build results:
total: 165 pass: 164 fail: 1
Failed builds:
powerpc:ppc64e_defconfig
Qemu test results:
total: 328 pass: 323 fail: 5
Failed tests:
ppc64:ppce500:corenet64_smp_defconfig:e5500:initrd
ppc64:ppce500:corenet64_smp_defconfig:e5500:nvme:rootfs
ppc64:ppce500:corenet64_smp_defconfig:e5500:sdhci:mmc:rootfs
ppc64:ppce500:corenet64_smp_defconfig:e5500:scsi[53C895A]:rootfs
ppc64:ppce500:corenet64_smp_defconfig:e5500:sata-sii3112:rootfs
Failure in all cases is:
In file included from arch/powerpc/kernel/ppc_ksyms.c:10:0:
arch/powerpc/include/asm/book3s/64/kup-radix.h:11:29: error: redefinition of ‘allow_user_access’
static __always_inline void allow_user_access(void __user *to, const void __user *from,
^~~~~~~~~~~~~~~~~
In file included from arch/powerpc/include/asm/uaccess.h:12:0,
from arch/powerpc/kernel/ppc_ksyms.c:8:
arch/powerpc/include/asm/kup.h:12:20: note: previous definition of ‘allow_user_access’ was here
static inline void allow_user_access(void __user *to, const void __user *from,
^~~~~~~~~~~~~~~~~
In file included from arch/powerpc/kernel/ppc_ksyms.c:10:0:
arch/powerpc/include/asm/book3s/64/kup-radix.h:16:20: error: redefinition of ‘prevent_user_access’
static inline void prevent_user_access(void __user *to, const void __user *from,
^~~~~~~~~~~~~~~~~~~
In file included from arch/powerpc/include/asm/uaccess.h:12:0,
from arch/powerpc/kernel/ppc_ksyms.c:8:
arch/powerpc/include/asm/kup.h:14:20: note: previous definition of ‘prevent_user_access’ was here
static inline void prevent_user_access(void __user *to, const void __user *from,
^~~~~~~~~~~~~~~~~~~
Tested-by: Guenter Roeck <linux@roeck-us.net>
Guenter
^ permalink raw reply [flat|nested] 22+ messages in thread* Re: [PATCH 4.4 00/15] 4.4.245-rc1 review
2020-11-21 18:29 ` Guenter Roeck
@ 2020-11-22 8:00 ` Greg Kroah-Hartman
2020-11-23 2:40 ` Daniel Axtens
0 siblings, 1 reply; 22+ messages in thread
From: Greg Kroah-Hartman @ 2020-11-22 8:00 UTC (permalink / raw)
To: Daniel Axtens, Guenter Roeck
Cc: linux-kernel, torvalds, akpm, shuah, patches, lkft-triage, pavel, stable
On Sat, Nov 21, 2020 at 10:29:03AM -0800, Guenter Roeck wrote:
> On Fri, Nov 20, 2020 at 12:02:58PM +0100, Greg Kroah-Hartman wrote:
> > This is the start of the stable review cycle for the 4.4.245 release.
> > There are 15 patches in this series, all will be posted as a response
> > to this one. If anyone has any issues with these being applied, please
> > let me know.
> >
> > Responses should be made by Sun, 22 Nov 2020 10:45:32 +0000.
> > Anything received after that time might be too late.
> >
> Build results:
> total: 165 pass: 164 fail: 1
> Failed builds:
> powerpc:ppc64e_defconfig
> Qemu test results:
> total: 328 pass: 323 fail: 5
> Failed tests:
> ppc64:ppce500:corenet64_smp_defconfig:e5500:initrd
> ppc64:ppce500:corenet64_smp_defconfig:e5500:nvme:rootfs
> ppc64:ppce500:corenet64_smp_defconfig:e5500:sdhci:mmc:rootfs
> ppc64:ppce500:corenet64_smp_defconfig:e5500:scsi[53C895A]:rootfs
> ppc64:ppce500:corenet64_smp_defconfig:e5500:sata-sii3112:rootfs
>
> Failure in all cases is:
>
> In file included from arch/powerpc/kernel/ppc_ksyms.c:10:0:
> arch/powerpc/include/asm/book3s/64/kup-radix.h:11:29: error: redefinition of ‘allow_user_access’
> static __always_inline void allow_user_access(void __user *to, const void __user *from,
> ^~~~~~~~~~~~~~~~~
> In file included from arch/powerpc/include/asm/uaccess.h:12:0,
> from arch/powerpc/kernel/ppc_ksyms.c:8:
> arch/powerpc/include/asm/kup.h:12:20: note: previous definition of ‘allow_user_access’ was here
> static inline void allow_user_access(void __user *to, const void __user *from,
> ^~~~~~~~~~~~~~~~~
> In file included from arch/powerpc/kernel/ppc_ksyms.c:10:0:
> arch/powerpc/include/asm/book3s/64/kup-radix.h:16:20: error: redefinition of ‘prevent_user_access’
> static inline void prevent_user_access(void __user *to, const void __user *from,
> ^~~~~~~~~~~~~~~~~~~
> In file included from arch/powerpc/include/asm/uaccess.h:12:0,
> from arch/powerpc/kernel/ppc_ksyms.c:8:
> arch/powerpc/include/asm/kup.h:14:20: note: previous definition of ‘prevent_user_access’ was here
> static inline void prevent_user_access(void __user *to, const void __user *from,
> ^~~~~~~~~~~~~~~~~~~
>
> Tested-by: Guenter Roeck <linux@roeck-us.net>
Thanks for testing these.
Daniel, looks like your patches broke some configurations on powerpc as
shown above. Care to send a fix-up patch for these?
thanks,
greg k-h
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH 4.4 00/15] 4.4.245-rc1 review
2020-11-22 8:00 ` Greg Kroah-Hartman
@ 2020-11-23 2:40 ` Daniel Axtens
0 siblings, 0 replies; 22+ messages in thread
From: Daniel Axtens @ 2020-11-23 2:40 UTC (permalink / raw)
To: Greg Kroah-Hartman, Guenter Roeck
Cc: linux-kernel, torvalds, akpm, shuah, patches, lkft-triage, pavel, stable
Hi,
>> Build results:
>> total: 165 pass: 164 fail: 1
>> Failed builds:
>> powerpc:ppc64e_defconfig
>> Qemu test results:
>> total: 328 pass: 323 fail: 5
>> Failed tests:
>> ppc64:ppce500:corenet64_smp_defconfig:e5500:initrd
>> ppc64:ppce500:corenet64_smp_defconfig:e5500:nvme:rootfs
>> ppc64:ppce500:corenet64_smp_defconfig:e5500:sdhci:mmc:rootfs
>> ppc64:ppce500:corenet64_smp_defconfig:e5500:scsi[53C895A]:rootfs
>> ppc64:ppce500:corenet64_smp_defconfig:e5500:sata-sii3112:rootfs
>>
>> Failure in all cases is:
>>
>> In file included from arch/powerpc/kernel/ppc_ksyms.c:10:0:
>> arch/powerpc/include/asm/book3s/64/kup-radix.h:11:29: error: redefinition of ‘allow_user_access’
>> static __always_inline void allow_user_access(void __user *to, const void __user *from,
>> ^~~~~~~~~~~~~~~~~
>> In file included from arch/powerpc/include/asm/uaccess.h:12:0,
>> from arch/powerpc/kernel/ppc_ksyms.c:8:
>> arch/powerpc/include/asm/kup.h:12:20: note: previous definition of ‘allow_user_access’ was here
>> static inline void allow_user_access(void __user *to, const void __user *from,
>> ^~~~~~~~~~~~~~~~~
>> In file included from arch/powerpc/kernel/ppc_ksyms.c:10:0:
>> arch/powerpc/include/asm/book3s/64/kup-radix.h:16:20: error: redefinition of ‘prevent_user_access’
>> static inline void prevent_user_access(void __user *to, const void __user *from,
>> ^~~~~~~~~~~~~~~~~~~
>> In file included from arch/powerpc/include/asm/uaccess.h:12:0,
>> from arch/powerpc/kernel/ppc_ksyms.c:8:
>> arch/powerpc/include/asm/kup.h:14:20: note: previous definition of ‘prevent_user_access’ was here
>> static inline void prevent_user_access(void __user *to, const void __user *from,
>> ^~~~~~~~~~~~~~~~~~~
>>
>> Tested-by: Guenter Roeck <linux@roeck-us.net>
>
> Thanks for testing these.
>
> Daniel, looks like your patches broke some configurations on powerpc as
> shown above. Care to send a fix-up patch for these?
Will do. I tested ppc64e_defconfig but clearly that wasn't comprehensive
enough.
Kind regards,
Daniel
^ permalink raw reply [flat|nested] 22+ messages in thread
* Re: [PATCH 4.4 00/15] 4.4.245-rc1 review
2020-11-20 11:02 [PATCH 4.4 00/15] 4.4.245-rc1 review Greg Kroah-Hartman
` (17 preceding siblings ...)
2020-11-21 18:29 ` Guenter Roeck
@ 2020-11-22 10:07 ` Naresh Kamboju
18 siblings, 0 replies; 22+ messages in thread
From: Naresh Kamboju @ 2020-11-22 10:07 UTC (permalink / raw)
To: Greg Kroah-Hartman
Cc: open list, Shuah Khan, patches, lkft-triage, linux-stable, pavel,
Andrew Morton, Linus Torvalds, Guenter Roeck
On Fri, 20 Nov 2020 at 16:33, Greg Kroah-Hartman
<gregkh@linuxfoundation.org> wrote:
>
> This is the start of the stable review cycle for the 4.4.245 release.
> There are 15 patches in this series, all will be posted as a response
> to this one. If anyone has any issues with these being applied, please
> let me know.
>
> Responses should be made by Sun, 22 Nov 2020 10:45:32 +0000.
> Anything received after that time might be too late.
>
> The whole patch series can be found in one patch at:
> https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.4.245-rc1.gz
> or in the git tree and branch at:
> git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.4.y
> and the diffstat can be found below.
>
> thanks,
>
> greg k-h
Results from Linaro’s test farm.
No regressions on arm64, arm, x86_64, and i386.
Tested-by: Linux Kernel Functional Testing <lkft@linaro.org>
Summary
------------------------------------------------------------------------
kernel: 4.4.245-rc1
git repo: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git
git branch: linux-4.4.y
git commit: 11095ab90e22ac875983239a445f6b4ad64b6e08
git describe: v4.4.244-16-g11095ab90e22
Test details: https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-4.4.y/build/v4.4.244-16-g11095ab90e22
No regressions (compared to build v4.4.244)
No fixes (compared to build v4.4.244)
Ran 32775 total tests in the following environments and test suites.
Environments
--------------
- i386
- juno-r2 - arm64
- juno-r2-compat
- juno-r2-kasan
- qemu-arm64-clang
- qemu-arm64-kasan
- qemu-x86_64-clang
- qemu-x86_64-kasan
- qemu_arm
- qemu_arm64
- qemu_arm64-compat
- qemu_i386
- qemu_x86_64
- qemu_x86_64-compat
- x15 - arm
- x86_64
- x86-kasan
Test Suites
-----------
* build
* libhugetlbfs
* linux-log-parser
* ltp-cap_bounds-tests
* ltp-commands-tests
* ltp-containers-tests
* ltp-controllers-tests
* ltp-cpuhotplug-tests
* ltp-crypto-tests
* ltp-cve-tests
* ltp-dio-tests
* ltp-fcntl-locktests-tests
* ltp-filecaps-tests
* ltp-fs-tests
* ltp-fs_bind-tests
* ltp-fs_perms_simple-tests
* ltp-fsx-tests
* ltp-hugetlb-tests
* ltp-io-tests
* ltp-ipc-tests
* ltp-math-tests
* ltp-mm-tests
* ltp-nptl-tests
* ltp-open-posix-tests
* ltp-pty-tests
* ltp-sched-tests
* ltp-securebits-tests
* ltp-syscalls-tests
* network-basic-tests
* perf
* v4l2-compliance
* kvm-unit-tests
* ltp-tracing-tests
* install-android-platform-tools-r2600
Summary
------------------------------------------------------------------------
kernel: 4.4.245-rc1
git repo: https://git.linaro.org/lkft/arm64-stable-rc.git
git branch: 4.4.245-rc1-hikey-20201120-861
git commit: a395e149575bc8d8ec23a677f979301bfefd8862
git describe: 4.4.245-rc1-hikey-20201120-861
Test details: https://qa-reports.linaro.org/lkft/linaro-hikey-stable-rc-4.4-oe/build/4.4.245-rc1-hikey-20201120-861
No regressions (compared to build 4.4.244-rc1-hikey-20201117-859)
No fixes (compared to build 4.4.244-rc1-hikey-20201117-859)
Ran 1722 total tests in the following environments and test suites.
Environments
--------------
- hi6220-hikey - arm64
Test Suites
-----------
* build
* install-android-platform-tools-r2600
* libhugetlbfs
* linux-log-parser
* ltp-cap_bounds-tests
* ltp-commands-tests
* ltp-containers-tests
* ltp-cpuhotplug-tests
* ltp-cve-tests
* ltp-dio-tests
* ltp-fcntl-locktests-tests
* ltp-filecaps-tests
* ltp-fs-tests
* ltp-fs_bind-tests
* ltp-fs_perms_simple-tests
* ltp-fsx-tests
* ltp-hugetlb-tests
* ltp-io-tests
* ltp-ipc-tests
* ltp-math-tests
* ltp-nptl-tests
* ltp-pty-tests
* ltp-sched-tests
* ltp-securebits-tests
* ltp-syscalls-tests
* perf
* spectre-meltdown-checker-test
* v4l2-compliance
--
Linaro LKFT
https://lkft.linaro.org
^ permalink raw reply [flat|nested] 22+ messages in thread