Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux
Pull arm64 updates from Will Deacon:
"Mostly just incremental improvements here:
- Introduce AT_HWCAP2 for advertising CPU features to userspace
- Expose SVE2 availability to userspace
- Support for "data cache clean to point of deep persistence" (DC PODP)
- Honour "mitigations=off" on the cmdline and advertise status via
sysfs
- CPU timer erratum workaround (Neoverse-N1 #1188873)
- Introduce perf PMU driver for the SMMUv3 performance counters
- Add config option to disable the kuser helpers page for AArch32 tasks
- Futex modifications to ensure liveness under contention
- Rework debug exception handling to seperate kernel and user
handlers
- Non-critical fixes and cleanup"
* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (92 commits)
Documentation: Add ARM64 to kernel-parameters.rst
arm64/speculation: Support 'mitigations=' cmdline option
arm64: ssbs: Don't treat CPUs with SSBS as unaffected by SSB
arm64: enable generic CPU vulnerabilites support
arm64: add sysfs vulnerability show for speculative store bypass
arm64: Fix size of __early_cpu_boot_status
clocksource/arm_arch_timer: Use arch_timer_read_counter to access stable counters
clocksource/arm_arch_timer: Remove use of workaround static key
clocksource/arm_arch_timer: Drop use of static key in arch_timer_reg_read_stable
clocksource/arm_arch_timer: Direcly assign set_next_event workaround
arm64: Use arch_timer_read_counter instead of arch_counter_get_cntvct
watchdog/sbsa: Use arch_timer_read_counter instead of arch_counter_get_cntvct
ARM: vdso: Remove dependency with the arch_timer driver internals
arm64: Apply ARM64_ERRATUM_1188873 to Neoverse-N1
arm64: Add part number for Neoverse N1
arm64: Make ARM64_ERRATUM_1188873 depend on COMPAT
arm64: Restrict ARM64_ERRATUM_1188873 mitigation to AArch32
arm64: mm: Remove pte_unmap_nested()
arm64: Fix compiler warning from pte_unmap() with -Wunused-but-set-variable
arm64: compat: Reduce address limit for 64K pages
...
diff --git a/Documentation/admin-guide/kernel-parameters.rst b/Documentation/admin-guide/kernel-parameters.rst
index b8d0bc0..0124980d 100644
--- a/Documentation/admin-guide/kernel-parameters.rst
+++ b/Documentation/admin-guide/kernel-parameters.rst
@@ -88,6 +88,7 @@
APIC APIC support is enabled.
APM Advanced Power Management support is enabled.
ARM ARM architecture is enabled.
+ ARM64 ARM64 architecture is enabled.
AX25 Appropriate AX.25 support is enabled.
CLK Common clock infrastructure is enabled.
CMA Contiguous Memory Area support is enabled.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 3c0646e..fd03e2b 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2548,8 +2548,8 @@
http://repo.or.cz/w/linux-2.6/mini2440.git
mitigations=
- [X86,PPC,S390] Control optional mitigations for CPU
- vulnerabilities. This is a set of curated,
+ [X86,PPC,S390,ARM64] Control optional mitigations for
+ CPU vulnerabilities. This is a set of curated,
arch-independent options, each of which is an
aggregation of existing arch-specific options.
@@ -2558,11 +2558,13 @@
improves system performance, but it may also
expose users to several CPU vulnerabilities.
Equivalent to: nopti [X86,PPC]
+ kpti=0 [ARM64]
nospectre_v1 [PPC]
nobp=0 [S390]
- nospectre_v2 [X86,PPC,S390]
+ nospectre_v2 [X86,PPC,S390,ARM64]
spectre_v2_user=off [X86]
spec_store_bypass_disable=off [X86,PPC]
+ ssbd=force-off [ARM64]
l1tf=off [X86]
auto (default)
@@ -2908,10 +2910,10 @@
check bypass). With this option data leaks are possible
in the system.
- nospectre_v2 [X86,PPC_FSL_BOOK3E] Disable all mitigations for the Spectre variant 2
- (indirect branch prediction) vulnerability. System may
- allow data leaks with this option, which is equivalent
- to spectre_v2=off.
+ nospectre_v2 [X86,PPC_FSL_BOOK3E,ARM64] Disable all mitigations for
+ the Spectre variant 2 (indirect branch prediction)
+ vulnerability. System may allow data leaks with this
+ option.
nospec_store_bypass_disable
[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
diff --git a/Documentation/arm64/cpu-feature-registers.txt b/Documentation/arm64/cpu-feature-registers.txt
index d4b4dd1f..684a0da 100644
--- a/Documentation/arm64/cpu-feature-registers.txt
+++ b/Documentation/arm64/cpu-feature-registers.txt
@@ -209,6 +209,22 @@
| AT | [35-32] | y |
x--------------------------------------------------x
+ 6) ID_AA64ZFR0_EL1 - SVE feature ID register 0
+
+ x--------------------------------------------------x
+ | Name | bits | visible |
+ |--------------------------------------------------|
+ | SM4 | [43-40] | y |
+ |--------------------------------------------------|
+ | SHA3 | [35-32] | y |
+ |--------------------------------------------------|
+ | BitPerm | [19-16] | y |
+ |--------------------------------------------------|
+ | AES | [7-4] | y |
+ |--------------------------------------------------|
+ | SVEVer | [3-0] | y |
+ x--------------------------------------------------x
+
Appendix I: Example
---------------------------
diff --git a/Documentation/arm64/elf_hwcaps.txt b/Documentation/arm64/elf_hwcaps.txt
index 13d6691..b73a251 100644
--- a/Documentation/arm64/elf_hwcaps.txt
+++ b/Documentation/arm64/elf_hwcaps.txt
@@ -13,9 +13,9 @@
kernel exposes the presence of these features to userspace through a set
of flags called hwcaps, exposed in the auxilliary vector.
-Userspace software can test for features by acquiring the AT_HWCAP entry
-of the auxilliary vector, and testing whether the relevant flags are
-set, e.g.
+Userspace software can test for features by acquiring the AT_HWCAP or
+AT_HWCAP2 entry of the auxiliary vector, and testing whether the relevant
+flags are set, e.g.
bool floating_point_is_present(void)
{
@@ -135,6 +135,10 @@
Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0001.
+HWCAP2_DCPODP
+
+ Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010.
+
HWCAP_SHA3
Functionality implied by ID_AA64ISAR0_EL1.SHA3 == 0b0001.
@@ -159,6 +163,30 @@
Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001.
+HWCAP2_SVE2
+
+ Functionality implied by ID_AA64ZFR0_EL1.SVEVer == 0b0001.
+
+HWCAP2_SVEAES
+
+ Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001.
+
+HWCAP2_SVEPMULL
+
+ Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0010.
+
+HWCAP2_SVEBITPERM
+
+ Functionality implied by ID_AA64ZFR0_EL1.BitPerm == 0b0001.
+
+HWCAP2_SVESHA3
+
+ Functionality implied by ID_AA64ZFR0_EL1.SHA3 == 0b0001.
+
+HWCAP2_SVESM4
+
+ Functionality implied by ID_AA64ZFR0_EL1.SM4 == 0b0001.
+
HWCAP_ASIMDFHM
Functionality implied by ID_AA64ISAR0_EL1.FHM == 0b0001.
@@ -194,3 +222,10 @@
Functionality implied by ID_AA64ISAR1_EL1.GPA == 0b0001 or
ID_AA64ISAR1_EL1.GPI == 0b0001, as described by
Documentation/arm64/pointer-authentication.txt.
+
+
+4. Unused AT_HWCAP bits
+-----------------------
+
+For interoperation with userspace, the kernel guarantees that bits 62
+and 63 of AT_HWCAP will always be returned as 0.
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index d1e2bb8..68d9b74 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -61,6 +61,7 @@
| ARM | Cortex-A76 | #1188873 | ARM64_ERRATUM_1188873 |
| ARM | Cortex-A76 | #1165522 | ARM64_ERRATUM_1165522 |
| ARM | Cortex-A76 | #1286807 | ARM64_ERRATUM_1286807 |
+| ARM | Neoverse-N1 | #1188873 | ARM64_ERRATUM_1188873 |
| ARM | MMU-500 | #841119,#826419 | N/A |
| | | | |
| Cavium | ThunderX ITS | #22375, #24313 | CAVIUM_ERRATUM_22375 |
@@ -77,6 +78,7 @@
| Hisilicon | Hip0{5,6,7} | #161010101 | HISILICON_ERRATUM_161010101 |
| Hisilicon | Hip0{6,7} | #161010701 | N/A |
| Hisilicon | Hip07 | #161600802 | HISILICON_ERRATUM_161600802 |
+| Hisilicon | Hip08 SMMU PMCG | #162001800 | N/A |
| | | | |
| Qualcomm Tech. | Kryo/Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 |
| Qualcomm Tech. | Falkor v1 | E1009 | QCOM_FALKOR_ERRATUM_1009 |
diff --git a/Documentation/arm64/sve.txt b/Documentation/arm64/sve.txt
index 7169a0e..9940e92 100644
--- a/Documentation/arm64/sve.txt
+++ b/Documentation/arm64/sve.txt
@@ -34,6 +34,23 @@
following sections: software that needs to verify that those interfaces are
present must check for HWCAP_SVE instead.
+* On hardware that supports the SVE2 extensions, HWCAP2_SVE2 will also
+ be reported in the AT_HWCAP2 aux vector entry. In addition to this,
+ optional extensions to SVE2 may be reported by the presence of:
+
+ HWCAP2_SVE2
+ HWCAP2_SVEAES
+ HWCAP2_SVEPMULL
+ HWCAP2_SVEBITPERM
+ HWCAP2_SVESHA3
+ HWCAP2_SVESM4
+
+ This list may be extended over time as the SVE architecture evolves.
+
+ These extensions are also reported via the CPU ID register ID_AA64ZFR0_EL1,
+ which userspace can read using an MRS instruction. See elf_hwcaps.txt and
+ cpu-feature-registers.txt for details.
+
* Debuggers should restrict themselves to interacting with the target via the
NT_ARM_SVE regset. The recommended way of detecting support for this regset
is to connect to a target process first and then attempt a
diff --git a/Documentation/robust-futexes.txt b/Documentation/robust-futexes.txt
index 6c42c75..6361fb0 100644
--- a/Documentation/robust-futexes.txt
+++ b/Documentation/robust-futexes.txt
@@ -218,5 +218,4 @@
the new syscalls yet.
Architectures need to implement the new futex_atomic_cmpxchg_inatomic()
-inline function before writing up the syscalls (that function returns
--ENOSYS right now).
+inline function before writing up the syscalls.
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index 0a8d7bb..4b66ecd 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -11,6 +11,10 @@
#include <clocksource/arm_arch_timer.h>
#ifdef CONFIG_ARM_ARCH_TIMER
+/* 32bit ARM doesn't know anything about timer errata... */
+#define has_erratum_handler(h) (false)
+#define erratum_handler(h) (arch_timer_##h)
+
int arch_timer_arch_init(void);
/*
@@ -79,7 +83,7 @@ static inline u32 arch_timer_get_cntfrq(void)
return val;
}
-static inline u64 arch_counter_get_cntpct(void)
+static inline u64 __arch_counter_get_cntpct(void)
{
u64 cval;
@@ -88,7 +92,12 @@ static inline u64 arch_counter_get_cntpct(void)
return cval;
}
-static inline u64 arch_counter_get_cntvct(void)
+static inline u64 __arch_counter_get_cntpct_stable(void)
+{
+ return __arch_counter_get_cntpct();
+}
+
+static inline u64 __arch_counter_get_cntvct(void)
{
u64 cval;
@@ -97,6 +106,11 @@ static inline u64 arch_counter_get_cntvct(void)
return cval;
}
+static inline u64 __arch_counter_get_cntvct_stable(void)
+{
+ return __arch_counter_get_cntvct();
+}
+
static inline u32 arch_timer_get_cntkctl(void)
{
u32 cntkctl;
diff --git a/arch/arm/include/asm/cp15.h b/arch/arm/include/asm/cp15.h
index 07e27f2..d2453e2d 100644
--- a/arch/arm/include/asm/cp15.h
+++ b/arch/arm/include/asm/cp15.h
@@ -68,6 +68,8 @@
#define BPIALL __ACCESS_CP15(c7, 0, c5, 6)
#define ICIALLU __ACCESS_CP15(c7, 0, c5, 0)
+#define CNTVCT __ACCESS_CP15_64(1, c14)
+
extern unsigned long cr_alignment; /* defined in entry-armv.S */
static inline unsigned long get_cr(void)
diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h
index 9e11dce..9587517 100644
--- a/arch/arm/include/asm/stage2_pgtable.h
+++ b/arch/arm/include/asm/stage2_pgtable.h
@@ -32,14 +32,14 @@
#define stage2_pgd_present(kvm, pgd) pgd_present(pgd)
#define stage2_pgd_populate(kvm, pgd, pud) pgd_populate(NULL, pgd, pud)
#define stage2_pud_offset(kvm, pgd, address) pud_offset(pgd, address)
-#define stage2_pud_free(kvm, pud) pud_free(NULL, pud)
+#define stage2_pud_free(kvm, pud) do { } while (0)
#define stage2_pud_none(kvm, pud) pud_none(pud)
#define stage2_pud_clear(kvm, pud) pud_clear(pud)
#define stage2_pud_present(kvm, pud) pud_present(pud)
#define stage2_pud_populate(kvm, pud, pmd) pud_populate(NULL, pud, pmd)
#define stage2_pmd_offset(kvm, pud, address) pmd_offset(pud, address)
-#define stage2_pmd_free(kvm, pmd) pmd_free(NULL, pmd)
+#define stage2_pmd_free(kvm, pmd) free_page((unsigned long)pmd)
#define stage2_pud_huge(kvm, pud) pud_huge(pud)
diff --git a/arch/arm/vdso/vgettimeofday.c b/arch/arm/vdso/vgettimeofday.c
index a9dd619..7bdbf5d 100644
--- a/arch/arm/vdso/vgettimeofday.c
+++ b/arch/arm/vdso/vgettimeofday.c
@@ -18,9 +18,9 @@
#include <linux/compiler.h>
#include <linux/hrtimer.h>
#include <linux/time.h>
-#include <asm/arch_timer.h>
#include <asm/barrier.h>
#include <asm/bug.h>
+#include <asm/cp15.h>
#include <asm/page.h>
#include <asm/unistd.h>
#include <asm/vdso_datapage.h>
@@ -123,7 +123,8 @@ static notrace u64 get_ns(struct vdso_data *vdata)
u64 cycle_now;
u64 nsec;
- cycle_now = arch_counter_get_cntvct();
+ isb();
+ cycle_now = read_sysreg(CNTVCT);
cycle_delta = (cycle_now - vdata->cs_cycle_last) & vdata->cs_mask;
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index d81adca..df350f4 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -90,6 +90,7 @@
select GENERIC_CLOCKEVENTS
select GENERIC_CLOCKEVENTS_BROADCAST
select GENERIC_CPU_AUTOPROBE
+ select GENERIC_CPU_VULNERABILITIES
select GENERIC_EARLY_IOREMAP
select GENERIC_IDLE_POLL_SETUP
select GENERIC_IRQ_MULTI_HANDLER
@@ -148,6 +149,7 @@
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
select HAVE_REGS_AND_STACK_ACCESS_API
+ select HAVE_FUNCTION_ARG_ACCESS_API
select HAVE_RCU_TABLE_FREE
select HAVE_RSEQ
select HAVE_STACKPROTECTOR
@@ -293,7 +295,7 @@
menu "ARM errata workarounds via the alternatives framework"
config ARM64_WORKAROUND_CLEAN_CACHE
- def_bool n
+ bool
config ARM64_ERRATUM_826319
bool "Cortex-A53: 826319: System might deadlock if a write cannot complete until read data is accepted"
@@ -460,26 +462,28 @@
bool "Cortex-A55: 1024718: Update of DBM/AP bits without break before make might result in incorrect update"
default y
help
- This option adds work around for Arm Cortex-A55 Erratum 1024718.
+ This option adds a workaround for ARM Cortex-A55 Erratum 1024718.
Affected Cortex-A55 cores (r0p0, r0p1, r1p0) could cause incorrect
update of the hardware dirty bit when the DBM/AP bits are updated
- without a break-before-make. The work around is to disable the usage
+ without a break-before-make. The workaround is to disable the usage
of hardware DBM locally on the affected cores. CPUs not affected by
- erratum will continue to use the feature.
+ this erratum will continue to use the feature.
If unsure, say Y.
config ARM64_ERRATUM_1188873
- bool "Cortex-A76: MRC read following MRRC read of specific Generic Timer in AArch32 might give incorrect result"
+ bool "Cortex-A76/Neoverse-N1: MRC read following MRRC read of specific Generic Timer in AArch32 might give incorrect result"
default y
+ depends on COMPAT
select ARM_ARCH_TIMER_OOL_WORKAROUND
help
- This option adds work arounds for ARM Cortex-A76 erratum 1188873
+ This option adds a workaround for ARM Cortex-A76/Neoverse-N1
+ erratum 1188873.
- Affected Cortex-A76 cores (r0p0, r1p0, r2p0) could cause
- register corruption when accessing the timer registers from
- AArch32 userspace.
+ Affected Cortex-A76/Neoverse-N1 cores (r0p0, r1p0, r2p0) could
+ cause register corruption when accessing the timer registers
+ from AArch32 userspace.
If unsure, say Y.
@@ -487,7 +491,7 @@
bool "Cortex-A76: Speculative AT instruction using out-of-context translation regime could cause subsequent request to generate an incorrect translation"
default y
help
- This option adds work arounds for ARM Cortex-A76 erratum 1165522
+ This option adds a workaround for ARM Cortex-A76 erratum 1165522.
Affected Cortex-A76 cores (r0p0, r1p0, r2p0) could end-up with
corrupted TLBs by speculating an AT instruction during a guest
@@ -500,7 +504,7 @@
default y
select ARM64_WORKAROUND_REPEAT_TLBI
help
- This option adds workaround for ARM Cortex-A76 erratum 1286807
+ This option adds a workaround for ARM Cortex-A76 erratum 1286807.
On the affected Cortex-A76 cores (r0p0 to r3p0), if a virtual
address for a cacheable mapping of a location is being
@@ -517,10 +521,10 @@
bool "Cavium erratum 22375, 24313"
default y
help
- Enable workaround for erratum 22375, 24313.
+ Enable workaround for errata 22375 and 24313.
This implements two gicv3-its errata workarounds for ThunderX. Both
- with small impact affecting only ITS table allocation.
+ with a small impact affecting only ITS table allocation.
erratum 22375: only alloc 8MB table size
erratum 24313: ignore memory access type
@@ -584,9 +588,6 @@
config ARM64_WORKAROUND_REPEAT_TLBI
bool
- help
- Enable the repeat TLBI workaround for Falkor erratum 1009 and
- Cortex-A76 erratum 1286807.
config QCOM_FALKOR_ERRATUM_1009
bool "Falkor E1009: Prematurely complete a DSB after a TLBI"
@@ -622,7 +623,7 @@
bool "Hip07 161600802: Erroneous redistributor VLPI base"
default y
help
- The HiSilicon Hip07 SoC usees the wrong redistributor base
+ The HiSilicon Hip07 SoC uses the wrong redistributor base
when issued ITS commands such as VMOVP and VMAPP, and requires
a 128kB offset to be applied to the target address in this commands.
@@ -642,7 +643,7 @@
bool "Fujitsu-A64FX erratum E#010001: Undefined fault may occur wrongly"
default y
help
- This option adds workaround for Fujitsu-A64FX erratum E#010001.
+ This option adds a workaround for Fujitsu-A64FX erratum E#010001.
On some variants of the Fujitsu-A64FX cores ver(1.0, 1.1), memory
accesses may cause undefined fault (Data abort, DFSC=0b111111).
This fault occurs under a specific hardware condition when a
@@ -653,7 +654,7 @@
case-4 TTBR1_EL2 with TCR_EL2.NFD1 == 1.
The workaround is to ensure these bits are clear in TCR_ELx.
- The workaround only affect the Fujitsu-A64FX.
+ The workaround only affects the Fujitsu-A64FX.
If unsure, say Y.
@@ -885,6 +886,9 @@
config ARCH_HAS_CACHE_LINE_SIZE
def_bool y
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+ def_bool y if PGTABLE_LEVELS > 2
+
config SECCOMP
bool "Enable seccomp to safely compute untrusted bytecode"
---help---
@@ -1074,9 +1078,65 @@
This requires the linear region to be mapped down to pages,
which may adversely affect performance in some cases.
+config ARM64_SW_TTBR0_PAN
+ bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
+ help
+ Enabling this option prevents the kernel from accessing
+ user-space memory directly by pointing TTBR0_EL1 to a reserved
+ zeroed area and reserved ASID. The user access routines
+ restore the valid TTBR0_EL1 temporarily.
+
+menuconfig COMPAT
+ bool "Kernel support for 32-bit EL0"
+ depends on ARM64_4K_PAGES || EXPERT
+ select COMPAT_BINFMT_ELF if BINFMT_ELF
+ select HAVE_UID16
+ select OLD_SIGSUSPEND3
+ select COMPAT_OLD_SIGACTION
+ help
+ This option enables support for a 32-bit EL0 running under a 64-bit
+ kernel at EL1. AArch32-specific components such as system calls,
+ the user helper functions, VFP support and the ptrace interface are
+ handled appropriately by the kernel.
+
+ If you use a page size other than 4KB (i.e, 16KB or 64KB), please be aware
+ that you will only be able to execute AArch32 binaries that were compiled
+ with page size aligned segments.
+
+ If you want to execute 32-bit userspace applications, say Y.
+
+if COMPAT
+
+config KUSER_HELPERS
+ bool "Enable kuser helpers page for 32 bit applications"
+ default y
+ help
+ Warning: disabling this option may break 32-bit user programs.
+
+ Provide kuser helpers to compat tasks. The kernel provides
+ helper code to userspace in read only form at a fixed location
+ to allow userspace to be independent of the CPU type fitted to
+ the system. This permits binaries to be run on ARMv4 through
+ to ARMv8 without modification.
+
+ See Documentation/arm/kernel_user_helpers.txt for details.
+
+ However, the fixed address nature of these helpers can be used
+ by ROP (return orientated programming) authors when creating
+ exploits.
+
+ If all of the binaries and libraries which run on your platform
+ are built specifically for your platform, and make no use of
+ these helpers, then you can turn this option off to hinder
+ such exploits. However, in that case, if a binary or library
+ relying on those helpers is run, it will not function correctly.
+
+ Say N here only if you are absolutely certain that you do not
+ need these helpers; otherwise, the safe option is to say Y.
+
+
menuconfig ARMV8_DEPRECATED
bool "Emulate deprecated/obsolete ARMv8 instructions"
- depends on COMPAT
depends on SYSCTL
help
Legacy software support may require certain instructions
@@ -1142,13 +1202,7 @@
If unsure, say Y
endif
-config ARM64_SW_TTBR0_PAN
- bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
- help
- Enabling this option prevents the kernel from accessing
- user-space memory directly by pointing TTBR0_EL1 to a reserved
- zeroed area and reserved ASID. The user access routines
- restore the valid TTBR0_EL1 temporarily.
+endif
menu "ARMv8.1 architectural features"
@@ -1314,6 +1368,9 @@
To enable use of this extension on CPUs that implement it, say Y.
+ On CPUs that support the SVE2 extensions, this option will enable
+ those too.
+
Note that for architectural reasons, firmware _must_ implement SVE
support when running on SVE capable hardware. The required support
is present in:
@@ -1347,7 +1404,7 @@
help
Adds support for mimicking Non-Maskable Interrupts through the use of
GIC interrupt priority. This support requires version 3 or later of
- Arm GIC.
+ ARM GIC.
This high priority configuration for interrupts needs to be
explicitly enabled by setting the kernel parameter
@@ -1471,25 +1528,6 @@
endmenu
-config COMPAT
- bool "Kernel support for 32-bit EL0"
- depends on ARM64_4K_PAGES || EXPERT
- select COMPAT_BINFMT_ELF if BINFMT_ELF
- select HAVE_UID16
- select OLD_SIGSUSPEND3
- select COMPAT_OLD_SIGACTION
- help
- This option enables support for a 32-bit EL0 running under a 64-bit
- kernel at EL1. AArch32-specific components such as system calls,
- the user helper functions, VFP support and the ptrace interface are
- handled appropriately by the kernel.
-
- If you use a page size other than 4KB (i.e, 16KB or 64KB), please be aware
- that you will only be able to execute AArch32 binaries that were compiled
- with page size aligned segments.
-
- If you want to execute 32-bit userspace applications, say Y.
-
config SYSVIPC_COMPAT
def_bool y
depends on COMPAT && SYSVIPC
diff --git a/arch/arm64/boot/dts/mediatek/mt2712-pinfunc.h b/arch/arm64/boot/dts/mediatek/mt2712-pinfunc.h
index 1b4cb0c..385c455 100644
--- a/arch/arm64/boot/dts/mediatek/mt2712-pinfunc.h
+++ b/arch/arm64/boot/dts/mediatek/mt2712-pinfunc.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2018 MediaTek Inc.
* Author: Zhiyong Tao <zhiyong.tao@mediatek.com>
diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c
index 5fc6f51..036ea77 100644
--- a/arch/arm64/crypto/aes-ce-ccm-glue.c
+++ b/arch/arm64/crypto/aes-ce-ccm-glue.c
@@ -372,7 +372,7 @@ static struct aead_alg ccm_aes_alg = {
static int __init aes_mod_init(void)
{
- if (!(elf_hwcap & HWCAP_AES))
+ if (!cpu_have_named_feature(AES))
return -ENODEV;
return crypto_register_aead(&ccm_aes_alg);
}
diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c
index e7a95a5..bf1b321 100644
--- a/arch/arm64/crypto/aes-neonbs-glue.c
+++ b/arch/arm64/crypto/aes-neonbs-glue.c
@@ -440,7 +440,7 @@ static int __init aes_init(void)
int err;
int i;
- if (!(elf_hwcap & HWCAP_ASIMD))
+ if (!cpu_have_named_feature(ASIMD))
return -ENODEV;
err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs));
diff --git a/arch/arm64/crypto/chacha-neon-glue.c b/arch/arm64/crypto/chacha-neon-glue.c
index bece1d8..cb054f5 100644
--- a/arch/arm64/crypto/chacha-neon-glue.c
+++ b/arch/arm64/crypto/chacha-neon-glue.c
@@ -173,7 +173,7 @@ static struct skcipher_alg algs[] = {
static int __init chacha_simd_mod_init(void)
{
- if (!(elf_hwcap & HWCAP_ASIMD))
+ if (!cpu_have_named_feature(ASIMD))
return -ENODEV;
return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
diff --git a/arch/arm64/crypto/crct10dif-ce-glue.c b/arch/arm64/crypto/crct10dif-ce-glue.c
index dd32582..e81d5bd 100644
--- a/arch/arm64/crypto/crct10dif-ce-glue.c
+++ b/arch/arm64/crypto/crct10dif-ce-glue.c
@@ -101,7 +101,7 @@ static struct shash_alg crc_t10dif_alg[] = {{
static int __init crc_t10dif_mod_init(void)
{
- if (elf_hwcap & HWCAP_PMULL)
+ if (cpu_have_named_feature(PMULL))
return crypto_register_shashes(crc_t10dif_alg,
ARRAY_SIZE(crc_t10dif_alg));
else
@@ -111,7 +111,7 @@ static int __init crc_t10dif_mod_init(void)
static void __exit crc_t10dif_mod_exit(void)
{
- if (elf_hwcap & HWCAP_PMULL)
+ if (cpu_have_named_feature(PMULL))
crypto_unregister_shashes(crc_t10dif_alg,
ARRAY_SIZE(crc_t10dif_alg));
else
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 791ad42..4e69bb78 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -704,10 +704,10 @@ static int __init ghash_ce_mod_init(void)
{
int ret;
- if (!(elf_hwcap & HWCAP_ASIMD))
+ if (!cpu_have_named_feature(ASIMD))
return -ENODEV;
- if (elf_hwcap & HWCAP_PMULL)
+ if (cpu_have_named_feature(PMULL))
ret = crypto_register_shashes(ghash_alg,
ARRAY_SIZE(ghash_alg));
else
@@ -717,7 +717,7 @@ static int __init ghash_ce_mod_init(void)
if (ret)
return ret;
- if (elf_hwcap & HWCAP_PMULL) {
+ if (cpu_have_named_feature(PMULL)) {
ret = crypto_register_aead(&gcm_aes_alg);
if (ret)
crypto_unregister_shashes(ghash_alg,
@@ -728,7 +728,7 @@ static int __init ghash_ce_mod_init(void)
static void __exit ghash_ce_mod_exit(void)
{
- if (elf_hwcap & HWCAP_PMULL)
+ if (cpu_have_named_feature(PMULL))
crypto_unregister_shashes(ghash_alg, ARRAY_SIZE(ghash_alg));
else
crypto_unregister_shash(ghash_alg);
diff --git a/arch/arm64/crypto/nhpoly1305-neon-glue.c b/arch/arm64/crypto/nhpoly1305-neon-glue.c
index 22cc32a..38a5890 100644
--- a/arch/arm64/crypto/nhpoly1305-neon-glue.c
+++ b/arch/arm64/crypto/nhpoly1305-neon-glue.c
@@ -56,7 +56,7 @@ static struct shash_alg nhpoly1305_alg = {
static int __init nhpoly1305_mod_init(void)
{
- if (!(elf_hwcap & HWCAP_ASIMD))
+ if (!cpu_have_named_feature(ASIMD))
return -ENODEV;
return crypto_register_shash(&nhpoly1305_alg);
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
index 4aedeae..0cccdb9 100644
--- a/arch/arm64/crypto/sha256-glue.c
+++ b/arch/arm64/crypto/sha256-glue.c
@@ -173,7 +173,7 @@ static int __init sha256_mod_init(void)
if (ret)
return ret;
- if (elf_hwcap & HWCAP_ASIMD) {
+ if (cpu_have_named_feature(ASIMD)) {
ret = crypto_register_shashes(neon_algs, ARRAY_SIZE(neon_algs));
if (ret)
crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
@@ -183,7 +183,7 @@ static int __init sha256_mod_init(void)
static void __exit sha256_mod_fini(void)
{
- if (elf_hwcap & HWCAP_ASIMD)
+ if (cpu_have_named_feature(ASIMD))
crypto_unregister_shashes(neon_algs, ARRAY_SIZE(neon_algs));
crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
}
diff --git a/arch/arm64/include/asm/arch_timer.h b/arch/arm64/include/asm/arch_timer.h
index f2a234d..b7bca1a 100644
--- a/arch/arm64/include/asm/arch_timer.h
+++ b/arch/arm64/include/asm/arch_timer.h
@@ -31,11 +31,23 @@
#include <clocksource/arm_arch_timer.h>
#if IS_ENABLED(CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND)
-extern struct static_key_false arch_timer_read_ool_enabled;
-#define needs_unstable_timer_counter_workaround() \
- static_branch_unlikely(&arch_timer_read_ool_enabled)
+#define has_erratum_handler(h) \
+ ({ \
+ const struct arch_timer_erratum_workaround *__wa; \
+ __wa = __this_cpu_read(timer_unstable_counter_workaround); \
+ (__wa && __wa->h); \
+ })
+
+#define erratum_handler(h) \
+ ({ \
+ const struct arch_timer_erratum_workaround *__wa; \
+ __wa = __this_cpu_read(timer_unstable_counter_workaround); \
+ (__wa && __wa->h) ? __wa->h : arch_timer_##h; \
+ })
+
#else
-#define needs_unstable_timer_counter_workaround() false
+#define has_erratum_handler(h) false
+#define erratum_handler(h) (arch_timer_##h)
#endif
enum arch_timer_erratum_match_type {
@@ -61,23 +73,37 @@ struct arch_timer_erratum_workaround {
DECLARE_PER_CPU(const struct arch_timer_erratum_workaround *,
timer_unstable_counter_workaround);
+/* inline sysreg accessors that make erratum_handler() work */
+static inline notrace u32 arch_timer_read_cntp_tval_el0(void)
+{
+ return read_sysreg(cntp_tval_el0);
+}
+
+static inline notrace u32 arch_timer_read_cntv_tval_el0(void)
+{
+ return read_sysreg(cntv_tval_el0);
+}
+
+static inline notrace u64 arch_timer_read_cntpct_el0(void)
+{
+ return read_sysreg(cntpct_el0);
+}
+
+static inline notrace u64 arch_timer_read_cntvct_el0(void)
+{
+ return read_sysreg(cntvct_el0);
+}
+
#define arch_timer_reg_read_stable(reg) \
-({ \
- u64 _val; \
- if (needs_unstable_timer_counter_workaround()) { \
- const struct arch_timer_erratum_workaround *wa; \
+ ({ \
+ u64 _val; \
+ \
preempt_disable_notrace(); \
- wa = __this_cpu_read(timer_unstable_counter_workaround); \
- if (wa && wa->read_##reg) \
- _val = wa->read_##reg(); \
- else \
- _val = read_sysreg(reg); \
+ _val = erratum_handler(read_ ## reg)(); \
preempt_enable_notrace(); \
- } else { \
- _val = read_sysreg(reg); \
- } \
- _val; \
-})
+ \
+ _val; \
+ })
/*
* These register accessors are marked inline so the compiler can
@@ -148,18 +174,67 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
isb();
}
-static inline u64 arch_counter_get_cntpct(void)
+/*
+ * Ensure that reads of the counter are treated the same as memory reads
+ * for the purposes of ordering by subsequent memory barriers.
+ *
+ * This insanity brought to you by speculative system register reads,
+ * out-of-order memory accesses, sequence locks and Thomas Gleixner.
+ *
+ * http://lists.infradead.org/pipermail/linux-arm-kernel/2019-February/631195.html
+ */
+#define arch_counter_enforce_ordering(val) do { \
+ u64 tmp, _val = (val); \
+ \
+ asm volatile( \
+ " eor %0, %1, %1\n" \
+ " add %0, sp, %0\n" \
+ " ldr xzr, [%0]" \
+ : "=r" (tmp) : "r" (_val)); \
+} while (0)
+
+static inline u64 __arch_counter_get_cntpct_stable(void)
{
+ u64 cnt;
+
isb();
- return arch_timer_reg_read_stable(cntpct_el0);
+ cnt = arch_timer_reg_read_stable(cntpct_el0);
+ arch_counter_enforce_ordering(cnt);
+ return cnt;
}
-static inline u64 arch_counter_get_cntvct(void)
+static inline u64 __arch_counter_get_cntpct(void)
{
+ u64 cnt;
+
isb();
- return arch_timer_reg_read_stable(cntvct_el0);
+ cnt = read_sysreg(cntpct_el0);
+ arch_counter_enforce_ordering(cnt);
+ return cnt;
}
+static inline u64 __arch_counter_get_cntvct_stable(void)
+{
+ u64 cnt;
+
+ isb();
+ cnt = arch_timer_reg_read_stable(cntvct_el0);
+ arch_counter_enforce_ordering(cnt);
+ return cnt;
+}
+
+static inline u64 __arch_counter_get_cntvct(void)
+{
+ u64 cnt;
+
+ isb();
+ cnt = read_sysreg(cntvct_el0);
+ arch_counter_enforce_ordering(cnt);
+ return cnt;
+}
+
+#undef arch_counter_enforce_ordering
+
static inline int arch_timer_arch_init(void)
{
return 0;
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index c5308d0..039fbd8 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -407,10 +407,14 @@ alternative_endif
.ifc \op, cvap
sys 3, c7, c12, 1, \kaddr // dc cvap
.else
+ .ifc \op, cvadp
+ sys 3, c7, c13, 1, \kaddr // dc cvadp
+ .else
dc \op, \kaddr
.endif
.endif
.endif
+ .endif
add \kaddr, \kaddr, \tmp1
cmp \kaddr, \size
b.lo 9998b
@@ -442,8 +446,8 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU
* reset_pmuserenr_el0 - reset PMUSERENR_EL0 if PMUv3 present
*/
.macro reset_pmuserenr_el0, tmpreg
- mrs \tmpreg, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer
- sbfx \tmpreg, \tmpreg, #8, #4
+ mrs \tmpreg, id_aa64dfr0_el1
+ sbfx \tmpreg, \tmpreg, #ID_AA64DFR0_PMUVER_SHIFT, #4
cmp \tmpreg, #1 // Skip if no PMU present
b.lt 9000f
msr pmuserenr_el0, xzr // Disable PMU access from EL0
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index f66bb04..85b6bed 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -20,6 +20,8 @@
#ifndef __ASSEMBLY__
+#include <linux/kasan-checks.h>
+
#define __nops(n) ".rept " #n "\nnop\n.endr\n"
#define nops(n) asm volatile(__nops(n))
@@ -72,31 +74,33 @@ static inline unsigned long array_index_mask_nospec(unsigned long idx,
#define __smp_store_release(p, v) \
do { \
+ typeof(p) __p = (p); \
union { typeof(*p) __val; char __c[1]; } __u = \
- { .__val = (__force typeof(*p)) (v) }; \
+ { .__val = (__force typeof(*p)) (v) }; \
compiletime_assert_atomic_type(*p); \
+ kasan_check_write(__p, sizeof(*p)); \
switch (sizeof(*p)) { \
case 1: \
asm volatile ("stlrb %w1, %0" \
- : "=Q" (*p) \
+ : "=Q" (*__p) \
: "r" (*(__u8 *)__u.__c) \
: "memory"); \
break; \
case 2: \
asm volatile ("stlrh %w1, %0" \
- : "=Q" (*p) \
+ : "=Q" (*__p) \
: "r" (*(__u16 *)__u.__c) \
: "memory"); \
break; \
case 4: \
asm volatile ("stlr %w1, %0" \
- : "=Q" (*p) \
+ : "=Q" (*__p) \
: "r" (*(__u32 *)__u.__c) \
: "memory"); \
break; \
case 8: \
asm volatile ("stlr %1, %0" \
- : "=Q" (*p) \
+ : "=Q" (*__p) \
: "r" (*(__u64 *)__u.__c) \
: "memory"); \
break; \
@@ -106,27 +110,29 @@ do { \
#define __smp_load_acquire(p) \
({ \
union { typeof(*p) __val; char __c[1]; } __u; \
+ typeof(p) __p = (p); \
compiletime_assert_atomic_type(*p); \
+ kasan_check_read(__p, sizeof(*p)); \
switch (sizeof(*p)) { \
case 1: \
asm volatile ("ldarb %w0, %1" \
: "=r" (*(__u8 *)__u.__c) \
- : "Q" (*p) : "memory"); \
+ : "Q" (*__p) : "memory"); \
break; \
case 2: \
asm volatile ("ldarh %w0, %1" \
: "=r" (*(__u16 *)__u.__c) \
- : "Q" (*p) : "memory"); \
+ : "Q" (*__p) : "memory"); \
break; \
case 4: \
asm volatile ("ldar %w0, %1" \
: "=r" (*(__u32 *)__u.__c) \
- : "Q" (*p) : "memory"); \
+ : "Q" (*__p) : "memory"); \
break; \
case 8: \
asm volatile ("ldar %0, %1" \
: "=r" (*(__u64 *)__u.__c) \
- : "Q" (*p) : "memory"); \
+ : "Q" (*__p) : "memory"); \
break; \
} \
__u.__val; \
diff --git a/arch/arm64/include/asm/brk-imm.h b/arch/arm64/include/asm/brk-imm.h
index 2945fe6..d8429406 100644
--- a/arch/arm64/include/asm/brk-imm.h
+++ b/arch/arm64/include/asm/brk-imm.h
@@ -11,6 +11,8 @@
/*
* #imm16 values used for BRK instruction generation
+ * 0x004: for installing kprobes
+ * 0x005: for installing uprobes
* Allowed values for kgdb are 0x400 - 0x7ff
* 0x100: for triggering a fault on purpose (reserved)
* 0x400: for dynamic BRK instruction
@@ -18,10 +20,13 @@
* 0x800: kernel-mode BUG() and WARN() traps
* 0x9xx: tag-based KASAN trap (allowed values 0x900 - 0x9ff)
*/
+#define KPROBES_BRK_IMM 0x004
+#define UPROBES_BRK_IMM 0x005
#define FAULT_BRK_IMM 0x100
#define KGDB_DYN_DBG_BRK_IMM 0x400
#define KGDB_COMPILED_DBG_BRK_IMM 0x401
#define BUG_BRK_IMM 0x800
#define KASAN_BRK_IMM 0x900
+#define KASAN_BRK_MASK 0x0ff
#endif
diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index f6a76e4..defdc67 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -61,7 +61,8 @@
#define ARM64_HAS_GENERIC_AUTH_ARCH 40
#define ARM64_HAS_GENERIC_AUTH_IMP_DEF 41
#define ARM64_HAS_IRQ_PRIO_MASKING 42
+#define ARM64_HAS_DCPODP 43
-#define ARM64_NCAPS 43
+#define ARM64_NCAPS 44
#endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index e505e1f..f210bcf 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -14,15 +14,8 @@
#include <asm/hwcap.h>
#include <asm/sysreg.h>
-/*
- * In the arm64 world (as in the ARM world), elf_hwcap is used both internally
- * in the kernel and for user space to keep track of which optional features
- * are supported by the current system. So let's map feature 'x' to HWCAP_x.
- * Note that HWCAP_x constants are bit fields so we need to take the log.
- */
-
-#define MAX_CPU_FEATURES (8 * sizeof(elf_hwcap))
-#define cpu_feature(x) ilog2(HWCAP_ ## x)
+#define MAX_CPU_FEATURES 64
+#define cpu_feature(x) KERNEL_HWCAP_ ## x
#ifndef __ASSEMBLY__
@@ -399,11 +392,13 @@ extern DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE);
for_each_set_bit(cap, cpu_hwcaps, ARM64_NCAPS)
bool this_cpu_has_cap(unsigned int cap);
+void cpu_set_feature(unsigned int num);
+bool cpu_have_feature(unsigned int num);
+unsigned long cpu_get_elf_hwcap(void);
+unsigned long cpu_get_elf_hwcap2(void);
-static inline bool cpu_have_feature(unsigned int num)
-{
- return elf_hwcap & (1UL << num);
-}
+#define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name))
+#define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name))
/* System capability check for constant caps */
static inline bool __cpus_have_const_cap(int num)
@@ -638,11 +633,7 @@ static inline int arm64_get_ssbd_state(void)
#endif
}
-#ifdef CONFIG_ARM64_SSBD
void arm64_set_ssbd_mitigation(bool state);
-#else
-static inline void arm64_set_ssbd_mitigation(bool state) {}
-#endif
extern int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 5f14370..2602bae 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -89,6 +89,7 @@
#define ARM_CPU_PART_CORTEX_A35 0xD04
#define ARM_CPU_PART_CORTEX_A55 0xD05
#define ARM_CPU_PART_CORTEX_A76 0xD0B
+#define ARM_CPU_PART_NEOVERSE_N1 0xD0C
#define APM_CPU_PART_POTENZA 0x000
@@ -118,6 +119,7 @@
#define MIDR_CORTEX_A35 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A35)
#define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55)
#define MIDR_CORTEX_A76 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A76)
+#define MIDR_NEOVERSE_N1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N1)
#define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
#define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
#define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index a44cf52..0679f78 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -65,12 +65,9 @@
#define CACHE_FLUSH_IS_SAFE 1
/* kprobes BRK opcodes with ESR encoding */
-#define BRK64_ESR_MASK 0xFFFF
-#define BRK64_ESR_KPROBES 0x0004
-#define BRK64_OPCODE_KPROBES (AARCH64_BREAK_MON | (BRK64_ESR_KPROBES << 5))
+#define BRK64_OPCODE_KPROBES (AARCH64_BREAK_MON | (KPROBES_BRK_IMM << 5))
/* uprobes BRK opcodes with ESR encoding */
-#define BRK64_ESR_UPROBES 0x0005
-#define BRK64_OPCODE_UPROBES (AARCH64_BREAK_MON | (BRK64_ESR_UPROBES << 5))
+#define BRK64_OPCODE_UPROBES (AARCH64_BREAK_MON | (UPROBES_BRK_IMM << 5))
/* AArch32 */
#define DBG_ESR_EVT_BKPT 0x4
@@ -94,18 +91,24 @@ struct step_hook {
int (*fn)(struct pt_regs *regs, unsigned int esr);
};
-void register_step_hook(struct step_hook *hook);
-void unregister_step_hook(struct step_hook *hook);
+void register_user_step_hook(struct step_hook *hook);
+void unregister_user_step_hook(struct step_hook *hook);
+
+void register_kernel_step_hook(struct step_hook *hook);
+void unregister_kernel_step_hook(struct step_hook *hook);
struct break_hook {
struct list_head node;
- u32 esr_val;
- u32 esr_mask;
int (*fn)(struct pt_regs *regs, unsigned int esr);
+ u16 imm;
+ u16 mask; /* These bits are ignored when comparing with imm */
};
-void register_break_hook(struct break_hook *hook);
-void unregister_break_hook(struct break_hook *hook);
+void register_user_break_hook(struct break_hook *hook);
+void unregister_user_break_hook(struct break_hook *hook);
+
+void register_kernel_break_hook(struct break_hook *hook);
+void unregister_kernel_break_hook(struct break_hook *hook);
u8 debug_monitors_arch(void);
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 6adc1a9..355d120 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -214,10 +214,10 @@ typedef compat_elf_greg_t compat_elf_gregset_t[COMPAT_ELF_NGREG];
set_thread_flag(TIF_32BIT); \
})
#define COMPAT_ARCH_DLINFO
-extern int aarch32_setup_vectors_page(struct linux_binprm *bprm,
- int uses_interp);
+extern int aarch32_setup_additional_pages(struct linux_binprm *bprm,
+ int uses_interp);
#define compat_arch_setup_additional_pages \
- aarch32_setup_vectors_page
+ aarch32_setup_additional_pages
#endif /* CONFIG_COMPAT */
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 52233f0..0e27fe9 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -156,9 +156,7 @@
ESR_ELx_WFx_ISS_WFI)
/* BRK instruction trap from AArch64 state */
-#define ESR_ELx_VAL_BRK64(imm) \
- ((ESR_ELx_EC_BRK64 << ESR_ELx_EC_SHIFT) | ESR_ELx_IL | \
- ((imm) & 0xffff))
+#define ESR_ELx_BRK64_ISS_COMMENT_MASK 0xffff
/* ISS field definitions for System instruction traps */
#define ESR_ELx_SYS64_ISS_RES0_SHIFT 22
@@ -198,9 +196,10 @@
/*
* User space cache operations have the following sysreg encoding
* in System instructions.
- * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 12, 14 }, WRITE (L=0)
+ * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 12, 13, 14 }, WRITE (L=0)
*/
#define ESR_ELx_SYS64_ISS_CRM_DC_CIVAC 14
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVADP 13
#define ESR_ELx_SYS64_ISS_CRM_DC_CVAP 12
#define ESR_ELx_SYS64_ISS_CRM_DC_CVAU 11
#define ESR_ELx_SYS64_ISS_CRM_DC_CVAC 10
diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index c7e1a78..a56efb5 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -23,26 +23,34 @@
#include <asm/errno.h>
+#define FUTEX_MAX_LOOPS 128 /* What's the largest number you can think of? */
+
#define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg) \
do { \
+ unsigned int loops = FUTEX_MAX_LOOPS; \
+ \
uaccess_enable(); \
asm volatile( \
" prfm pstl1strm, %2\n" \
"1: ldxr %w1, %2\n" \
insn "\n" \
"2: stlxr %w0, %w3, %2\n" \
-" cbnz %w0, 1b\n" \
-" dmb ish\n" \
+" cbz %w0, 3f\n" \
+" sub %w4, %w4, %w0\n" \
+" cbnz %w4, 1b\n" \
+" mov %w0, %w7\n" \
"3:\n" \
+" dmb ish\n" \
" .pushsection .fixup,\"ax\"\n" \
" .align 2\n" \
-"4: mov %w0, %w5\n" \
+"4: mov %w0, %w6\n" \
" b 3b\n" \
" .popsection\n" \
_ASM_EXTABLE(1b, 4b) \
_ASM_EXTABLE(2b, 4b) \
- : "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp) \
- : "r" (oparg), "Ir" (-EFAULT) \
+ : "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp), \
+ "+r" (loops) \
+ : "r" (oparg), "Ir" (-EFAULT), "Ir" (-EAGAIN) \
: "memory"); \
uaccess_disable(); \
} while (0)
@@ -57,23 +65,23 @@ arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
switch (op) {
case FUTEX_OP_SET:
- __futex_atomic_op("mov %w3, %w4",
+ __futex_atomic_op("mov %w3, %w5",
ret, oldval, uaddr, tmp, oparg);
break;
case FUTEX_OP_ADD:
- __futex_atomic_op("add %w3, %w1, %w4",
+ __futex_atomic_op("add %w3, %w1, %w5",
ret, oldval, uaddr, tmp, oparg);
break;
case FUTEX_OP_OR:
- __futex_atomic_op("orr %w3, %w1, %w4",
+ __futex_atomic_op("orr %w3, %w1, %w5",
ret, oldval, uaddr, tmp, oparg);
break;
case FUTEX_OP_ANDN:
- __futex_atomic_op("and %w3, %w1, %w4",
+ __futex_atomic_op("and %w3, %w1, %w5",
ret, oldval, uaddr, tmp, ~oparg);
break;
case FUTEX_OP_XOR:
- __futex_atomic_op("eor %w3, %w1, %w4",
+ __futex_atomic_op("eor %w3, %w1, %w5",
ret, oldval, uaddr, tmp, oparg);
break;
default:
@@ -93,6 +101,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
u32 oldval, u32 newval)
{
int ret = 0;
+ unsigned int loops = FUTEX_MAX_LOOPS;
u32 val, tmp;
u32 __user *uaddr;
@@ -104,24 +113,30 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *_uaddr,
asm volatile("// futex_atomic_cmpxchg_inatomic\n"
" prfm pstl1strm, %2\n"
"1: ldxr %w1, %2\n"
-" sub %w3, %w1, %w4\n"
-" cbnz %w3, 3f\n"
-"2: stlxr %w3, %w5, %2\n"
-" cbnz %w3, 1b\n"
-" dmb ish\n"
+" sub %w3, %w1, %w5\n"
+" cbnz %w3, 4f\n"
+"2: stlxr %w3, %w6, %2\n"
+" cbz %w3, 3f\n"
+" sub %w4, %w4, %w3\n"
+" cbnz %w4, 1b\n"
+" mov %w0, %w8\n"
"3:\n"
+" dmb ish\n"
+"4:\n"
" .pushsection .fixup,\"ax\"\n"
-"4: mov %w0, %w6\n"
-" b 3b\n"
+"5: mov %w0, %w7\n"
+" b 4b\n"
" .popsection\n"
- _ASM_EXTABLE(1b, 4b)
- _ASM_EXTABLE(2b, 4b)
- : "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
- : "r" (oldval), "r" (newval), "Ir" (-EFAULT)
+ _ASM_EXTABLE(1b, 5b)
+ _ASM_EXTABLE(2b, 5b)
+ : "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp), "+r" (loops)
+ : "r" (oldval), "r" (newval), "Ir" (-EFAULT), "Ir" (-EAGAIN)
: "memory");
uaccess_disable();
- *uval = val;
+ if (!ret)
+ *uval = val;
+
return ret;
}
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 400b80b..b4bfb66 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -17,6 +17,7 @@
#define __ASM_HWCAP_H
#include <uapi/asm/hwcap.h>
+#include <asm/cpufeature.h>
#define COMPAT_HWCAP_HALF (1 << 1)
#define COMPAT_HWCAP_THUMB (1 << 2)
@@ -40,11 +41,67 @@
#define COMPAT_HWCAP2_CRC32 (1 << 4)
#ifndef __ASSEMBLY__
+#include <linux/log2.h>
+
+/*
+ * For userspace we represent hwcaps as a collection of HWCAP{,2}_x bitfields
+ * as described in uapi/asm/hwcap.h. For the kernel we represent hwcaps as
+ * natural numbers (in a single range of size MAX_CPU_FEATURES) defined here
+ * with prefix KERNEL_HWCAP_ mapped to their HWCAP{,2}_x counterpart.
+ *
+ * Hwcaps should be set and tested within the kernel via the
+ * cpu_{set,have}_named_feature(feature) where feature is the unique suffix
+ * of KERNEL_HWCAP_{feature}.
+ */
+#define __khwcap_feature(x) const_ilog2(HWCAP_ ## x)
+#define KERNEL_HWCAP_FP __khwcap_feature(FP)
+#define KERNEL_HWCAP_ASIMD __khwcap_feature(ASIMD)
+#define KERNEL_HWCAP_EVTSTRM __khwcap_feature(EVTSTRM)
+#define KERNEL_HWCAP_AES __khwcap_feature(AES)
+#define KERNEL_HWCAP_PMULL __khwcap_feature(PMULL)
+#define KERNEL_HWCAP_SHA1 __khwcap_feature(SHA1)
+#define KERNEL_HWCAP_SHA2 __khwcap_feature(SHA2)
+#define KERNEL_HWCAP_CRC32 __khwcap_feature(CRC32)
+#define KERNEL_HWCAP_ATOMICS __khwcap_feature(ATOMICS)
+#define KERNEL_HWCAP_FPHP __khwcap_feature(FPHP)
+#define KERNEL_HWCAP_ASIMDHP __khwcap_feature(ASIMDHP)
+#define KERNEL_HWCAP_CPUID __khwcap_feature(CPUID)
+#define KERNEL_HWCAP_ASIMDRDM __khwcap_feature(ASIMDRDM)
+#define KERNEL_HWCAP_JSCVT __khwcap_feature(JSCVT)
+#define KERNEL_HWCAP_FCMA __khwcap_feature(FCMA)
+#define KERNEL_HWCAP_LRCPC __khwcap_feature(LRCPC)
+#define KERNEL_HWCAP_DCPOP __khwcap_feature(DCPOP)
+#define KERNEL_HWCAP_SHA3 __khwcap_feature(SHA3)
+#define KERNEL_HWCAP_SM3 __khwcap_feature(SM3)
+#define KERNEL_HWCAP_SM4 __khwcap_feature(SM4)
+#define KERNEL_HWCAP_ASIMDDP __khwcap_feature(ASIMDDP)
+#define KERNEL_HWCAP_SHA512 __khwcap_feature(SHA512)
+#define KERNEL_HWCAP_SVE __khwcap_feature(SVE)
+#define KERNEL_HWCAP_ASIMDFHM __khwcap_feature(ASIMDFHM)
+#define KERNEL_HWCAP_DIT __khwcap_feature(DIT)
+#define KERNEL_HWCAP_USCAT __khwcap_feature(USCAT)
+#define KERNEL_HWCAP_ILRCPC __khwcap_feature(ILRCPC)
+#define KERNEL_HWCAP_FLAGM __khwcap_feature(FLAGM)
+#define KERNEL_HWCAP_SSBS __khwcap_feature(SSBS)
+#define KERNEL_HWCAP_SB __khwcap_feature(SB)
+#define KERNEL_HWCAP_PACA __khwcap_feature(PACA)
+#define KERNEL_HWCAP_PACG __khwcap_feature(PACG)
+
+#define __khwcap2_feature(x) (const_ilog2(HWCAP2_ ## x) + 32)
+#define KERNEL_HWCAP_DCPODP __khwcap2_feature(DCPODP)
+#define KERNEL_HWCAP_SVE2 __khwcap2_feature(SVE2)
+#define KERNEL_HWCAP_SVEAES __khwcap2_feature(SVEAES)
+#define KERNEL_HWCAP_SVEPMULL __khwcap2_feature(SVEPMULL)
+#define KERNEL_HWCAP_SVEBITPERM __khwcap2_feature(SVEBITPERM)
+#define KERNEL_HWCAP_SVESHA3 __khwcap2_feature(SVESHA3)
+#define KERNEL_HWCAP_SVESM4 __khwcap2_feature(SVESM4)
+
/*
* This yields a mask that user programs can use to figure out what
* instruction set this cpu supports.
*/
-#define ELF_HWCAP (elf_hwcap)
+#define ELF_HWCAP cpu_get_elf_hwcap()
+#define ELF_HWCAP2 cpu_get_elf_hwcap2()
#ifdef CONFIG_COMPAT
#define COMPAT_ELF_HWCAP (compat_elf_hwcap)
@@ -60,6 +117,5 @@ enum {
#endif
};
-extern unsigned long elf_hwcap;
#endif
#endif
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index 43d8366..62996318 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -43,7 +43,7 @@ static inline void arch_local_irq_enable(void)
asm volatile(ALTERNATIVE(
"msr daifclr, #2 // arch_local_irq_enable\n"
"nop",
- "msr_s " __stringify(SYS_ICC_PMR_EL1) ",%0\n"
+ __msr_s(SYS_ICC_PMR_EL1, "%0")
"dsb sy",
ARM64_HAS_IRQ_PRIO_MASKING)
:
@@ -55,7 +55,7 @@ static inline void arch_local_irq_disable(void)
{
asm volatile(ALTERNATIVE(
"msr daifset, #2 // arch_local_irq_disable",
- "msr_s " __stringify(SYS_ICC_PMR_EL1) ", %0",
+ __msr_s(SYS_ICC_PMR_EL1, "%0"),
ARM64_HAS_IRQ_PRIO_MASKING)
:
: "r" ((unsigned long) GIC_PRIO_IRQOFF)
@@ -86,7 +86,7 @@ static inline unsigned long arch_local_save_flags(void)
"mov %0, %1\n"
"nop\n"
"nop",
- "mrs_s %0, " __stringify(SYS_ICC_PMR_EL1) "\n"
+ __mrs_s("%0", SYS_ICC_PMR_EL1)
"ands %1, %1, " __stringify(PSR_I_BIT) "\n"
"csel %0, %0, %2, eq",
ARM64_HAS_IRQ_PRIO_MASKING)
@@ -116,7 +116,7 @@ static inline void arch_local_irq_restore(unsigned long flags)
asm volatile(ALTERNATIVE(
"msr daif, %0\n"
"nop",
- "msr_s " __stringify(SYS_ICC_PMR_EL1) ", %0\n"
+ __msr_s(SYS_ICC_PMR_EL1, "%0")
"dsb sy",
ARM64_HAS_IRQ_PRIO_MASKING)
: "+r" (flags)
diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index d5a44cf..21721fbf 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -54,8 +54,6 @@ void arch_remove_kprobe(struct kprobe *);
int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
int kprobe_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data);
-int kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr);
-int kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr);
void kretprobe_trampoline(void);
void __kprobes *trampoline_probe_handler(struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 4da765f..c306083 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -30,7 +30,7 @@
({ \
u64 reg; \
asm volatile(ALTERNATIVE("mrs %0, " __stringify(r##nvh),\
- "mrs_s %0, " __stringify(r##vh),\
+ __mrs_s("%0", r##vh), \
ARM64_HAS_VIRT_HOST_EXTN) \
: "=r" (reg)); \
reg; \
@@ -40,7 +40,7 @@
do { \
u64 __val = (u64)(v); \
asm volatile(ALTERNATIVE("msr " __stringify(r##nvh) ", %x0",\
- "msr_s " __stringify(r##vh) ", %x0",\
+ __msr_s(r##vh, "%x0"), \
ARM64_HAS_VIRT_HOST_EXTN) \
: : "rZ" (__val)); \
} while (0)
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 2901951..2cb8248 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -302,7 +302,7 @@ static inline void *phys_to_virt(phys_addr_t x)
*/
#define ARCH_PFN_OFFSET ((unsigned long)PHYS_PFN_OFFSET)
-#ifndef CONFIG_SPARSEMEM_VMEMMAP
+#if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL)
#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
#define _virt_addr_valid(kaddr) pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
#else
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index 52fa47c..dabba4b 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -33,12 +33,22 @@
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
- return (pmd_t *)__get_free_page(PGALLOC_GFP);
+ struct page *page;
+
+ page = alloc_page(PGALLOC_GFP);
+ if (!page)
+ return NULL;
+ if (!pgtable_pmd_page_ctor(page)) {
+ __free_page(page);
+ return NULL;
+ }
+ return page_address(page);
}
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmdp)
{
BUG_ON((unsigned long)pmdp & (PAGE_SIZE-1));
+ pgtable_pmd_page_dtor(virt_to_page(pmdp));
free_page((unsigned long)pmdp);
}
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index de70c1e..2c41b04 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -478,6 +478,8 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
return __pmd_to_phys(pmd);
}
+static inline void pte_unmap(pte_t *pte) { }
+
/* Find an entry in the third-level page table. */
#define pte_index(addr) (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
@@ -485,9 +487,6 @@ static inline phys_addr_t pmd_page_paddr(pmd_t pmd)
#define pte_offset_kernel(dir,addr) ((pte_t *)__va(pte_offset_phys((dir), (addr))))
#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr))
-#define pte_offset_map_nested(dir,addr) pte_offset_kernel((dir), (addr))
-#define pte_unmap(pte) do { } while (0)
-#define pte_unmap_nested(pte) do { } while (0)
#define pte_set_fixmap(addr) ((pte_t *)set_fixmap_offset(FIX_PTE, addr))
#define pte_set_fixmap_offset(pmd, addr) pte_set_fixmap(pte_offset_phys(pmd, addr))
diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h
index 15d4951..d328540 100644
--- a/arch/arm64/include/asm/pointer_auth.h
+++ b/arch/arm64/include/asm/pointer_auth.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __ASM_POINTER_AUTH_H
#define __ASM_POINTER_AUTH_H
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 5d9ce62..fcd0e69 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -57,7 +57,15 @@
#define TASK_SIZE_64 (UL(1) << vabits_user)
#ifdef CONFIG_COMPAT
+#if defined(CONFIG_ARM64_64K_PAGES) && defined(CONFIG_KUSER_HELPERS)
+/*
+ * With CONFIG_ARM64_64K_PAGES enabled, the last page is occupied
+ * by the compat vectors page.
+ */
#define TASK_SIZE_32 UL(0x100000000)
+#else
+#define TASK_SIZE_32 (UL(0x100000000) - PAGE_SIZE)
+#endif /* CONFIG_ARM64_64K_PAGES */
#define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \
TASK_SIZE_32 : TASK_SIZE_64)
#define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT) ? \
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index ec60174..b2de329 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -305,6 +305,28 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
return regs->regs[0];
}
+/**
+ * regs_get_kernel_argument() - get Nth function argument in kernel
+ * @regs: pt_regs of that context
+ * @n: function argument number (start from 0)
+ *
+ * regs_get_argument() returns @n th argument of the function call.
+ *
+ * Note that this chooses the most likely register mapping. In very rare
+ * cases this may not return correct data, for example, if one of the
+ * function parameters is 16 bytes or bigger. In such cases, we cannot
+ * get access the parameter correctly and the register assignment of
+ * subsequent parameters will be shifted.
+ */
+static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs,
+ unsigned int n)
+{
+#define NR_REG_ARGUMENTS 8
+ if (n < NR_REG_ARGUMENTS)
+ return pt_regs_read_reg(regs, n);
+ return 0;
+}
+
/* We must avoid circular header include via sched.h */
struct task_struct;
int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task);
diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h
index ffe47d7..63e0b92 100644
--- a/arch/arm64/include/asm/sdei.h
+++ b/arch/arm64/include/asm/sdei.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
// Copyright (C) 2017 Arm Ltd.
#ifndef __ASM_SDEI_H
#define __ASM_SDEI_H
diff --git a/arch/arm64/include/asm/signal32.h b/arch/arm64/include/asm/signal32.h
index 81abea0..58e288a 100644
--- a/arch/arm64/include/asm/signal32.h
+++ b/arch/arm64/include/asm/signal32.h
@@ -20,8 +20,6 @@
#ifdef CONFIG_COMPAT
#include <linux/compat.h>
-#define AARCH32_KERN_SIGRET_CODE_OFFSET 0x500
-
int compat_setup_frame(int usig, struct ksignal *ksig, sigset_t *set,
struct pt_regs *regs);
int compat_setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set,
diff --git a/arch/arm64/include/asm/stage2_pgtable.h b/arch/arm64/include/asm/stage2_pgtable.h
index 5412fa4..915809e 100644
--- a/arch/arm64/include/asm/stage2_pgtable.h
+++ b/arch/arm64/include/asm/stage2_pgtable.h
@@ -119,7 +119,7 @@ static inline pud_t *stage2_pud_offset(struct kvm *kvm,
static inline void stage2_pud_free(struct kvm *kvm, pud_t *pud)
{
if (kvm_stage2_has_pud(kvm))
- pud_free(NULL, pud);
+ free_page((unsigned long)pud);
}
static inline bool stage2_pud_table_empty(struct kvm *kvm, pud_t *pudp)
@@ -192,7 +192,7 @@ static inline pmd_t *stage2_pmd_offset(struct kvm *kvm,
static inline void stage2_pmd_free(struct kvm *kvm, pmd_t *pmd)
{
if (kvm_stage2_has_pmd(kvm))
- pmd_free(NULL, pmd);
+ free_page((unsigned long)pmd);
}
static inline bool stage2_pud_huge(struct kvm *kvm, pud_t pud)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 5b267de..3f7b917 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -606,6 +606,20 @@
#define ID_AA64PFR1_SSBS_PSTATE_ONLY 1
#define ID_AA64PFR1_SSBS_PSTATE_INSNS 2
+/* id_aa64zfr0 */
+#define ID_AA64ZFR0_SM4_SHIFT 40
+#define ID_AA64ZFR0_SHA3_SHIFT 32
+#define ID_AA64ZFR0_BITPERM_SHIFT 16
+#define ID_AA64ZFR0_AES_SHIFT 4
+#define ID_AA64ZFR0_SVEVER_SHIFT 0
+
+#define ID_AA64ZFR0_SM4 0x1
+#define ID_AA64ZFR0_SHA3 0x1
+#define ID_AA64ZFR0_BITPERM 0x1
+#define ID_AA64ZFR0_AES 0x1
+#define ID_AA64ZFR0_AES_PMULL 0x2
+#define ID_AA64ZFR0_SVEVER_SVE2 0x1
+
/* id_aa64mmfr0 */
#define ID_AA64MMFR0_TGRAN4_SHIFT 28
#define ID_AA64MMFR0_TGRAN64_SHIFT 24
@@ -746,20 +760,39 @@
#include <linux/build_bug.h>
#include <linux/types.h>
-asm(
-" .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n"
-" .equ .L__reg_num_x\\num, \\num\n"
-" .endr\n"
+#define __DEFINE_MRS_MSR_S_REGNUM \
+" .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" \
+" .equ .L__reg_num_x\\num, \\num\n" \
+" .endr\n" \
" .equ .L__reg_num_xzr, 31\n"
-"\n"
-" .macro mrs_s, rt, sreg\n"
- __emit_inst(0xd5200000|(\\sreg)|(.L__reg_num_\\rt))
+
+#define DEFINE_MRS_S \
+ __DEFINE_MRS_MSR_S_REGNUM \
+" .macro mrs_s, rt, sreg\n" \
+ __emit_inst(0xd5200000|(\\sreg)|(.L__reg_num_\\rt)) \
" .endm\n"
-"\n"
-" .macro msr_s, sreg, rt\n"
- __emit_inst(0xd5000000|(\\sreg)|(.L__reg_num_\\rt))
+
+#define DEFINE_MSR_S \
+ __DEFINE_MRS_MSR_S_REGNUM \
+" .macro msr_s, sreg, rt\n" \
+ __emit_inst(0xd5000000|(\\sreg)|(.L__reg_num_\\rt)) \
" .endm\n"
-);
+
+#define UNDEFINE_MRS_S \
+" .purgem mrs_s\n"
+
+#define UNDEFINE_MSR_S \
+" .purgem msr_s\n"
+
+#define __mrs_s(v, r) \
+ DEFINE_MRS_S \
+" mrs_s " v ", " __stringify(r) "\n" \
+ UNDEFINE_MRS_S
+
+#define __msr_s(r, v) \
+ DEFINE_MSR_S \
+" msr_s " __stringify(r) ", " v "\n" \
+ UNDEFINE_MSR_S
/*
* Unlike read_cpuid, calls to read_sysreg are never expected to be
@@ -787,13 +820,13 @@ asm(
*/
#define read_sysreg_s(r) ({ \
u64 __val; \
- asm volatile("mrs_s %0, " __stringify(r) : "=r" (__val)); \
+ asm volatile(__mrs_s("%0", r) : "=r" (__val)); \
__val; \
})
#define write_sysreg_s(v, r) do { \
u64 __val = (u64)(v); \
- asm volatile("msr_s " __stringify(r) ", %x0" : : "rZ" (__val)); \
+ asm volatile(__msr_s(r, "%x0") : : "rZ" (__val)); \
} while (0)
/*
diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h
index 32693f3..fca9542 100644
--- a/arch/arm64/include/asm/system_misc.h
+++ b/arch/arm64/include/asm/system_misc.h
@@ -41,7 +41,6 @@ void hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
int sig, int code, const char *name);
struct mm_struct;
-extern void show_pte(unsigned long addr);
extern void __show_regs(struct pt_regs *);
extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 37603b5..a287189 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -63,7 +63,10 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
unsigned long addr)
{
- tlb_remove_table(tlb, virt_to_page(pmdp));
+ struct page *page = virt_to_page(pmdp);
+
+ pgtable_pmd_page_dtor(page);
+ tlb_remove_table(tlb, page);
}
#endif
diff --git a/arch/arm64/include/asm/vdso_datapage.h b/arch/arm64/include/asm/vdso_datapage.h
index 2b9a637..f89263c 100644
--- a/arch/arm64/include/asm/vdso_datapage.h
+++ b/arch/arm64/include/asm/vdso_datapage.h
@@ -38,6 +38,7 @@ struct vdso_data {
__u32 tz_minuteswest; /* Whacky timezone stuff */
__u32 tz_dsttime;
__u32 use_syscall;
+ __u32 hrtimer_res;
};
#endif /* !__ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/vmap_stack.h b/arch/arm64/include/asm/vmap_stack.h
index 0b5ec6e..0a12115 100644
--- a/arch/arm64/include/asm/vmap_stack.h
+++ b/arch/arm64/include/asm/vmap_stack.h
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+/* SPDX-License-Identifier: GPL-2.0 */
// Copyright (C) 2017 Arm Ltd.
#ifndef __ASM_VMAP_STACK_H
#define __ASM_VMAP_STACK_H
diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h
index 5f0750c..1a772b1 100644
--- a/arch/arm64/include/uapi/asm/hwcap.h
+++ b/arch/arm64/include/uapi/asm/hwcap.h
@@ -18,7 +18,7 @@
#define _UAPI__ASM_HWCAP_H
/*
- * HWCAP flags - for elf_hwcap (in kernel) and AT_HWCAP
+ * HWCAP flags - for AT_HWCAP
*/
#define HWCAP_FP (1 << 0)
#define HWCAP_ASIMD (1 << 1)
@@ -53,4 +53,15 @@
#define HWCAP_PACA (1 << 30)
#define HWCAP_PACG (1UL << 31)
+/*
+ * HWCAP2 flags - for AT_HWCAP2
+ */
+#define HWCAP2_DCPODP (1 << 0)
+#define HWCAP2_SVE2 (1 << 1)
+#define HWCAP2_SVEAES (1 << 2)
+#define HWCAP2_SVEPMULL (1 << 3)
+#define HWCAP2_SVEBITPERM (1 << 4)
+#define HWCAP2_SVESHA3 (1 << 5)
+#define HWCAP2_SVESM4 (1 << 6)
+
#endif /* _UAPI__ASM_HWCAP_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index cd434d0..9e7dcb2 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -7,9 +7,9 @@
AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET)
CFLAGS_armv8_deprecated.o := -I$(src)
-CFLAGS_REMOVE_ftrace.o = -pg
-CFLAGS_REMOVE_insn.o = -pg
-CFLAGS_REMOVE_return_address.o = -pg
+CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_insn.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
# Object file lists.
obj-y := debug-monitors.o entry.o irq.o fpsimd.o \
@@ -27,8 +27,9 @@
$(obj)/%.stub.o: $(obj)/%.o FORCE
$(call if_changed,objcopy)
-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \
- sys_compat.o
+obj-$(CONFIG_COMPAT) += sys32.o signal32.o \
+ sigreturn32.o sys_compat.o
+obj-$(CONFIG_KUSER_HELPERS) += kuser32.o
obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o
obj-$(CONFIG_MODULES) += module.o
obj-$(CONFIG_ARM64_MODULE_PLTS) += module-plts.o
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 7f40dcb..e10e2a5 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -94,7 +94,7 @@ int main(void)
DEFINE(CLOCK_REALTIME, CLOCK_REALTIME);
DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC);
DEFINE(CLOCK_MONOTONIC_RAW, CLOCK_MONOTONIC_RAW);
- DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC);
+ DEFINE(CLOCK_REALTIME_RES, offsetof(struct vdso_data, hrtimer_res));
DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE);
DEFINE(CLOCK_MONOTONIC_COARSE,CLOCK_MONOTONIC_COARSE);
DEFINE(CLOCK_COARSE_RES, LOW_RES_NSEC);
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 9950bb0..e88d4e7 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -19,6 +19,7 @@
#include <linux/arm-smccc.h>
#include <linux/psci.h>
#include <linux/types.h>
+#include <linux/cpu.h>
#include <asm/cpu.h>
#include <asm/cputype.h>
#include <asm/cpufeature.h>
@@ -109,7 +110,6 @@ cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
@@ -131,9 +131,9 @@ static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
__flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
}
-static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
- const char *hyp_vecs_start,
- const char *hyp_vecs_end)
+static void install_bp_hardening_cb(bp_hardening_cb_t fn,
+ const char *hyp_vecs_start,
+ const char *hyp_vecs_end)
{
static DEFINE_RAW_SPINLOCK(bp_lock);
int cpu, slot = -1;
@@ -169,7 +169,7 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
#define __smccc_workaround_1_smc_start NULL
#define __smccc_workaround_1_smc_end NULL
-static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
+static void install_bp_hardening_cb(bp_hardening_cb_t fn,
const char *hyp_vecs_start,
const char *hyp_vecs_end)
{
@@ -177,23 +177,6 @@ static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
}
#endif /* CONFIG_KVM_INDIRECT_VECTORS */
-static void install_bp_hardening_cb(const struct arm64_cpu_capabilities *entry,
- bp_hardening_cb_t fn,
- const char *hyp_vecs_start,
- const char *hyp_vecs_end)
-{
- u64 pfr0;
-
- if (!entry->matches(entry, SCOPE_LOCAL_CPU))
- return;
-
- pfr0 = read_cpuid(ID_AA64PFR0_EL1);
- if (cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_CSV2_SHIFT))
- return;
-
- __install_bp_hardening_cb(fn, hyp_vecs_start, hyp_vecs_end);
-}
-
#include <uapi/linux/psci.h>
#include <linux/arm-smccc.h>
#include <linux/psci.h>
@@ -220,60 +203,83 @@ static void qcom_link_stack_sanitization(void)
: "=&r" (tmp));
}
-static void
-enable_smccc_arch_workaround_1(const struct arm64_cpu_capabilities *entry)
+static bool __nospectre_v2;
+static int __init parse_nospectre_v2(char *str)
+{
+ __nospectre_v2 = true;
+ return 0;
+}
+early_param("nospectre_v2", parse_nospectre_v2);
+
+/*
+ * -1: No workaround
+ * 0: No workaround required
+ * 1: Workaround installed
+ */
+static int detect_harden_bp_fw(void)
{
bp_hardening_cb_t cb;
void *smccc_start, *smccc_end;
struct arm_smccc_res res;
u32 midr = read_cpuid_id();
- if (!entry->matches(entry, SCOPE_LOCAL_CPU))
- return;
-
if (psci_ops.smccc_version == SMCCC_VERSION_1_0)
- return;
+ return -1;
switch (psci_ops.conduit) {
case PSCI_CONDUIT_HVC:
arm_smccc_1_1_hvc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
ARM_SMCCC_ARCH_WORKAROUND_1, &res);
- if ((int)res.a0 < 0)
- return;
- cb = call_hvc_arch_workaround_1;
- /* This is a guest, no need to patch KVM vectors */
- smccc_start = NULL;
- smccc_end = NULL;
+ switch ((int)res.a0) {
+ case 1:
+ /* Firmware says we're just fine */
+ return 0;
+ case 0:
+ cb = call_hvc_arch_workaround_1;
+ /* This is a guest, no need to patch KVM vectors */
+ smccc_start = NULL;
+ smccc_end = NULL;
+ break;
+ default:
+ return -1;
+ }
break;
case PSCI_CONDUIT_SMC:
arm_smccc_1_1_smc(ARM_SMCCC_ARCH_FEATURES_FUNC_ID,
ARM_SMCCC_ARCH_WORKAROUND_1, &res);
- if ((int)res.a0 < 0)
- return;
- cb = call_smc_arch_workaround_1;
- smccc_start = __smccc_workaround_1_smc_start;
- smccc_end = __smccc_workaround_1_smc_end;
+ switch ((int)res.a0) {
+ case 1:
+ /* Firmware says we're just fine */
+ return 0;
+ case 0:
+ cb = call_smc_arch_workaround_1;
+ smccc_start = __smccc_workaround_1_smc_start;
+ smccc_end = __smccc_workaround_1_smc_end;
+ break;
+ default:
+ return -1;
+ }
break;
default:
- return;
+ return -1;
}
if (((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR) ||
((midr & MIDR_CPU_MODEL_MASK) == MIDR_QCOM_FALKOR_V1))
cb = qcom_link_stack_sanitization;
- install_bp_hardening_cb(entry, cb, smccc_start, smccc_end);
+ if (IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR))
+ install_bp_hardening_cb(cb, smccc_start, smccc_end);
- return;
+ return 1;
}
-#endif /* CONFIG_HARDEN_BRANCH_PREDICTOR */
-#ifdef CONFIG_ARM64_SSBD
DEFINE_PER_CPU_READ_MOSTLY(u64, arm64_ssbd_callback_required);
int ssbd_state __read_mostly = ARM64_SSBD_KERNEL;
+static bool __ssb_safe = true;
static const struct ssbd_options {
const char *str;
@@ -343,6 +349,11 @@ void __init arm64_enable_wa2_handling(struct alt_instr *alt,
void arm64_set_ssbd_mitigation(bool state)
{
+ if (!IS_ENABLED(CONFIG_ARM64_SSBD)) {
+ pr_info_once("SSBD disabled by kernel configuration\n");
+ return;
+ }
+
if (this_cpu_has_cap(ARM64_SSBS)) {
if (state)
asm volatile(SET_PSTATE_SSBS(0));
@@ -372,16 +383,28 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
struct arm_smccc_res res;
bool required = true;
s32 val;
+ bool this_cpu_safe = false;
WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+ if (cpu_mitigations_off())
+ ssbd_state = ARM64_SSBD_FORCE_DISABLE;
+
+ /* delay setting __ssb_safe until we get a firmware response */
+ if (is_midr_in_range_list(read_cpuid_id(), entry->midr_range_list))
+ this_cpu_safe = true;
+
if (this_cpu_has_cap(ARM64_SSBS)) {
+ if (!this_cpu_safe)
+ __ssb_safe = false;
required = false;
goto out_printmsg;
}
if (psci_ops.smccc_version == SMCCC_VERSION_1_0) {
ssbd_state = ARM64_SSBD_UNKNOWN;
+ if (!this_cpu_safe)
+ __ssb_safe = false;
return false;
}
@@ -398,6 +421,8 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
default:
ssbd_state = ARM64_SSBD_UNKNOWN;
+ if (!this_cpu_safe)
+ __ssb_safe = false;
return false;
}
@@ -406,14 +431,18 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
switch (val) {
case SMCCC_RET_NOT_SUPPORTED:
ssbd_state = ARM64_SSBD_UNKNOWN;
+ if (!this_cpu_safe)
+ __ssb_safe = false;
return false;
+ /* machines with mixed mitigation requirements must not return this */
case SMCCC_RET_NOT_REQUIRED:
pr_info_once("%s mitigation not required\n", entry->desc);
ssbd_state = ARM64_SSBD_MITIGATED;
return false;
case SMCCC_RET_SUCCESS:
+ __ssb_safe = false;
required = true;
break;
@@ -423,6 +452,8 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
default:
WARN_ON(1);
+ if (!this_cpu_safe)
+ __ssb_safe = false;
return false;
}
@@ -462,7 +493,14 @@ static bool has_ssbd_mitigation(const struct arm64_cpu_capabilities *entry,
return required;
}
-#endif /* CONFIG_ARM64_SSBD */
+
+/* known invulnerable cores */
+static const struct midr_range arm64_ssb_cpus[] = {
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+ {},
+};
static void __maybe_unused
cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
@@ -507,26 +545,67 @@ cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM, \
CAP_MIDR_RANGE_LIST(midr_list)
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
+/* Track overall mitigation state. We are only mitigated if all cores are ok */
+static bool __hardenbp_enab = true;
+static bool __spectrev2_safe = true;
/*
- * List of CPUs where we need to issue a psci call to
- * harden the branch predictor.
+ * List of CPUs that do not need any Spectre-v2 mitigation at all.
*/
-static const struct midr_range arm64_bp_harden_smccc_cpus[] = {
- MIDR_ALL_VERSIONS(MIDR_CORTEX_A57),
- MIDR_ALL_VERSIONS(MIDR_CORTEX_A72),
- MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
- MIDR_ALL_VERSIONS(MIDR_CORTEX_A75),
- MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN),
- MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2),
- MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR_V1),
- MIDR_ALL_VERSIONS(MIDR_QCOM_FALKOR),
- MIDR_ALL_VERSIONS(MIDR_NVIDIA_DENVER),
- {},
+static const struct midr_range spectre_v2_safe_list[] = {
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A35),
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A53),
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_A55),
+ { /* sentinel */ }
};
-#endif
+/*
+ * Track overall bp hardening for all heterogeneous cores in the machine.
+ * We are only considered "safe" if all booted cores are known safe.
+ */
+static bool __maybe_unused
+check_branch_predictor(const struct arm64_cpu_capabilities *entry, int scope)
+{
+ int need_wa;
+
+ WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+
+ /* If the CPU has CSV2 set, we're safe */
+ if (cpuid_feature_extract_unsigned_field(read_cpuid(ID_AA64PFR0_EL1),
+ ID_AA64PFR0_CSV2_SHIFT))
+ return false;
+
+ /* Alternatively, we have a list of unaffected CPUs */
+ if (is_midr_in_range_list(read_cpuid_id(), spectre_v2_safe_list))
+ return false;
+
+ /* Fallback to firmware detection */
+ need_wa = detect_harden_bp_fw();
+ if (!need_wa)
+ return false;
+
+ __spectrev2_safe = false;
+
+ if (!IS_ENABLED(CONFIG_HARDEN_BRANCH_PREDICTOR)) {
+ pr_warn_once("spectrev2 mitigation disabled by kernel configuration\n");
+ __hardenbp_enab = false;
+ return false;
+ }
+
+ /* forced off */
+ if (__nospectre_v2 || cpu_mitigations_off()) {
+ pr_info_once("spectrev2 mitigation disabled by command line option\n");
+ __hardenbp_enab = false;
+ return false;
+ }
+
+ if (need_wa < 0) {
+ pr_warn_once("ARM_SMCCC_ARCH_WORKAROUND_1 missing from firmware\n");
+ __hardenbp_enab = false;
+ }
+
+ return (need_wa > 0);
+}
#ifdef CONFIG_HARDEN_EL2_VECTORS
@@ -603,6 +682,16 @@ static const struct midr_range workaround_clean_cache[] = {
};
#endif
+#ifdef CONFIG_ARM64_ERRATUM_1188873
+static const struct midr_range erratum_1188873_list[] = {
+ /* Cortex-A76 r0p0 to r2p0 */
+ MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0),
+ /* Neoverse-N1 r0p0 to r2p0 */
+ MIDR_RANGE(MIDR_NEOVERSE_N1, 0, 0, 2, 0),
+ {},
+};
+#endif
+
const struct arm64_cpu_capabilities arm64_errata[] = {
#ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
{
@@ -701,13 +790,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A73),
},
#endif
-#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
{
.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
- .cpu_enable = enable_smccc_arch_workaround_1,
- ERRATA_MIDR_RANGE_LIST(arm64_bp_harden_smccc_cpus),
+ .type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+ .matches = check_branch_predictor,
},
-#endif
#ifdef CONFIG_HARDEN_EL2_VECTORS
{
.desc = "EL2 vector hardening",
@@ -715,20 +802,18 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors),
},
#endif
-#ifdef CONFIG_ARM64_SSBD
{
.desc = "Speculative Store Bypass Disable",
.capability = ARM64_SSBD,
.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
.matches = has_ssbd_mitigation,
+ .midr_range_list = arm64_ssb_cpus,
},
-#endif
#ifdef CONFIG_ARM64_ERRATUM_1188873
{
- /* Cortex-A76 r0p0 to r2p0 */
.desc = "ARM erratum 1188873",
.capability = ARM64_WORKAROUND_1188873,
- ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0),
+ ERRATA_MIDR_RANGE_LIST(erratum_1188873_list),
},
#endif
#ifdef CONFIG_ARM64_ERRATUM_1165522
@@ -742,3 +827,38 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
{
}
};
+
+ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ return sprintf(buf, "Mitigation: __user pointer sanitization\n");
+}
+
+ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ if (__spectrev2_safe)
+ return sprintf(buf, "Not affected\n");
+
+ if (__hardenbp_enab)
+ return sprintf(buf, "Mitigation: Branch predictor hardening\n");
+
+ return sprintf(buf, "Vulnerable\n");
+}
+
+ssize_t cpu_show_spec_store_bypass(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ if (__ssb_safe)
+ return sprintf(buf, "Not affected\n");
+
+ switch (ssbd_state) {
+ case ARM64_SSBD_KERNEL:
+ case ARM64_SSBD_FORCE_ENABLE:
+ if (IS_ENABLED(CONFIG_ARM64_SSBD))
+ return sprintf(buf,
+ "Mitigation: Speculative Store Bypass disabled via prctl\n");
+ }
+
+ return sprintf(buf, "Vulnerable\n");
+}
diff --git a/arch/arm64/kernel/cpu_ops.c b/arch/arm64/kernel/cpu_ops.c
index ea00124..00f8b86 100644
--- a/arch/arm64/kernel/cpu_ops.c
+++ b/arch/arm64/kernel/cpu_ops.c
@@ -85,6 +85,7 @@ static const char *__init cpu_read_enable_method(int cpu)
pr_err("%pOF: missing enable-method property\n",
dn);
}
+ of_node_put(dn);
} else {
enable_method = acpi_get_enable_method(cpu);
if (!enable_method) {
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 4061de1..2b807f1 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -25,6 +25,7 @@
#include <linux/stop_machine.h>
#include <linux/types.h>
#include <linux/mm.h>
+#include <linux/cpu.h>
#include <asm/cpu.h>
#include <asm/cpufeature.h>
#include <asm/cpu_ops.h>
@@ -35,8 +36,8 @@
#include <asm/traps.h>
#include <asm/virt.h>
-unsigned long elf_hwcap __read_mostly;
-EXPORT_SYMBOL_GPL(elf_hwcap);
+/* Kernel representation of AT_HWCAP and AT_HWCAP2 */
+static unsigned long elf_hwcap __read_mostly;
#ifdef CONFIG_COMPAT
#define COMPAT_ELF_HWCAP_DEFAULT \
@@ -184,6 +185,15 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = {
ARM64_FTR_END,
};
+static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0),
+ ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0),
+ ARM64_FTR_END,
+};
+
static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
S_ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
@@ -392,7 +402,7 @@ static const struct __ftr_reg_entry {
/* Op1 = 0, CRn = 0, CRm = 4 */
ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0),
ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1),
- ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_raz),
+ ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0),
/* Op1 = 0, CRn = 0, CRm = 5 */
ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0),
@@ -947,7 +957,7 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope)
return has_cpuid_feature(entry, scope);
}
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
+static bool __meltdown_safe = true;
static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */
static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
@@ -966,7 +976,17 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
MIDR_ALL_VERSIONS(MIDR_HISI_TSV110),
{ /* sentinel */ }
};
- char const *str = "command line option";
+ char const *str = "kpti command line option";
+ bool meltdown_safe;
+
+ meltdown_safe = is_midr_in_range_list(read_cpuid_id(), kpti_safe_list);
+
+ /* Defer to CPU feature registers */
+ if (has_cpuid_feature(entry, scope))
+ meltdown_safe = true;
+
+ if (!meltdown_safe)
+ __meltdown_safe = false;
/*
* For reasons that aren't entirely clear, enabling KPTI on Cavium
@@ -978,6 +998,24 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
__kpti_forced = -1;
}
+ /* Useful for KASLR robustness */
+ if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0) {
+ if (!__kpti_forced) {
+ str = "KASLR";
+ __kpti_forced = 1;
+ }
+ }
+
+ if (cpu_mitigations_off() && !__kpti_forced) {
+ str = "mitigations=off";
+ __kpti_forced = -1;
+ }
+
+ if (!IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) {
+ pr_info_once("kernel page table isolation disabled by kernel configuration\n");
+ return false;
+ }
+
/* Forced? */
if (__kpti_forced) {
pr_info_once("kernel page table isolation forced %s by %s\n",
@@ -985,18 +1023,10 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry,
return __kpti_forced > 0;
}
- /* Useful for KASLR robustness */
- if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
- return kaslr_offset() > 0;
-
- /* Don't force KPTI for CPUs that are not vulnerable */
- if (is_midr_in_range_list(read_cpuid_id(), kpti_safe_list))
- return false;
-
- /* Defer to CPU feature registers */
- return !has_cpuid_feature(entry, scope);
+ return !meltdown_safe;
}
+#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
static void
kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
{
@@ -1026,6 +1056,12 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
return;
}
+#else
+static void
+kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused)
+{
+}
+#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
static int __init parse_kpti(char *str)
{
@@ -1039,7 +1075,6 @@ static int __init parse_kpti(char *str)
return 0;
}
early_param("kpti", parse_kpti);
-#endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
#ifdef CONFIG_ARM64_HW_AFDBM
static inline void __cpu_enable_hw_dbm(void)
@@ -1306,7 +1341,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.field_pos = ID_AA64PFR0_EL0_SHIFT,
.min_field_value = ID_AA64PFR0_EL0_32BIT_64BIT,
},
-#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
{
.desc = "Kernel page table isolation (KPTI)",
.capability = ARM64_UNMAP_KERNEL_AT_EL0,
@@ -1322,7 +1356,6 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.matches = unmap_kernel_at_el0,
.cpu_enable = kpti_install_ng_mappings,
},
-#endif
{
/* FP/SIMD is not implemented */
.capability = ARM64_HAS_NO_FPSIMD,
@@ -1340,6 +1373,16 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
.field_pos = ID_AA64ISAR1_DPB_SHIFT,
.min_field_value = 1,
},
+ {
+ .desc = "Data cache clean to Point of Deep Persistence",
+ .capability = ARM64_HAS_DCPODP,
+ .type = ARM64_CPUCAP_SYSTEM_FEATURE,
+ .matches = has_cpuid_feature,
+ .sys_reg = SYS_ID_AA64ISAR1_EL1,
+ .sign = FTR_UNSIGNED,
+ .field_pos = ID_AA64ISAR1_DPB_SHIFT,
+ .min_field_value = 2,
+ },
#endif
#ifdef CONFIG_ARM64_SVE
{
@@ -1571,39 +1614,46 @@ static const struct arm64_cpu_capabilities ptr_auth_hwcap_gen_matches[] = {
#endif
static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_PMULL),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_AES),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA1),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA2),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_SHA512),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_CRC32),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ATOMICS),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDRDM),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA3),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM3),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM4),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDDP),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDFHM),
- HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FLAGM),
- HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_FP),
- HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP),
- HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD),
- HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_ASIMDHP),
- HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_DIT),
- HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_DCPOP),
- HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_JSCVT),
- HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FCMA),
- HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_LRCPC),
- HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ILRCPC),
- HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SB),
- HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_USCAT),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_PMULL),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AES),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA1),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA2),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_SHA512),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_CRC32),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ATOMICS),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA3),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM3),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM4),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM),
+ HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM),
+ HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP),
+ HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP),
+ HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD),
+ HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP),
+ HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT),
+ HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DCPOP),
+ HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_DCPODP),
+ HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_JSCVT),
+ HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FCMA),
+ HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_LRCPC),
+ HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC),
+ HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB),
+ HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT),
#ifdef CONFIG_ARM64_SVE
- HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, HWCAP_SVE),
+ HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, KERNEL_HWCAP_SVE),
+ HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SVEVER_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SVEVER_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2),
+ HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
+ HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES_PMULL, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
+ HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BITPERM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_BITPERM, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM),
+ HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SHA3_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SHA3, CAP_HWCAP, KERNEL_HWCAP_SVESHA3),
+ HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SM4_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SM4, CAP_HWCAP, KERNEL_HWCAP_SVESM4),
#endif
- HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, HWCAP_SSBS),
+ HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS),
#ifdef CONFIG_ARM64_PTR_AUTH
- HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, HWCAP_PACA),
- HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, HWCAP_PACG),
+ HWCAP_MULTI_CAP(ptr_auth_hwcap_addr_matches, CAP_HWCAP, KERNEL_HWCAP_PACA),
+ HWCAP_MULTI_CAP(ptr_auth_hwcap_gen_matches, CAP_HWCAP, KERNEL_HWCAP_PACG),
#endif
{},
};
@@ -1623,7 +1673,7 @@ static void __init cap_set_elf_hwcap(const struct arm64_cpu_capabilities *cap)
{
switch (cap->hwcap_type) {
case CAP_HWCAP:
- elf_hwcap |= cap->hwcap;
+ cpu_set_feature(cap->hwcap);
break;
#ifdef CONFIG_COMPAT
case CAP_COMPAT_HWCAP:
@@ -1646,7 +1696,7 @@ static bool cpus_have_elf_hwcap(const struct arm64_cpu_capabilities *cap)
switch (cap->hwcap_type) {
case CAP_HWCAP:
- rc = (elf_hwcap & cap->hwcap) != 0;
+ rc = cpu_have_feature(cap->hwcap);
break;
#ifdef CONFIG_COMPAT
case CAP_COMPAT_HWCAP:
@@ -1667,7 +1717,7 @@ static bool cpus_have_elf_hwcap(const struct arm64_cpu_capabilities *cap)
static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps)
{
/* We support emulation of accesses to CPU ID feature registers */
- elf_hwcap |= HWCAP_CPUID;
+ cpu_set_named_feature(CPUID);
for (; hwcaps->matches; hwcaps++)
if (hwcaps->matches(hwcaps, cpucap_default_scope(hwcaps)))
cap_set_elf_hwcap(hwcaps);
@@ -1947,6 +1997,35 @@ bool this_cpu_has_cap(unsigned int n)
return false;
}
+void cpu_set_feature(unsigned int num)
+{
+ WARN_ON(num >= MAX_CPU_FEATURES);
+ elf_hwcap |= BIT(num);
+}
+EXPORT_SYMBOL_GPL(cpu_set_feature);
+
+bool cpu_have_feature(unsigned int num)
+{
+ WARN_ON(num >= MAX_CPU_FEATURES);
+ return elf_hwcap & BIT(num);
+}
+EXPORT_SYMBOL_GPL(cpu_have_feature);
+
+unsigned long cpu_get_elf_hwcap(void)
+{
+ /*
+ * We currently only populate the first 32 bits of AT_HWCAP. Please
+ * note that for userspace compatibility we guarantee that bits 62
+ * and 63 will always be returned as 0.
+ */
+ return lower_32_bits(elf_hwcap);
+}
+
+unsigned long cpu_get_elf_hwcap2(void)
+{
+ return upper_32_bits(elf_hwcap);
+}
+
static void __init setup_system_capabilities(void)
{
/*
@@ -2101,3 +2180,15 @@ static int __init enable_mrs_emulation(void)
}
core_initcall(enable_mrs_emulation);
+
+ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ if (__meltdown_safe)
+ return sprintf(buf, "Not affected\n");
+
+ if (arm64_kernel_unmapped_at_el0())
+ return sprintf(buf, "Mitigation: PTI\n");
+
+ return sprintf(buf, "Vulnerable\n");
+}
diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c
index ca0685f..f6f7936 100644
--- a/arch/arm64/kernel/cpuinfo.c
+++ b/arch/arm64/kernel/cpuinfo.c
@@ -85,6 +85,13 @@ static const char *const hwcap_str[] = {
"sb",
"paca",
"pacg",
+ "dcpodp",
+ "sve2",
+ "sveaes",
+ "svepmull",
+ "svebitperm",
+ "svesha3",
+ "svesm4",
NULL
};
@@ -167,7 +174,7 @@ static int c_show(struct seq_file *m, void *v)
#endif /* CONFIG_COMPAT */
} else {
for (j = 0; hwcap_str[j]; j++)
- if (elf_hwcap & (1 << j))
+ if (cpu_have_feature(j))
seq_printf(m, " %s", hwcap_str[j]);
}
seq_puts(m, "\n");
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index d7bb6ae..555b6bd 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -135,6 +135,7 @@ NOKPROBE_SYMBOL(disable_debug_monitors);
*/
static int clear_os_lock(unsigned int cpu)
{
+ write_sysreg(0, osdlr_el1);
write_sysreg(0, oslar_el1);
isb();
return 0;
@@ -163,25 +164,46 @@ static void clear_regs_spsr_ss(struct pt_regs *regs)
}
NOKPROBE_SYMBOL(clear_regs_spsr_ss);
-/* EL1 Single Step Handler hooks */
-static LIST_HEAD(step_hook);
-static DEFINE_SPINLOCK(step_hook_lock);
+static DEFINE_SPINLOCK(debug_hook_lock);
+static LIST_HEAD(user_step_hook);
+static LIST_HEAD(kernel_step_hook);
-void register_step_hook(struct step_hook *hook)
+static void register_debug_hook(struct list_head *node, struct list_head *list)
{
- spin_lock(&step_hook_lock);
- list_add_rcu(&hook->node, &step_hook);
- spin_unlock(&step_hook_lock);
+ spin_lock(&debug_hook_lock);
+ list_add_rcu(node, list);
+ spin_unlock(&debug_hook_lock);
+
}
-void unregister_step_hook(struct step_hook *hook)
+static void unregister_debug_hook(struct list_head *node)
{
- spin_lock(&step_hook_lock);
- list_del_rcu(&hook->node);
- spin_unlock(&step_hook_lock);
+ spin_lock(&debug_hook_lock);
+ list_del_rcu(node);
+ spin_unlock(&debug_hook_lock);
synchronize_rcu();
}
+void register_user_step_hook(struct step_hook *hook)
+{
+ register_debug_hook(&hook->node, &user_step_hook);
+}
+
+void unregister_user_step_hook(struct step_hook *hook)
+{
+ unregister_debug_hook(&hook->node);
+}
+
+void register_kernel_step_hook(struct step_hook *hook)
+{
+ register_debug_hook(&hook->node, &kernel_step_hook);
+}
+
+void unregister_kernel_step_hook(struct step_hook *hook)
+{
+ unregister_debug_hook(&hook->node);
+}
+
/*
* Call registered single step handlers
* There is no Syndrome info to check for determining the handler.
@@ -191,11 +213,14 @@ void unregister_step_hook(struct step_hook *hook)
static int call_step_hook(struct pt_regs *regs, unsigned int esr)
{
struct step_hook *hook;
+ struct list_head *list;
int retval = DBG_HOOK_ERROR;
+ list = user_mode(regs) ? &user_step_hook : &kernel_step_hook;
+
rcu_read_lock();
- list_for_each_entry_rcu(hook, &step_hook, node) {
+ list_for_each_entry_rcu(hook, list, node) {
retval = hook->fn(regs, esr);
if (retval == DBG_HOOK_HANDLED)
break;
@@ -222,7 +247,7 @@ static void send_user_sigtrap(int si_code)
"User debug trap");
}
-static int single_step_handler(unsigned long addr, unsigned int esr,
+static int single_step_handler(unsigned long unused, unsigned int esr,
struct pt_regs *regs)
{
bool handler_found = false;
@@ -234,10 +259,6 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
if (!reinstall_suspended_bps(regs))
return 0;
-#ifdef CONFIG_KPROBES
- if (kprobe_single_step_handler(regs, esr) == DBG_HOOK_HANDLED)
- handler_found = true;
-#endif
if (!handler_found && call_step_hook(regs, esr) == DBG_HOOK_HANDLED)
handler_found = true;
@@ -264,61 +285,59 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
}
NOKPROBE_SYMBOL(single_step_handler);
-/*
- * Breakpoint handler is re-entrant as another breakpoint can
- * hit within breakpoint handler, especically in kprobes.
- * Use reader/writer locks instead of plain spinlock.
- */
-static LIST_HEAD(break_hook);
-static DEFINE_SPINLOCK(break_hook_lock);
+static LIST_HEAD(user_break_hook);
+static LIST_HEAD(kernel_break_hook);
-void register_break_hook(struct break_hook *hook)
+void register_user_break_hook(struct break_hook *hook)
{
- spin_lock(&break_hook_lock);
- list_add_rcu(&hook->node, &break_hook);
- spin_unlock(&break_hook_lock);
+ register_debug_hook(&hook->node, &user_break_hook);
}
-void unregister_break_hook(struct break_hook *hook)
+void unregister_user_break_hook(struct break_hook *hook)
{
- spin_lock(&break_hook_lock);
- list_del_rcu(&hook->node);
- spin_unlock(&break_hook_lock);
- synchronize_rcu();
+ unregister_debug_hook(&hook->node);
+}
+
+void register_kernel_break_hook(struct break_hook *hook)
+{
+ register_debug_hook(&hook->node, &kernel_break_hook);
+}
+
+void unregister_kernel_break_hook(struct break_hook *hook)
+{
+ unregister_debug_hook(&hook->node);
}
static int call_break_hook(struct pt_regs *regs, unsigned int esr)
{
struct break_hook *hook;
+ struct list_head *list;
int (*fn)(struct pt_regs *regs, unsigned int esr) = NULL;
+ list = user_mode(regs) ? &user_break_hook : &kernel_break_hook;
+
rcu_read_lock();
- list_for_each_entry_rcu(hook, &break_hook, node)
- if ((esr & hook->esr_mask) == hook->esr_val)
+ list_for_each_entry_rcu(hook, list, node) {
+ unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
+
+ if ((comment & ~hook->mask) == hook->imm)
fn = hook->fn;
+ }
rcu_read_unlock();
return fn ? fn(regs, esr) : DBG_HOOK_ERROR;
}
NOKPROBE_SYMBOL(call_break_hook);
-static int brk_handler(unsigned long addr, unsigned int esr,
+static int brk_handler(unsigned long unused, unsigned int esr,
struct pt_regs *regs)
{
- bool handler_found = false;
+ if (call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
+ return 0;
-#ifdef CONFIG_KPROBES
- if ((esr & BRK64_ESR_MASK) == BRK64_ESR_KPROBES) {
- if (kprobe_breakpoint_handler(regs, esr) == DBG_HOOK_HANDLED)
- handler_found = true;
- }
-#endif
- if (!handler_found && call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
- handler_found = true;
-
- if (!handler_found && user_mode(regs)) {
+ if (user_mode(regs)) {
send_user_sigtrap(TRAP_BRKPT);
- } else if (!handler_found) {
+ } else {
pr_warn("Unexpected kernel BRK exception at EL1\n");
return -EFAULT;
}
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index c50a7a7..1a7811b 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -336,6 +336,21 @@
alternative_else_nop_endif
#endif
3:
+#ifdef CONFIG_ARM64_ERRATUM_1188873
+alternative_if_not ARM64_WORKAROUND_1188873
+ b 4f
+alternative_else_nop_endif
+ /*
+ * if (x22.mode32 == cntkctl_el1.el0vcten)
+ * cntkctl_el1.el0vcten = ~cntkctl_el1.el0vcten
+ */
+ mrs x1, cntkctl_el1
+ eon x0, x1, x22, lsr #3
+ tbz x0, #1, 4f
+ eor x1, x1, #2 // ARCH_TIMER_USR_VCT_ACCESS_EN
+ msr cntkctl_el1, x1
+4:
+#endif
apply_ssbd 0, x0, x1
.endif
@@ -362,11 +377,11 @@
.if \el == 0
alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
- bne 4f
+ bne 5f
msr far_el1, x30
tramp_alias x30, tramp_exit_native
br x30
-4:
+5:
tramp_alias x30, tramp_exit_compat
br x30
#endif
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 5ebe73b..735cf1f 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1258,14 +1258,14 @@ static inline void fpsimd_hotplug_init(void) { }
*/
static int __init fpsimd_init(void)
{
- if (elf_hwcap & HWCAP_FP) {
+ if (cpu_have_named_feature(FP)) {
fpsimd_pm_init();
fpsimd_hotplug_init();
} else {
pr_notice("Floating-point is not implemented\n");
}
- if (!(elf_hwcap & HWCAP_ASIMD))
+ if (!cpu_have_named_feature(ASIMD))
pr_notice("Advanced SIMD is not implemented\n");
return sve_sysctl_init();
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index eecf792..fcae3f8 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -505,7 +505,7 @@
* kernel is intended to run at EL2.
*/
mrs x2, id_aa64mmfr1_el1
- ubfx x2, x2, #8, #4
+ ubfx x2, x2, #ID_AA64MMFR1_VHE_SHIFT, #4
#else
mov x2, xzr
#endif
@@ -538,7 +538,7 @@
#ifdef CONFIG_ARM_GIC_V3
/* GICv3 system register access */
mrs x0, id_aa64pfr0_el1
- ubfx x0, x0, #24, #4
+ ubfx x0, x0, #ID_AA64PFR0_GIC_SHIFT, #4
cbz x0, 3f
mrs_s x0, SYS_ICC_SRE_EL2
@@ -564,8 +564,8 @@
#endif
/* EL2 debug */
- mrs x1, id_aa64dfr0_el1 // Check ID_AA64DFR0_EL1 PMUVer
- sbfx x0, x1, #8, #4
+ mrs x1, id_aa64dfr0_el1
+ sbfx x0, x1, #ID_AA64DFR0_PMUVER_SHIFT, #4
cmp x0, #1
b.lt 4f // Skip if no PMU present
mrs x0, pmcr_el0 // Disable debug access traps
@@ -574,7 +574,7 @@
csel x3, xzr, x0, lt // all PMU counters from EL1
/* Statistical profiling */
- ubfx x0, x1, #32, #4 // Check ID_AA64DFR0_EL1 PMSVer
+ ubfx x0, x1, #ID_AA64DFR0_PMSVER_SHIFT, #4
cbz x0, 7f // Skip if SPE not present
cbnz x2, 6f // VHE?
mrs_s x4, SYS_PMBIDR_EL1 // If SPE available at EL2,
@@ -684,7 +684,7 @@
* with MMU turned off.
*/
ENTRY(__early_cpu_boot_status)
- .long 0
+ .quad 0
.popsection
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index 691854b..30853d5 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -244,9 +244,6 @@ int kgdb_arch_handle_exception(int exception_vector, int signo,
static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr)
{
- if (user_mode(regs))
- return DBG_HOOK_ERROR;
-
kgdb_handle_exception(1, SIGTRAP, 0, regs);
return DBG_HOOK_HANDLED;
}
@@ -254,9 +251,6 @@ NOKPROBE_SYMBOL(kgdb_brk_fn)
static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
{
- if (user_mode(regs))
- return DBG_HOOK_ERROR;
-
compiled_break = 1;
kgdb_handle_exception(1, SIGTRAP, 0, regs);
@@ -266,7 +260,7 @@ NOKPROBE_SYMBOL(kgdb_compiled_brk_fn);
static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
{
- if (user_mode(regs) || !kgdb_single_step)
+ if (!kgdb_single_step)
return DBG_HOOK_ERROR;
kgdb_handle_exception(1, SIGTRAP, 0, regs);
@@ -275,15 +269,13 @@ static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
NOKPROBE_SYMBOL(kgdb_step_brk_fn);
static struct break_hook kgdb_brkpt_hook = {
- .esr_mask = 0xffffffff,
- .esr_val = (u32)ESR_ELx_VAL_BRK64(KGDB_DYN_DBG_BRK_IMM),
- .fn = kgdb_brk_fn
+ .fn = kgdb_brk_fn,
+ .imm = KGDB_DYN_DBG_BRK_IMM,
};
static struct break_hook kgdb_compiled_brkpt_hook = {
- .esr_mask = 0xffffffff,
- .esr_val = (u32)ESR_ELx_VAL_BRK64(KGDB_COMPILED_DBG_BRK_IMM),
- .fn = kgdb_compiled_brk_fn
+ .fn = kgdb_compiled_brk_fn,
+ .imm = KGDB_COMPILED_DBG_BRK_IMM,
};
static struct step_hook kgdb_step_hook = {
@@ -332,9 +324,9 @@ int kgdb_arch_init(void)
if (ret != 0)
return ret;
- register_break_hook(&kgdb_brkpt_hook);
- register_break_hook(&kgdb_compiled_brkpt_hook);
- register_step_hook(&kgdb_step_hook);
+ register_kernel_break_hook(&kgdb_brkpt_hook);
+ register_kernel_break_hook(&kgdb_compiled_brkpt_hook);
+ register_kernel_step_hook(&kgdb_step_hook);
return 0;
}
@@ -345,9 +337,9 @@ int kgdb_arch_init(void)
*/
void kgdb_arch_exit(void)
{
- unregister_break_hook(&kgdb_brkpt_hook);
- unregister_break_hook(&kgdb_compiled_brkpt_hook);
- unregister_step_hook(&kgdb_step_hook);
+ unregister_kernel_break_hook(&kgdb_brkpt_hook);
+ unregister_kernel_break_hook(&kgdb_compiled_brkpt_hook);
+ unregister_kernel_step_hook(&kgdb_step_hook);
unregister_die_notifier(&kgdb_notifier);
}
diff --git a/arch/arm64/kernel/kuser32.S b/arch/arm64/kernel/kuser32.S
index 997e6b2..49825e9 100644
--- a/arch/arm64/kernel/kuser32.S
+++ b/arch/arm64/kernel/kuser32.S
@@ -1,29 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
/*
- * Low-level user helpers placed in the vectors page for AArch32.
+ * AArch32 user helpers.
* Based on the kuser helpers in arch/arm/kernel/entry-armv.S.
*
* Copyright (C) 2005-2011 Nicolas Pitre <nico@fluxnic.net>
- * Copyright (C) 2012 ARM Ltd.
+ * Copyright (C) 2012-2018 ARM Ltd.
*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program. If not, see <http://www.gnu.org/licenses/>.
- *
- *
- * AArch32 user helpers.
- *
- * Each segment is 32-byte aligned and will be moved to the top of the high
- * vector page. New segments (if ever needed) must be added in front of
- * existing ones. This mechanism should be used only for things that are
- * really small and justified, and not be abused freely.
+ * The kuser helpers below are mapped at a fixed address by
+ * aarch32_setup_additional_pages() and are provided for compatibility
+ * reasons with 32 bit (aarch32) applications that need them.
*
* See Documentation/arm/kernel_user_helpers.txt for formal definitions.
*/
@@ -77,42 +62,3 @@
.word ((__kuser_helper_end - __kuser_helper_start) >> 5)
.globl __kuser_helper_end
__kuser_helper_end:
-
-/*
- * AArch32 sigreturn code
- *
- * For ARM syscalls, the syscall number has to be loaded into r7.
- * We do not support an OABI userspace.
- *
- * For Thumb syscalls, we also pass the syscall number via r7. We therefore
- * need two 16-bit instructions.
- */
- .globl __aarch32_sigret_code_start
-__aarch32_sigret_code_start:
-
- /*
- * ARM Code
- */
- .byte __NR_compat_sigreturn, 0x70, 0xa0, 0xe3 // mov r7, #__NR_compat_sigreturn
- .byte __NR_compat_sigreturn, 0x00, 0x00, 0xef // svc #__NR_compat_sigreturn
-
- /*
- * Thumb code
- */
- .byte __NR_compat_sigreturn, 0x27 // svc #__NR_compat_sigreturn
- .byte __NR_compat_sigreturn, 0xdf // mov r7, #__NR_compat_sigreturn
-
- /*
- * ARM code
- */
- .byte __NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3 // mov r7, #__NR_compat_rt_sigreturn
- .byte __NR_compat_rt_sigreturn, 0x00, 0x00, 0xef // svc #__NR_compat_rt_sigreturn
-
- /*
- * Thumb code
- */
- .byte __NR_compat_rt_sigreturn, 0x27 // svc #__NR_compat_rt_sigreturn
- .byte __NR_compat_rt_sigreturn, 0xdf // mov r7, #__NR_compat_rt_sigreturn
-
- .globl __aarch32_sigret_code_end
-__aarch32_sigret_code_end:
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 4addb38..6164d38 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -431,7 +431,7 @@ static inline u64 armv8pmu_read_hw_counter(struct perf_event *event)
return val;
}
-static inline u64 armv8pmu_read_counter(struct perf_event *event)
+static u64 armv8pmu_read_counter(struct perf_event *event)
{
struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
struct hw_perf_event *hwc = &event->hw;
@@ -468,7 +468,7 @@ static inline void armv8pmu_write_hw_counter(struct perf_event *event,
}
}
-static inline void armv8pmu_write_counter(struct perf_event *event, u64 value)
+static void armv8pmu_write_counter(struct perf_event *event, u64 value)
{
struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
struct hw_perf_event *hwc = &event->hw;
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 7a679ca..2509fcb 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -439,15 +439,12 @@ kprobe_ss_hit(struct kprobe_ctlblk *kcb, unsigned long addr)
return DBG_HOOK_ERROR;
}
-int __kprobes
+static int __kprobes
kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
{
struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
int retval;
- if (user_mode(regs))
- return DBG_HOOK_ERROR;
-
/* return error if this is not our step */
retval = kprobe_ss_hit(kcb, instruction_pointer(regs));
@@ -461,16 +458,22 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
return retval;
}
-int __kprobes
+static struct step_hook kprobes_step_hook = {
+ .fn = kprobe_single_step_handler,
+};
+
+static int __kprobes
kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
{
- if (user_mode(regs))
- return DBG_HOOK_ERROR;
-
kprobe_handler(regs);
return DBG_HOOK_HANDLED;
}
+static struct break_hook kprobes_break_hook = {
+ .imm = KPROBES_BRK_IMM,
+ .fn = kprobe_breakpoint_handler,
+};
+
/*
* Provide a blacklist of symbols identifying ranges which cannot be kprobed.
* This blacklist is exposed to userspace via debugfs (kprobes/blacklist).
@@ -599,5 +602,8 @@ int __kprobes arch_trampoline_kprobe(struct kprobe *p)
int __init arch_init_kprobes(void)
{
+ register_kernel_break_hook(&kprobes_break_hook);
+ register_kernel_step_hook(&kprobes_step_hook);
+
return 0;
}
diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c
index 636ca01..605945e 100644
--- a/arch/arm64/kernel/probes/uprobes.c
+++ b/arch/arm64/kernel/probes/uprobes.c
@@ -171,7 +171,7 @@ int arch_uprobe_exception_notify(struct notifier_block *self,
static int uprobe_breakpoint_handler(struct pt_regs *regs,
unsigned int esr)
{
- if (user_mode(regs) && uprobe_pre_sstep_notifier(regs))
+ if (uprobe_pre_sstep_notifier(regs))
return DBG_HOOK_HANDLED;
return DBG_HOOK_ERROR;
@@ -182,21 +182,16 @@ static int uprobe_single_step_handler(struct pt_regs *regs,
{
struct uprobe_task *utask = current->utask;
- if (user_mode(regs)) {
- WARN_ON(utask &&
- (instruction_pointer(regs) != utask->xol_vaddr + 4));
-
- if (uprobe_post_sstep_notifier(regs))
- return DBG_HOOK_HANDLED;
- }
+ WARN_ON(utask && (instruction_pointer(regs) != utask->xol_vaddr + 4));
+ if (uprobe_post_sstep_notifier(regs))
+ return DBG_HOOK_HANDLED;
return DBG_HOOK_ERROR;
}
/* uprobe breakpoint handler hook */
static struct break_hook uprobes_break_hook = {
- .esr_mask = BRK64_ESR_MASK,
- .esr_val = BRK64_ESR_UPROBES,
+ .imm = UPROBES_BRK_IMM,
.fn = uprobe_breakpoint_handler,
};
@@ -207,8 +202,8 @@ static struct step_hook uprobes_step_hook = {
static int __init arch_init_uprobes(void)
{
- register_break_hook(&uprobes_break_hook);
- register_step_hook(&uprobes_step_hook);
+ register_user_break_hook(&uprobes_break_hook);
+ register_user_step_hook(&uprobes_step_hook);
return 0;
}
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index cb7800a..caea6e2 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -403,8 +403,7 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
if (ka->sa.sa_flags & SA_SIGINFO)
idx += 3;
- retcode = AARCH32_VECTORS_BASE +
- AARCH32_KERN_SIGRET_CODE_OFFSET +
+ retcode = (unsigned long)current->mm->context.vdso +
(idx << 2) + thumb;
}
diff --git a/arch/arm64/kernel/sigreturn32.S b/arch/arm64/kernel/sigreturn32.S
new file mode 100644
index 0000000..475d30d
--- /dev/null
+++ b/arch/arm64/kernel/sigreturn32.S
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AArch32 sigreturn code.
+ * Based on the kuser helpers in arch/arm/kernel/entry-armv.S.
+ *
+ * Copyright (C) 2005-2011 Nicolas Pitre <nico@fluxnic.net>
+ * Copyright (C) 2012-2018 ARM Ltd.
+ *
+ * For ARM syscalls, the syscall number has to be loaded into r7.
+ * We do not support an OABI userspace.
+ *
+ * For Thumb syscalls, we also pass the syscall number via r7. We therefore
+ * need two 16-bit instructions.
+ */
+
+#include <asm/unistd.h>
+
+ .globl __aarch32_sigret_code_start
+__aarch32_sigret_code_start:
+
+ /*
+ * ARM Code
+ */
+ .byte __NR_compat_sigreturn, 0x70, 0xa0, 0xe3 // mov r7, #__NR_compat_sigreturn
+ .byte __NR_compat_sigreturn, 0x00, 0x00, 0xef // svc #__NR_compat_sigreturn
+
+ /*
+ * Thumb code
+ */
+ .byte __NR_compat_sigreturn, 0x27 // svc #__NR_compat_sigreturn
+ .byte __NR_compat_sigreturn, 0xdf // mov r7, #__NR_compat_sigreturn
+
+ /*
+ * ARM code
+ */
+ .byte __NR_compat_rt_sigreturn, 0x70, 0xa0, 0xe3 // mov r7, #__NR_compat_rt_sigreturn
+ .byte __NR_compat_rt_sigreturn, 0x00, 0x00, 0xef // svc #__NR_compat_rt_sigreturn
+
+ /*
+ * Thumb code
+ */
+ .byte __NR_compat_rt_sigreturn, 0x27 // svc #__NR_compat_rt_sigreturn
+ .byte __NR_compat_rt_sigreturn, 0xdf // mov r7, #__NR_compat_rt_sigreturn
+
+ .globl __aarch32_sigret_code_end
+__aarch32_sigret_code_end:
diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c
index b44065f..6f91e81 100644
--- a/arch/arm64/kernel/sys.c
+++ b/arch/arm64/kernel/sys.c
@@ -31,7 +31,7 @@
SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
unsigned long, prot, unsigned long, flags,
- unsigned long, fd, off_t, off)
+ unsigned long, fd, unsigned long, off)
{
if (offset_in_page(off) != 0)
return -EINVAL;
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 2975598..ade3204 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -462,6 +462,9 @@ static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
case ESR_ELx_SYS64_ISS_CRM_DC_CVAC: /* DC CVAC, gets promoted */
__user_cache_maint("dc civac", address, ret);
break;
+ case ESR_ELx_SYS64_ISS_CRM_DC_CVADP: /* DC CVADP */
+ __user_cache_maint("sys 3, c7, c13, 1", address, ret);
+ break;
case ESR_ELx_SYS64_ISS_CRM_DC_CVAP: /* DC CVAP */
__user_cache_maint("sys 3, c7, c12, 1", address, ret);
break;
@@ -496,7 +499,7 @@ static void cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
{
int rt = ESR_ELx_SYS64_ISS_RT(esr);
- pt_regs_write_reg(regs, rt, arch_counter_get_cntvct());
+ pt_regs_write_reg(regs, rt, arch_timer_read_counter());
arm64_skip_faulting_instruction(regs, AARCH64_INSN_SIZE);
}
@@ -668,7 +671,7 @@ static void compat_cntvct_read_handler(unsigned int esr, struct pt_regs *regs)
{
int rt = (esr & ESR_ELx_CP15_64_ISS_RT_MASK) >> ESR_ELx_CP15_64_ISS_RT_SHIFT;
int rt2 = (esr & ESR_ELx_CP15_64_ISS_RT2_MASK) >> ESR_ELx_CP15_64_ISS_RT2_SHIFT;
- u64 val = arch_counter_get_cntvct();
+ u64 val = arch_timer_read_counter();
pt_regs_write_reg(regs, rt, lower_32_bits(val));
pt_regs_write_reg(regs, rt2, upper_32_bits(val));
@@ -950,9 +953,6 @@ int is_valid_bugaddr(unsigned long addr)
static int bug_handler(struct pt_regs *regs, unsigned int esr)
{
- if (user_mode(regs))
- return DBG_HOOK_ERROR;
-
switch (report_bug(regs->pc, regs)) {
case BUG_TRAP_TYPE_BUG:
die("Oops - BUG", regs, 0);
@@ -972,9 +972,8 @@ static int bug_handler(struct pt_regs *regs, unsigned int esr)
}
static struct break_hook bug_break_hook = {
- .esr_val = 0xf2000000 | BUG_BRK_IMM,
- .esr_mask = 0xffffffff,
.fn = bug_handler,
+ .imm = BUG_BRK_IMM,
};
#ifdef CONFIG_KASAN_SW_TAGS
@@ -992,9 +991,6 @@ static int kasan_handler(struct pt_regs *regs, unsigned int esr)
u64 addr = regs->regs[0];
u64 pc = regs->pc;
- if (user_mode(regs))
- return DBG_HOOK_ERROR;
-
kasan_report(addr, size, write, pc);
/*
@@ -1019,13 +1015,10 @@ static int kasan_handler(struct pt_regs *regs, unsigned int esr)
return DBG_HOOK_HANDLED;
}
-#define KASAN_ESR_VAL (0xf2000000 | KASAN_BRK_IMM)
-#define KASAN_ESR_MASK 0xffffff00
-
static struct break_hook kasan_break_hook = {
- .esr_val = KASAN_ESR_VAL,
- .esr_mask = KASAN_ESR_MASK,
- .fn = kasan_handler,
+ .fn = kasan_handler,
+ .imm = KASAN_BRK_IMM,
+ .mask = KASAN_BRK_MASK,
};
#endif
@@ -1037,7 +1030,9 @@ int __init early_brk64(unsigned long addr, unsigned int esr,
struct pt_regs *regs)
{
#ifdef CONFIG_KASAN_SW_TAGS
- if ((esr & KASAN_ESR_MASK) == KASAN_ESR_VAL)
+ unsigned int comment = esr & ESR_ELx_BRK64_ISS_COMMENT_MASK;
+
+ if ((comment & ~KASAN_BRK_MASK) == KASAN_BRK_IMM)
return kasan_handler(regs, esr) != DBG_HOOK_HANDLED;
#endif
return bug_handler(regs, esr) != DBG_HOOK_HANDLED;
@@ -1046,8 +1041,8 @@ int __init early_brk64(unsigned long addr, unsigned int esr,
/* This registration must happen early, before debug_traps_init(). */
void __init trap_init(void)
{
- register_break_hook(&bug_break_hook);
+ register_kernel_break_hook(&bug_break_hook);
#ifdef CONFIG_KASAN_SW_TAGS
- register_break_hook(&kasan_break_hook);
+ register_kernel_break_hook(&kasan_break_hook);
#endif
}
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 2d41900..8074cbd 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -1,5 +1,5 @@
/*
- * VDSO implementation for AArch64 and vector page setup for AArch32.
+ * VDSO implementations.
*
* Copyright (C) 2012 ARM Limited
*
@@ -53,60 +53,128 @@ struct vdso_data *vdso_data = &vdso_data_store.data;
/*
* Create and map the vectors page for AArch32 tasks.
*/
-static struct page *vectors_page[1] __ro_after_init;
+#define C_VECTORS 0
+#define C_SIGPAGE 1
+#define C_PAGES (C_SIGPAGE + 1)
+static struct page *aarch32_vdso_pages[C_PAGES] __ro_after_init;
+static const struct vm_special_mapping aarch32_vdso_spec[C_PAGES] = {
+ {
+ .name = "[vectors]", /* ABI */
+ .pages = &aarch32_vdso_pages[C_VECTORS],
+ },
+ {
+ .name = "[sigpage]", /* ABI */
+ .pages = &aarch32_vdso_pages[C_SIGPAGE],
+ },
+};
-static int __init alloc_vectors_page(void)
+static int aarch32_alloc_kuser_vdso_page(void)
{
extern char __kuser_helper_start[], __kuser_helper_end[];
- extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
-
int kuser_sz = __kuser_helper_end - __kuser_helper_start;
- int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
- unsigned long vpage;
+ unsigned long vdso_page;
- vpage = get_zeroed_page(GFP_ATOMIC);
+ if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
+ return 0;
- if (!vpage)
+ vdso_page = get_zeroed_page(GFP_ATOMIC);
+ if (!vdso_page)
return -ENOMEM;
- /* kuser helpers */
- memcpy((void *)vpage + 0x1000 - kuser_sz, __kuser_helper_start,
- kuser_sz);
-
- /* sigreturn code */
- memcpy((void *)vpage + AARCH32_KERN_SIGRET_CODE_OFFSET,
- __aarch32_sigret_code_start, sigret_sz);
-
- flush_icache_range(vpage, vpage + PAGE_SIZE);
- vectors_page[0] = virt_to_page(vpage);
-
+ memcpy((void *)(vdso_page + 0x1000 - kuser_sz), __kuser_helper_start,
+ kuser_sz);
+ aarch32_vdso_pages[C_VECTORS] = virt_to_page(vdso_page);
+ flush_dcache_page(aarch32_vdso_pages[C_VECTORS]);
return 0;
}
-arch_initcall(alloc_vectors_page);
-int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp)
+static int __init aarch32_alloc_vdso_pages(void)
+{
+ extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
+ int sigret_sz = __aarch32_sigret_code_end - __aarch32_sigret_code_start;
+ unsigned long sigpage;
+ int ret;
+
+ sigpage = get_zeroed_page(GFP_ATOMIC);
+ if (!sigpage)
+ return -ENOMEM;
+
+ memcpy((void *)sigpage, __aarch32_sigret_code_start, sigret_sz);
+ aarch32_vdso_pages[C_SIGPAGE] = virt_to_page(sigpage);
+ flush_dcache_page(aarch32_vdso_pages[C_SIGPAGE]);
+
+ ret = aarch32_alloc_kuser_vdso_page();
+ if (ret)
+ free_page(sigpage);
+
+ return ret;
+}
+arch_initcall(aarch32_alloc_vdso_pages);
+
+static int aarch32_kuser_helpers_setup(struct mm_struct *mm)
+{
+ void *ret;
+
+ if (!IS_ENABLED(CONFIG_KUSER_HELPERS))
+ return 0;
+
+ /*
+ * Avoid VM_MAYWRITE for compatibility with arch/arm/, where it's
+ * not safe to CoW the page containing the CPU exception vectors.
+ */
+ ret = _install_special_mapping(mm, AARCH32_VECTORS_BASE, PAGE_SIZE,
+ VM_READ | VM_EXEC |
+ VM_MAYREAD | VM_MAYEXEC,
+ &aarch32_vdso_spec[C_VECTORS]);
+
+ return PTR_ERR_OR_ZERO(ret);
+}
+
+static int aarch32_sigreturn_setup(struct mm_struct *mm)
+{
+ unsigned long addr;
+ void *ret;
+
+ addr = get_unmapped_area(NULL, 0, PAGE_SIZE, 0, 0);
+ if (IS_ERR_VALUE(addr)) {
+ ret = ERR_PTR(addr);
+ goto out;
+ }
+
+ /*
+ * VM_MAYWRITE is required to allow gdb to Copy-on-Write and
+ * set breakpoints.
+ */
+ ret = _install_special_mapping(mm, addr, PAGE_SIZE,
+ VM_READ | VM_EXEC | VM_MAYREAD |
+ VM_MAYWRITE | VM_MAYEXEC,
+ &aarch32_vdso_spec[C_SIGPAGE]);
+ if (IS_ERR(ret))
+ goto out;
+
+ mm->context.vdso = (void *)addr;
+
+out:
+ return PTR_ERR_OR_ZERO(ret);
+}
+
+int aarch32_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
struct mm_struct *mm = current->mm;
- unsigned long addr = AARCH32_VECTORS_BASE;
- static const struct vm_special_mapping spec = {
- .name = "[vectors]",
- .pages = vectors_page,
-
- };
- void *ret;
+ int ret;
if (down_write_killable(&mm->mmap_sem))
return -EINTR;
- current->mm->context.vdso = (void *)addr;
- /* Map vectors page at the high address. */
- ret = _install_special_mapping(mm, addr, PAGE_SIZE,
- VM_READ|VM_EXEC|VM_MAYREAD|VM_MAYEXEC,
- &spec);
+ ret = aarch32_kuser_helpers_setup(mm);
+ if (ret)
+ goto out;
+ ret = aarch32_sigreturn_setup(mm);
+
+out:
up_write(&mm->mmap_sem);
-
- return PTR_ERR_OR_ZERO(ret);
+ return ret;
}
#endif /* CONFIG_COMPAT */
@@ -146,8 +214,6 @@ static int __init vdso_init(void)
}
vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
- pr_info("vdso: %ld pages (%ld code @ %p, %ld data @ %p)\n",
- vdso_pages + 1, vdso_pages, vdso_start, 1L, vdso_data);
/* Allocate the vDSO pagelist, plus a page for the data. */
vdso_pagelist = kcalloc(vdso_pages + 1, sizeof(struct page *),
@@ -232,6 +298,9 @@ void update_vsyscall(struct timekeeper *tk)
vdso_data->wtm_clock_sec = tk->wall_to_monotonic.tv_sec;
vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec;
+ /* Read without the seqlock held by clock_getres() */
+ WRITE_ONCE(vdso_data->hrtimer_res, hrtimer_resolution);
+
if (!use_syscall) {
/* tkr_mono.cycle_last == tkr_raw.cycle_last */
vdso_data->cs_cycle_last = tk->tkr_mono.cycle_last;
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
index b215c71..744b9db 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
@@ -12,17 +12,12 @@
targets := $(obj-vdso) vdso.so vdso.so.dbg
obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
-ccflags-y := -shared -fno-common -fno-builtin
-ccflags-y += -nostdlib -Wl,-soname=linux-vdso.so.1 \
- $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 \
+ $(call ld-option, --hash-style=sysv) -n -T
# Disable gcov profiling for VDSO code
GCOV_PROFILE := n
-# Workaround for bare-metal (ELF) toolchains that neglect to pass -shared
-# down to collect2, resulting in silent corruption of the vDSO image.
-ccflags-y += -Wl,-shared
-
obj-y += vdso.o
extra-y += vdso.lds
CPPFLAGS_vdso.lds += -P -C -U$(ARCH)
@@ -31,8 +26,8 @@
$(obj)/vdso.o : $(obj)/vdso.so
# Link rule for the .so file, .lds has to be first
-$(obj)/vdso.so.dbg: $(src)/vdso.lds $(obj-vdso)
- $(call if_changed,vdsold)
+$(obj)/vdso.so.dbg: $(obj)/vdso.lds $(obj-vdso) FORCE
+ $(call if_changed,ld)
# Strip rule for the .so file
$(obj)/%.so: OBJCOPYFLAGS := -S
@@ -42,9 +37,7 @@
# Generate VDSO offsets using helper script
gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh
quiet_cmd_vdsosym = VDSOSYM $@
-define cmd_vdsosym
- $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
-endef
+ cmd_vdsosym = $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@
include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE
$(call if_changed,vdsosym)
@@ -54,8 +47,6 @@
$(call if_changed_dep,vdsoas)
# Actual build commands
-quiet_cmd_vdsold = VDSOL $@
- cmd_vdsold = $(CC) $(c_flags) -Wl,-n -Wl,-T $^ -o $@
quiet_cmd_vdsoas = VDSOA $@
cmd_vdsoas = $(CC) $(a_flags) -c -o $@ $<
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index c39872a..856fee6 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -73,6 +73,13 @@
movn x_tmp, #0xff00, lsl #48
and \res, x_tmp, \res
mul \res, \res, \mult
+ /*
+ * Fake address dependency from the value computed from the counter
+ * register to subsequent data page accesses so that the sequence
+ * locking also orders the read of the counter.
+ */
+ and x_tmp, \res, xzr
+ add vdso_data, vdso_data, x_tmp
.endm
/*
@@ -147,12 +154,12 @@
/* w11 = cs_mono_mult, w12 = cs_shift */
ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
- seqcnt_check fail=1b
get_nsec_per_sec res=x9
lsl x9, x9, x12
get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+ seqcnt_check fail=1b
get_ts_realtime res_sec=x10, res_nsec=x11, \
clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
@@ -211,13 +218,13 @@
/* w11 = cs_mono_mult, w12 = cs_shift */
ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
- seqcnt_check fail=realtime
/* All computations are done with left-shifted nsecs. */
get_nsec_per_sec res=x9
lsl x9, x9, x12
get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+ seqcnt_check fail=realtime
get_ts_realtime res_sec=x10, res_nsec=x11, \
clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
clock_gettime_return, shift=1
@@ -231,7 +238,6 @@
ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
ldp x3, x4, [vdso_data, #VDSO_WTM_CLK_SEC]
- seqcnt_check fail=monotonic
/* All computations are done with left-shifted nsecs. */
lsl x4, x4, x12
@@ -239,6 +245,7 @@
lsl x9, x9, x12
get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+ seqcnt_check fail=monotonic
get_ts_realtime res_sec=x10, res_nsec=x11, \
clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
@@ -253,13 +260,13 @@
/* w11 = cs_raw_mult, w12 = cs_shift */
ldp w12, w11, [vdso_data, #VDSO_CS_SHIFT]
ldp x13, x14, [vdso_data, #VDSO_RAW_TIME_SEC]
- seqcnt_check fail=monotonic_raw
/* All computations are done with left-shifted nsecs. */
get_nsec_per_sec res=x9
lsl x9, x9, x12
get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+ seqcnt_check fail=monotonic_raw
get_ts_clock_raw res_sec=x10, res_nsec=x11, \
clock_nsec=x15, nsec_to_sec=x9
@@ -301,13 +308,14 @@
ccmp w0, #CLOCK_MONOTONIC_RAW, #0x4, ne
b.ne 1f
- ldr x2, 5f
+ adr vdso_data, _vdso_data
+ ldr w2, [vdso_data, #CLOCK_REALTIME_RES]
b 2f
1:
cmp w0, #CLOCK_REALTIME_COARSE
ccmp w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne
b.ne 4f
- ldr x2, 6f
+ ldr x2, 5f
2:
cbz x1, 3f
stp xzr, x2, [x1]
@@ -321,8 +329,6 @@
svc #0
ret
5:
- .quad CLOCK_REALTIME_RES
-6:
.quad CLOCK_COARSE_RES
.cfi_endproc
ENDPROC(__kernel_clock_getres)
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 5540a16..33c2a4a 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -24,7 +24,7 @@
-fcall-saved-x10 -fcall-saved-x11 -fcall-saved-x12 \
-fcall-saved-x13 -fcall-saved-x14 -fcall-saved-x15 \
-fcall-saved-x18 -fomit-frame-pointer
-CFLAGS_REMOVE_atomic_ll_sc.o := -pg
+CFLAGS_REMOVE_atomic_ll_sc.o := $(CC_FLAGS_FTRACE)
GCOV_PROFILE_atomic_ll_sc.o := n
KASAN_SANITIZE_atomic_ll_sc.o := n
KCOV_INSTRUMENT_atomic_ll_sc.o := n
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 1a7e92a..0cb0e09 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -148,7 +148,7 @@ static inline bool is_ttbr1_addr(unsigned long addr)
/*
* Dump out the page tables associated with 'addr' in the currently active mm.
*/
-void show_pte(unsigned long addr)
+static void show_pte(unsigned long addr)
{
struct mm_struct *mm;
pgd_t *pgdp;
@@ -810,13 +810,12 @@ void __init hook_debug_fault_code(int nr,
debug_fault_info[nr].name = name;
}
-asmlinkage int __exception do_debug_exception(unsigned long addr_if_watchpoint,
- unsigned int esr,
- struct pt_regs *regs)
+asmlinkage void __exception do_debug_exception(unsigned long addr_if_watchpoint,
+ unsigned int esr,
+ struct pt_regs *regs)
{
const struct fault_info *inf = esr_to_debug_fault_info(esr);
unsigned long pc = instruction_pointer(regs);
- int rv;
/*
* Tell lockdep we disabled irqs in entry.S. Do nothing if they were
@@ -828,17 +827,12 @@ asmlinkage int __exception do_debug_exception(unsigned long addr_if_watchpoint,
if (user_mode(regs) && !is_ttbr0_addr(pc))
arm64_apply_bp_hardening();
- if (!inf->fn(addr_if_watchpoint, esr, regs)) {
- rv = 1;
- } else {
+ if (inf->fn(addr_if_watchpoint, esr, regs)) {
arm64_notify_die(inf->name, regs,
inf->sig, inf->code, (void __user *)pc, esr);
- rv = 0;
}
if (interrupts_enabled(regs))
trace_hardirqs_on();
-
- return rv;
}
NOKPROBE_SYMBOL(do_debug_exception);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 7cae155..40e2d7e 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -377,7 +377,7 @@ void __init arm64_memblock_init(void)
base + size > memblock_start_of_DRAM() +
linear_region_size,
"initrd not fully accessible via the linear mapping -- please check your bootloader ...\n")) {
- initrd_start = 0;
+ phys_initrd_size = 0;
} else {
memblock_remove(base, size); /* clear MEMBLOCK_ flags */
memblock_add(base, size);
@@ -440,6 +440,7 @@ void __init bootmem_init(void)
early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);
max_pfn = max_low_pfn = max;
+ min_low_pfn = min;
arm64_numa_init();
/*
@@ -535,7 +536,7 @@ void __init mem_init(void)
else
swiotlb_force = SWIOTLB_NO_FORCE;
- set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
+ set_max_mapnr(max_pfn - PHYS_PFN_OFFSET);
#ifndef CONFIG_SPARSEMEM_VMEMMAP
free_unused_memmap();
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index e97f018..ef82312 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -97,7 +97,7 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
}
EXPORT_SYMBOL(phys_mem_access_prot);
-static phys_addr_t __init early_pgtable_alloc(void)
+static phys_addr_t __init early_pgtable_alloc(int shift)
{
phys_addr_t phys;
void *ptr;
@@ -174,7 +174,7 @@ static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
unsigned long end, phys_addr_t phys,
pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void),
+ phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long next;
@@ -184,7 +184,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
if (pmd_none(pmd)) {
phys_addr_t pte_phys;
BUG_ON(!pgtable_alloc);
- pte_phys = pgtable_alloc();
+ pte_phys = pgtable_alloc(PAGE_SHIFT);
__pmd_populate(pmdp, pte_phys, PMD_TYPE_TABLE);
pmd = READ_ONCE(*pmdp);
}
@@ -208,7 +208,7 @@ static void alloc_init_cont_pte(pmd_t *pmdp, unsigned long addr,
static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void), int flags)
+ phys_addr_t (*pgtable_alloc)(int), int flags)
{
unsigned long next;
pmd_t *pmdp;
@@ -246,7 +246,7 @@ static void init_pmd(pud_t *pudp, unsigned long addr, unsigned long end,
static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
unsigned long end, phys_addr_t phys,
pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void), int flags)
+ phys_addr_t (*pgtable_alloc)(int), int flags)
{
unsigned long next;
pud_t pud = READ_ONCE(*pudp);
@@ -258,7 +258,7 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
if (pud_none(pud)) {
phys_addr_t pmd_phys;
BUG_ON(!pgtable_alloc);
- pmd_phys = pgtable_alloc();
+ pmd_phys = pgtable_alloc(PMD_SHIFT);
__pud_populate(pudp, pmd_phys, PUD_TYPE_TABLE);
pud = READ_ONCE(*pudp);
}
@@ -294,7 +294,7 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next,
static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
phys_addr_t phys, pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void),
+ phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long next;
@@ -304,7 +304,7 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
if (pgd_none(pgd)) {
phys_addr_t pud_phys;
BUG_ON(!pgtable_alloc);
- pud_phys = pgtable_alloc();
+ pud_phys = pgtable_alloc(PUD_SHIFT);
__pgd_populate(pgdp, pud_phys, PUD_TYPE_TABLE);
pgd = READ_ONCE(*pgdp);
}
@@ -345,7 +345,7 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
unsigned long virt, phys_addr_t size,
pgprot_t prot,
- phys_addr_t (*pgtable_alloc)(void),
+ phys_addr_t (*pgtable_alloc)(int),
int flags)
{
unsigned long addr, length, end, next;
@@ -371,17 +371,36 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
} while (pgdp++, addr = next, addr != end);
}
-static phys_addr_t pgd_pgtable_alloc(void)
+static phys_addr_t __pgd_pgtable_alloc(int shift)
{
void *ptr = (void *)__get_free_page(PGALLOC_GFP);
- if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
- BUG();
+ BUG_ON(!ptr);
/* Ensure the zeroed page is visible to the page table walker */
dsb(ishst);
return __pa(ptr);
}
+static phys_addr_t pgd_pgtable_alloc(int shift)
+{
+ phys_addr_t pa = __pgd_pgtable_alloc(shift);
+
+ /*
+ * Call proper page table ctor in case later we need to
+ * call core mm functions like apply_to_page_range() on
+ * this pre-allocated page table.
+ *
+ * We don't select ARCH_ENABLE_SPLIT_PMD_PTLOCK if pmd is
+ * folded, and if so pgtable_pmd_page_ctor() becomes nop.
+ */
+ if (shift == PAGE_SHIFT)
+ BUG_ON(!pgtable_page_ctor(phys_to_page(pa)));
+ else if (shift == PMD_SHIFT)
+ BUG_ON(!pgtable_pmd_page_ctor(phys_to_page(pa)));
+
+ return pa;
+}
+
/*
* This function can only be used to modify existing table entries,
* without allocating new levels of table. Note that this permits the
@@ -583,7 +602,7 @@ static int __init map_entry_trampoline(void)
/* Map only the text into the trampoline page table */
memset(tramp_pg_dir, 0, PGD_SIZE);
__create_pgd_mapping(tramp_pg_dir, pa_start, TRAMP_VALIAS, PAGE_SIZE,
- prot, pgd_pgtable_alloc, 0);
+ prot, __pgd_pgtable_alloc, 0);
/* Map both the text and data into the kernel page table */
__set_fixmap(FIX_ENTRY_TRAMP_TEXT, pa_start, prot);
@@ -1055,7 +1074,7 @@ int arch_add_memory(int nid, u64 start, u64 size, struct vmem_altmap *altmap,
flags = NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
- size, PAGE_KERNEL, pgd_pgtable_alloc, flags);
+ size, PAGE_KERNEL, __pgd_pgtable_alloc, flags);
return __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT,
altmap, want_memblock);
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 06a6f26..5202f63 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -124,7 +124,7 @@ static void __init setup_node_to_cpumask_map(void)
}
/*
- * Set the cpu to node and mem mapping
+ * Set the cpu to node and mem mapping
*/
void numa_store_cpu_info(unsigned int cpu)
{
@@ -200,7 +200,7 @@ void __init setup_per_cpu_areas(void)
#endif
/**
- * numa_add_memblk - Set node id to memblk
+ * numa_add_memblk() - Set node id to memblk
* @nid: NUMA node ID of the new memblk
* @start: Start address of the new memblk
* @end: End address of the new memblk
@@ -223,7 +223,7 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
return ret;
}
-/**
+/*
* Initialize NODE_DATA for a node on the local memory
*/
static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
@@ -257,7 +257,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
}
-/**
+/*
* numa_free_distance
*
* The current table is freed.
@@ -277,10 +277,8 @@ void __init numa_free_distance(void)
numa_distance = NULL;
}
-/**
- *
+/*
* Create a new NUMA distance table.
- *
*/
static int __init numa_alloc_distance(void)
{
@@ -311,7 +309,7 @@ static int __init numa_alloc_distance(void)
}
/**
- * numa_set_distance - Set inter node NUMA distance from node to node.
+ * numa_set_distance() - Set inter node NUMA distance from node to node.
* @from: the 'from' node to set distance
* @to: the 'to' node to set distance
* @distance: NUMA distance
@@ -321,7 +319,6 @@ static int __init numa_alloc_distance(void)
*
* If @from or @to is higher than the highest known node or lower than zero
* or @distance doesn't make sense, the call is ignored.
- *
*/
void __init numa_set_distance(int from, int to, int distance)
{
@@ -347,7 +344,7 @@ void __init numa_set_distance(int from, int to, int distance)
numa_distance[from * numa_distance_cnt + to] = distance;
}
-/**
+/*
* Return NUMA distance @from to @to
*/
int __node_distance(int from, int to)
@@ -422,13 +419,15 @@ static int __init numa_init(int (*init_func)(void))
}
/**
- * dummy_numa_init - Fallback dummy NUMA init
+ * dummy_numa_init() - Fallback dummy NUMA init
*
* Used if there's no underlying NUMA architecture, NUMA initialization
* fails, or NUMA is disabled on the command line.
*
* Must online at least one node (node 0) and add memory blocks that cover all
* allowed memory. It is unlikely that this function fails.
+ *
+ * Return: 0 on success, -errno on failure.
*/
static int __init dummy_numa_init(void)
{
@@ -454,9 +453,9 @@ static int __init dummy_numa_init(void)
}
/**
- * arm64_numa_init - Initialize NUMA
+ * arm64_numa_init() - Initialize NUMA
*
- * Try each configured NUMA initialization method until one succeeds. The
+ * Try each configured NUMA initialization method until one succeeds. The
* last fallback is dummy single node config encomapssing whole memory.
*/
void __init arm64_numa_init(void)
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index aa0817c..fdd626d 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -65,24 +65,25 @@
mrs x2, tpidr_el0
mrs x3, tpidrro_el0
mrs x4, contextidr_el1
- mrs x5, cpacr_el1
- mrs x6, tcr_el1
- mrs x7, vbar_el1
- mrs x8, mdscr_el1
- mrs x9, oslsr_el1
- mrs x10, sctlr_el1
+ mrs x5, osdlr_el1
+ mrs x6, cpacr_el1
+ mrs x7, tcr_el1
+ mrs x8, vbar_el1
+ mrs x9, mdscr_el1
+ mrs x10, oslsr_el1
+ mrs x11, sctlr_el1
alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
- mrs x11, tpidr_el1
+ mrs x12, tpidr_el1
alternative_else
- mrs x11, tpidr_el2
+ mrs x12, tpidr_el2
alternative_endif
- mrs x12, sp_el0
+ mrs x13, sp_el0
stp x2, x3, [x0]
- stp x4, xzr, [x0, #16]
- stp x5, x6, [x0, #32]
- stp x7, x8, [x0, #48]
- stp x9, x10, [x0, #64]
- stp x11, x12, [x0, #80]
+ stp x4, x5, [x0, #16]
+ stp x6, x7, [x0, #32]
+ stp x8, x9, [x0, #48]
+ stp x10, x11, [x0, #64]
+ stp x12, x13, [x0, #80]
ret
ENDPROC(cpu_do_suspend)
@@ -105,8 +106,8 @@
msr cpacr_el1, x6
/* Don't change t0sz here, mask those bits when restoring */
- mrs x5, tcr_el1
- bfi x8, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
+ mrs x7, tcr_el1
+ bfi x8, x7, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
msr tcr_el1, x8
msr vbar_el1, x9
@@ -130,6 +131,7 @@
/*
* Restore oslsr_el1 by writing oslar_el1
*/
+ msr osdlr_el1, x5
ubfx x11, x11, #1, #1
msr oslar_el1, x11
reset_pmuserenr_el0 x0 // Disable PMU access from EL0
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index e48894e..adbf7cb 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -356,7 +356,8 @@ static struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node,
if (map->flags & ACPI_IORT_ID_SINGLE_MAPPING) {
if (node->type == ACPI_IORT_NODE_NAMED_COMPONENT ||
node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX ||
- node->type == ACPI_IORT_NODE_SMMU_V3) {
+ node->type == ACPI_IORT_NODE_SMMU_V3 ||
+ node->type == ACPI_IORT_NODE_PMCG) {
*id_out = map->output_base;
return parent;
}
@@ -394,6 +395,8 @@ static int iort_get_id_mapping_index(struct acpi_iort_node *node)
}
return smmu->id_mapping_index;
+ case ACPI_IORT_NODE_PMCG:
+ return 0;
default:
return -EINVAL;
}
@@ -1218,32 +1221,47 @@ static void __init arm_smmu_v3_init_resources(struct resource *res,
}
}
-static bool __init arm_smmu_v3_is_coherent(struct acpi_iort_node *node)
+static void __init arm_smmu_v3_dma_configure(struct device *dev,
+ struct acpi_iort_node *node)
{
struct acpi_iort_smmu_v3 *smmu;
+ enum dev_dma_attr attr;
/* Retrieve SMMUv3 specific data */
smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
- return smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE;
+ attr = (smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE) ?
+ DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
+
+ /* We expect the dma masks to be equivalent for all SMMUv3 set-ups */
+ dev->dma_mask = &dev->coherent_dma_mask;
+
+ /* Configure DMA for the page table walker */
+ acpi_dma_configure(dev, attr);
}
#if defined(CONFIG_ACPI_NUMA)
/*
* set numa proximity domain for smmuv3 device
*/
-static void __init arm_smmu_v3_set_proximity(struct device *dev,
+static int __init arm_smmu_v3_set_proximity(struct device *dev,
struct acpi_iort_node *node)
{
struct acpi_iort_smmu_v3 *smmu;
smmu = (struct acpi_iort_smmu_v3 *)node->node_data;
if (smmu->flags & ACPI_IORT_SMMU_V3_PXM_VALID) {
- set_dev_node(dev, acpi_map_pxm_to_node(smmu->pxm));
+ int node = acpi_map_pxm_to_node(smmu->pxm);
+
+ if (node != NUMA_NO_NODE && !node_online(node))
+ return -EINVAL;
+
+ set_dev_node(dev, node);
pr_info("SMMU-v3[%llx] Mapped to Proximity domain %d\n",
smmu->base_address,
smmu->pxm);
}
+ return 0;
}
#else
#define arm_smmu_v3_set_proximity NULL
@@ -1301,30 +1319,96 @@ static void __init arm_smmu_init_resources(struct resource *res,
}
}
-static bool __init arm_smmu_is_coherent(struct acpi_iort_node *node)
+static void __init arm_smmu_dma_configure(struct device *dev,
+ struct acpi_iort_node *node)
{
struct acpi_iort_smmu *smmu;
+ enum dev_dma_attr attr;
/* Retrieve SMMU specific data */
smmu = (struct acpi_iort_smmu *)node->node_data;
- return smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK;
+ attr = (smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK) ?
+ DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
+
+ /* We expect the dma masks to be equivalent for SMMU set-ups */
+ dev->dma_mask = &dev->coherent_dma_mask;
+
+ /* Configure DMA for the page table walker */
+ acpi_dma_configure(dev, attr);
+}
+
+static int __init arm_smmu_v3_pmcg_count_resources(struct acpi_iort_node *node)
+{
+ struct acpi_iort_pmcg *pmcg;
+
+ /* Retrieve PMCG specific data */
+ pmcg = (struct acpi_iort_pmcg *)node->node_data;
+
+ /*
+ * There are always 2 memory resources.
+ * If the overflow_gsiv is present then add that for a total of 3.
+ */
+ return pmcg->overflow_gsiv ? 3 : 2;
+}
+
+static void __init arm_smmu_v3_pmcg_init_resources(struct resource *res,
+ struct acpi_iort_node *node)
+{
+ struct acpi_iort_pmcg *pmcg;
+
+ /* Retrieve PMCG specific data */
+ pmcg = (struct acpi_iort_pmcg *)node->node_data;
+
+ res[0].start = pmcg->page0_base_address;
+ res[0].end = pmcg->page0_base_address + SZ_4K - 1;
+ res[0].flags = IORESOURCE_MEM;
+ res[1].start = pmcg->page1_base_address;
+ res[1].end = pmcg->page1_base_address + SZ_4K - 1;
+ res[1].flags = IORESOURCE_MEM;
+
+ if (pmcg->overflow_gsiv)
+ acpi_iort_register_irq(pmcg->overflow_gsiv, "overflow",
+ ACPI_EDGE_SENSITIVE, &res[2]);
+}
+
+static struct acpi_platform_list pmcg_plat_info[] __initdata = {
+ /* HiSilicon Hip08 Platform */
+ {"HISI ", "HIP08 ", 0, ACPI_SIG_IORT, greater_than_or_equal,
+ "Erratum #162001800", IORT_SMMU_V3_PMCG_HISI_HIP08},
+ { }
+};
+
+static int __init arm_smmu_v3_pmcg_add_platdata(struct platform_device *pdev)
+{
+ u32 model;
+ int idx;
+
+ idx = acpi_match_platform_list(pmcg_plat_info);
+ if (idx >= 0)
+ model = pmcg_plat_info[idx].data;
+ else
+ model = IORT_SMMU_V3_PMCG_GENERIC;
+
+ return platform_device_add_data(pdev, &model, sizeof(model));
}
struct iort_dev_config {
const char *name;
int (*dev_init)(struct acpi_iort_node *node);
- bool (*dev_is_coherent)(struct acpi_iort_node *node);
+ void (*dev_dma_configure)(struct device *dev,
+ struct acpi_iort_node *node);
int (*dev_count_resources)(struct acpi_iort_node *node);
void (*dev_init_resources)(struct resource *res,
struct acpi_iort_node *node);
- void (*dev_set_proximity)(struct device *dev,
+ int (*dev_set_proximity)(struct device *dev,
struct acpi_iort_node *node);
+ int (*dev_add_platdata)(struct platform_device *pdev);
};
static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = {
.name = "arm-smmu-v3",
- .dev_is_coherent = arm_smmu_v3_is_coherent,
+ .dev_dma_configure = arm_smmu_v3_dma_configure,
.dev_count_resources = arm_smmu_v3_count_resources,
.dev_init_resources = arm_smmu_v3_init_resources,
.dev_set_proximity = arm_smmu_v3_set_proximity,
@@ -1332,9 +1416,16 @@ static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = {
static const struct iort_dev_config iort_arm_smmu_cfg __initconst = {
.name = "arm-smmu",
- .dev_is_coherent = arm_smmu_is_coherent,
+ .dev_dma_configure = arm_smmu_dma_configure,
.dev_count_resources = arm_smmu_count_resources,
- .dev_init_resources = arm_smmu_init_resources
+ .dev_init_resources = arm_smmu_init_resources,
+};
+
+static const struct iort_dev_config iort_arm_smmu_v3_pmcg_cfg __initconst = {
+ .name = "arm-smmu-v3-pmcg",
+ .dev_count_resources = arm_smmu_v3_pmcg_count_resources,
+ .dev_init_resources = arm_smmu_v3_pmcg_init_resources,
+ .dev_add_platdata = arm_smmu_v3_pmcg_add_platdata,
};
static __init const struct iort_dev_config *iort_get_dev_cfg(
@@ -1345,6 +1436,8 @@ static __init const struct iort_dev_config *iort_get_dev_cfg(
return &iort_arm_smmu_v3_cfg;
case ACPI_IORT_NODE_SMMU:
return &iort_arm_smmu_cfg;
+ case ACPI_IORT_NODE_PMCG:
+ return &iort_arm_smmu_v3_pmcg_cfg;
default:
return NULL;
}
@@ -1362,15 +1455,17 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node,
struct fwnode_handle *fwnode;
struct platform_device *pdev;
struct resource *r;
- enum dev_dma_attr attr;
int ret, count;
pdev = platform_device_alloc(ops->name, PLATFORM_DEVID_AUTO);
if (!pdev)
return -ENOMEM;
- if (ops->dev_set_proximity)
- ops->dev_set_proximity(&pdev->dev, node);
+ if (ops->dev_set_proximity) {
+ ret = ops->dev_set_proximity(&pdev->dev, node);
+ if (ret)
+ goto dev_put;
+ }
count = ops->dev_count_resources(node);
@@ -1393,19 +1488,19 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node,
goto dev_put;
/*
- * Add a copy of IORT node pointer to platform_data to
- * be used to retrieve IORT data information.
+ * Platform devices based on PMCG nodes uses platform_data to
+ * pass the hardware model info to the driver. For others, add
+ * a copy of IORT node pointer to platform_data to be used to
+ * retrieve IORT data information.
*/
- ret = platform_device_add_data(pdev, &node, sizeof(node));
+ if (ops->dev_add_platdata)
+ ret = ops->dev_add_platdata(pdev);
+ else
+ ret = platform_device_add_data(pdev, &node, sizeof(node));
+
if (ret)
goto dev_put;
- /*
- * We expect the dma masks to be equivalent for
- * all SMMUs set-ups
- */
- pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask;
-
fwnode = iort_get_fwnode(node);
if (!fwnode) {
@@ -1415,11 +1510,8 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node,
pdev->dev.fwnode = fwnode;
- attr = ops->dev_is_coherent && ops->dev_is_coherent(node) ?
- DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT;
-
- /* Configure DMA for the page table walker */
- acpi_dma_configure(&pdev->dev, attr);
+ if (ops->dev_dma_configure)
+ ops->dev_dma_configure(&pdev->dev, node);
iort_set_device_domain(&pdev->dev, node);
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index ea373cf..b2a951a 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -149,6 +149,26 @@ u32 arch_timer_reg_read(int access, enum arch_timer_reg reg,
return val;
}
+static u64 arch_counter_get_cntpct_stable(void)
+{
+ return __arch_counter_get_cntpct_stable();
+}
+
+static u64 arch_counter_get_cntpct(void)
+{
+ return __arch_counter_get_cntpct();
+}
+
+static u64 arch_counter_get_cntvct_stable(void)
+{
+ return __arch_counter_get_cntvct_stable();
+}
+
+static u64 arch_counter_get_cntvct(void)
+{
+ return __arch_counter_get_cntvct();
+}
+
/*
* Default to cp15 based access because arm64 uses this function for
* sched_clock() before DT is probed and the cp15 method is guaranteed
@@ -316,13 +336,6 @@ static u64 notrace arm64_858921_read_cntvct_el0(void)
}
#endif
-#ifdef CONFIG_ARM64_ERRATUM_1188873
-static u64 notrace arm64_1188873_read_cntvct_el0(void)
-{
- return read_sysreg(cntvct_el0);
-}
-#endif
-
#ifdef CONFIG_SUN50I_ERRATUM_UNKNOWN1
/*
* The low bits of the counter registers are indeterminate while bit 10 or
@@ -369,8 +382,7 @@ static u32 notrace sun50i_a64_read_cntv_tval_el0(void)
DEFINE_PER_CPU(const struct arch_timer_erratum_workaround *, timer_unstable_counter_workaround);
EXPORT_SYMBOL_GPL(timer_unstable_counter_workaround);
-DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled);
-EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled);
+static atomic_t timer_unstable_counter_workaround_in_use = ATOMIC_INIT(0);
static void erratum_set_next_event_tval_generic(const int access, unsigned long evt,
struct clock_event_device *clk)
@@ -454,14 +466,6 @@ static const struct arch_timer_erratum_workaround ool_workarounds[] = {
.read_cntvct_el0 = arm64_858921_read_cntvct_el0,
},
#endif
-#ifdef CONFIG_ARM64_ERRATUM_1188873
- {
- .match_type = ate_match_local_cap_id,
- .id = (void *)ARM64_WORKAROUND_1188873,
- .desc = "ARM erratum 1188873",
- .read_cntvct_el0 = arm64_1188873_read_cntvct_el0,
- },
-#endif
#ifdef CONFIG_SUN50I_ERRATUM_UNKNOWN1
{
.match_type = ate_match_dt,
@@ -549,11 +553,8 @@ void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa
per_cpu(timer_unstable_counter_workaround, i) = wa;
}
- /*
- * Use the locked version, as we're called from the CPU
- * hotplug framework. Otherwise, we end-up in deadlock-land.
- */
- static_branch_enable_cpuslocked(&arch_timer_read_ool_enabled);
+ if (wa->read_cntvct_el0 || wa->read_cntpct_el0)
+ atomic_set(&timer_unstable_counter_workaround_in_use, 1);
/*
* Don't use the vdso fastpath if errata require using the
@@ -570,7 +571,7 @@ void arch_timer_enable_workaround(const struct arch_timer_erratum_workaround *wa
static void arch_timer_check_ool_workaround(enum arch_timer_erratum_match_type type,
void *arg)
{
- const struct arch_timer_erratum_workaround *wa;
+ const struct arch_timer_erratum_workaround *wa, *__wa;
ate_match_fn_t match_fn = NULL;
bool local = false;
@@ -594,53 +595,32 @@ static void arch_timer_check_ool_workaround(enum arch_timer_erratum_match_type t
if (!wa)
return;
- if (needs_unstable_timer_counter_workaround()) {
- const struct arch_timer_erratum_workaround *__wa;
- __wa = __this_cpu_read(timer_unstable_counter_workaround);
- if (__wa && wa != __wa)
- pr_warn("Can't enable workaround for %s (clashes with %s\n)",
- wa->desc, __wa->desc);
+ __wa = __this_cpu_read(timer_unstable_counter_workaround);
+ if (__wa && wa != __wa)
+ pr_warn("Can't enable workaround for %s (clashes with %s\n)",
+ wa->desc, __wa->desc);
- if (__wa)
- return;
- }
+ if (__wa)
+ return;
arch_timer_enable_workaround(wa, local);
pr_info("Enabling %s workaround for %s\n",
local ? "local" : "global", wa->desc);
}
-#define erratum_handler(fn, r, ...) \
-({ \
- bool __val; \
- if (needs_unstable_timer_counter_workaround()) { \
- const struct arch_timer_erratum_workaround *__wa; \
- __wa = __this_cpu_read(timer_unstable_counter_workaround); \
- if (__wa && __wa->fn) { \
- r = __wa->fn(__VA_ARGS__); \
- __val = true; \
- } else { \
- __val = false; \
- } \
- } else { \
- __val = false; \
- } \
- __val; \
-})
-
static bool arch_timer_this_cpu_has_cntvct_wa(void)
{
- const struct arch_timer_erratum_workaround *wa;
+ return has_erratum_handler(read_cntvct_el0);
+}
- wa = __this_cpu_read(timer_unstable_counter_workaround);
- return wa && wa->read_cntvct_el0;
+static bool arch_timer_counter_has_wa(void)
+{
+ return atomic_read(&timer_unstable_counter_workaround_in_use);
}
#else
#define arch_timer_check_ool_workaround(t,a) do { } while(0)
-#define erratum_set_next_event_tval_virt(...) ({BUG(); 0;})
-#define erratum_set_next_event_tval_phys(...) ({BUG(); 0;})
-#define erratum_handler(fn, r, ...) ({false;})
#define arch_timer_this_cpu_has_cntvct_wa() ({false;})
+#define arch_timer_counter_has_wa() ({false;})
#endif /* CONFIG_ARM_ARCH_TIMER_OOL_WORKAROUND */
static __always_inline irqreturn_t timer_handler(const int access,
@@ -733,11 +713,6 @@ static __always_inline void set_next_event(const int access, unsigned long evt,
static int arch_timer_set_next_event_virt(unsigned long evt,
struct clock_event_device *clk)
{
- int ret;
-
- if (erratum_handler(set_next_event_virt, ret, evt, clk))
- return ret;
-
set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
return 0;
}
@@ -745,11 +720,6 @@ static int arch_timer_set_next_event_virt(unsigned long evt,
static int arch_timer_set_next_event_phys(unsigned long evt,
struct clock_event_device *clk)
{
- int ret;
-
- if (erratum_handler(set_next_event_phys, ret, evt, clk))
- return ret;
-
set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
return 0;
}
@@ -774,6 +744,10 @@ static void __arch_timer_setup(unsigned type,
clk->features = CLOCK_EVT_FEAT_ONESHOT;
if (type == ARCH_TIMER_TYPE_CP15) {
+ typeof(clk->set_next_event) sne;
+
+ arch_timer_check_ool_workaround(ate_match_local_cap_id, NULL);
+
if (arch_timer_c3stop)
clk->features |= CLOCK_EVT_FEAT_C3STOP;
clk->name = "arch_sys_timer";
@@ -784,20 +758,20 @@ static void __arch_timer_setup(unsigned type,
case ARCH_TIMER_VIRT_PPI:
clk->set_state_shutdown = arch_timer_shutdown_virt;
clk->set_state_oneshot_stopped = arch_timer_shutdown_virt;
- clk->set_next_event = arch_timer_set_next_event_virt;
+ sne = erratum_handler(set_next_event_virt);
break;
case ARCH_TIMER_PHYS_SECURE_PPI:
case ARCH_TIMER_PHYS_NONSECURE_PPI:
case ARCH_TIMER_HYP_PPI:
clk->set_state_shutdown = arch_timer_shutdown_phys;
clk->set_state_oneshot_stopped = arch_timer_shutdown_phys;
- clk->set_next_event = arch_timer_set_next_event_phys;
+ sne = erratum_handler(set_next_event_phys);
break;
default:
BUG();
}
- arch_timer_check_ool_workaround(ate_match_local_cap_id, NULL);
+ clk->set_next_event = sne;
} else {
clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
clk->name = "arch_mem_timer";
@@ -830,7 +804,11 @@ static void arch_timer_evtstrm_enable(int divider)
cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT)
| ARCH_TIMER_VIRT_EVT_EN;
arch_timer_set_cntkctl(cntkctl);
+#ifdef CONFIG_ARM64
+ cpu_set_named_feature(EVTSTRM);
+#else
elf_hwcap |= HWCAP_EVTSTRM;
+#endif
#ifdef CONFIG_COMPAT
compat_elf_hwcap |= COMPAT_HWCAP_EVTSTRM;
#endif
@@ -995,12 +973,22 @@ static void __init arch_counter_register(unsigned type)
/* Register the CP15 based counter if we have one */
if (type & ARCH_TIMER_TYPE_CP15) {
- if ((IS_ENABLED(CONFIG_ARM64) && !is_hyp_mode_available()) ||
- arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI)
- arch_timer_read_counter = arch_counter_get_cntvct;
- else
- arch_timer_read_counter = arch_counter_get_cntpct;
+ u64 (*rd)(void);
+ if ((IS_ENABLED(CONFIG_ARM64) && !is_hyp_mode_available()) ||
+ arch_timer_uses_ppi == ARCH_TIMER_VIRT_PPI) {
+ if (arch_timer_counter_has_wa())
+ rd = arch_counter_get_cntvct_stable;
+ else
+ rd = arch_counter_get_cntvct;
+ } else {
+ if (arch_timer_counter_has_wa())
+ rd = arch_counter_get_cntpct_stable;
+ else
+ rd = arch_counter_get_cntpct;
+ }
+
+ arch_timer_read_counter = rd;
clocksource_counter.archdata.vdso_direct = vdso_default;
} else {
arch_timer_read_counter = arch_counter_get_cntvct_mem;
@@ -1052,7 +1040,11 @@ static int arch_timer_cpu_pm_notify(struct notifier_block *self,
} else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT) {
arch_timer_set_cntkctl(__this_cpu_read(saved_cntkctl));
+#ifdef CONFIG_ARM64
+ if (cpu_have_named_feature(EVTSTRM))
+#else
if (elf_hwcap & HWCAP_EVTSTRM)
+#endif
cpumask_set_cpu(smp_processor_id(), &evtstrm_available);
}
return NOTIFY_OK;
diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
index e6376f9..9cd70d1 100644
--- a/drivers/firmware/arm_sdei.c
+++ b/drivers/firmware/arm_sdei.c
@@ -165,6 +165,7 @@ static int invoke_sdei_fn(unsigned long function_id, unsigned long arg0,
return err;
}
+NOKPROBE_SYMBOL(invoke_sdei_fn);
static struct sdei_event *sdei_event_find(u32 event_num)
{
@@ -879,6 +880,7 @@ static void sdei_smccc_smc(unsigned long function_id,
{
arm_smccc_smc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
}
+NOKPROBE_SYMBOL(sdei_smccc_smc);
static void sdei_smccc_hvc(unsigned long function_id,
unsigned long arg0, unsigned long arg1,
@@ -887,6 +889,7 @@ static void sdei_smccc_hvc(unsigned long function_id,
{
arm_smccc_hvc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
}
+NOKPROBE_SYMBOL(sdei_smccc_hvc);
int sdei_register_ghes(struct ghes *ghes, sdei_event_callback *normal_cb,
sdei_event_callback *critical_cb)
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index b1f7b64..0460c75 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -16,9 +16,9 @@
# arm64 uses the full KBUILD_CFLAGS so it's necessary to explicitly
# disable the stackleak plugin
-cflags-$(CONFIG_ARM64) := $(subst -pg,,$(KBUILD_CFLAGS)) -fpie \
- $(DISABLE_STACKLEAK_PLUGIN)
-cflags-$(CONFIG_ARM) := $(subst -pg,,$(KBUILD_CFLAGS)) \
+cflags-$(CONFIG_ARM64) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
+ -fpie $(DISABLE_STACKLEAK_PLUGIN)
+cflags-$(CONFIG_ARM) := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) \
-fno-builtin -fpic \
$(call cc-option,-mno-single-pic-base)
diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index af9bc17..a94e586 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -52,6 +52,15 @@
depends on ARM_PMU && ACPI
def_bool y
+config ARM_SMMU_V3_PMU
+ tristate "ARM SMMUv3 Performance Monitors Extension"
+ depends on ARM64 && ACPI && ARM_SMMU_V3
+ help
+ Provides support for the ARM SMMUv3 Performance Monitor Counter
+ Groups (PMCG), which provide monitoring of transactions passing
+ through the SMMU and allow the resulting information to be filtered
+ based on the Stream ID of the corresponding master.
+
config ARM_DSU_PMU
tristate "ARM DynamIQ Shared Unit (DSU) PMU"
depends on ARM64
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index 909f27f..3048994 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -4,6 +4,7 @@
obj-$(CONFIG_ARM_DSU_PMU) += arm_dsu_pmu.o
obj-$(CONFIG_ARM_PMU) += arm_pmu.o arm_pmu_platform.o
obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o
+obj-$(CONFIG_ARM_SMMU_V3_PMU) += arm_smmuv3_pmu.o
obj-$(CONFIG_HISI_PMU) += hisilicon/
obj-$(CONFIG_QCOM_L2_PMU) += qcom_l2_pmu.o
obj-$(CONFIG_QCOM_L3_PMU) += qcom_l3_pmu.o
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index bfd03e0..8f8606b 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -1684,21 +1684,24 @@ static int cci_pmu_probe(struct platform_device *pdev)
raw_spin_lock_init(&cci_pmu->hw_events.pmu_lock);
mutex_init(&cci_pmu->reserve_mutex);
atomic_set(&cci_pmu->active_events, 0);
- cci_pmu->cpu = get_cpu();
- ret = cci_pmu_init(cci_pmu, pdev);
- if (ret) {
- put_cpu();
- return ret;
- }
-
+ cci_pmu->cpu = raw_smp_processor_id();
+ g_cci_pmu = cci_pmu;
cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_CCI_ONLINE,
"perf/arm/cci:online", NULL,
cci_pmu_offline_cpu);
- put_cpu();
- g_cci_pmu = cci_pmu;
+
+ ret = cci_pmu_init(cci_pmu, pdev);
+ if (ret)
+ goto error_pmu_init;
+
pr_info("ARM %s PMU driver probed", cci_pmu->model->name);
return 0;
+
+error_pmu_init:
+ cpuhp_remove_state(CPUHP_AP_PERF_ARM_CCI_ONLINE);
+ g_cci_pmu = NULL;
+ return ret;
}
static int cci_pmu_remove(struct platform_device *pdev)
diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index 2ae7602..0bb52d9 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -167,7 +167,7 @@ struct arm_ccn_dt {
struct hrtimer hrtimer;
- cpumask_t cpu;
+ unsigned int cpu;
struct hlist_node node;
struct pmu pmu;
@@ -559,7 +559,7 @@ static ssize_t arm_ccn_pmu_cpumask_show(struct device *dev,
{
struct arm_ccn *ccn = pmu_to_arm_ccn(dev_get_drvdata(dev));
- return cpumap_print_to_pagebuf(true, buf, &ccn->dt.cpu);
+ return cpumap_print_to_pagebuf(true, buf, cpumask_of(ccn->dt.cpu));
}
static struct device_attribute arm_ccn_pmu_cpumask_attr =
@@ -759,7 +759,7 @@ static int arm_ccn_pmu_event_init(struct perf_event *event)
* mitigate this, we enforce CPU assignment to one, selected
* processor (the one described in the "cpumask" attribute).
*/
- event->cpu = cpumask_first(&ccn->dt.cpu);
+ event->cpu = ccn->dt.cpu;
node_xp = CCN_CONFIG_NODE(event->attr.config);
type = CCN_CONFIG_TYPE(event->attr.config);
@@ -1215,15 +1215,15 @@ static int arm_ccn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
struct arm_ccn *ccn = container_of(dt, struct arm_ccn, dt);
unsigned int target;
- if (!cpumask_test_and_clear_cpu(cpu, &dt->cpu))
+ if (cpu != dt->cpu)
return 0;
target = cpumask_any_but(cpu_online_mask, cpu);
if (target >= nr_cpu_ids)
return 0;
perf_pmu_migrate_context(&dt->pmu, cpu, target);
- cpumask_set_cpu(target, &dt->cpu);
+ dt->cpu = target;
if (ccn->irq)
- WARN_ON(irq_set_affinity_hint(ccn->irq, &dt->cpu) != 0);
+ WARN_ON(irq_set_affinity_hint(ccn->irq, cpumask_of(dt->cpu)));
return 0;
}
@@ -1299,29 +1299,30 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
}
/* Pick one CPU which we will use to collect data from CCN... */
- cpumask_set_cpu(get_cpu(), &ccn->dt.cpu);
+ ccn->dt.cpu = raw_smp_processor_id();
/* Also make sure that the overflow interrupt is handled by this CPU */
if (ccn->irq) {
- err = irq_set_affinity_hint(ccn->irq, &ccn->dt.cpu);
+ err = irq_set_affinity_hint(ccn->irq, cpumask_of(ccn->dt.cpu));
if (err) {
dev_err(ccn->dev, "Failed to set interrupt affinity!\n");
goto error_set_affinity;
}
}
+ cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+ &ccn->dt.node);
+
err = perf_pmu_register(&ccn->dt.pmu, name, -1);
if (err)
goto error_pmu_register;
- cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
- &ccn->dt.node);
- put_cpu();
return 0;
error_pmu_register:
+ cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+ &ccn->dt.node);
error_set_affinity:
- put_cpu();
error_choose_name:
ida_simple_remove(&arm_ccn_pmu_ida, ccn->dt.id);
for (i = 0; i < ccn->num_xps; i++)
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
new file mode 100644
index 0000000..da71c74
--- /dev/null
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -0,0 +1,865 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * This driver adds support for perf events to use the Performance
+ * Monitor Counter Groups (PMCG) associated with an SMMUv3 node
+ * to monitor that node.
+ *
+ * SMMUv3 PMCG devices are named as smmuv3_pmcg_<phys_addr_page> where
+ * <phys_addr_page> is the physical page address of the SMMU PMCG wrapped
+ * to 4K boundary. For example, the PMCG at 0xff88840000 is named
+ * smmuv3_pmcg_ff88840
+ *
+ * Filtering by stream id is done by specifying filtering parameters
+ * with the event. options are:
+ * filter_enable - 0 = no filtering, 1 = filtering enabled
+ * filter_span - 0 = exact match, 1 = pattern match
+ * filter_stream_id - pattern to filter against
+ *
+ * To match a partial StreamID where the X most-significant bits must match
+ * but the Y least-significant bits might differ, STREAMID is programmed
+ * with a value that contains:
+ * STREAMID[Y - 1] == 0.
+ * STREAMID[Y - 2:0] == 1 (where Y > 1).
+ * The remainder of implemented bits of STREAMID (X bits, from bit Y upwards)
+ * contain a value to match from the corresponding bits of event StreamID.
+ *
+ * Example: perf stat -e smmuv3_pmcg_ff88840/transaction,filter_enable=1,
+ * filter_span=1,filter_stream_id=0x42/ -a netperf
+ * Applies filter pattern 0x42 to transaction events, which means events
+ * matching stream ids 0x42 and 0x43 are counted. Further filtering
+ * information is available in the SMMU documentation.
+ *
+ * SMMU events are not attributable to a CPU, so task mode and sampling
+ * are not supported.
+ */
+
+#include <linux/acpi.h>
+#include <linux/acpi_iort.h>
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/cpuhotplug.h>
+#include <linux/cpumask.h>
+#include <linux/device.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/msi.h>
+#include <linux/perf_event.h>
+#include <linux/platform_device.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+
+#define SMMU_PMCG_EVCNTR0 0x0
+#define SMMU_PMCG_EVCNTR(n, stride) (SMMU_PMCG_EVCNTR0 + (n) * (stride))
+#define SMMU_PMCG_EVTYPER0 0x400
+#define SMMU_PMCG_EVTYPER(n) (SMMU_PMCG_EVTYPER0 + (n) * 4)
+#define SMMU_PMCG_SID_SPAN_SHIFT 29
+#define SMMU_PMCG_SMR0 0xA00
+#define SMMU_PMCG_SMR(n) (SMMU_PMCG_SMR0 + (n) * 4)
+#define SMMU_PMCG_CNTENSET0 0xC00
+#define SMMU_PMCG_CNTENCLR0 0xC20
+#define SMMU_PMCG_INTENSET0 0xC40
+#define SMMU_PMCG_INTENCLR0 0xC60
+#define SMMU_PMCG_OVSCLR0 0xC80
+#define SMMU_PMCG_OVSSET0 0xCC0
+#define SMMU_PMCG_CFGR 0xE00
+#define SMMU_PMCG_CFGR_SID_FILTER_TYPE BIT(23)
+#define SMMU_PMCG_CFGR_MSI BIT(21)
+#define SMMU_PMCG_CFGR_RELOC_CTRS BIT(20)
+#define SMMU_PMCG_CFGR_SIZE GENMASK(13, 8)
+#define SMMU_PMCG_CFGR_NCTR GENMASK(5, 0)
+#define SMMU_PMCG_CR 0xE04
+#define SMMU_PMCG_CR_ENABLE BIT(0)
+#define SMMU_PMCG_CEID0 0xE20
+#define SMMU_PMCG_CEID1 0xE28
+#define SMMU_PMCG_IRQ_CTRL 0xE50
+#define SMMU_PMCG_IRQ_CTRL_IRQEN BIT(0)
+#define SMMU_PMCG_IRQ_CFG0 0xE58
+#define SMMU_PMCG_IRQ_CFG1 0xE60
+#define SMMU_PMCG_IRQ_CFG2 0xE64
+
+/* MSI config fields */
+#define MSI_CFG0_ADDR_MASK GENMASK_ULL(51, 2)
+#define MSI_CFG2_MEMATTR_DEVICE_nGnRE 0x1
+
+#define SMMU_PMCG_DEFAULT_FILTER_SPAN 1
+#define SMMU_PMCG_DEFAULT_FILTER_SID GENMASK(31, 0)
+
+#define SMMU_PMCG_MAX_COUNTERS 64
+#define SMMU_PMCG_ARCH_MAX_EVENTS 128
+
+#define SMMU_PMCG_PA_SHIFT 12
+
+#define SMMU_PMCG_EVCNTR_RDONLY BIT(0)
+
+static int cpuhp_state_num;
+
+struct smmu_pmu {
+ struct hlist_node node;
+ struct perf_event *events[SMMU_PMCG_MAX_COUNTERS];
+ DECLARE_BITMAP(used_counters, SMMU_PMCG_MAX_COUNTERS);
+ DECLARE_BITMAP(supported_events, SMMU_PMCG_ARCH_MAX_EVENTS);
+ unsigned int irq;
+ unsigned int on_cpu;
+ struct pmu pmu;
+ unsigned int num_counters;
+ struct device *dev;
+ void __iomem *reg_base;
+ void __iomem *reloc_base;
+ u64 counter_mask;
+ u32 options;
+ bool global_filter;
+ u32 global_filter_span;
+ u32 global_filter_sid;
+};
+
+#define to_smmu_pmu(p) (container_of(p, struct smmu_pmu, pmu))
+
+#define SMMU_PMU_EVENT_ATTR_EXTRACTOR(_name, _config, _start, _end) \
+ static inline u32 get_##_name(struct perf_event *event) \
+ { \
+ return FIELD_GET(GENMASK_ULL(_end, _start), \
+ event->attr._config); \
+ } \
+
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(event, config, 0, 15);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_stream_id, config1, 0, 31);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_span, config1, 32, 32);
+SMMU_PMU_EVENT_ATTR_EXTRACTOR(filter_enable, config1, 33, 33);
+
+static inline void smmu_pmu_enable(struct pmu *pmu)
+{
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
+
+ writel(SMMU_PMCG_IRQ_CTRL_IRQEN,
+ smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL);
+ writel(SMMU_PMCG_CR_ENABLE, smmu_pmu->reg_base + SMMU_PMCG_CR);
+}
+
+static inline void smmu_pmu_disable(struct pmu *pmu)
+{
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
+
+ writel(0, smmu_pmu->reg_base + SMMU_PMCG_CR);
+ writel(0, smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL);
+}
+
+static inline void smmu_pmu_counter_set_value(struct smmu_pmu *smmu_pmu,
+ u32 idx, u64 value)
+{
+ if (smmu_pmu->counter_mask & BIT(32))
+ writeq(value, smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 8));
+ else
+ writel(value, smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 4));
+}
+
+static inline u64 smmu_pmu_counter_get_value(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+ u64 value;
+
+ if (smmu_pmu->counter_mask & BIT(32))
+ value = readq(smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 8));
+ else
+ value = readl(smmu_pmu->reloc_base + SMMU_PMCG_EVCNTR(idx, 4));
+
+ return value;
+}
+
+static inline void smmu_pmu_counter_enable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+ writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_CNTENSET0);
+}
+
+static inline void smmu_pmu_counter_disable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+ writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_CNTENCLR0);
+}
+
+static inline void smmu_pmu_interrupt_enable(struct smmu_pmu *smmu_pmu, u32 idx)
+{
+ writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_INTENSET0);
+}
+
+static inline void smmu_pmu_interrupt_disable(struct smmu_pmu *smmu_pmu,
+ u32 idx)
+{
+ writeq(BIT(idx), smmu_pmu->reg_base + SMMU_PMCG_INTENCLR0);
+}
+
+static inline void smmu_pmu_set_evtyper(struct smmu_pmu *smmu_pmu, u32 idx,
+ u32 val)
+{
+ writel(val, smmu_pmu->reg_base + SMMU_PMCG_EVTYPER(idx));
+}
+
+static inline void smmu_pmu_set_smr(struct smmu_pmu *smmu_pmu, u32 idx, u32 val)
+{
+ writel(val, smmu_pmu->reg_base + SMMU_PMCG_SMR(idx));
+}
+
+static void smmu_pmu_event_update(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+ u64 delta, prev, now;
+ u32 idx = hwc->idx;
+
+ do {
+ prev = local64_read(&hwc->prev_count);
+ now = smmu_pmu_counter_get_value(smmu_pmu, idx);
+ } while (local64_cmpxchg(&hwc->prev_count, prev, now) != prev);
+
+ /* handle overflow. */
+ delta = now - prev;
+ delta &= smmu_pmu->counter_mask;
+
+ local64_add(delta, &event->count);
+}
+
+static void smmu_pmu_set_period(struct smmu_pmu *smmu_pmu,
+ struct hw_perf_event *hwc)
+{
+ u32 idx = hwc->idx;
+ u64 new;
+
+ if (smmu_pmu->options & SMMU_PMCG_EVCNTR_RDONLY) {
+ /*
+ * On platforms that require this quirk, if the counter starts
+ * at < half_counter value and wraps, the current logic of
+ * handling the overflow may not work. It is expected that,
+ * those platforms will have full 64 counter bits implemented
+ * so that such a possibility is remote(eg: HiSilicon HIP08).
+ */
+ new = smmu_pmu_counter_get_value(smmu_pmu, idx);
+ } else {
+ /*
+ * We limit the max period to half the max counter value
+ * of the counter size, so that even in the case of extreme
+ * interrupt latency the counter will (hopefully) not wrap
+ * past its initial value.
+ */
+ new = smmu_pmu->counter_mask >> 1;
+ smmu_pmu_counter_set_value(smmu_pmu, idx, new);
+ }
+
+ local64_set(&hwc->prev_count, new);
+}
+
+static void smmu_pmu_set_event_filter(struct perf_event *event,
+ int idx, u32 span, u32 sid)
+{
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+ u32 evtyper;
+
+ evtyper = get_event(event) | span << SMMU_PMCG_SID_SPAN_SHIFT;
+ smmu_pmu_set_evtyper(smmu_pmu, idx, evtyper);
+ smmu_pmu_set_smr(smmu_pmu, idx, sid);
+}
+
+static int smmu_pmu_apply_event_filter(struct smmu_pmu *smmu_pmu,
+ struct perf_event *event, int idx)
+{
+ u32 span, sid;
+ unsigned int num_ctrs = smmu_pmu->num_counters;
+ bool filter_en = !!get_filter_enable(event);
+
+ span = filter_en ? get_filter_span(event) :
+ SMMU_PMCG_DEFAULT_FILTER_SPAN;
+ sid = filter_en ? get_filter_stream_id(event) :
+ SMMU_PMCG_DEFAULT_FILTER_SID;
+
+ /* Support individual filter settings */
+ if (!smmu_pmu->global_filter) {
+ smmu_pmu_set_event_filter(event, idx, span, sid);
+ return 0;
+ }
+
+ /* Requested settings same as current global settings*/
+ if (span == smmu_pmu->global_filter_span &&
+ sid == smmu_pmu->global_filter_sid)
+ return 0;
+
+ if (!bitmap_empty(smmu_pmu->used_counters, num_ctrs))
+ return -EAGAIN;
+
+ smmu_pmu_set_event_filter(event, 0, span, sid);
+ smmu_pmu->global_filter_span = span;
+ smmu_pmu->global_filter_sid = sid;
+ return 0;
+}
+
+static int smmu_pmu_get_event_idx(struct smmu_pmu *smmu_pmu,
+ struct perf_event *event)
+{
+ int idx, err;
+ unsigned int num_ctrs = smmu_pmu->num_counters;
+
+ idx = find_first_zero_bit(smmu_pmu->used_counters, num_ctrs);
+ if (idx == num_ctrs)
+ /* The counters are all in use. */
+ return -EAGAIN;
+
+ err = smmu_pmu_apply_event_filter(smmu_pmu, event, idx);
+ if (err)
+ return err;
+
+ set_bit(idx, smmu_pmu->used_counters);
+
+ return idx;
+}
+
+/*
+ * Implementation of abstract pmu functionality required by
+ * the core perf events code.
+ */
+
+static int smmu_pmu_event_init(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+ struct device *dev = smmu_pmu->dev;
+ struct perf_event *sibling;
+ u16 event_id;
+
+ if (event->attr.type != event->pmu->type)
+ return -ENOENT;
+
+ if (hwc->sample_period) {
+ dev_dbg(dev, "Sampling not supported\n");
+ return -EOPNOTSUPP;
+ }
+
+ if (event->cpu < 0) {
+ dev_dbg(dev, "Per-task mode not supported\n");
+ return -EOPNOTSUPP;
+ }
+
+ /* Verify specified event is supported on this PMU */
+ event_id = get_event(event);
+ if (event_id < SMMU_PMCG_ARCH_MAX_EVENTS &&
+ (!test_bit(event_id, smmu_pmu->supported_events))) {
+ dev_dbg(dev, "Invalid event %d for this PMU\n", event_id);
+ return -EINVAL;
+ }
+
+ /* Don't allow groups with mixed PMUs, except for s/w events */
+ if (event->group_leader->pmu != event->pmu &&
+ !is_software_event(event->group_leader)) {
+ dev_dbg(dev, "Can't create mixed PMU group\n");
+ return -EINVAL;
+ }
+
+ for_each_sibling_event(sibling, event->group_leader) {
+ if (sibling->pmu != event->pmu &&
+ !is_software_event(sibling)) {
+ dev_dbg(dev, "Can't create mixed PMU group\n");
+ return -EINVAL;
+ }
+ }
+
+ hwc->idx = -1;
+
+ /*
+ * Ensure all events are on the same cpu so all events are in the
+ * same cpu context, to avoid races on pmu_enable etc.
+ */
+ event->cpu = smmu_pmu->on_cpu;
+
+ return 0;
+}
+
+static void smmu_pmu_event_start(struct perf_event *event, int flags)
+{
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
+
+ hwc->state = 0;
+
+ smmu_pmu_set_period(smmu_pmu, hwc);
+
+ smmu_pmu_counter_enable(smmu_pmu, idx);
+}
+
+static void smmu_pmu_event_stop(struct perf_event *event, int flags)
+{
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
+
+ if (hwc->state & PERF_HES_STOPPED)
+ return;
+
+ smmu_pmu_counter_disable(smmu_pmu, idx);
+ /* As the counter gets updated on _start, ignore PERF_EF_UPDATE */
+ smmu_pmu_event_update(event);
+ hwc->state |= PERF_HES_STOPPED | PERF_HES_UPTODATE;
+}
+
+static int smmu_pmu_event_add(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ int idx;
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+
+ idx = smmu_pmu_get_event_idx(smmu_pmu, event);
+ if (idx < 0)
+ return idx;
+
+ hwc->idx = idx;
+ hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+ smmu_pmu->events[idx] = event;
+ local64_set(&hwc->prev_count, 0);
+
+ smmu_pmu_interrupt_enable(smmu_pmu, idx);
+
+ if (flags & PERF_EF_START)
+ smmu_pmu_event_start(event, flags);
+
+ /* Propagate changes to the userspace mapping. */
+ perf_event_update_userpage(event);
+
+ return 0;
+}
+
+static void smmu_pmu_event_del(struct perf_event *event, int flags)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(event->pmu);
+ int idx = hwc->idx;
+
+ smmu_pmu_event_stop(event, flags | PERF_EF_UPDATE);
+ smmu_pmu_interrupt_disable(smmu_pmu, idx);
+ smmu_pmu->events[idx] = NULL;
+ clear_bit(idx, smmu_pmu->used_counters);
+
+ perf_event_update_userpage(event);
+}
+
+static void smmu_pmu_event_read(struct perf_event *event)
+{
+ smmu_pmu_event_update(event);
+}
+
+/* cpumask */
+
+static ssize_t smmu_pmu_cpumask_show(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
+
+ return cpumap_print_to_pagebuf(true, buf, cpumask_of(smmu_pmu->on_cpu));
+}
+
+static struct device_attribute smmu_pmu_cpumask_attr =
+ __ATTR(cpumask, 0444, smmu_pmu_cpumask_show, NULL);
+
+static struct attribute *smmu_pmu_cpumask_attrs[] = {
+ &smmu_pmu_cpumask_attr.attr,
+ NULL
+};
+
+static struct attribute_group smmu_pmu_cpumask_group = {
+ .attrs = smmu_pmu_cpumask_attrs,
+};
+
+/* Events */
+
+static ssize_t smmu_pmu_event_show(struct device *dev,
+ struct device_attribute *attr, char *page)
+{
+ struct perf_pmu_events_attr *pmu_attr;
+
+ pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+
+ return sprintf(page, "event=0x%02llx\n", pmu_attr->id);
+}
+
+#define SMMU_EVENT_ATTR(name, config) \
+ PMU_EVENT_ATTR(name, smmu_event_attr_##name, \
+ config, smmu_pmu_event_show)
+SMMU_EVENT_ATTR(cycles, 0);
+SMMU_EVENT_ATTR(transaction, 1);
+SMMU_EVENT_ATTR(tlb_miss, 2);
+SMMU_EVENT_ATTR(config_cache_miss, 3);
+SMMU_EVENT_ATTR(trans_table_walk_access, 4);
+SMMU_EVENT_ATTR(config_struct_access, 5);
+SMMU_EVENT_ATTR(pcie_ats_trans_rq, 6);
+SMMU_EVENT_ATTR(pcie_ats_trans_passed, 7);
+
+static struct attribute *smmu_pmu_events[] = {
+ &smmu_event_attr_cycles.attr.attr,
+ &smmu_event_attr_transaction.attr.attr,
+ &smmu_event_attr_tlb_miss.attr.attr,
+ &smmu_event_attr_config_cache_miss.attr.attr,
+ &smmu_event_attr_trans_table_walk_access.attr.attr,
+ &smmu_event_attr_config_struct_access.attr.attr,
+ &smmu_event_attr_pcie_ats_trans_rq.attr.attr,
+ &smmu_event_attr_pcie_ats_trans_passed.attr.attr,
+ NULL
+};
+
+static umode_t smmu_pmu_event_is_visible(struct kobject *kobj,
+ struct attribute *attr, int unused)
+{
+ struct device *dev = kobj_to_dev(kobj);
+ struct smmu_pmu *smmu_pmu = to_smmu_pmu(dev_get_drvdata(dev));
+ struct perf_pmu_events_attr *pmu_attr;
+
+ pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr.attr);
+
+ if (test_bit(pmu_attr->id, smmu_pmu->supported_events))
+ return attr->mode;
+
+ return 0;
+}
+
+static struct attribute_group smmu_pmu_events_group = {
+ .name = "events",
+ .attrs = smmu_pmu_events,
+ .is_visible = smmu_pmu_event_is_visible,
+};
+
+/* Formats */
+PMU_FORMAT_ATTR(event, "config:0-15");
+PMU_FORMAT_ATTR(filter_stream_id, "config1:0-31");
+PMU_FORMAT_ATTR(filter_span, "config1:32");
+PMU_FORMAT_ATTR(filter_enable, "config1:33");
+
+static struct attribute *smmu_pmu_formats[] = {
+ &format_attr_event.attr,
+ &format_attr_filter_stream_id.attr,
+ &format_attr_filter_span.attr,
+ &format_attr_filter_enable.attr,
+ NULL
+};
+
+static struct attribute_group smmu_pmu_format_group = {
+ .name = "format",
+ .attrs = smmu_pmu_formats,
+};
+
+static const struct attribute_group *smmu_pmu_attr_grps[] = {
+ &smmu_pmu_cpumask_group,
+ &smmu_pmu_events_group,
+ &smmu_pmu_format_group,
+ NULL
+};
+
+/*
+ * Generic device handlers
+ */
+
+static int smmu_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
+{
+ struct smmu_pmu *smmu_pmu;
+ unsigned int target;
+
+ smmu_pmu = hlist_entry_safe(node, struct smmu_pmu, node);
+ if (cpu != smmu_pmu->on_cpu)
+ return 0;
+
+ target = cpumask_any_but(cpu_online_mask, cpu);
+ if (target >= nr_cpu_ids)
+ return 0;
+
+ perf_pmu_migrate_context(&smmu_pmu->pmu, cpu, target);
+ smmu_pmu->on_cpu = target;
+ WARN_ON(irq_set_affinity_hint(smmu_pmu->irq, cpumask_of(target)));
+
+ return 0;
+}
+
+static irqreturn_t smmu_pmu_handle_irq(int irq_num, void *data)
+{
+ struct smmu_pmu *smmu_pmu = data;
+ u64 ovsr;
+ unsigned int idx;
+
+ ovsr = readq(smmu_pmu->reloc_base + SMMU_PMCG_OVSSET0);
+ if (!ovsr)
+ return IRQ_NONE;
+
+ writeq(ovsr, smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0);
+
+ for_each_set_bit(idx, (unsigned long *)&ovsr, smmu_pmu->num_counters) {
+ struct perf_event *event = smmu_pmu->events[idx];
+ struct hw_perf_event *hwc;
+
+ if (WARN_ON_ONCE(!event))
+ continue;
+
+ smmu_pmu_event_update(event);
+ hwc = &event->hw;
+
+ smmu_pmu_set_period(smmu_pmu, hwc);
+ }
+
+ return IRQ_HANDLED;
+}
+
+static void smmu_pmu_free_msis(void *data)
+{
+ struct device *dev = data;
+
+ platform_msi_domain_free_irqs(dev);
+}
+
+static void smmu_pmu_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
+{
+ phys_addr_t doorbell;
+ struct device *dev = msi_desc_to_dev(desc);
+ struct smmu_pmu *pmu = dev_get_drvdata(dev);
+
+ doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo;
+ doorbell &= MSI_CFG0_ADDR_MASK;
+
+ writeq_relaxed(doorbell, pmu->reg_base + SMMU_PMCG_IRQ_CFG0);
+ writel_relaxed(msg->data, pmu->reg_base + SMMU_PMCG_IRQ_CFG1);
+ writel_relaxed(MSI_CFG2_MEMATTR_DEVICE_nGnRE,
+ pmu->reg_base + SMMU_PMCG_IRQ_CFG2);
+}
+
+static void smmu_pmu_setup_msi(struct smmu_pmu *pmu)
+{
+ struct msi_desc *desc;
+ struct device *dev = pmu->dev;
+ int ret;
+
+ /* Clear MSI address reg */
+ writeq_relaxed(0, pmu->reg_base + SMMU_PMCG_IRQ_CFG0);
+
+ /* MSI supported or not */
+ if (!(readl(pmu->reg_base + SMMU_PMCG_CFGR) & SMMU_PMCG_CFGR_MSI))
+ return;
+
+ ret = platform_msi_domain_alloc_irqs(dev, 1, smmu_pmu_write_msi_msg);
+ if (ret) {
+ dev_warn(dev, "failed to allocate MSIs\n");
+ return;
+ }
+
+ desc = first_msi_entry(dev);
+ if (desc)
+ pmu->irq = desc->irq;
+
+ /* Add callback to free MSIs on teardown */
+ devm_add_action(dev, smmu_pmu_free_msis, dev);
+}
+
+static int smmu_pmu_setup_irq(struct smmu_pmu *pmu)
+{
+ unsigned long flags = IRQF_NOBALANCING | IRQF_SHARED | IRQF_NO_THREAD;
+ int irq, ret = -ENXIO;
+
+ smmu_pmu_setup_msi(pmu);
+
+ irq = pmu->irq;
+ if (irq)
+ ret = devm_request_irq(pmu->dev, irq, smmu_pmu_handle_irq,
+ flags, "smmuv3-pmu", pmu);
+ return ret;
+}
+
+static void smmu_pmu_reset(struct smmu_pmu *smmu_pmu)
+{
+ u64 counter_present_mask = GENMASK_ULL(smmu_pmu->num_counters - 1, 0);
+
+ smmu_pmu_disable(&smmu_pmu->pmu);
+
+ /* Disable counter and interrupt */
+ writeq_relaxed(counter_present_mask,
+ smmu_pmu->reg_base + SMMU_PMCG_CNTENCLR0);
+ writeq_relaxed(counter_present_mask,
+ smmu_pmu->reg_base + SMMU_PMCG_INTENCLR0);
+ writeq_relaxed(counter_present_mask,
+ smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0);
+}
+
+static void smmu_pmu_get_acpi_options(struct smmu_pmu *smmu_pmu)
+{
+ u32 model;
+
+ model = *(u32 *)dev_get_platdata(smmu_pmu->dev);
+
+ switch (model) {
+ case IORT_SMMU_V3_PMCG_HISI_HIP08:
+ /* HiSilicon Erratum 162001800 */
+ smmu_pmu->options |= SMMU_PMCG_EVCNTR_RDONLY;
+ break;
+ }
+
+ dev_notice(smmu_pmu->dev, "option mask 0x%x\n", smmu_pmu->options);
+}
+
+static int smmu_pmu_probe(struct platform_device *pdev)
+{
+ struct smmu_pmu *smmu_pmu;
+ struct resource *res_0, *res_1;
+ u32 cfgr, reg_size;
+ u64 ceid_64[2];
+ int irq, err;
+ char *name;
+ struct device *dev = &pdev->dev;
+
+ smmu_pmu = devm_kzalloc(dev, sizeof(*smmu_pmu), GFP_KERNEL);
+ if (!smmu_pmu)
+ return -ENOMEM;
+
+ smmu_pmu->dev = dev;
+ platform_set_drvdata(pdev, smmu_pmu);
+
+ smmu_pmu->pmu = (struct pmu) {
+ .task_ctx_nr = perf_invalid_context,
+ .pmu_enable = smmu_pmu_enable,
+ .pmu_disable = smmu_pmu_disable,
+ .event_init = smmu_pmu_event_init,
+ .add = smmu_pmu_event_add,
+ .del = smmu_pmu_event_del,
+ .start = smmu_pmu_event_start,
+ .stop = smmu_pmu_event_stop,
+ .read = smmu_pmu_event_read,
+ .attr_groups = smmu_pmu_attr_grps,
+ .capabilities = PERF_PMU_CAP_NO_EXCLUDE,
+ };
+
+ res_0 = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ smmu_pmu->reg_base = devm_ioremap_resource(dev, res_0);
+ if (IS_ERR(smmu_pmu->reg_base))
+ return PTR_ERR(smmu_pmu->reg_base);
+
+ cfgr = readl_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CFGR);
+
+ /* Determine if page 1 is present */
+ if (cfgr & SMMU_PMCG_CFGR_RELOC_CTRS) {
+ res_1 = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+ smmu_pmu->reloc_base = devm_ioremap_resource(dev, res_1);
+ if (IS_ERR(smmu_pmu->reloc_base))
+ return PTR_ERR(smmu_pmu->reloc_base);
+ } else {
+ smmu_pmu->reloc_base = smmu_pmu->reg_base;
+ }
+
+ irq = platform_get_irq(pdev, 0);
+ if (irq > 0)
+ smmu_pmu->irq = irq;
+
+ ceid_64[0] = readq_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CEID0);
+ ceid_64[1] = readq_relaxed(smmu_pmu->reg_base + SMMU_PMCG_CEID1);
+ bitmap_from_arr32(smmu_pmu->supported_events, (u32 *)ceid_64,
+ SMMU_PMCG_ARCH_MAX_EVENTS);
+
+ smmu_pmu->num_counters = FIELD_GET(SMMU_PMCG_CFGR_NCTR, cfgr) + 1;
+
+ smmu_pmu->global_filter = !!(cfgr & SMMU_PMCG_CFGR_SID_FILTER_TYPE);
+
+ reg_size = FIELD_GET(SMMU_PMCG_CFGR_SIZE, cfgr);
+ smmu_pmu->counter_mask = GENMASK_ULL(reg_size, 0);
+
+ smmu_pmu_reset(smmu_pmu);
+
+ err = smmu_pmu_setup_irq(smmu_pmu);
+ if (err) {
+ dev_err(dev, "Setup irq failed, PMU @%pa\n", &res_0->start);
+ return err;
+ }
+
+ name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "smmuv3_pmcg_%llx",
+ (res_0->start) >> SMMU_PMCG_PA_SHIFT);
+ if (!name) {
+ dev_err(dev, "Create name failed, PMU @%pa\n", &res_0->start);
+ return -EINVAL;
+ }
+
+ smmu_pmu_get_acpi_options(smmu_pmu);
+
+ /* Pick one CPU to be the preferred one to use */
+ smmu_pmu->on_cpu = raw_smp_processor_id();
+ WARN_ON(irq_set_affinity_hint(smmu_pmu->irq,
+ cpumask_of(smmu_pmu->on_cpu)));
+
+ err = cpuhp_state_add_instance_nocalls(cpuhp_state_num,
+ &smmu_pmu->node);
+ if (err) {
+ dev_err(dev, "Error %d registering hotplug, PMU @%pa\n",
+ err, &res_0->start);
+ goto out_cpuhp_err;
+ }
+
+ err = perf_pmu_register(&smmu_pmu->pmu, name, -1);
+ if (err) {
+ dev_err(dev, "Error %d registering PMU @%pa\n",
+ err, &res_0->start);
+ goto out_unregister;
+ }
+
+ dev_info(dev, "Registered PMU @ %pa using %d counters with %s filter settings\n",
+ &res_0->start, smmu_pmu->num_counters,
+ smmu_pmu->global_filter ? "Global(Counter0)" :
+ "Individual");
+
+ return 0;
+
+out_unregister:
+ cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
+out_cpuhp_err:
+ put_cpu();
+ return err;
+}
+
+static int smmu_pmu_remove(struct platform_device *pdev)
+{
+ struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev);
+
+ perf_pmu_unregister(&smmu_pmu->pmu);
+ cpuhp_state_remove_instance_nocalls(cpuhp_state_num, &smmu_pmu->node);
+
+ return 0;
+}
+
+static void smmu_pmu_shutdown(struct platform_device *pdev)
+{
+ struct smmu_pmu *smmu_pmu = platform_get_drvdata(pdev);
+
+ smmu_pmu_disable(&smmu_pmu->pmu);
+}
+
+static struct platform_driver smmu_pmu_driver = {
+ .driver = {
+ .name = "arm-smmu-v3-pmcg",
+ },
+ .probe = smmu_pmu_probe,
+ .remove = smmu_pmu_remove,
+ .shutdown = smmu_pmu_shutdown,
+};
+
+static int __init arm_smmu_pmu_init(void)
+{
+ cpuhp_state_num = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+ "perf/arm/pmcg:online",
+ NULL,
+ smmu_pmu_offline_cpu);
+ if (cpuhp_state_num < 0)
+ return cpuhp_state_num;
+
+ return platform_driver_register(&smmu_pmu_driver);
+}
+module_init(arm_smmu_pmu_init);
+
+static void __exit arm_smmu_pmu_exit(void)
+{
+ platform_driver_unregister(&smmu_pmu_driver);
+ cpuhp_remove_multi_state(cpuhp_state_num);
+}
+
+module_exit(arm_smmu_pmu_exit);
+
+MODULE_DESCRIPTION("PMU driver for ARM SMMUv3 Performance Monitors Extension");
+MODULE_AUTHOR("Neil Leeder <nleeder@codeaurora.org>");
+MODULE_AUTHOR("Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/watchdog/sbsa_gwdt.c b/drivers/watchdog/sbsa_gwdt.c
index e8bd988..e221e47 100644
--- a/drivers/watchdog/sbsa_gwdt.c
+++ b/drivers/watchdog/sbsa_gwdt.c
@@ -161,7 +161,7 @@ static unsigned int sbsa_gwdt_get_timeleft(struct watchdog_device *wdd)
timeleft += readl(gwdt->control_base + SBSA_GWDT_WOR);
timeleft += lo_hi_readq(gwdt->control_base + SBSA_GWDT_WCV) -
- arch_counter_get_cntvct();
+ arch_timer_read_counter();
do_div(timeleft, gwdt->clk);
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index fcb61b4..8666fe7 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -23,7 +23,9 @@
*
* Return:
* 0 - On success
- * <0 - On error
+ * -EFAULT - User access resulted in a page fault
+ * -EAGAIN - Atomic operation was unable to complete due to contention
+ * -ENOSYS - Operation not supported
*/
static inline int
arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
@@ -85,7 +87,9 @@ arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
*
* Return:
* 0 - On success
- * <0 - On error
+ * -EFAULT - User access resulted in a page fault
+ * -EAGAIN - Atomic operation was unable to complete due to contention
+ * -ENOSYS - Function not implemented (only if !HAVE_FUTEX_CMPXCHG)
*/
static inline int
futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index 38cd77b..723e4df 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -26,6 +26,14 @@
#define IORT_IRQ_MASK(irq) (irq & 0xffffffffULL)
#define IORT_IRQ_TRIGGER_MASK(irq) ((irq >> 32) & 0xffffffffULL)
+/*
+ * PMCG model identifiers for use in smmu pmu driver. Please note
+ * that this is purely for the use of software and has nothing to
+ * do with hardware or with IORT specification.
+ */
+#define IORT_SMMU_V3_PMCG_GENERIC 0x00000000 /* Generic SMMUv3 PMCG */
+#define IORT_SMMU_V3_PMCG_HISI_HIP08 0x00000001 /* HiSilicon HIP08 PMCG */
+
int iort_register_domain_token(int trans_id, phys_addr_t base,
struct fwnode_handle *fw_node);
void iort_deregister_domain_token(int trans_id);
diff --git a/kernel/futex.c b/kernel/futex.c
index 9e40cf7..6262f15 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -1311,13 +1311,15 @@ static int lookup_pi_state(u32 __user *uaddr, u32 uval,
static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
{
+ int err;
u32 uninitialized_var(curval);
if (unlikely(should_fail_futex(true)))
return -EFAULT;
- if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
- return -EFAULT;
+ err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+ if (unlikely(err))
+ return err;
/* If user space value changed, let the caller retry */
return curval != uval ? -EAGAIN : 0;
@@ -1502,10 +1504,8 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
if (unlikely(should_fail_futex(true)))
ret = -EFAULT;
- if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
- ret = -EFAULT;
-
- } else if (curval != uval) {
+ ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+ if (!ret && (curval != uval)) {
/*
* If a unconditional UNLOCK_PI operation (user space did not
* try the TID->0 transition) raced with a waiter setting the
@@ -1700,32 +1700,32 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
double_lock_hb(hb1, hb2);
op_ret = futex_atomic_op_inuser(op, uaddr2);
if (unlikely(op_ret < 0)) {
-
double_unlock_hb(hb1, hb2);
-#ifndef CONFIG_MMU
- /*
- * we don't get EFAULT from MMU faults if we don't have an MMU,
- * but we might get them from range checking
- */
- ret = op_ret;
- goto out_put_keys;
-#endif
-
- if (unlikely(op_ret != -EFAULT)) {
+ if (!IS_ENABLED(CONFIG_MMU) ||
+ unlikely(op_ret != -EFAULT && op_ret != -EAGAIN)) {
+ /*
+ * we don't get EFAULT from MMU faults if we don't have
+ * an MMU, but we might get them from range checking
+ */
ret = op_ret;
goto out_put_keys;
}
- ret = fault_in_user_writeable(uaddr2);
- if (ret)
- goto out_put_keys;
+ if (op_ret == -EFAULT) {
+ ret = fault_in_user_writeable(uaddr2);
+ if (ret)
+ goto out_put_keys;
+ }
- if (!(flags & FLAGS_SHARED))
+ if (!(flags & FLAGS_SHARED)) {
+ cond_resched();
goto retry_private;
+ }
put_futex_key(&key2);
put_futex_key(&key1);
+ cond_resched();
goto retry;
}
@@ -2350,7 +2350,7 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
u32 uval, uninitialized_var(curval), newval;
struct task_struct *oldowner, *newowner;
u32 newtid;
- int ret;
+ int ret, err = 0;
lockdep_assert_held(q->lock_ptr);
@@ -2421,14 +2421,17 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
if (!pi_state->owner)
newtid |= FUTEX_OWNER_DIED;
- if (get_futex_value_locked(&uval, uaddr))
- goto handle_fault;
+ err = get_futex_value_locked(&uval, uaddr);
+ if (err)
+ goto handle_err;
for (;;) {
newval = (uval & FUTEX_OWNER_DIED) | newtid;
- if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
- goto handle_fault;
+ err = cmpxchg_futex_value_locked(&curval, uaddr, uval, newval);
+ if (err)
+ goto handle_err;
+
if (curval == uval)
break;
uval = curval;
@@ -2456,23 +2459,37 @@ static int fixup_pi_state_owner(u32 __user *uaddr, struct futex_q *q,
return 0;
/*
- * To handle the page fault we need to drop the locks here. That gives
- * the other task (either the highest priority waiter itself or the
- * task which stole the rtmutex) the chance to try the fixup of the
- * pi_state. So once we are back from handling the fault we need to
- * check the pi_state after reacquiring the locks and before trying to
- * do another fixup. When the fixup has been done already we simply
- * return.
+ * In order to reschedule or handle a page fault, we need to drop the
+ * locks here. In the case of a fault, this gives the other task
+ * (either the highest priority waiter itself or the task which stole
+ * the rtmutex) the chance to try the fixup of the pi_state. So once we
+ * are back from handling the fault we need to check the pi_state after
+ * reacquiring the locks and before trying to do another fixup. When
+ * the fixup has been done already we simply return.
*
* Note: we hold both hb->lock and pi_mutex->wait_lock. We can safely
* drop hb->lock since the caller owns the hb -> futex_q relation.
* Dropping the pi_mutex->wait_lock requires the state revalidate.
*/
-handle_fault:
+handle_err:
raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
spin_unlock(q->lock_ptr);
- ret = fault_in_user_writeable(uaddr);
+ switch (err) {
+ case -EFAULT:
+ ret = fault_in_user_writeable(uaddr);
+ break;
+
+ case -EAGAIN:
+ cond_resched();
+ ret = 0;
+ break;
+
+ default:
+ WARN_ON_ONCE(1);
+ ret = err;
+ break;
+ }
spin_lock(q->lock_ptr);
raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
@@ -3041,10 +3058,8 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
* A unconditional UNLOCK_PI op raced against a waiter
* setting the FUTEX_WAITERS bit. Try again.
*/
- if (ret == -EAGAIN) {
- put_futex_key(&key);
- goto retry;
- }
+ if (ret == -EAGAIN)
+ goto pi_retry;
/*
* wake_futex_pi has detected invalid state. Tell user
* space.
@@ -3059,9 +3074,19 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
* preserve the WAITERS bit not the OWNER_DIED one. We are the
* owner.
*/
- if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) {
+ if ((ret = cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))) {
spin_unlock(&hb->lock);
- goto pi_faulted;
+ switch (ret) {
+ case -EFAULT:
+ goto pi_faulted;
+
+ case -EAGAIN:
+ goto pi_retry;
+
+ default:
+ WARN_ON_ONCE(1);
+ goto out_putkey;
+ }
}
/*
@@ -3075,6 +3100,11 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
put_futex_key(&key);
return ret;
+pi_retry:
+ put_futex_key(&key);
+ cond_resched();
+ goto retry;
+
pi_faulted:
put_futex_key(&key);
@@ -3435,6 +3465,7 @@ SYSCALL_DEFINE3(get_robust_list, int, pid,
static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int pi)
{
u32 uval, uninitialized_var(nval), mval;
+ int err;
/* Futex address must be 32bit aligned */
if ((((unsigned long)uaddr) % sizeof(*uaddr)) != 0)
@@ -3444,42 +3475,57 @@ static int handle_futex_death(u32 __user *uaddr, struct task_struct *curr, int p
if (get_user(uval, uaddr))
return -1;
- if ((uval & FUTEX_TID_MASK) == task_pid_vnr(curr)) {
- /*
- * Ok, this dying thread is truly holding a futex
- * of interest. Set the OWNER_DIED bit atomically
- * via cmpxchg, and if the value had FUTEX_WAITERS
- * set, wake up a waiter (if any). (We have to do a
- * futex_wake() even if OWNER_DIED is already set -
- * to handle the rare but possible case of recursive
- * thread-death.) The rest of the cleanup is done in
- * userspace.
- */
- mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
- /*
- * We are not holding a lock here, but we want to have
- * the pagefault_disable/enable() protection because
- * we want to handle the fault gracefully. If the
- * access fails we try to fault in the futex with R/W
- * verification via get_user_pages. get_user() above
- * does not guarantee R/W access. If that fails we
- * give up and leave the futex locked.
- */
- if (cmpxchg_futex_value_locked(&nval, uaddr, uval, mval)) {
+ if ((uval & FUTEX_TID_MASK) != task_pid_vnr(curr))
+ return 0;
+
+ /*
+ * Ok, this dying thread is truly holding a futex
+ * of interest. Set the OWNER_DIED bit atomically
+ * via cmpxchg, and if the value had FUTEX_WAITERS
+ * set, wake up a waiter (if any). (We have to do a
+ * futex_wake() even if OWNER_DIED is already set -
+ * to handle the rare but possible case of recursive
+ * thread-death.) The rest of the cleanup is done in
+ * userspace.
+ */
+ mval = (uval & FUTEX_WAITERS) | FUTEX_OWNER_DIED;
+
+ /*
+ * We are not holding a lock here, but we want to have
+ * the pagefault_disable/enable() protection because
+ * we want to handle the fault gracefully. If the
+ * access fails we try to fault in the futex with R/W
+ * verification via get_user_pages. get_user() above
+ * does not guarantee R/W access. If that fails we
+ * give up and leave the futex locked.
+ */
+ if ((err = cmpxchg_futex_value_locked(&nval, uaddr, uval, mval))) {
+ switch (err) {
+ case -EFAULT:
if (fault_in_user_writeable(uaddr))
return -1;
goto retry;
- }
- if (nval != uval)
+
+ case -EAGAIN:
+ cond_resched();
goto retry;
- /*
- * Wake robust non-PI futexes here. The wakeup of
- * PI futexes happens in exit_pi_state():
- */
- if (!pi && (uval & FUTEX_WAITERS))
- futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+ default:
+ WARN_ON_ONCE(1);
+ return err;
+ }
}
+
+ if (nval != uval)
+ goto retry;
+
+ /*
+ * Wake robust non-PI futexes here. The wakeup of
+ * PI futexes happens in exit_pi_state():
+ */
+ if (!pi && (uval & FUTEX_WAITERS))
+ futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY);
+
return 0;
}
diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile
index 613dfe6..08b43de 100644
--- a/mm/kasan/Makefile
+++ b/mm/kasan/Makefile
@@ -6,10 +6,10 @@
UBSAN_SANITIZE_tags.o := n
KCOV_INSTRUMENT := n
-CFLAGS_REMOVE_common.o = -pg
-CFLAGS_REMOVE_generic.o = -pg
-CFLAGS_REMOVE_generic_report.o = -pg
-CFLAGS_REMOVE_tags.o = -pg
+CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_generic.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_generic_report.o = $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_tags.o = $(CC_FLAGS_FTRACE)
# Function splitter causes unnecessary splits in __asan_load1/__asan_store1
# see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index a39dcfd..74b6582 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -189,7 +189,7 @@ static void clear_stage2_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr
VM_BUG_ON(pmd_thp_or_huge(*pmd));
pmd_clear(pmd);
kvm_tlb_flush_vmid_ipa(kvm, addr);
- pte_free_kernel(NULL, pte_table);
+ free_page((unsigned long)pte_table);
put_page(virt_to_page(pmd));
}