summaryrefslogtreecommitdiffstats
path: root/arch/arm64
diff options
context:
space:
mode:
Diffstat (limited to 'arch/arm64')
-rw-r--r--arch/arm64/Kconfig1
-rw-r--r--arch/arm64/Makefile2
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts4
-rw-r--r--arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi43
-rw-r--r--arch/arm64/boot/dts/lg/lg1312.dtsi2
-rw-r--r--arch/arm64/boot/dts/mediatek/mt8173.dtsi62
-rw-r--r--arch/arm64/boot/dts/rockchip/rk3399.dtsi10
-rw-r--r--arch/arm64/include/asm/acpi.h10
-rw-r--r--arch/arm64/include/asm/atomic.h60
-rw-r--r--arch/arm64/include/asm/atomic_ll_sc.h110
-rw-r--r--arch/arm64/include/asm/atomic_lse.h278
-rw-r--r--arch/arm64/include/asm/barrier.h13
-rw-r--r--arch/arm64/include/asm/cmpxchg.h51
-rw-r--r--arch/arm64/include/asm/cputype.h2
-rw-r--r--arch/arm64/include/asm/efi.h4
-rw-r--r--arch/arm64/include/asm/io.h4
-rw-r--r--arch/arm64/include/asm/kgdb.h45
-rw-r--r--arch/arm64/include/asm/numa.h2
-rw-r--r--arch/arm64/include/asm/pgalloc.h2
-rw-r--r--arch/arm64/include/asm/ptrace.h2
-rw-r--r--arch/arm64/include/asm/smp.h12
-rw-r--r--arch/arm64/include/asm/spinlock.h42
-rw-r--r--arch/arm64/kernel/Makefile1
-rw-r--r--arch/arm64/kernel/acpi_numa.c112
-rw-r--r--arch/arm64/kernel/asm-offsets.c1
-rw-r--r--arch/arm64/kernel/cpu_errata.c6
-rw-r--r--arch/arm64/kernel/cpuidle.c20
-rw-r--r--arch/arm64/kernel/entry.S19
-rw-r--r--arch/arm64/kernel/hibernate.c6
-rw-r--r--arch/arm64/kernel/kgdb.c14
-rw-r--r--arch/arm64/kernel/setup.c6
-rw-r--r--arch/arm64/kernel/smp.c20
-rw-r--r--arch/arm64/kernel/traps.c26
-rw-r--r--arch/arm64/kvm/hyp/sysreg-sr.c8
-rw-r--r--arch/arm64/mm/context.c9
-rw-r--r--arch/arm64/mm/fault.c9
-rw-r--r--arch/arm64/mm/flush.c4
-rw-r--r--arch/arm64/mm/numa.c28
38 files changed, 879 insertions, 171 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 5a0a691d4220..20d5a60530b1 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -4,6 +4,7 @@ config ARM64
select ACPI_GENERIC_GSI if ACPI
select ACPI_REDUCED_HARDWARE_ONLY if ACPI
select ARCH_HAS_DEVMEM_IS_ALLOWED
+ select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_GCOV_PROFILE_ALL
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 7085e322dc42..648a32c89541 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -95,7 +95,7 @@ boot := arch/arm64/boot
Image: vmlinux
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
-Image.%: vmlinux
+Image.%: Image
$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
zinstall install:
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
index f895fc02ab06..40846319be69 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
@@ -49,6 +49,10 @@
/ {
model = "LS1043A RDB Board";
+
+ aliases {
+ crypto = &crypto;
+ };
};
&i2c0 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index de0323b48b1e..6bd46c133010 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -159,6 +159,49 @@
big-endian;
};
+ crypto: crypto@1700000 {
+ compatible = "fsl,sec-v5.4", "fsl,sec-v5.0",
+ "fsl,sec-v4.0";
+ fsl,sec-era = <3>;
+ #address-cells = <1>;
+ #size-cells = <1>;
+ ranges = <0x0 0x00 0x1700000 0x100000>;
+ reg = <0x00 0x1700000 0x0 0x100000>;
+ interrupts = <0 75 0x4>;
+
+ sec_jr0: jr@10000 {
+ compatible = "fsl,sec-v5.4-job-ring",
+ "fsl,sec-v5.0-job-ring",
+ "fsl,sec-v4.0-job-ring";
+ reg = <0x10000 0x10000>;
+ interrupts = <0 71 0x4>;
+ };
+
+ sec_jr1: jr@20000 {
+ compatible = "fsl,sec-v5.4-job-ring",
+ "fsl,sec-v5.0-job-ring",
+ "fsl,sec-v4.0-job-ring";
+ reg = <0x20000 0x10000>;
+ interrupts = <0 72 0x4>;
+ };
+
+ sec_jr2: jr@30000 {
+ compatible = "fsl,sec-v5.4-job-ring",
+ "fsl,sec-v5.0-job-ring",
+ "fsl,sec-v4.0-job-ring";
+ reg = <0x30000 0x10000>;
+ interrupts = <0 73 0x4>;
+ };
+
+ sec_jr3: jr@40000 {
+ compatible = "fsl,sec-v5.4-job-ring",
+ "fsl,sec-v5.0-job-ring",
+ "fsl,sec-v4.0-job-ring";
+ reg = <0x40000 0x10000>;
+ interrupts = <0 74 0x4>;
+ };
+ };
+
dcfg: dcfg@1ee0000 {
compatible = "fsl,ls1043a-dcfg", "syscon";
reg = <0x0 0x1ee0000 0x0 0x10000>;
diff --git a/arch/arm64/boot/dts/lg/lg1312.dtsi b/arch/arm64/boot/dts/lg/lg1312.dtsi
index 3a4e9a2ab313..fbafa24cd533 100644
--- a/arch/arm64/boot/dts/lg/lg1312.dtsi
+++ b/arch/arm64/boot/dts/lg/lg1312.dtsi
@@ -125,7 +125,7 @@
#size-cells = <1>;
#interrupts-cells = <3>;
- compatible = "arm,amba-bus";
+ compatible = "simple-bus";
interrupt-parent = <&gic>;
ranges;
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index 05f89c4a5413..77b8c4e388ca 100644
--- a/arch/arm64/boot/dts/mediatek/mt8173.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
@@ -168,6 +168,18 @@
};
};
+ reserved-memory {
+ #address-cells = <2>;
+ #size-cells = <2>;
+ ranges;
+ vpu_dma_reserved: vpu_dma_mem_region {
+ compatible = "shared-dma-pool";
+ reg = <0 0xb7000000 0 0x500000>;
+ alignment = <0x1000>;
+ no-map;
+ };
+ };
+
timer {
compatible = "arm,armv8-timer";
interrupt-parent = <&gic>;
@@ -312,6 +324,17 @@
clock-names = "spi", "wrap";
};
+ vpu: vpu@10020000 {
+ compatible = "mediatek,mt8173-vpu";
+ reg = <0 0x10020000 0 0x30000>,
+ <0 0x10050000 0 0x100>;
+ reg-names = "tcm", "cfg_reg";
+ interrupts = <GIC_SPI 166 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&topckgen CLK_TOP_SCP_SEL>;
+ clock-names = "main";
+ memory-region = <&vpu_dma_reserved>;
+ };
+
sysirq: intpol-controller@10200620 {
compatible = "mediatek,mt8173-sysirq",
"mediatek,mt6577-sysirq";
@@ -754,6 +777,45 @@
clock-names = "apb", "smi";
};
+ vcodec_enc: vcodec@18002000 {
+ compatible = "mediatek,mt8173-vcodec-enc";
+ reg = <0 0x18002000 0 0x1000>, /* VENC_SYS */
+ <0 0x19002000 0 0x1000>; /* VENC_LT_SYS */
+ interrupts = <GIC_SPI 198 IRQ_TYPE_LEVEL_LOW>,
+ <GIC_SPI 202 IRQ_TYPE_LEVEL_LOW>;
+ mediatek,larb = <&larb3>,
+ <&larb5>;
+ iommus = <&iommu M4U_PORT_VENC_RCPU>,
+ <&iommu M4U_PORT_VENC_REC>,
+ <&iommu M4U_PORT_VENC_BSDMA>,
+ <&iommu M4U_PORT_VENC_SV_COMV>,
+ <&iommu M4U_PORT_VENC_RD_COMV>,
+ <&iommu M4U_PORT_VENC_CUR_LUMA>,
+ <&iommu M4U_PORT_VENC_CUR_CHROMA>,
+ <&iommu M4U_PORT_VENC_REF_LUMA>,
+ <&iommu M4U_PORT_VENC_REF_CHROMA>,
+ <&iommu M4U_PORT_VENC_NBM_RDMA>,
+ <&iommu M4U_PORT_VENC_NBM_WDMA>,
+ <&iommu M4U_PORT_VENC_RCPU_SET2>,
+ <&iommu M4U_PORT_VENC_REC_FRM_SET2>,
+ <&iommu M4U_PORT_VENC_BSDMA_SET2>,
+ <&iommu M4U_PORT_VENC_SV_COMA_SET2>,
+ <&iommu M4U_PORT_VENC_RD_COMA_SET2>,
+ <&iommu M4U_PORT_VENC_CUR_LUMA_SET2>,
+ <&iommu M4U_PORT_VENC_CUR_CHROMA_SET2>,
+ <&iommu M4U_PORT_VENC_REF_LUMA_SET2>,
+ <&iommu M4U_PORT_VENC_REC_CHROMA_SET2>;
+ mediatek,vpu = <&vpu>;
+ clocks = <&topckgen CLK_TOP_VENCPLL_D2>,
+ <&topckgen CLK_TOP_VENC_SEL>,
+ <&topckgen CLK_TOP_UNIVPLL1_D2>,
+ <&topckgen CLK_TOP_VENC_LT_SEL>;
+ clock-names = "venc_sel_src",
+ "venc_sel",
+ "venc_lt_sel_src",
+ "venc_lt_sel";
+ };
+
vencltsys: clock-controller@19000000 {
compatible = "mediatek,mt8173-vencltsys", "syscon";
reg = <0 0x19000000 0 0x1000>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index 46f325a143b0..188bbeab92b9 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -163,7 +163,7 @@
};
amba {
- compatible = "arm,amba-bus";
+ compatible = "simple-bus";
#address-cells = <2>;
#size-cells = <2>;
ranges;
@@ -492,6 +492,14 @@
interrupts = <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
};
+ rktimer: rktimer@ff850000 {
+ compatible = "rockchip,rk3399-timer";
+ reg = <0x0 0xff850000 0x0 0x1000>;
+ interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>;
+ clocks = <&cru PCLK_TIMER0>, <&cru SCLK_TIMER00>;
+ clock-names = "pclk", "timer";
+ };
+
spdif: spdif@ff870000 {
compatible = "rockchip,rk3399-spdif";
reg = <0x0 0xff870000 0x0 0x1000>;
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index aee323b13802..5420cb0fcb3e 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -113,4 +113,14 @@ static inline const char *acpi_get_enable_method(int cpu)
pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr);
#endif
+#ifdef CONFIG_ACPI_NUMA
+int arm64_acpi_numa_init(void);
+int acpi_numa_get_nid(unsigned int cpu, u64 hwid);
+#else
+static inline int arm64_acpi_numa_init(void) { return -ENOSYS; }
+static inline int acpi_numa_get_nid(unsigned int cpu, u64 hwid) { return NUMA_NO_NODE; }
+#endif /* CONFIG_ACPI_NUMA */
+
+#define ACPI_TABLE_UPGRADE_MAX_PHYS MEMBLOCK_ALLOC_ACCESSIBLE
+
#endif /*_ASM_ACPI_H*/
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index f3a3586a421c..c0235e0ff849 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -76,6 +76,36 @@
#define atomic_dec_return_release(v) atomic_sub_return_release(1, (v))
#define atomic_dec_return(v) atomic_sub_return(1, (v))
+#define atomic_fetch_add_relaxed atomic_fetch_add_relaxed
+#define atomic_fetch_add_acquire atomic_fetch_add_acquire
+#define atomic_fetch_add_release atomic_fetch_add_release
+#define atomic_fetch_add atomic_fetch_add
+
+#define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed
+#define atomic_fetch_sub_acquire atomic_fetch_sub_acquire
+#define atomic_fetch_sub_release atomic_fetch_sub_release
+#define atomic_fetch_sub atomic_fetch_sub
+
+#define atomic_fetch_and_relaxed atomic_fetch_and_relaxed
+#define atomic_fetch_and_acquire atomic_fetch_and_acquire
+#define atomic_fetch_and_release atomic_fetch_and_release
+#define atomic_fetch_and atomic_fetch_and
+
+#define atomic_fetch_andnot_relaxed atomic_fetch_andnot_relaxed
+#define atomic_fetch_andnot_acquire atomic_fetch_andnot_acquire
+#define atomic_fetch_andnot_release atomic_fetch_andnot_release
+#define atomic_fetch_andnot atomic_fetch_andnot
+
+#define atomic_fetch_or_relaxed atomic_fetch_or_relaxed
+#define atomic_fetch_or_acquire atomic_fetch_or_acquire
+#define atomic_fetch_or_release atomic_fetch_or_release
+#define atomic_fetch_or atomic_fetch_or
+
+#define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed
+#define atomic_fetch_xor_acquire atomic_fetch_xor_acquire
+#define atomic_fetch_xor_release atomic_fetch_xor_release
+#define atomic_fetch_xor atomic_fetch_xor
+
#define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
#define atomic_xchg_acquire(v, new) xchg_acquire(&((v)->counter), (new))
#define atomic_xchg_release(v, new) xchg_release(&((v)->counter), (new))
@@ -125,6 +155,36 @@
#define atomic64_dec_return_release(v) atomic64_sub_return_release(1, (v))
#define atomic64_dec_return(v) atomic64_sub_return(1, (v))
+#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed
+#define atomic64_fetch_add_acquire atomic64_fetch_add_acquire
+#define atomic64_fetch_add_release atomic64_fetch_add_release
+#define atomic64_fetch_add atomic64_fetch_add
+
+#define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed
+#define atomic64_fetch_sub_acquire atomic64_fetch_sub_acquire
+#define atomic64_fetch_sub_release atomic64_fetch_sub_release
+#define atomic64_fetch_sub atomic64_fetch_sub
+
+#define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed
+#define atomic64_fetch_and_acquire atomic64_fetch_and_acquire
+#define atomic64_fetch_and_release atomic64_fetch_and_release
+#define atomic64_fetch_and atomic64_fetch_and
+
+#define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot_relaxed
+#define atomic64_fetch_andnot_acquire atomic64_fetch_andnot_acquire
+#define atomic64_fetch_andnot_release atomic64_fetch_andnot_release
+#define atomic64_fetch_andnot atomic64_fetch_andnot
+
+#define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed
+#define atomic64_fetch_or_acquire atomic64_fetch_or_acquire
+#define atomic64_fetch_or_release atomic64_fetch_or_release
+#define atomic64_fetch_or atomic64_fetch_or
+
+#define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed
+#define atomic64_fetch_xor_acquire atomic64_fetch_xor_acquire
+#define atomic64_fetch_xor_release atomic64_fetch_xor_release
+#define atomic64_fetch_xor atomic64_fetch_xor
+
#define atomic64_xchg_relaxed atomic_xchg_relaxed
#define atomic64_xchg_acquire atomic_xchg_acquire
#define atomic64_xchg_release atomic_xchg_release
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index f61c84f6ba02..f819fdcff1ac 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -77,26 +77,57 @@ __LL_SC_PREFIX(atomic_##op##_return##name(int i, atomic_t *v)) \
} \
__LL_SC_EXPORT(atomic_##op##_return##name);
+#define ATOMIC_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \
+__LL_SC_INLINE int \
+__LL_SC_PREFIX(atomic_fetch_##op##name(int i, atomic_t *v)) \
+{ \
+ unsigned long tmp; \
+ int val, result; \
+ \
+ asm volatile("// atomic_fetch_" #op #name "\n" \
+" prfm pstl1strm, %3\n" \
+"1: ld" #acq "xr %w0, %3\n" \
+" " #asm_op " %w1, %w0, %w4\n" \
+" st" #rel "xr %w2, %w1, %3\n" \
+" cbnz %w2, 1b\n" \
+" " #mb \
+ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \
+ : "Ir" (i) \
+ : cl); \
+ \
+ return result; \
+} \
+__LL_SC_EXPORT(atomic_fetch_##op##name);
+
#define ATOMIC_OPS(...) \
ATOMIC_OP(__VA_ARGS__) \
- ATOMIC_OP_RETURN( , dmb ish, , l, "memory", __VA_ARGS__)
-
-#define ATOMIC_OPS_RLX(...) \
- ATOMIC_OPS(__VA_ARGS__) \
+ ATOMIC_OP_RETURN( , dmb ish, , l, "memory", __VA_ARGS__)\
ATOMIC_OP_RETURN(_relaxed, , , , , __VA_ARGS__)\
ATOMIC_OP_RETURN(_acquire, , a, , "memory", __VA_ARGS__)\
- ATOMIC_OP_RETURN(_release, , , l, "memory", __VA_ARGS__)
+ ATOMIC_OP_RETURN(_release, , , l, "memory", __VA_ARGS__)\
+ ATOMIC_FETCH_OP ( , dmb ish, , l, "memory", __VA_ARGS__)\
+ ATOMIC_FETCH_OP (_relaxed, , , , , __VA_ARGS__)\
+ ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\
+ ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__)
-ATOMIC_OPS_RLX(add, add)
-ATOMIC_OPS_RLX(sub, sub)
+ATOMIC_OPS(add, add)
+ATOMIC_OPS(sub, sub)
+
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(...) \
+ ATOMIC_OP(__VA_ARGS__) \
+ ATOMIC_FETCH_OP ( , dmb ish, , l, "memory", __VA_ARGS__)\
+ ATOMIC_FETCH_OP (_relaxed, , , , , __VA_ARGS__)\
+ ATOMIC_FETCH_OP (_acquire, , a, , "memory", __VA_ARGS__)\
+ ATOMIC_FETCH_OP (_release, , , l, "memory", __VA_ARGS__)
-ATOMIC_OP(and, and)
-ATOMIC_OP(andnot, bic)
-ATOMIC_OP(or, orr)
-ATOMIC_OP(xor, eor)
+ATOMIC_OPS(and, and)
+ATOMIC_OPS(andnot, bic)
+ATOMIC_OPS(or, orr)
+ATOMIC_OPS(xor, eor)
-#undef ATOMIC_OPS_RLX
#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
#undef ATOMIC_OP
@@ -140,26 +171,57 @@ __LL_SC_PREFIX(atomic64_##op##_return##name(long i, atomic64_t *v)) \
} \
__LL_SC_EXPORT(atomic64_##op##_return##name);
+#define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op) \
+__LL_SC_INLINE long \
+__LL_SC_PREFIX(atomic64_fetch_##op##name(long i, atomic64_t *v)) \
+{ \
+ long result, val; \
+ unsigned long tmp; \
+ \
+ asm volatile("// atomic64_fetch_" #op #name "\n" \
+" prfm pstl1strm, %3\n" \
+"1: ld" #acq "xr %0, %3\n" \
+" " #asm_op " %1, %0, %4\n" \
+" st" #rel "xr %w2, %1, %3\n" \
+" cbnz %w2, 1b\n" \
+" " #mb \
+ : "=&r" (result), "=&r" (val), "=&r" (tmp), "+Q" (v->counter) \
+ : "Ir" (i) \
+ : cl); \
+ \
+ return result; \
+} \
+__LL_SC_EXPORT(atomic64_fetch_##op##name);
+
#define ATOMIC64_OPS(...) \
ATOMIC64_OP(__VA_ARGS__) \
- ATOMIC64_OP_RETURN(, dmb ish, , l, "memory", __VA_ARGS__)
-
-#define ATOMIC64_OPS_RLX(...) \
- ATOMIC64_OPS(__VA_ARGS__) \
+ ATOMIC64_OP_RETURN(, dmb ish, , l, "memory", __VA_ARGS__) \
ATOMIC64_OP_RETURN(_relaxed,, , , , __VA_ARGS__) \
ATOMIC64_OP_RETURN(_acquire,, a, , "memory", __VA_ARGS__) \
- ATOMIC64_OP_RETURN(_release,, , l, "memory", __VA_ARGS__)
+ ATOMIC64_OP_RETURN(_release,, , l, "memory", __VA_ARGS__) \
+ ATOMIC64_FETCH_OP (, dmb ish, , l, "memory", __VA_ARGS__) \
+ ATOMIC64_FETCH_OP (_relaxed,, , , , __VA_ARGS__) \
+ ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \
+ ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__)
-ATOMIC64_OPS_RLX(add, add)
-ATOMIC64_OPS_RLX(sub, sub)
+ATOMIC64_OPS(add, add)
+ATOMIC64_OPS(sub, sub)
+
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(...) \
+ ATOMIC64_OP(__VA_ARGS__) \
+ ATOMIC64_FETCH_OP (, dmb ish, , l, "memory", __VA_ARGS__) \
+ ATOMIC64_FETCH_OP (_relaxed,, , , , __VA_ARGS__) \
+ ATOMIC64_FETCH_OP (_acquire,, a, , "memory", __VA_ARGS__) \
+ ATOMIC64_FETCH_OP (_release,, , l, "memory", __VA_ARGS__)
-ATOMIC64_OP(and, and)
-ATOMIC64_OP(andnot, bic)
-ATOMIC64_OP(or, orr)
-ATOMIC64_OP(xor, eor)
+ATOMIC64_OPS(and, and)
+ATOMIC64_OPS(andnot, bic)
+ATOMIC64_OPS(or, orr)
+ATOMIC64_OPS(xor, eor)
-#undef ATOMIC64_OPS_RLX
#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
#undef ATOMIC64_OP_RETURN
#undef ATOMIC64_OP
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 39c1d340fec5..b5890be8f257 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -26,54 +26,57 @@
#endif
#define __LL_SC_ATOMIC(op) __LL_SC_CALL(atomic_##op)
-
-static inline void atomic_andnot(int i, atomic_t *v)
-{
- register int w0 asm ("w0") = i;
- register atomic_t *x1 asm ("x1") = v;
-
- asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(andnot),
- " stclr %w[i], %[v]\n")
- : [i] "+r" (w0), [v] "+Q" (v->counter)
- : "r" (x1)
- : __LL_SC_CLOBBERS);
+#define ATOMIC_OP(op, asm_op) \
+static inline void atomic_##op(int i, atomic_t *v) \
+{ \
+ register int w0 asm ("w0") = i; \
+ register atomic_t *x1 asm ("x1") = v; \
+ \
+ asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(op), \
+" " #asm_op " %w[i], %[v]\n") \
+ : [i] "+r" (w0), [v] "+Q" (v->counter) \
+ : "r" (x1) \
+ : __LL_SC_CLOBBERS); \
}
-static inline void atomic_or(int i, atomic_t *v)
-{
- register int w0 asm ("w0") = i;
- register atomic_t *x1 asm ("x1") = v;
+ATOMIC_OP(andnot, stclr)
+ATOMIC_OP(or, stset)
+ATOMIC_OP(xor, steor)
+ATOMIC_OP(add, stadd)
- asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(or),
- " stset %w[i], %[v]\n")
- : [i] "+r" (w0), [v] "+Q" (v->counter)
- : "r" (x1)
- : __LL_SC_CLOBBERS);
-}
+#undef ATOMIC_OP
-static inline void atomic_xor(int i, atomic_t *v)
-{
- register int w0 asm ("w0") = i;
- register atomic_t *x1 asm ("x1") = v;
-
- asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(xor),
- " steor %w[i], %[v]\n")
- : [i] "+r" (w0), [v] "+Q" (v->counter)
- : "r" (x1)
- : __LL_SC_CLOBBERS);
+#define ATOMIC_FETCH_OP(name, mb, op, asm_op, cl...) \
+static inline int atomic_fetch_##op##name(int i, atomic_t *v) \
+{ \
+ register int w0 asm ("w0") = i; \
+ register atomic_t *x1 asm ("x1") = v; \
+ \
+ asm volatile(ARM64_LSE_ATOMIC_INSN( \
+ /* LL/SC */ \
+ __LL_SC_ATOMIC(fetch_##op##name), \
+ /* LSE atomics */ \
+" " #asm_op #mb " %w[i], %w[i], %[v]") \
+ : [i] "+r" (w0), [v] "+Q" (v->counter) \
+ : "r" (x1) \
+ : __LL_SC_CLOBBERS, ##cl); \
+ \
+ return w0; \
}
-static inline void atomic_add(int i, atomic_t *v)
-{
- register int w0 asm ("w0") = i;
- register atomic_t *x1 asm ("x1") = v;
+#define ATOMIC_FETCH_OPS(op, asm_op) \
+ ATOMIC_FETCH_OP(_relaxed, , op, asm_op) \
+ ATOMIC_FETCH_OP(_acquire, a, op, asm_op, "memory") \
+ ATOMIC_FETCH_OP(_release, l, op, asm_op, "memory") \
+ ATOMIC_FETCH_OP( , al, op, asm_op, "memory")
- asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(add),
- " stadd %w[i], %[v]\n")
- : [i] "+r" (w0), [v] "+Q" (v->counter)
- : "r" (x1)
- : __LL_SC_CLOBBERS);
-}
+ATOMIC_FETCH_OPS(andnot, ldclr)
+ATOMIC_FETCH_OPS(or, ldset)
+ATOMIC_FETCH_OPS(xor, ldeor)
+ATOMIC_FETCH_OPS(add, ldadd)
+
+#undef ATOMIC_FETCH_OP
+#undef ATOMIC_FETCH_OPS
#define ATOMIC_OP_ADD_RETURN(name, mb, cl...) \
static inline int atomic_add_return##name(int i, atomic_t *v) \
@@ -119,6 +122,33 @@ static inline void atomic_and(int i, atomic_t *v)
: __LL_SC_CLOBBERS);
}
+#define ATOMIC_FETCH_OP_AND(name, mb, cl...) \
+static inline int atomic_fetch_and##name(int i, atomic_t *v) \
+{ \
+ register int w0 asm ("w0") = i; \
+ register atomic_t *x1 asm ("x1") = v; \
+ \
+ asm volatile(ARM64_LSE_ATOMIC_INSN( \
+ /* LL/SC */ \
+ " nop\n" \
+ __LL_SC_ATOMIC(fetch_and##name), \
+ /* LSE atomics */ \
+ " mvn %w[i], %w[i]\n" \
+ " ldclr" #mb " %w[i], %w[i], %[v]") \
+ : [i] "+r" (w0), [v] "+Q" (v->counter) \
+ : "r" (x1) \
+ : __LL_SC_CLOBBERS, ##cl); \
+ \
+ return w0; \
+}
+
+ATOMIC_FETCH_OP_AND(_relaxed, )
+ATOMIC_FETCH_OP_AND(_acquire, a, "memory")
+ATOMIC_FETCH_OP_AND(_release, l, "memory")
+ATOMIC_FETCH_OP_AND( , al, "memory")
+
+#undef ATOMIC_FETCH_OP_AND
+
static inline void atomic_sub(int i, atomic_t *v)
{
register int w0 asm ("w0") = i;
@@ -164,57 +194,87 @@ ATOMIC_OP_SUB_RETURN(_release, l, "memory")
ATOMIC_OP_SUB_RETURN( , al, "memory")
#undef ATOMIC_OP_SUB_RETURN
-#undef __LL_SC_ATOMIC
-
-#define __LL_SC_ATOMIC64(op) __LL_SC_CALL(atomic64_##op)
-
-static inline void atomic64_andnot(long i, atomic64_t *v)
-{
- register long x0 asm ("x0") = i;
- register atomic64_t *x1 asm ("x1") = v;
- asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(andnot),
- " stclr %[i], %[v]\n")
- : [i] "+r" (x0), [v] "+Q" (v->counter)
- : "r" (x1)
- : __LL_SC_CLOBBERS);
+#define ATOMIC_FETCH_OP_SUB(name, mb, cl...) \
+static inline int atomic_fetch_sub##name(int i, atomic_t *v) \
+{ \
+ register int w0 asm ("w0") = i; \
+ register atomic_t *x1 asm ("x1") = v; \
+ \
+ asm volatile(ARM64_LSE_ATOMIC_INSN( \
+ /* LL/SC */ \
+ " nop\n" \
+ __LL_SC_ATOMIC(fetch_sub##name), \
+ /* LSE atomics */ \
+ " neg %w[i], %w[i]\n" \
+ " ldadd" #mb " %w[i], %w[i], %[v]") \
+ : [i] "+r" (w0), [v] "+Q" (v->counter) \
+ : "r" (x1) \
+ : __LL_SC_CLOBBERS, ##cl); \
+ \
+ return w0; \
}
-static inline void atomic64_or(long i, atomic64_t *v)
-{
- register long x0 asm ("x0") = i;
- register atomic64_t *x1 asm ("x1") = v;
+ATOMIC_FETCH_OP_SUB(_relaxed, )
+ATOMIC_FETCH_OP_SUB(_acquire, a, "memory")
+ATOMIC_FETCH_OP_SUB(_release, l, "memory")
+ATOMIC_FETCH_OP_SUB( , al, "memory")
- asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(or),
- " stset %[i], %[v]\n")
- : [i] "+r" (x0), [v] "+Q" (v->counter)
- : "r" (x1)
- : __LL_SC_CLOBBERS);
+#undef ATOMIC_FETCH_OP_SUB
+#undef __LL_SC_ATOMIC
+
+#define __LL_SC_ATOMIC64(op) __LL_SC_CALL(atomic64_##op)
+#define ATOMIC64_OP(op, asm_op) \
+static inline void atomic64_##op(long i, atomic64_t *v) \
+{ \
+ register long x0 asm ("x0") = i; \
+ register atomic64_t *x1 asm ("x1") = v; \
+ \
+ asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(op), \
+" " #asm_op " %[i], %[v]\n") \
+ : [i] "+r" (x0), [v] "+Q" (v->counter) \
+ : "r" (x1) \
+ : __LL_SC_CLOBBERS); \
}
-static inline void atomic64_xor(long i, atomic64_t *v)
-{
- register long x0 asm ("x0") = i;
- register atomic64_t *x1 asm ("x1") = v;
+ATOMIC64_OP(andnot, stclr)
+ATOMIC64_OP(or, stset)
+ATOMIC64_OP(xor, steor)
+ATOMIC64_OP(add, stadd)
- asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(xor),
- " steor %[i], %[v]\n")
- : [i] "+r" (x0), [v] "+Q" (v->counter)
- : "r" (x1)
- : __LL_SC_CLOBBERS);
+#undef ATOMIC64_OP
+
+#define ATOMIC64_FETCH_OP(name, mb, op, asm_op, cl...) \
+static inline long atomic64_fetch_##op##name(long i, atomic64_t *v) \
+{ \
+ register long x0 asm ("x0") = i; \
+ register atomic64_t *x1 asm ("x1") = v; \
+ \
+ asm volatile(ARM64_LSE_ATOMIC_INSN( \
+ /* LL/SC */ \
+ __LL_SC_ATOMIC64(fetch_##op##name), \
+ /* LSE atomics */ \
+" " #asm_op #mb " %[i], %[i], %[v]") \
+ : [i] "+r" (x0), [v] "+Q" (v->counter) \
+ : "r" (x1) \
+ : __LL_SC_CLOBBERS, ##cl); \
+ \
+ return x0; \
}
-static inline void atomic64_add(long i, atomic64_t *v)
-{
- register long x0 asm ("x0") = i;
- register atomic64_t *x1 asm ("x1") = v;
+#define ATOMIC64_FETCH_OPS(op, asm_op) \
+ ATOMIC64_FETCH_OP(_relaxed, , op, asm_op) \
+ ATOMIC64_FETCH_OP(_acquire, a, op, asm_op, "memory") \
+ ATOMIC64_FETCH_OP(_release, l, op, asm_op, "memory") \
+ ATOMIC64_FETCH_OP( , al, op, asm_op, "memory")
- asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(add),
- " stadd %[i], %[v]\n")
- : [i] "+r" (x0), [v] "+Q" (v->counter)
- : "r" (x1)
- : __LL_SC_CLOBBERS);
-}
+ATOMIC64_FETCH_OPS(andnot, ldclr)
+ATOMIC64_FETCH_OPS(or, ldset)
+ATOMIC64_FETCH_OPS(xor, ldeor)
+ATOMIC64_FETCH_OPS(add, ldadd)
+
+#undef ATOMIC64_FETCH_OP
+#undef ATOMIC64_FETCH_OPS
#define ATOMIC64_OP_ADD_RETURN(name, mb, cl...) \
static inline long atomic64_add_return##name(long i, atomic64_t *v) \
@@ -260,6 +320,33 @@ static inline void atomic64_and(long i, atomic64_t *v)
: __LL_SC_CLOBBERS);
}
+#define ATOMIC64_FETCH_OP_AND(name, mb, cl...) \
+static inline long atomic64_fetch_and##name(long i, atomic64_t *v) \
+{ \
+ register long x0 asm ("w0") = i; \
+ register atomic64_t *x1 asm ("x1") = v; \
+ \
+ asm volatile(ARM64_LSE_ATOMIC_INSN( \
+ /* LL/SC */ \
+ " nop\n" \
+ __LL_SC_ATOMIC64(fetch_and##name), \
+ /* LSE atomics */ \
+ " mvn %[i], %[i]\n" \
+ " ldclr" #mb " %[i], %[i], %[v]") \
+ : [i] "+r" (x0), [v] "+Q" (v->counter) \
+ : "r" (x1) \
+ : __LL_SC_CLOBBERS, ##cl); \
+ \
+ return x0; \
+}
+
+ATOMIC64_FETCH_OP_AND(_relaxed, )
+ATOMIC64_FETCH_OP_AND(_acquire, a, "memory")
+ATOMIC64_FETCH_OP_AND(_release, l, "memory")
+ATOMIC64_FETCH_OP_AND( , al, "memory")
+
+#undef ATOMIC64_FETCH_OP_AND
+
static inline void atomic64_sub(long i, atomic64_t *v)
{
register long x0 asm ("x0") = i;
@@ -306,6 +393,33 @@ ATOMIC64_OP_SUB_RETURN( , al, "memory")
#undef ATOMIC64_OP_SUB_RETURN
+#define ATOMIC64_FETCH_OP_SUB(name, mb, cl...) \
+static inline long atomic64_fetch_sub##name(long i, atomic64_t *v) \
+{ \
+ register long x0 asm ("w0") = i; \
+ register atomic64_t *x1 asm ("x1") = v; \
+ \
+ asm volatile(ARM64_LSE_ATOMIC_INSN( \
+ /* LL/SC */ \
+ " nop\n" \
+ __LL_SC_ATOMIC64(fetch_sub##name), \
+ /* LSE atomics */ \
+ " neg %[i], %[i]\n" \
+ " ldadd" #mb " %[i], %[i], %[v]") \
+ : [i] "+r" (x0), [v] "+Q" (v->counter) \
+ : "r" (x1) \
+ : __LL_SC_CLOBBERS, ##cl); \
+ \
+ return x0; \
+}
+
+ATOMIC64_FETCH_OP_SUB(_relaxed, )
+ATOMIC64_FETCH_OP_SUB(_acquire, a, "memory")
+ATOMIC64_FETCH_OP_SUB(_release, l, "memory")
+ATOMIC64_FETCH_OP_SUB( , al, "memory")
+
+#undef ATOMIC64_FETCH_OP_SUB
+
static inline long atomic64_dec_if_positive(atomic64_t *v)
{
register long x0 asm ("x0") = (long)v;
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index dae5c49618db..4eea7f618dce 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -91,6 +91,19 @@ do { \
__u.__val; \
})
+#define smp_cond_load_acquire(ptr, cond_expr) \
+({ \
+ typeof(ptr) __PTR = (ptr); \
+ typeof(*ptr) VAL; \
+ for (;;) { \
+ VAL = smp_load_acquire(__PTR); \
+ if (cond_expr) \
+ break; \
+ __cmpwait_relaxed(__PTR, VAL); \
+ } \
+ VAL; \
+})
+
#include <asm-generic/barrier.h>
#endif /* __ASSEMBLY__ */
diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
index 510c7b404454..bd86a79491bc 100644
--- a/arch/arm64/include/asm/cmpxchg.h
+++ b/arch/arm64/include/asm/cmpxchg.h
@@ -224,4 +224,55 @@ __CMPXCHG_GEN(_mb)
__ret; \
})
+#define __CMPWAIT_CASE(w, sz, name) \
+static inline void __cmpwait_case_##name(volatile void *ptr, \
+ unsigned long val) \
+{ \
+ unsigned long tmp; \
+ \
+ asm volatile( \
+ " ldxr" #sz "\t%" #w "[tmp], %[v]\n" \
+ " eor %" #w "[tmp], %" #w "[tmp], %" #w "[val]\n" \
+ " cbnz %" #w "[tmp], 1f\n" \
+ " wfe\n" \
+ "1:" \
+ : [tmp] "=&r" (tmp), [v] "+Q" (*(unsigned long *)ptr) \
+ : [val] "r" (val)); \
+}
+
+__CMPWAIT_CASE(w, b, 1);
+__CMPWAIT_CASE(w, h, 2);
+__CMPWAIT_CASE(w, , 4);
+__CMPWAIT_CASE( , , 8);
+
+#undef __CMPWAIT_CASE
+
+#define __CMPWAIT_GEN(sfx) \
+static inline void __cmpwait##sfx(volatile void *ptr, \
+ unsigned long val, \
+ int size) \
+{ \
+ switch (size) { \
+ case 1: \
+ return __cmpwait_case##sfx##_1(ptr, (u8)val); \
+ case 2: \
+ return __cmpwait_case##sfx##_2(ptr, (u16)val); \
+ case 4: \
+ return __cmpwait_case##sfx##_4(ptr, val); \
+ case 8: \
+ return __cmpwait_case##sfx##_8(ptr, val); \
+ default: \
+ BUILD_BUG(); \
+ } \
+ \
+ unreachable(); \
+}
+
+__CMPWAIT_GEN()
+
+#undef __CMPWAIT_GEN
+
+#define __cmpwait_relaxed(ptr, val) \
+ __cmpwait((ptr), (unsigned long)(val), sizeof(*(ptr)))
+
#endif /* __ASM_CMPXCHG_H */
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 87e1985f3be8..9d9fd4b9a72e 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -80,12 +80,14 @@
#define APM_CPU_PART_POTENZA 0x000
#define CAVIUM_CPU_PART_THUNDERX 0x0A1
+#define CAVIUM_CPU_PART_THUNDERX_81XX 0x0A2
#define BRCM_CPU_PART_VULCAN 0x516
#define MIDR_CORTEX_A53 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A53)
#define MIDR_CORTEX_A57 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A57)
#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)
#ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 622db3c6474e..bd887663689b 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -23,10 +23,10 @@ int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md);
efi_virtmap_load(); \
})
-#define arch_efi_call_virt(f, args...) \
+#define arch_efi_call_virt(p, f, args...) \
({ \
efi_##f##_t *__f; \
- __f = efi.systab->runtime->f; \
+ __f = p->f; \
__f(args); \
})
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 44be1e03ed65..9b6e408cfa51 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -174,13 +174,15 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
#define iounmap __iounmap
/*
- * io{read,write}{16,32}be() macros
+ * io{read,write}{16,32,64}be() macros
*/
#define ioread16be(p) ({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
#define ioread32be(p) ({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
+#define ioread64be(p) ({ __u64 __v = be64_to_cpu((__force __be64)__raw_readq(p)); __iormb(); __v; })
#define iowrite16be(v,p) ({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); })
#define iowrite32be(v,p) ({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
+#define iowrite64be(v,p) ({ __iowmb(); __raw_writeq((__force __u64)cpu_to_be64(v), p); })
/*
* Convert a physical pointer to a virtual kernel pointer for /dev/mem
diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h
index f69f69c8120c..da84645525b9 100644
--- a/arch/arm64/include/asm/kgdb.h
+++ b/arch/arm64/include/asm/kgdb.h
@@ -38,25 +38,54 @@ extern int kgdb_fault_expected;
#endif /* !__ASSEMBLY__ */
/*
- * gdb is expecting the following registers layout.
+ * gdb remote procotol (well most versions of it) expects the following
+ * register layout.
*
* General purpose regs:
* r0-r30: 64 bit
* sp,pc : 64 bit
- * pstate : 64 bit
- * Total: 34
+ * pstate : 32 bit
+ * Total: 33 + 1
* FPU regs:
* f0-f31: 128 bit
- * Total: 32
- * Extra regs
* fpsr & fpcr: 32 bit
- * Total: 2
+ * Total: 32 + 2
*
+ * To expand a little on the "most versions of it"... when the gdb remote
+ * protocol for AArch64 was developed it depended on a statement in the
+ * Architecture Reference Manual that claimed "SPSR_ELx is a 32-bit register".
+ * and, as a result, allocated only 32-bits for the PSTATE in the remote
+ * protocol. In fact this statement is still present in ARM DDI 0487A.i.
+ *
+ * Unfortunately "is a 32-bit register" has a very special meaning for
+ * system registers. It means that "the upper bits, bits[63:32], are
+ * RES0.". RES0 is heavily used in the ARM architecture documents as a
+ * way to leave space for future architecture changes. So to translate a
+ * little for people who don't spend their spare time reading ARM architecture
+ * manuals, what "is a 32-bit register" actually means in this context is
+ * "is a 64-bit register but one with no meaning allocated to any of the
+ * upper 32-bits... *yet*".
+ *
+ * Perhaps then we should not be surprised that this has led to some
+ * confusion. Specifically a patch, influenced by the above translation,
+ * that extended PSTATE to 64-bit was accepted into gdb-7.7 but the patch
+ * was reverted in gdb-7.8.1 and all later releases, when this was
+ * discovered to be an undocumented protocol change.
+ *
+ * So... it is *not* wrong for us to only allocate 32-bits to PSTATE
+ * here even though the kernel itself allocates 64-bits for the same
+ * state. That is because this bit of code tells the kernel how the gdb
+ * remote protocol (well most versions of it) describes the register state.
+ *
+ * Note that if you are using one of the versions of gdb that supports
+ * the gdb-7.7 version of the protocol you cannot use kgdb directly
+ * without providing a custom register description (gdb can load new
+ * protocol descriptions at runtime).
*/
-#define _GP_REGS 34
+#define _GP_REGS 33
#define _FP_REGS 32
-#define _EXTRA_REGS 2
+#define _EXTRA_REGS 3
/*
* general purpose registers size in bytes.
* pstate is only 4 bytes. subtract 4 bytes
diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h
index e9b4f2942335..600887e491fd 100644
--- a/arch/arm64/include/asm/numa.h
+++ b/arch/arm64/include/asm/numa.h
@@ -5,6 +5,8 @@
#ifdef CONFIG_NUMA
+#define NR_NODE_MEMBLKS (MAX_NUMNODES * 2)
+
/* currently, arm64 implements flat NUMA topology */
#define parent_node(node) (node)
diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h
index ff98585d085a..d25f4f137c2a 100644
--- a/arch/arm64/include/asm/pgalloc.h
+++ b/arch/arm64/include/asm/pgalloc.h
@@ -26,7 +26,7 @@
#define check_pgt_cache() do { } while (0)
-#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO)
#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t))
#if CONFIG_PGTABLE_LEVELS > 2
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index a307eb6e7fa8..7f94755089e2 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -117,6 +117,8 @@ struct pt_regs {
};
u64 orig_x0;
u64 syscallno;
+ u64 orig_addr_limit;
+ u64 unused; // maintain 16 byte alignment
};
#define arch_has_single_step() (1)
diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 433e50405274..022644704a93 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -124,6 +124,18 @@ static inline void cpu_panic_kernel(void)
cpu_park_loop();
}
+/*
+ * If a secondary CPU enters the kernel but fails to come online,
+ * (e.g. due to mismatched features), and cannot exit the kernel,
+ * we increment cpus_stuck_in_kernel and leave the CPU in a
+ * quiesecent loop within the kernel text. The memory containing
+ * this loop must not be re-used for anything else as the 'stuck'
+ * core is executing it.
+ *
+ * This function is used to inhibit features like kexec and hibernate.
+ */
+bool cpus_are_stuck_in_kernel(void);
+
#endif /* ifndef __ASSEMBLY__ */
#endif /* ifndef __ASM_SMP_H */
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index fc9682bfe002..e875a5a551d7 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -30,22 +30,53 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
{
unsigned int tmp;
arch_spinlock_t lockval;
+ u32 owner;
+
+ /*
+ * Ensure prior spin_lock operations to other locks have completed
+ * on this CPU before we test whether "lock" is locked.
+ */
+ smp_mb();
+ owner = READ_ONCE(lock->owner) << 16;
asm volatile(
" sevl\n"
"1: wfe\n"
"2: ldaxr %w0, %2\n"
+ /* Is the lock free? */
" eor %w1, %w0, %w0, ror #16\n"
-" cbnz %w1, 1b\n"
+" cbz %w1, 3f\n"
+ /* Lock taken -- has there been a subsequent unlock->lock transition? */
+" eor %w1, %w3, %w0, lsl #16\n"
+" cbz %w1, 1b\n"
+ /*
+ * The owner has been updated, so there was an unlock->lock
+ * transition that we missed. That means we can rely on the
+ * store-release of the unlock operation paired with the
+ * load-acquire of the lock operation to publish any of our
+ * previous stores to the new lock owner and therefore don't
+ * need to bother with the writeback below.
+ */
+" b 4f\n"
+"3:\n"
+ /*
+ * Serialise against any concurrent lockers by writing back the
+ * unlocked lock value
+ */
ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
" stxr %w1, %w0, %2\n"
-" cbnz %w1, 2b\n", /* Serialise against any concurrent lockers */
- /* LSE atomics */
" nop\n"
-" nop\n")
+" nop\n",
+ /* LSE atomics */
+" mov %w1, %w0\n"
+" cas %w0, %w0, %2\n"
+" eor %w1, %w1, %w0\n")
+ /* Somebody else wrote to the lock, GOTO 10 and reload the value */
+" cbnz %w1, 2b\n"
+"4:"
: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
- :
+ : "r" (owner)
: "memory");
}
@@ -148,6 +179,7 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
+ smp_mb(); /* See arch_spin_unlock_wait */
return !arch_spin_value_unlocked(READ_ONCE(*lock));
}
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 2173149d8954..a5125c6d1f87 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -42,6 +42,7 @@ arm64-obj-$(CONFIG_EFI) += efi.o efi-entry.stub.o
arm64-obj-$(CONFIG_PCI) += pci.o
arm64-obj-$(CONFIG_ARMV8_DEPRECATED) += armv8_deprecated.o
arm64-obj-$(CONFIG_ACPI) += acpi.o
+arm64-obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o
arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o
arm64-obj-$(CONFIG_PARAVIRT) += paravirt.o
arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c
new file mode 100644
index 000000000000..f85149cc7c71
--- /dev/null
+++ b/arch/arm64/kernel/acpi_numa.c
@@ -0,0 +1,112 @@
+/*
+ * ACPI 5.1 based NUMA setup for ARM64
+ * Lots of code was borrowed from arch/x86/mm/srat.c
+ *
+ * Copyright 2004 Andi Kleen, SuSE Labs.
+ * Copyright (C) 2013-2016, Linaro Ltd.
+ * Author: Hanjun Guo <hanjun.guo@linaro.org>
+ *
+ * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs.
+ *
+ * Called from acpi_numa_init while reading the SRAT and SLIT tables.
+ * Assumes all memory regions belonging to a single proximity domain
+ * are in one chunk. Holes between them will be included in the node.
+ */
+
+#define pr_fmt(fmt) "ACPI: NUMA: " fmt
+
+#include <linux/acpi.h>
+#include <linux/bitmap.h>
+#include <linux/bootmem.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/memblock.h>
+#include <linux/mmzone.h>
+#include <linux/module.h>
+#include <linux/topology.h>
+
+#include <acpi/processor.h>
+#include <asm/numa.h>
+
+static int cpus_in_srat;
+
+struct __node_cpu_hwid {
+ u32 node_id; /* logical node containing this CPU */
+ u64 cpu_hwid; /* MPIDR for this CPU */
+};
+
+static struct __node_cpu_hwid early_node_cpu_hwid[NR_CPUS] = {
+[0 ... NR_CPUS - 1] = {NUMA_NO_NODE, PHYS_CPUID_INVALID} };
+
+int acpi_numa_get_nid(unsigned int cpu, u64 hwid)
+{
+ int i;
+
+ for (i = 0; i < cpus_in_srat; i++) {
+ if (hwid == early_node_cpu_hwid[i].cpu_hwid)
+ return early_node_cpu_hwid[i].node_id;
+ }
+
+ return NUMA_NO_NODE;
+}
+
+/* Callback for Proximity Domain -> ACPI processor UID mapping */
+void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa)
+{
+ int pxm, node;
+ phys_cpuid_t mpidr;
+
+ if (srat_disabled())
+ return;
+
+ if (pa->header.length < sizeof(struct acpi_srat_gicc_affinity)) {
+ pr_err("SRAT: Invalid SRAT header length: %d\n",
+ pa->header.length);
+ bad_srat();
+ return;
+ }
+
+ if (!(pa->flags & ACPI_SRAT_GICC_ENABLED))
+ return;
+
+ if (cpus_in_srat >= NR_CPUS) {
+ pr_warn_once("SRAT: cpu_to_node_map[%d] is too small, may not be able to use all cpus\n",
+ NR_CPUS);
+ return;
+ }
+
+ pxm = pa->proximity_domain;
+ node = acpi_map_pxm_to_node(pxm);
+
+ if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) {
+ pr_err("SRAT: Too many proximity domains %d\n", pxm);
+ bad_srat();
+ return;
+ }
+
+ mpidr = acpi_map_madt_entry(pa->acpi_processor_uid);
+ if (mpidr == PHYS_CPUID_INVALID) {
+ pr_err("SRAT: PXM %d with ACPI ID %d has no valid MPIDR in MADT\n",
+ pxm, pa->acpi_processor_uid);
+ bad_srat();
+ return;
+ }
+
+ early_node_cpu_hwid[cpus_in_srat].node_id = node;
+ early_node_cpu_hwid[cpus_in_srat].cpu_hwid = mpidr;
+ node_set(node, numa_nodes_parsed);
+ cpus_in_srat++;
+ pr_info("SRAT: PXM %d -> MPIDR 0x%Lx -> Node %d\n",
+ pxm, mpidr, node);
+}
+
+int __init arm64_acpi_numa_init(void)
+{
+ int ret;
+
+ ret = acpi_numa_init();
+ if (ret)
+ return ret;
+
+ return srat_disabled() ? -EINVAL : 0;
+}
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index f8e5d47f0880..2f4ba774488a 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -60,6 +60,7 @@ int main(void)
DEFINE(S_PC, offsetof(struct pt_regs, pc));
DEFINE(S_ORIG_X0, offsetof(struct pt_regs, orig_x0));
DEFINE(S_SYSCALLNO, offsetof(struct pt_regs, syscallno));
+ DEFINE(S_ORIG_ADDR_LIMIT, offsetof(struct pt_regs, orig_addr_limit));
DEFINE(S_FRAME_SIZE, sizeof(struct pt_regs));
BLANK();
DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter));
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index d42789499f17..af716b65110d 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -98,6 +98,12 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
MIDR_RANGE(MIDR_THUNDERX, 0x00,
(1 << MIDR_VARIANT_SHIFT) | 1),
},
+ {
+ /* Cavium ThunderX, T81 pass 1.0 */
+ .desc = "Cavium erratum 27456",
+ .capability = ARM64_WORKAROUND_CAVIUM_27456,
+ MIDR_RANGE(MIDR_THUNDERX_81XX, 0x00, 0x00),
+ },
#endif
{
}
diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c
index e11857fce05f..75a0f8acef66 100644
--- a/arch/arm64/kernel/cpuidle.c
+++ b/arch/arm64/kernel/cpuidle.c
@@ -9,13 +9,16 @@
* published by the Free Software Foundation.
*/
+#include <linux/acpi.h>
+#include <linux/cpuidle.h>
+#include <linux/cpu_pm.h>
#include <linux/of.h>
#include <linux/of_device.h>
#include <asm/cpuidle.h>
#include <asm/cpu_ops.h>
-int __init arm_cpuidle_init(unsigned int cpu)
+int arm_cpuidle_init(unsigned int cpu)
{
int ret = -EOPNOTSUPP;
@@ -39,3 +42,18 @@ int arm_cpuidle_suspend(int index)
return cpu_ops[cpu]->cpu_suspend(index);
}
+
+#ifdef CONFIG_ACPI
+
+#include <acpi/processor.h>
+
+int acpi_processor_ffh_lpi_probe(unsigned int cpu)
+{
+ return arm_cpuidle_init(cpu);
+}
+
+int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi)
+{
+ return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, lpi->index);
+}
+#endif
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 12e8d2bcb3f9..6c3b7345a6c4 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -28,6 +28,7 @@
#include <asm/errno.h>
#include <asm/esr.h>
#include <asm/irq.h>
+#include <asm/memory.h>
#include <asm/thread_info.h>
#include <asm/unistd.h>
@@ -97,7 +98,14 @@
mov x29, xzr // fp pointed to user-space
.else
add x21, sp, #S_FRAME_SIZE
- .endif
+ get_thread_info tsk
+ /* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
+ ldr x20, [tsk, #TI_ADDR_LIMIT]
+ str x20, [sp, #S_ORIG_ADDR_LIMIT]
+ mov x20, #TASK_SIZE_64
+ str x20, [tsk, #TI_ADDR_LIMIT]
+ ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO)
+ .endif /* \el == 0 */
mrs x22, elr_el1
mrs x23, spsr_el1
stp lr, x21, [sp, #S_LR]
@@ -128,6 +136,14 @@
.endm
.macro kernel_exit, el
+ .if \el != 0
+ /* Restore the task's original addr_limit. */
+ ldr x20, [sp, #S_ORIG_ADDR_LIMIT]
+ str x20, [tsk, #TI_ADDR_LIMIT]
+
+ /* No need to restore UAO, it will be restored from SPSR_EL1 */
+ .endif
+
ldp x21, x22, [sp, #S_PC] // load ELR, SPSR
.if \el == 0
ct_user_enter
@@ -406,7 +422,6 @@ el1_irq:
bl trace_hardirqs_off
#endif
- get_thread_info tsk
irq_handler
#ifdef CONFIG_PREEMPT
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index f8df75d740f4..21ab5df9fa76 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -33,6 +33,7 @@
#include <asm/pgtable.h>
#include <asm/pgtable-hwdef.h>
#include <asm/sections.h>
+#include <asm/smp.h>
#include <asm/suspend.h>
#include <asm/virt.h>
@@ -236,6 +237,11 @@ int swsusp_arch_suspend(void)
unsigned long flags;
struct sleep_stack_data state;
+ if (cpus_are_stuck_in_kernel()) {
+ pr_err("Can't hibernate: no mechanism to offline secondary CPUs.\n");
+ return -EBUSY;
+ }
+
local_dbg_save(flags);
if (__cpu_suspend_enter(&state)) {
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
index b67531a13136..b5f063e5eff7 100644
--- a/arch/arm64/kernel/kgdb.c
+++ b/arch/arm64/kernel/kgdb.c
@@ -58,7 +58,17 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
{ "x30", 8, offsetof(struct pt_regs, regs[30])},
{ "sp", 8, offsetof(struct pt_regs, sp)},
{ "pc", 8, offsetof(struct pt_regs, pc)},
- { "pstate", 8, offsetof(struct pt_regs, pstate)},
+ /*
+ * struct pt_regs thinks PSTATE is 64-bits wide but gdb remote
+ * protocol disagrees. Therefore we must extract only the lower
+ * 32-bits. Look for the big comment in asm/kgdb.h for more
+ * detail.
+ */
+ { "pstate", 4, offsetof(struct pt_regs, pstate)
+#ifdef CONFIG_CPU_BIG_ENDIAN
+ + 4
+#endif
+ },
{ "v0", 16, -1 },
{ "v1", 16, -1 },
{ "v2", 16, -1 },
@@ -128,6 +138,8 @@ sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
memset((char *)gdb_regs, 0, NUMREGBYTES);
thread_regs = task_pt_regs(task);
memcpy((void *)gdb_regs, (void *)thread_regs->regs, GP_REG_BYTES);
+ /* Special case for PSTATE (check comments in asm/kgdb.h for details) */
+ dbg_get_reg(33, gdb_regs + GP_REG_BYTES, thread_regs);
}
void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 3279defabaa2..92f0e1e767cf 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -260,11 +260,13 @@ void __init setup_arch(char **cmdline_p)
efi_init();
arm64_memblock_init();
+ paging_init();
+
+ acpi_table_upgrade();
+
/* Parse the ACPI tables for possible boot-time configuration */
acpi_boot_table_init();
- paging_init();
-
if (acpi_disabled)
unflatten_device_tree();
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 678e0842cb3b..a68e0ccd9f4b 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -560,6 +560,8 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
*/
acpi_set_mailbox_entry(cpu_count, processor);
+ early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count, hwid));
+
cpu_count++;
}
@@ -909,3 +911,21 @@ int setup_profiling_timer(unsigned int multiplier)
{
return -EINVAL;
}
+
+static bool have_cpu_die(void)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+ int any_cpu = raw_smp_processor_id();
+
+ if (cpu_ops[any_cpu]->cpu_die)
+ return true;
+#endif
+ return false;
+}
+
+bool cpus_are_stuck_in_kernel(void)
+{
+ bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die());
+
+ return !!cpus_stuck_in_kernel || smp_spin_tables;
+}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index f7cf463107df..2a43012616b7 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -64,8 +64,7 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom,
/*
* We need to switch to kernel mode so that we can use __get_user
- * to safely read from kernel space. Note that we now dump the
- * code first, just in case the backtrace kills us.
+ * to safely read from kernel space.
*/
fs = get_fs();
set_fs(KERNEL_DS);
@@ -111,21 +110,12 @@ static void dump_backtrace_entry(unsigned long where)
print_ip_sym(where);
}
-static void dump_instr(const char *lvl, struct pt_regs *regs)
+static void __dump_instr(const char *lvl, struct pt_regs *regs)
{
unsigned long addr = instruction_pointer(regs);
- mm_segment_t fs;
char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str;
int i;
- /*
- * We need to switch to kernel mode so that we can use __get_user
- * to safely read from kernel space. Note that we now dump the
- * code first, just in case the backtrace kills us.
- */
- fs = get_fs();
- set_fs(KERNEL_DS);
-
for (i = -4; i < 1; i++) {
unsigned int val, bad;
@@ -139,8 +129,18 @@ static void dump_instr(const char *lvl, struct pt_regs *regs)
}
}
printk("%sCode: %s\n", lvl, str);
+}
- set_fs(fs);
+static void dump_instr(const char *lvl, struct pt_regs *regs)
+{
+ if (!user_mode(regs)) {
+ mm_segment_t fs = get_fs();
+ set_fs(KERNEL_DS);
+ __dump_instr(lvl, regs);
+ set_fs(fs);
+ } else {
+ __dump_instr(lvl, regs);
+ }
}
static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
diff --git a/arch/arm64/kvm/hyp/sysreg-sr.c b/arch/arm64/kvm/hyp/sysreg-sr.c
index 0f7c40eb3f53..934137647837 100644
--- a/arch/arm64/kvm/hyp/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/sysreg-sr.c
@@ -27,8 +27,8 @@ static void __hyp_text __sysreg_do_nothing(struct kvm_cpu_context *ctxt) { }
/*
* Non-VHE: Both host and guest must save everything.
*
- * VHE: Host must save tpidr*_el[01], actlr_el1, sp0, pc, pstate, and
- * guest must save everything.
+ * VHE: Host must save tpidr*_el[01], actlr_el1, mdscr_el1, sp0, pc,
+ * pstate, and guest must save everything.
*/
static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
@@ -37,6 +37,7 @@ static void __hyp_text __sysreg_save_common_state(struct kvm_cpu_context *ctxt)
ctxt->sys_regs[TPIDR_EL0] = read_sysreg(tpidr_el0);
ctxt->sys_regs[TPIDRRO_EL0] = read_sysreg(tpidrro_el0);
ctxt->sys_regs[TPIDR_EL1] = read_sysreg(tpidr_el1);
+ ctxt->sys_regs[MDSCR_EL1] = read_sysreg(mdscr_el1);
ctxt->gp_regs.regs.sp = read_sysreg(sp_el0);
ctxt->gp_regs.regs.pc = read_sysreg_el2(elr);
ctxt->gp_regs.regs.pstate = read_sysreg_el2(spsr);
@@ -61,7 +62,6 @@ static void __hyp_text __sysreg_save_state(struct kvm_cpu_context *ctxt)
ctxt->sys_regs[AMAIR_EL1] = read_sysreg_el1(amair);
ctxt->sys_regs[CNTKCTL_EL1] = read_sysreg_el1(cntkctl);
ctxt->sys_regs[PAR_EL1] = read_sysreg(par_el1);
- ctxt->sys_regs[MDSCR_EL1] = read_sysreg(mdscr_el1);
ctxt->gp_regs.sp_el1 = read_sysreg(sp_el1);
ctxt->gp_regs.elr_el1 = read_sysreg_el1(elr);
@@ -90,6 +90,7 @@ static void __hyp_text __sysreg_restore_common_state(struct kvm_cpu_context *ctx
write_sysreg(ctxt->sys_regs[TPIDR_EL0], tpidr_el0);
write_sysreg(ctxt->sys_regs[TPIDRRO_EL0], tpidrro_el0);
write_sysreg(ctxt->sys_regs[TPIDR_EL1], tpidr_el1);
+ write_sysreg(ctxt->sys_regs[MDSCR_EL1], mdscr_el1);
write_sysreg(ctxt->gp_regs.regs.sp, sp_el0);
write_sysreg_el2(ctxt->gp_regs.regs.pc, elr);
write_sysreg_el2(ctxt->gp_regs.regs.pstate, spsr);
@@ -114,7 +115,6 @@ static void __hyp_text __sysreg_restore_state(struct kvm_cpu_context *ctxt)
write_sysreg_el1(ctxt->sys_regs[AMAIR_EL1], amair);
write_sysreg_el1(ctxt->sys_regs[CNTKCTL_EL1], cntkctl);
write_sysreg(ctxt->sys_regs[PAR_EL1], par_el1);
- write_sysreg(ctxt->sys_regs[MDSCR_EL1], mdscr_el1);
write_sysreg(ctxt->gp_regs.sp_el1, sp_el1);
write_sysreg_el1(ctxt->gp_regs.elr_el1, elr);
diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index b7b397802088..efcf1f7ef1e4 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -179,7 +179,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
&asid_generation);
flush_context(cpu);
- /* We have at least 1 ASID per CPU, so this will always succeed */
+ /* We have more ASIDs than CPUs, so this will always succeed */
asid = find_next_zero_bit(asid_map, NUM_USER_ASIDS, 1);
set_asid:
@@ -227,8 +227,11 @@ switch_mm_fastpath:
static int asids_init(void)
{
asid_bits = get_cpu_asid_bits();
- /* If we end up with more CPUs than ASIDs, expect things to crash */
- WARN_ON(NUM_USER_ASIDS < num_possible_cpus());
+ /*
+ * Expect allocation after rollover to fail if we don't have at least
+ * one more ASID than CPUs. ASID #0 is reserved for init_mm.
+ */
+ WARN_ON(NUM_USER_ASIDS - 1 <= num_possible_cpus());
atomic64_set(&asid_generation, ASID_FIRST_VERSION);
asid_map = kzalloc(BITS_TO_LONGS(NUM_USER_ASIDS) * sizeof(*asid_map),
GFP_KERNEL);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 5954881a35ac..031820d989a8 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -109,7 +109,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
* PTE_RDONLY is cleared by default in the asm below, so set it in
* back if necessary (read-only or clean PTE).
*/
- if (!pte_write(entry) || !dirty)
+ if (!pte_write(entry) || !pte_sw_dirty(entry))
pte_val(entry) |= PTE_RDONLY;
/*
@@ -233,7 +233,7 @@ good_area:
goto out;
}
- return handle_mm_fault(mm, vma, addr & PAGE_MASK, mm_flags);
+ return handle_mm_fault(vma, addr & PAGE_MASK, mm_flags);
check_stack:
if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
@@ -280,7 +280,8 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
}
if (permission_fault(esr) && (addr < USER_DS)) {
- if (get_fs() == KERNEL_DS)
+ /* regs->orig_addr_limit may be 0 if we entered from EL0 */
+ if (regs->orig_addr_limit == KERNEL_DS)
die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
if (!search_exception_tables(regs->pc))
@@ -441,7 +442,7 @@ static int do_bad(unsigned long addr, unsigned int esr, struct pt_regs *regs)
return 1;
}
-static struct fault_info {
+static const struct fault_info {
int (*fn)(unsigned long addr, unsigned int esr, struct pt_regs *regs);
int sig;
int code;
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index dbd12ea8ce68..43a76b07eb32 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -71,10 +71,6 @@ void __sync_icache_dcache(pte_t pte, unsigned long addr)
{
struct page *page = pte_page(pte);
- /* no flushing needed for anonymous pages */
- if (!page_mapping(page))
- return;
-
if (!test_and_set_bit(PG_dcache_clean, &page->flags))
sync_icache_aliases(page_address(page),
PAGE_SIZE << compound_order(page));
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index 98dc1047f2a2..c7fe3ec70774 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -17,6 +17,7 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
+#include <linux/acpi.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/module.h>
@@ -29,7 +30,7 @@ static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE };
static int numa_distance_cnt;
static u8 *numa_distance;
-static int numa_off;
+static bool numa_off;
static __init int numa_parse_early_param(char *opt)
{
@@ -37,7 +38,7 @@ static __init int numa_parse_early_param(char *opt)
return -EINVAL;
if (!strncmp(opt, "off", 3)) {
pr_info("%s\n", "NUMA turned off");
- numa_off = 1;
+ numa_off = true;
}
return 0;
}
@@ -131,25 +132,25 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid)
* numa_add_memblk - Set node id to memblk
* @nid: NUMA node ID of the new memblk
* @start: Start address of the new memblk
- * @size: Size of the new memblk
+ * @end: End address of the new memblk
*
* RETURNS:
* 0 on success, -errno on failure.
*/
-int __init numa_add_memblk(int nid, u64 start, u64 size)
+int __init numa_add_memblk(int nid, u64 start, u64 end)
{
int ret;
- ret = memblock_set_node(start, size, &memblock.memory, nid);
+ ret = memblock_set_node(start, (end - start), &memblock.memory, nid);
if (ret < 0) {
pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n",
- start, (start + size - 1), nid);
+ start, (end - 1), nid);
return ret;
}
node_set(nid, numa_nodes_parsed);
pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n",
- start, (start + size - 1), nid);
+ start, (end - 1), nid);
return ret;
}
@@ -362,12 +363,15 @@ static int __init dummy_numa_init(void)
int ret;
struct memblock_region *mblk;
- pr_info("%s\n", "No NUMA configuration found");
+ if (numa_off)
+ pr_info("NUMA disabled\n"); /* Forced off on command line. */
+ else
+ pr_info("No NUMA configuration found\n");
pr_info("NUMA: Faking a node at [mem %#018Lx-%#018Lx]\n",
0LLU, PFN_PHYS(max_pfn) - 1);
for_each_memblock(memory, mblk) {
- ret = numa_add_memblk(0, mblk->base, mblk->size);
+ ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size);
if (!ret)
continue;
@@ -375,7 +379,7 @@ static int __init dummy_numa_init(void)
return ret;
}
- numa_off = 1;
+ numa_off = true;
return 0;
}
@@ -388,7 +392,9 @@ static int __init dummy_numa_init(void)
void __init arm64_numa_init(void)
{
if (!numa_off) {
- if (!numa_init(of_numa_init))
+ if (!acpi_disabled && !numa_init(arm64_acpi_numa_init))
+ return;
+ if (acpi_disabled && !numa_init(of_numa_init))
return;
}