135 files changed, 2098 insertions, 1471 deletions

diff --git a/Documentation/arm/memory.txt b/Documentation/arm/memory.txt
index 4bfb9ffbdbc1..38dc06d0a791 100644
--- a/Documentation/arm/memory.txt
+++ b/Documentation/arm/memory.txt
@@ -41,16 +41,9 @@ fffe8000	fffeffff	DTCM mapping area for platforms with
 fffe0000        fffe7fff        ITCM mapping area for platforms with
                                 ITCM mounted inside the CPU.
 
-fff00000        fffdffff        Fixmap mapping region.  Addresses provided
+ffc00000        ffdfffff        Fixmap mapping region.  Addresses provided
                                 by fix_to_virt() will be located here.
 
-ffc00000        ffefffff        DMA memory mapping region.  Memory returned
-                                by the dma_alloc_xxx functions will be
-                                dynamically mapped here.
-
-ff000000        ffbfffff        Reserved for future expansion of DMA
-                                mapping region.
-
 fee00000        feffffff        Mapping of PCI I/O space. This is a static
                                 mapping within the vmalloc space.
 
diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt
index fe5cef8976cb..75ef91d08f3b 100644
--- a/Documentation/devicetree/bindings/arm/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/pmu.txt
@@ -8,6 +8,7 @@ Required properties:
 
 - compatible : should be one of
         "arm,armv8-pmuv3"
+        "arm,cortex-a17-pmu"
         "arm,cortex-a15-pmu"
         "arm,cortex-a12-pmu"
         "arm,cortex-a9-pmu"
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index db3c5414223e..8615dfa604c4 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -165,12 +165,9 @@ config TRACE_IRQFLAGS_SUPPORT
         bool
         default y
 
-config RWSEM_GENERIC_SPINLOCK
-        bool
-        default y
-
 config RWSEM_XCHGADD_ALGORITHM
         bool
+        default y
 
 config ARCH_HAS_ILOG2_U32
         bool
@@ -1105,11 +1102,6 @@ source "arch/arm/firmware/Kconfig"
 
 source arch/arm/mm/Kconfig
 
-config ARM_NR_BANKS
-        int
-        default 16 if ARCH_EP93XX
-        default 8
-
 config IWMMXT
         bool "Enable iWMMXt support"
         depends on CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_PJ4 || CPU_PJ4B
@@ -1230,19 +1222,6 @@ config ARM_ERRATA_742231
           register of the Cortex-A9 which reduces the linefill issuing
           capabilities of the processor.
 
-config PL310_ERRATA_588369
-        bool "PL310 errata: Clean & Invalidate maintenance operations do not invalidate clean lines"
-        depends on CACHE_L2X0
-        help
-           The PL310 L2 cache controller implements three types of Clean &
-           Invalidate maintenance operations: by Physical Address
-           (offset 0x7F0), by Index/Way (0x7F8) and by Way (0x7FC).
-           They are architecturally defined to behave as the execution of a
-           clean operation followed immediately by an invalidate operation,
-           both performing to the same memory location. This functionality
-           is not correctly implemented in PL310 as clean lines are not
-           invalidated as a result of these operations.
-
 config ARM_ERRATA_643719
         bool "ARM errata: LoUIS bit field in CLIDR register is incorrect"
         depends on CPU_V7 && SMP
@@ -1265,17 +1244,6 @@ config ARM_ERRATA_720789
           tables. The workaround changes the TLB flushing routines to invalidate
           entries regardless of the ASID.
 
-config PL310_ERRATA_727915
-        bool "PL310 errata: Background Clean & Invalidate by Way operation can cause data corruption"
-        depends on CACHE_L2X0
-        help
-          PL310 implements the Clean & Invalidate by Way L2 cache maintenance
-          operation (offset 0x7FC). This operation runs in background so that
-          PL310 can handle normal accesses while it is in progress. Under very
-          rare circumstances, due to this erratum, write data can be lost when
-          PL310 treats a cacheable write transaction during a Clean &
-          Invalidate by Way operation.
-
 config ARM_ERRATA_743622
         bool "ARM errata: Faulty hazard checking in the Store Buffer may lead to data corruption"
         depends on CPU_V7
@@ -1301,21 +1269,6 @@ config ARM_ERRATA_751472
           operation is received by a CPU before the ICIALLUIS has completed,
           potentially leading to corrupted entries in the cache or TLB.
 
-config PL310_ERRATA_753970
-        bool "PL310 errata: cache sync operation may be faulty"
-        depends on CACHE_PL310
-        help
-          This option enables the workaround for the 753970 PL310 (r3p0) erratum.
-
-          Under some condition the effect of cache sync operation on
-          the store buffer still remains when the operation completes.
-          This means that the store buffer is always asked to drain and
-          this prevents it from merging any further writes. The workaround
-          is to replace the normal offset of cache sync operation (0x730)
-          by another offset targeting an unmapped PL310 register 0x740.
-          This has the same effect as the cache sync operation: store buffer
-          drain and waiting for all buffers empty.
-
 config ARM_ERRATA_754322
         bool "ARM errata: possible faulty MMU translations following an ASID switch"
         depends on CPU_V7
@@ -1364,18 +1317,6 @@ config ARM_ERRATA_764369
           relevant cache maintenance functions and sets a specific bit
           in the diagnostic control register of the SCU.
 
-config PL310_ERRATA_769419
-        bool "PL310 errata: no automatic Store Buffer drain"
-        depends on CACHE_L2X0
-        help
-          On revisions of the PL310 prior to r3p2, the Store Buffer does
-          not automatically drain. This can cause normal, non-cacheable
-          writes to be retained when the memory system is idle, leading
-          to suboptimal I/O performance for drivers using coherent DMA.
-          This option adds a write barrier to the cpu_idle loop so that,
-          on systems with an outer cache, the store buffer is drained
-          explicitly.
-
 config ARM_ERRATA_775420
        bool "ARM errata: A data cache maintenance operation which aborts, might lead to deadlock"
        depends on CPU_V7
@@ -2295,6 +2236,11 @@ config ARCH_SUSPEND_POSSIBLE
 config ARM_CPU_SUSPEND
         def_bool PM_SLEEP
 
+config ARCH_HIBERNATION_POSSIBLE
+        bool
+        depends on MMU
+        default y if ARCH_SUSPEND_POSSIBLE
+
 endmenu
 
 source "net/Kconfig"
diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c
index d1153c8a765a..9448aa0c6686 100644
--- a/arch/arm/boot/compressed/atags_to_fdt.c
+++ b/arch/arm/boot/compressed/atags_to_fdt.c
@@ -7,6 +7,8 @@
 #define do_extend_cmdline 0
 #endif
 
+#define NR_BANKS 16
+
 static int node_offset(void *fdt, const char *node_path)
 {
         int offset = fdt_path_offset(fdt, node_path);
diff --git a/arch/arm/boot/dts/marco.dtsi b/arch/arm/boot/dts/marco.dtsi
index 0c9647d28765..fb354225740a 100644
--- a/arch/arm/boot/dts/marco.dtsi
+++ b/arch/arm/boot/dts/marco.dtsi
@@ -36,7 +36,7 @@
                 ranges = <0x40000000 0x40000000 0xa0000000>;
 
                 l2-cache-controller@c0030000 {
-                        compatible = "sirf,marco-pl310-cache", "arm,pl310-cache";
+                        compatible = "arm,pl310-cache";
                         reg = <0xc0030000 0x1000>;
                         interrupts = <0 59 0>;
                         arm,tag-latency = <1 1 1>;
diff --git a/arch/arm/boot/dts/prima2.dtsi b/arch/arm/boot/dts/prima2.dtsi
index 1e82571d6823..0d6588d549bf 100644
--- a/arch/arm/boot/dts/prima2.dtsi
+++ b/arch/arm/boot/dts/prima2.dtsi
@@ -48,7 +48,7 @@
                 ranges = <0x40000000 0x40000000 0x80000000>;
 
                 l2-cache-controller@80040000 {
-                        compatible = "arm,pl310-cache", "sirf,prima2-pl310-cache";
+                        compatible = "arm,pl310-cache";
                         reg = <0x80040000 0x1000>;
                         interrupts = <59>;
                         arm,tag-latency = <1 1 1>;
diff --git a/arch/arm/common/bL_switcher.c b/arch/arm/common/bL_switcher.c
index f01c0ee0c87e..490f3dced749 100644
--- a/arch/arm/common/bL_switcher.c
+++ b/arch/arm/common/bL_switcher.c
@@ -433,8 +433,12 @@ static void bL_switcher_restore_cpus(void)
 {
         int i;
 
-        for_each_cpu(i, &bL_switcher_removed_logical_cpus)
-                cpu_up(i);
+        for_each_cpu(i, &bL_switcher_removed_logical_cpus) {
+                struct device *cpu_dev = get_cpu_device(i);
+                int ret = device_online(cpu_dev);
+                if (ret)
+                        dev_err(cpu_dev, "switcher: unable to restore CPU\n");
+        }
 }
 
 static int bL_switcher_halve_cpus(void)
@@ -521,7 +525,7 @@ static int bL_switcher_halve_cpus(void)
                         continue;
                 }
 
-                ret = cpu_down(i);
+                ret = device_offline(get_cpu_device(i));
                 if (ret) {
                         bL_switcher_restore_cpus();
                         return ret;
diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c
index 86fd60fefbc9..f91136ab447e 100644
--- a/arch/arm/common/mcpm_entry.c
+++ b/arch/arm/common/mcpm_entry.c
@@ -106,14 +106,14 @@ void mcpm_cpu_power_down(void)
         BUG();
 }
 
-int mcpm_cpu_power_down_finish(unsigned int cpu, unsigned int cluster)
+int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster)
 {
         int ret;
 
-        if (WARN_ON_ONCE(!platform_ops || !platform_ops->power_down_finish))
+        if (WARN_ON_ONCE(!platform_ops || !platform_ops->wait_for_powerdown))
                 return -EUNATCH;
 
-        ret = platform_ops->power_down_finish(cpu, cluster);
+        ret = platform_ops->wait_for_powerdown(cpu, cluster);
         if (ret)
                 pr_warn("%s: cpu %u, cluster %u failed to power down (%d)\n",
                         __func__, cpu, cluster, ret);
diff --git a/arch/arm/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c
index 177251a4dd9a..92e54d7c6f46 100644
--- a/arch/arm/common/mcpm_platsmp.c
+++ b/arch/arm/common/mcpm_platsmp.c
@@ -62,7 +62,7 @@ static int mcpm_cpu_kill(unsigned int cpu)
 
         cpu_to_pcpu(cpu, &pcpu, &pcluster);
 
-        return !mcpm_cpu_power_down_finish(pcpu, pcluster);
+        return !mcpm_wait_for_cpu_powerdown(pcpu, pcluster);
 }
 
 static int mcpm_cpu_disable(unsigned int cpu)
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 23e728ecf8ab..f5a357601983 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -21,6 +21,7 @@ generic-y += parport.h
 generic-y += poll.h
 generic-y += preempt.h
 generic-y += resource.h
+generic-y += rwsem.h
 generic-y += sections.h
 generic-y += segment.h
 generic-y += sembuf.h
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index b974184f9941..57f0584e8d97 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -312,7 +312,7 @@
  * you cannot return to the original mode.
  */
 .macro safe_svcmode_maskall reg:req
-#if __LINUX_ARM_ARCH__ >= 6
+#if __LINUX_ARM_ARCH__ >= 6 && !defined(CONFIG_CPU_V7M)
         mrs     \reg , cpsr
         eor     \reg, \reg, #HYP_MODE
         tst     \reg, #MODE_MASK
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 8b8b61685a34..fd43f7f55b70 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -212,7 +212,7 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *,
 static inline void __flush_icache_all(void)
 {
         __flush_icache_preferred();
-        dsb();
+        dsb(ishst);
 }
 
 /*
@@ -487,4 +487,6 @@ int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_x(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
 
+void flush_uprobe_xol_access(struct page *page, unsigned long uaddr,
+                             void *kaddr, unsigned long len);
 #endif
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 4764344367d4..8c2b7321a478 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -72,6 +72,7 @@
 #define ARM_CPU_PART_CORTEX_A15         0xC0F0
 #define ARM_CPU_PART_CORTEX_A7          0xC070
 #define ARM_CPU_PART_CORTEX_A12         0xC0D0
+#define ARM_CPU_PART_CORTEX_A17         0xC0E0
 
 #define ARM_CPU_XSCALE_ARCH_MASK        0xe000
 #define ARM_CPU_XSCALE_ARCH_V1          0x2000
diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
index bbae919bceb4..74124b0d0d79 100644
--- a/arch/arm/include/asm/fixmap.h
+++ b/arch/arm/include/asm/fixmap.h
@@ -1,24 +1,11 @@
 #ifndef _ASM_FIXMAP_H
 #define _ASM_FIXMAP_H
 
-/*
- * Nothing too fancy for now.
- *
- * On ARM we already have well known fixed virtual addresses imposed by
- * the architecture such as the vector page which is located at 0xffff0000,
- * therefore a second level page table is already allocated covering
- * 0xfff00000 upwards.
- *
- * The cache flushing code in proc-xscale.S uses the virtual area between
- * 0xfffe0000 and 0xfffeffff.
- */
-
-#define FIXADDR_START           0xfff00000UL
-#define FIXADDR_TOP             0xfffe0000UL
+#define FIXADDR_START           0xffc00000UL
+#define FIXADDR_TOP             0xffe00000UL
 #define FIXADDR_SIZE            (FIXADDR_TOP - FIXADDR_START)
 
-#define FIX_KMAP_BEGIN          0
-#define FIX_KMAP_END            (FIXADDR_SIZE >> PAGE_SHIFT)
+#define FIX_KMAP_NR_PTES        (FIXADDR_SIZE >> PAGE_SHIFT)
 
 #define __fix_to_virt(x)        (FIXADDR_START + ((x) << PAGE_SHIFT))
 #define __virt_to_fix(x)        (((x) - FIXADDR_START) >> PAGE_SHIFT)
@@ -27,7 +14,7 @@ extern void __this_fixmap_does_not_exist(void);
 
 static inline unsigned long fix_to_virt(const unsigned int idx)
 {
-        if (idx >= FIX_KMAP_END)
+        if (idx >= FIX_KMAP_NR_PTES)
                 __this_fixmap_does_not_exist();
         return __fix_to_virt(idx);
 }
diff --git a/arch/arm/include/asm/glue-df.h b/arch/arm/include/asm/glue-df.h
index 6b70f1b46a6e..04e18b656659 100644
--- a/arch/arm/include/asm/glue-df.h
+++ b/arch/arm/include/asm/glue-df.h
@@ -31,14 +31,6 @@
 #undef CPU_DABORT_HANDLER
 #undef MULTI_DABORT
 
-#if defined(CONFIG_CPU_ARM710)
-# ifdef CPU_DABORT_HANDLER
-#  define MULTI_DABORT 1
-# else
-#  define CPU_DABORT_HANDLER cpu_arm7_data_abort
-# endif
-#endif
-
 #ifdef CONFIG_CPU_ABRT_EV4
 # ifdef CPU_DABORT_HANDLER
 #  define MULTI_DABORT 1
diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h
index 6795ff743b3d..3a5ec1c25659 100644
--- a/arch/arm/include/asm/hardware/cache-l2x0.h
+++ b/arch/arm/include/asm/hardware/cache-l2x0.h
@@ -26,8 +26,8 @@
 #define L2X0_CACHE_TYPE                 0x004
 #define L2X0_CTRL                       0x100
 #define L2X0_AUX_CTRL                   0x104
-#define L2X0_TAG_LATENCY_CTRL           0x108
-#define L2X0_DATA_LATENCY_CTRL          0x10C
+#define L310_TAG_LATENCY_CTRL           0x108
+#define L310_DATA_LATENCY_CTRL          0x10C
 #define L2X0_EVENT_CNT_CTRL             0x200
 #define L2X0_EVENT_CNT1_CFG             0x204
 #define L2X0_EVENT_CNT0_CFG             0x208
@@ -54,53 +54,93 @@
 #define L2X0_LOCKDOWN_WAY_D_BASE        0x900
 #define L2X0_LOCKDOWN_WAY_I_BASE        0x904
 #define L2X0_LOCKDOWN_STRIDE            0x08
-#define L2X0_ADDR_FILTER_START          0xC00
-#define L2X0_ADDR_FILTER_END            0xC04
+#define L310_ADDR_FILTER_START          0xC00
+#define L310_ADDR_FILTER_END            0xC04
 #define L2X0_TEST_OPERATION             0xF00
 #define L2X0_LINE_DATA                  0xF10
 #define L2X0_LINE_TAG                   0xF30
 #define L2X0_DEBUG_CTRL                 0xF40
-#define L2X0_PREFETCH_CTRL              0xF60
-#define L2X0_POWER_CTRL                 0xF80
-#define   L2X0_DYNAMIC_CLK_GATING_EN    (1 << 1)
-#define   L2X0_STNDBY_MODE_EN           (1 << 0)
+#define L310_PREFETCH_CTRL              0xF60
+#define L310_POWER_CTRL                 0xF80
+#define   L310_DYNAMIC_CLK_GATING_EN    (1 << 1)
+#define   L310_STNDBY_MODE_EN           (1 << 0)
 
 /* Registers shifts and masks */
 #define L2X0_CACHE_ID_PART_MASK         (0xf << 6)
 #define L2X0_CACHE_ID_PART_L210         (1 << 6)
+#define L2X0_CACHE_ID_PART_L220         (2 << 6)
 #define L2X0_CACHE_ID_PART_L310         (3 << 6)
 #define L2X0_CACHE_ID_RTL_MASK          0x3f
-#define L2X0_CACHE_ID_RTL_R0P0          0x0
-#define L2X0_CACHE_ID_RTL_R1P0          0x2
-#define L2X0_CACHE_ID_RTL_R2P0          0x4
-#define L2X0_CACHE_ID_RTL_R3P0          0x5
-#define L2X0_CACHE_ID_RTL_R3P1          0x6
-#define L2X0_CACHE_ID_RTL_R3P2          0x8
+#define L210_CACHE_ID_RTL_R0P2_02       0x00
+#define L210_CACHE_ID_RTL_R0P1          0x01
+#define L210_CACHE_ID_RTL_R0P2_01       0x02
+#define L210_CACHE_ID_RTL_R0P3          0x03
+#define L210_CACHE_ID_RTL_R0P4          0x0b
+#define L210_CACHE_ID_RTL_R0P5          0x0f
+#define L220_CACHE_ID_RTL_R1P7_01REL0   0x06
+#define L310_CACHE_ID_RTL_R0P0          0x00
+#define L310_CACHE_ID_RTL_R1P0          0x02
+#define L310_CACHE_ID_RTL_R2P0          0x04
+#define L310_CACHE_ID_RTL_R3P0          0x05
+#define L310_CACHE_ID_RTL_R3P1          0x06
+#define L310_CACHE_ID_RTL_R3P1_50REL0   0x07
+#define L310_CACHE_ID_RTL_R3P2          0x08
+#define L310_CACHE_ID_RTL_R3P3          0x09
 
-#define L2X0_AUX_CTRL_MASK                      0xc0000fff
+/* L2C auxiliary control register - bits common to L2C-210/220/310 */
+#define L2C_AUX_CTRL_WAY_SIZE_SHIFT             17
+#define L2C_AUX_CTRL_WAY_SIZE_MASK              (7 << 17)
+#define L2C_AUX_CTRL_WAY_SIZE(n)                ((n) << 17)
+#define L2C_AUX_CTRL_EVTMON_ENABLE              BIT(20)
+#define L2C_AUX_CTRL_PARITY_ENABLE              BIT(21)
+#define L2C_AUX_CTRL_SHARED_OVERRIDE            BIT(22)
+/* L2C-210/220 common bits */
 #define L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT     0
-#define L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK      0x7
+#define L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK      (7 << 0)
 #define L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT     3
-#define L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK      (0x7 << 3)
+#define L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK      (7 << 3)
 #define L2X0_AUX_CTRL_TAG_LATENCY_SHIFT         6
-#define L2X0_AUX_CTRL_TAG_LATENCY_MASK          (0x7 << 6)
+#define L2X0_AUX_CTRL_TAG_LATENCY_MASK          (7 << 6)
 #define L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT       9
-#define L2X0_AUX_CTRL_DIRTY_LATENCY_MASK        (0x7 << 9)
-#define L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT       16
-#define L2X0_AUX_CTRL_WAY_SIZE_SHIFT            17
-#define L2X0_AUX_CTRL_WAY_SIZE_MASK             (0x7 << 17)
-#define L2X0_AUX_CTRL_SHARE_OVERRIDE_SHIFT      22
-#define L2X0_AUX_CTRL_NS_LOCKDOWN_SHIFT         26
-#define L2X0_AUX_CTRL_NS_INT_CTRL_SHIFT         27
-#define L2X0_AUX_CTRL_DATA_PREFETCH_SHIFT       28
-#define L2X0_AUX_CTRL_INSTR_PREFETCH_SHIFT      29
-#define L2X0_AUX_CTRL_EARLY_BRESP_SHIFT         30
+#define L2X0_AUX_CTRL_DIRTY_LATENCY_MASK        (7 << 9)
+#define L2X0_AUX_CTRL_ASSOC_SHIFT               13
+#define L2X0_AUX_CTRL_ASSOC_MASK                (15 << 13)
+/* L2C-210 specific bits */
+#define L210_AUX_CTRL_WRAP_DISABLE              BIT(12)
+#define L210_AUX_CTRL_WA_OVERRIDE               BIT(23)
+#define L210_AUX_CTRL_EXCLUSIVE_ABORT           BIT(24)
+/* L2C-220 specific bits */
+#define L220_AUX_CTRL_EXCLUSIVE_CACHE           BIT(12)
+#define L220_AUX_CTRL_FWA_SHIFT                 23
+#define L220_AUX_CTRL_FWA_MASK                  (3 << 23)
+#define L220_AUX_CTRL_NS_LOCKDOWN               BIT(26)
+#define L220_AUX_CTRL_NS_INT_CTRL               BIT(27)
+/* L2C-310 specific bits */
+#define L310_AUX_CTRL_FULL_LINE_ZERO            BIT(0)  /* R2P0+ */
+#define L310_AUX_CTRL_HIGHPRIO_SO_DEV           BIT(10) /* R2P0+ */
+#define L310_AUX_CTRL_STORE_LIMITATION          BIT(11) /* R2P0+ */
+#define L310_AUX_CTRL_EXCLUSIVE_CACHE           BIT(12)
+#define L310_AUX_CTRL_ASSOCIATIVITY_16          BIT(16)
+#define L310_AUX_CTRL_CACHE_REPLACE_RR          BIT(25) /* R2P0+ */
+#define L310_AUX_CTRL_NS_LOCKDOWN               BIT(26)
+#define L310_AUX_CTRL_NS_INT_CTRL               BIT(27)
+#define L310_AUX_CTRL_DATA_PREFETCH             BIT(28)
+#define L310_AUX_CTRL_INSTR_PREFETCH            BIT(29)
+#define L310_AUX_CTRL_EARLY_BRESP               BIT(30) /* R2P0+ */
 
-#define L2X0_LATENCY_CTRL_SETUP_SHIFT   0
-#define L2X0_LATENCY_CTRL_RD_SHIFT      4
-#define L2X0_LATENCY_CTRL_WR_SHIFT      8
+#define L310_LATENCY_CTRL_SETUP(n)              ((n) << 0)
+#define L310_LATENCY_CTRL_RD(n)                 ((n) << 4)
+#define L310_LATENCY_CTRL_WR(n)                 ((n) << 8)
 
-#define L2X0_ADDR_FILTER_EN             1
+#define L310_ADDR_FILTER_EN             1
+
+#define L310_PREFETCH_CTRL_OFFSET_MASK          0x1f
+#define L310_PREFETCH_CTRL_DBL_LINEFILL_INCR    BIT(23)
+#define L310_PREFETCH_CTRL_PREFETCH_DROP        BIT(24)
+#define L310_PREFETCH_CTRL_DBL_LINEFILL_WRAP    BIT(27)
+#define L310_PREFETCH_CTRL_DATA_PREFETCH        BIT(28)
+#define L310_PREFETCH_CTRL_INSTR_PREFETCH       BIT(29)
+#define L310_PREFETCH_CTRL_DBL_LINEFILL         BIT(30)
 
 #define L2X0_CTRL_EN                    1
 
diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h
index 91b99abe7a95..535579511ed0 100644
--- a/arch/arm/include/asm/highmem.h
+++ b/arch/arm/include/asm/highmem.h
@@ -18,6 +18,7 @@
         } while (0)
 
 extern pte_t *pkmap_page_table;
+extern pte_t *fixmap_page_table;
 
 extern void *kmap_high(struct page *page);
 extern void kunmap_high(struct page *page);
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 8aa4cca74501..3d23418cbddd 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -179,6 +179,12 @@ static inline void __iomem *__typesafe_io(unsigned long addr)
 /* PCI fixed i/o mapping */
 #define PCI_IO_VIRT_BASE        0xfee00000
 
+#if defined(CONFIG_PCI)
+void pci_ioremap_set_mem_type(int mem_type);
+#else
+static inline void pci_ioremap_set_mem_type(int mem_type) {}
+#endif
+
 extern int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr);
 
 /*
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 17a3fa2979e8..060a75e99263 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -14,7 +14,6 @@
 #include <linux/reboot.h>
 
 struct tag;
-struct meminfo;
 struct pt_regs;
 struct smp_operations;
 #ifdef CONFIG_SMP
@@ -45,10 +44,12 @@ struct machine_desc {
         unsigned char           reserve_lp1 :1; /* never has lp1        */
         unsigned char           reserve_lp2 :1; /* never has lp2        */
         enum reboot_mode        reboot_mode;    /* default restart mode */
+        unsigned                l2c_aux_val;    /* L2 cache aux value   */
+        unsigned                l2c_aux_mask;   /* L2 cache aux mask    */
+        void                    (*l2c_write_sec)(unsigned long, unsigned);
         struct smp_operations   *smp;           /* SMP operations       */
         bool                    (*smp_init)(void);
-        void                    (*fixup)(struct tag *, char **,
-                                         struct meminfo *);
+        void                    (*fixup)(struct tag *, char **);
         void                    (*init_meminfo)(void);
         void                    (*reserve)(void);/* reserve mem blocks  */
         void                    (*map_io)(void);/* IO mapping function  */
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index a5ff410dcdb6..d9702eb0b02b 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -98,14 +98,14 @@ int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster);
  * previously in which case the caller should take appropriate action.
  *
  * On success, the CPU is not guaranteed to be truly halted until
- * mcpm_cpu_power_down_finish() subsequently returns non-zero for the
+ * mcpm_wait_for_cpu_powerdown() subsequently returns non-zero for the
  * specified cpu.  Until then, other CPUs should make sure they do not
  * trash memory the target CPU might be executing/accessing.
  */
 void mcpm_cpu_power_down(void);
 
 /**
- * mcpm_cpu_power_down_finish - wait for a specified CPU to halt, and
+ * mcpm_wait_for_cpu_powerdown - wait for a specified CPU to halt, and
  *      make sure it is powered off
  *
  * @cpu: CPU number within given cluster
@@ -127,7 +127,7 @@ void mcpm_cpu_power_down(void);
  *      - zero if the CPU is in a safely parked state
  *      - nonzero otherwise (e.g., timeout)
  */
-int mcpm_cpu_power_down_finish(unsigned int cpu, unsigned int cluster);
+int mcpm_wait_for_cpu_powerdown(unsigned int cpu, unsigned int cluster);
 
 /**
  * mcpm_cpu_suspend - bring the calling CPU in a suspended state
@@ -171,7 +171,7 @@ int mcpm_cpu_powered_up(void);
 struct mcpm_platform_ops {
         int (*power_up)(unsigned int cpu, unsigned int cluster);
         void (*power_down)(void);
-        int (*power_down_finish)(unsigned int cpu, unsigned int cluster);
+        int (*wait_for_powerdown)(unsigned int cpu, unsigned int cluster);
         void (*suspend)(u64);
         void (*powered_up)(void);
 };
diff --git a/arch/arm/include/asm/memblock.h b/arch/arm/include/asm/memblock.h
index c2f5102ae659..bf47a6c110a2 100644
--- a/arch/arm/include/asm/memblock.h
+++ b/arch/arm/include/asm/memblock.h
@@ -1,10 +1,9 @@
 #ifndef _ASM_ARM_MEMBLOCK_H
 #define _ASM_ARM_MEMBLOCK_H
 
-struct meminfo;
 struct machine_desc;
 
-void arm_memblock_init(struct meminfo *, const struct machine_desc *);
+void arm_memblock_init(const struct machine_desc *);
 phys_addr_t arm_memblock_steal(phys_addr_t size, phys_addr_t align);
 
 #endif
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 02fa2558f662..2b751464d6ff 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -83,8 +83,6 @@
  */
 #define IOREMAP_MAX_ORDER       24
 
-#define CONSISTENT_END          (0xffe00000UL)
-
 #else /* CONFIG_MMU */
 
 /*
diff --git a/arch/arm/include/asm/outercache.h b/arch/arm/include/asm/outercache.h
index f94784f0e3a6..891a56b35bcf 100644
--- a/arch/arm/include/asm/outercache.h
+++ b/arch/arm/include/asm/outercache.h
@@ -28,53 +28,84 @@ struct outer_cache_fns {
         void (*clean_range)(unsigned long, unsigned long);
         void (*flush_range)(unsigned long, unsigned long);
         void (*flush_all)(void);
-        void (*inv_all)(void);
         void (*disable)(void);
 #ifdef CONFIG_OUTER_CACHE_SYNC
         void (*sync)(void);
 #endif
-        void (*set_debug)(unsigned long);
         void (*resume)(void);
+
+        /* This is an ARM L2C thing */
+        void (*write_sec)(unsigned long, unsigned);
 };
 
 extern struct outer_cache_fns outer_cache;
 
 #ifdef CONFIG_OUTER_CACHE
-
+/**
+ * outer_inv_range - invalidate range of outer cache lines
+ * @start: starting physical address, inclusive
+ * @end: end physical address, exclusive
+ */
 static inline void outer_inv_range(phys_addr_t start, phys_addr_t end)
 {
         if (outer_cache.inv_range)
                 outer_cache.inv_range(start, end);
 }
+
+/**
+ * outer_clean_range - clean dirty outer cache lines
+ * @start: starting physical address, inclusive
+ * @end: end physical address, exclusive
+ */
 static inline void outer_clean_range(phys_addr_t start, phys_addr_t end)
 {
         if (outer_cache.clean_range)
                 outer_cache.clean_range(start, end);
 }
+
+/**
+ * outer_flush_range - clean and invalidate outer cache lines
+ * @start: starting physical address, inclusive
+ * @end: end physical address, exclusive
+ */
 static inline void outer_flush_range(phys_addr_t start, phys_addr_t end)
 {
         if (outer_cache.flush_range)
                 outer_cache.flush_range(start, end);
 }
 
+/**
+ * outer_flush_all - clean and invalidate all cache lines in the outer cache
+ *
+ * Note: depending on implementation, this may not be atomic - it must
+ * only be called with interrupts disabled and no other active outer
+ * cache masters.
+ *
+ * It is intended that this function is only used by implementations
+ * needing to override the outer_cache.disable() method due to security.
+ * (Some implementations perform this as a clean followed by an invalidate.)
+ */
 static inline void outer_flush_all(void)
 {
         if (outer_cache.flush_all)
                 outer_cache.flush_all();
 }
 
-static inline void outer_inv_all(void)
-{
-        if (outer_cache.inv_all)
-                outer_cache.inv_all();
-}
-
-static inline void outer_disable(void)
-{
-        if (outer_cache.disable)
-                outer_cache.disable();
-}
+/**
+ * outer_disable - clean, invalidate and disable the outer cache
+ *
+ * Disable the outer cache, ensuring that any data contained in the outer
+ * cache is pushed out to lower levels of system memory.  The note and
+ * conditions above concerning outer_flush_all() applies here.
+ */
+extern void outer_disable(void);
 
+/**
+ * outer_resume - restore the cache configuration and re-enable outer cache
+ *
+ * Restore any configuration that the cache had when previously enabled,
+ * and re-enable the outer cache.
+ */
 static inline void outer_resume(void)
 {
         if (outer_cache.resume)
@@ -90,13 +121,18 @@ static inline void outer_clean_range(phys_addr_t start, phys_addr_t end)
 static inline void outer_flush_range(phys_addr_t start, phys_addr_t end)
 { }
 static inline void outer_flush_all(void) { }
-static inline void outer_inv_all(void) { }
 static inline void outer_disable(void) { }
 static inline void outer_resume(void) { }
 
 #endif
 
 #ifdef CONFIG_OUTER_CACHE_SYNC
+/**
+ * outer_sync - perform a sync point for outer cache
+ *
+ * Ensure that all outer cache operations are complete and any store
+ * buffers are drained.
+ */
 static inline void outer_sync(void)
 {
         if (outer_cache.sync)
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index 8d6a089dfb76..e0adb9f1bf94 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -21,34 +21,6 @@
 #define __tagtable(tag, fn) \
 static const struct tagtable __tagtable_##fn __tag = { tag, fn }
 
-/*
- * Memory map description
- */
-#define NR_BANKS        CONFIG_ARM_NR_BANKS
-
-struct membank {
-        phys_addr_t start;
-        phys_addr_t size;
-        unsigned int highmem;
-};
-
-struct meminfo {
-        int nr_banks;
-        struct membank bank[NR_BANKS];
-};
-
-extern struct meminfo meminfo;
-
-#define for_each_bank(iter,mi)                          \
-        for (iter = 0; iter < (mi)->nr_banks; iter++)
-
-#define bank_pfn_start(bank)    __phys_to_pfn((bank)->start)
-#define bank_pfn_end(bank)      __phys_to_pfn((bank)->start + (bank)->size)
-#define bank_pfn_size(bank)     ((bank)->size >> PAGE_SHIFT)
-#define bank_phys_start(bank)   (bank)->start
-#define bank_phys_end(bank)     ((bank)->start + (bank)->size)
-#define bank_phys_size(bank)    (bank)->size
-
 extern int arm_add_memory(u64 start, u64 size);
 extern void early_print(const char *str, ...);
 extern void dump_machine_table(void);
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 12c3a5decc60..75d95799b6e6 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -171,8 +171,9 @@ extern int __put_user_8(void *, unsigned long long);
 #define __put_user_check(x,p)                                                   \
         ({                                                              \
                 unsigned long __limit = current_thread_info()->addr_limit - 1; \
+                const typeof(*(p)) __user *__tmp_p = (p);               \
                 register const typeof(*(p)) __r2 asm("r2") = (x);       \
-                register const typeof(*(p)) __user *__p asm("r0") = (p);\
+                register const typeof(*(p)) __user *__p asm("r0") = __tmp_p; \
                 register unsigned long __l asm("r1") = __limit;         \
                 register int __e asm("r0");                             \
                 switch (sizeof(*(__p))) {                               \
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 040619c32d68..38ddd9f83d0e 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_ARTHUR)		+= arthur.o
 obj-$(CONFIG_ISA_DMA)           += dma-isa.o
 obj-$(CONFIG_PCI)               += bios32.o isa.o
 obj-$(CONFIG_ARM_CPU_SUSPEND)   += sleep.o suspend.o
+obj-$(CONFIG_HIBERNATION)       += hibernate.o
 obj-$(CONFIG_SMP)               += smp.o
 ifdef CONFIG_MMU
 obj-$(CONFIG_SMP)               += smp_tlb.o
diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c
index 8c14de8180c0..7807ef58a2ab 100644
--- a/arch/arm/kernel/atags_parse.c
+++ b/arch/arm/kernel/atags_parse.c
@@ -22,6 +22,7 @@
 #include <linux/fs.h>
 #include <linux/root_dev.h>
 #include <linux/screen_info.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/system_info.h>
@@ -222,10 +223,10 @@ setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr)
         }
 
         if (mdesc->fixup)
-                mdesc->fixup(tags, &from, &meminfo);
+                mdesc->fixup(tags, &from);
 
         if (tags->hdr.tag == ATAG_CORE) {
-                if (meminfo.nr_banks != 0)
+                if (memblock_phys_mem_size())
                         squash_mem_tags(tags);
                 save_atags(tags);
                 parse_tags(tags);
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index c7419a585ddc..679a83d470cc 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -27,11 +27,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mach-types.h>
 
-void __init early_init_dt_add_memory_arch(u64 base, u64 size)
-{
-        arm_add_memory(base, size);
-}
-
 void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 {
         return memblock_virt_alloc(size, align);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index cb6fa30c22a7..52a949a8077d 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -413,6 +413,11 @@ __und_usr:
         @
         adr     r9, BSYM(ret_from_exception)
 
+        @ IRQs must be enabled before attempting to read the instruction from
+        @ user space since that could cause a page/translation fault if the
+        @ page table was modified by another CPU.
+        enable_irq
+
         tst     r3, #PSR_T_BIT                  @ Thumb mode?
         bne     __und_usr_thumb
         sub     r4, r2, #4                      @ ARM instr at LR - 4
@@ -484,7 +489,8 @@ ENDPROC(__und_usr)
  */
         .pushsection .fixup, "ax"
         .align  2
-4:      mov     pc, r9
+4:      str     r4, [sp, #S_PC]                 @ retry current instruction
+        mov     pc, r9
         .popsection
         .pushsection __ex_table,"a"
         .long   1b, 4b
@@ -517,7 +523,7 @@ ENDPROC(__und_usr)
  *  r9  = normal "successful" return address
  *  r10 = this threads thread_info structure
  *  lr  = unrecognised instruction return address
- * IRQs disabled, FIQs enabled.
+ * IRQs enabled, FIQs enabled.
  */
         @
         @ Fall-through from Thumb-2 __und_usr
@@ -624,7 +630,6 @@ call_fpe:
 #endif
 
 do_fpe:
-        enable_irq
         ldr     r4, .LCfp
         add     r10, r10, #TI_FPSTATE           @ r10 = workspace
         ldr     pc, [r4]                        @ Call FP module USR entry point
@@ -652,8 +657,7 @@ __und_usr_fault_32:
         b       1f
 __und_usr_fault_16:
         mov     r1, #2
-1:      enable_irq
-        mov     r0, sp
+1:      mov     r0, sp
         adr     lr, BSYM(ret_from_exception)
         b       __und_fault
 ENDPROC(__und_usr_fault_32)
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 45a1df9bf759..5d702f8900b1 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -132,6 +132,10 @@
         orrne   r5, V7M_xPSR_FRAMEPTRALIGN
         biceq   r5, V7M_xPSR_FRAMEPTRALIGN
 
+        @ ensure bit 0 is cleared in the PC, otherwise behaviour is
+        @ unpredictable
+        bic     r4, #1
+
         @ write basic exception frame
         stmdb   r2!, {r1, r3-r5}
         ldmia   sp, {r1, r3-r5}
diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index c108ddcb9ba4..af9a8a927a4e 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -14,6 +14,7 @@
 
 #include <linux/ftrace.h>
 #include <linux/uaccess.h>
+#include <linux/module.h>
 
 #include <asm/cacheflush.h>
 #include <asm/opcodes.h>
@@ -63,6 +64,18 @@ static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr)
 }
 #endif
 
+int ftrace_arch_code_modify_prepare(void)
+{
+        set_all_modules_text_rw();
+        return 0;
+}
+
+int ftrace_arch_code_modify_post_process(void)
+{
+        set_all_modules_text_ro();
+        return 0;
+}
+
 static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr)
 {
         return arm_gen_branch_link(pc, addr);
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 591d6e4a6492..2c35f0ff2fdc 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -475,7 +475,7 @@ ENDPROC(__turn_mmu_on)
 
 
 #ifdef CONFIG_SMP_ON_UP
-        __INIT
+        __HEAD
 __fixup_smp:
         and     r3, r9, #0x000f0000     @ architecture version
         teq     r3, #0x000f0000         @ CPU ID supported?
diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c
new file mode 100644
index 000000000000..bb8b79648643
--- /dev/null
+++ b/arch/arm/kernel/hibernate.c
@@ -0,0 +1,107 @@
+/*
+ * Hibernation support specific for ARM
+ *
+ * Derived from work on ARM hibernation support by:
+ *
+ * Ubuntu project, hibernation support for mach-dove
+ * Copyright (C) 2010 Nokia Corporation (Hiroshi Doyu)
+ * Copyright (C) 2010 Texas Instruments, Inc. (Teerth Reddy et al.)
+ *  https://lkml.org/lkml/2010/6/18/4
+ *  https://lists.linux-foundation.org/pipermail/linux-pm/2010-June/027422.html
+ *  https://patchwork.kernel.org/patch/96442/
+ *
+ * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ *
+ * License terms: GNU General Public License (GPL) version 2
+ */
+
+#include <linux/mm.h>
+#include <linux/suspend.h>
+#include <asm/system_misc.h>
+#include <asm/idmap.h>
+#include <asm/suspend.h>
+#include <asm/memory.h>
+
+extern const void __nosave_begin, __nosave_end;
+
+int pfn_is_nosave(unsigned long pfn)
+{
+        unsigned long nosave_begin_pfn = virt_to_pfn(&__nosave_begin);
+        unsigned long nosave_end_pfn = virt_to_pfn(&__nosave_end - 1);
+
+        return (pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn);
+}
+
+void notrace save_processor_state(void)
+{
+        WARN_ON(num_online_cpus() != 1);
+        local_fiq_disable();
+}
+
+void notrace restore_processor_state(void)
+{
+        local_fiq_enable();
+}
+
+/*
+ * Snapshot kernel memory and reset the system.
+ *
+ * swsusp_save() is executed in the suspend finisher so that the CPU
+ * context pointer and memory are part of the saved image, which is
+ * required by the resume kernel image to restart execution from
+ * swsusp_arch_suspend().
+ *
+ * soft_restart is not technically needed, but is used to get success
+ * returned from cpu_suspend.
+ *
+ * When soft reboot completes, the hibernation snapshot is written out.
+ */
+static int notrace arch_save_image(unsigned long unused)
+{
+        int ret;
+
+        ret = swsusp_save();
+        if (ret == 0)
+                soft_restart(virt_to_phys(cpu_resume));
+        return ret;
+}
+
+/*
+ * Save the current CPU state before suspend / poweroff.
+ */
+int notrace swsusp_arch_suspend(void)
+{
+        return cpu_suspend(0, arch_save_image);
+}
+
+/*
+ * Restore page contents for physical pages that were in use during loading
+ * hibernation image.  Switch to idmap_pgd so the physical page tables
+ * are overwritten with the same contents.
+ */
+static void notrace arch_restore_image(void *unused)
+{
+        struct pbe *pbe;
+
+        cpu_switch_mm(idmap_pgd, &init_mm);
+        for (pbe = restore_pblist; pbe; pbe = pbe->next)
+                copy_page(pbe->orig_address, pbe->address);
+
+        soft_restart(virt_to_phys(cpu_resume));
+}
+
+static u64 resume_stack[PAGE_SIZE/2/sizeof(u64)] __nosavedata;
+
+/*
+ * Resume from the hibernation image.
+ * Due to the kernel heap / data restore, stack contents change underneath
+ * and that would make function calls impossible; switch to a temporary
+ * stack within the nosave region to avoid that problem.
+ */
+int swsusp_arch_resume(void)
+{
+        extern void call_with_stack(void (*fn)(void *), void *arg, void *sp);
+        call_with_stack(arch_restore_image, 0,
+                resume_stack + ARRAY_SIZE(resume_stack));
+        return 0;
+}
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 9723d17b8f38..2c4257604513 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -37,6 +37,7 @@
 #include <linux/proc_fs.h>
 #include <linux/export.h>
 
+#include <asm/hardware/cache-l2x0.h>
 #include <asm/exception.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/irq.h>
@@ -115,10 +116,21 @@ EXPORT_SYMBOL_GPL(set_irq_flags);
 
 void __init init_IRQ(void)
 {
+        int ret;
+
         if (IS_ENABLED(CONFIG_OF) && !machine_desc->init_irq)
                 irqchip_init();
         else
                 machine_desc->init_irq();
+
+        if (IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_CACHE_L2X0) &&
+            (machine_desc->l2c_aux_mask || machine_desc->l2c_aux_val)) {
+                outer_cache.write_sec = machine_desc->l2c_write_sec;
+                ret = l2x0_of_init(machine_desc->l2c_aux_val,
+                                   machine_desc->l2c_aux_mask);
+                if (ret)
+                        pr_err("L2C: failed to init: %d\n", ret);
+        }
 }
 
 #ifdef CONFIG_MULTI_IRQ_HANDLER
diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S
index 2452dd1bef53..a5599cfc43cb 100644
--- a/arch/arm/kernel/iwmmxt.S
+++ b/arch/arm/kernel/iwmmxt.S
@@ -18,6 +18,7 @@
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
+#include <asm/assembler.h>
 
 #if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B)
 #define PJ4(code...)            code
@@ -65,17 +66,18 @@
  * r9  = ret_from_exception
  * lr  = undefined instr exit
  *
- * called from prefetch exception handler with interrupts disabled
+ * called from prefetch exception handler with interrupts enabled
  */
 
 ENTRY(iwmmxt_task_enable)
+        inc_preempt_count r10, r3
 
         XSC(mrc p15, 0, r2, c15, c1, 0)
         PJ4(mrc p15, 0, r2, c1, c0, 2)
         @ CP0 and CP1 accessible?
         XSC(tst r2, #0x3)
         PJ4(tst r2, #0xf)
-        movne   pc, lr                          @ if so no business here
+        bne     4f                              @ if so no business here
         @ enable access to CP0 and CP1
         XSC(orr r2, r2, #0x3)
         XSC(mcr p15, 0, r2, c15, c1, 0)
@@ -136,7 +138,7 @@ concan_dump:
         wstrd   wR15, [r1, #MMX_WR15]
 
 2:      teq     r0, #0                          @ anything to load?
-        moveq   pc, lr
+        beq     3f
 
 concan_load:
 
@@ -169,8 +171,14 @@ concan_load:
         @ clear CUP/MUP (only if r1 != 0)
         teq     r1, #0
         mov     r2, #0
-        moveq   pc, lr
+        beq     3f
         tmcr    wCon, r2
+
+3:
+#ifdef CONFIG_PREEMPT_COUNT
+        get_thread_info r10
+#endif
+4:      dec_preempt_count r10, r3
         mov     pc, lr
 
 /*
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 51798d7854ac..a71ae1523620 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -221,6 +221,7 @@ static struct notifier_block cpu_pmu_hotplug_notifier = {
  * PMU platform driver and devicetree bindings.
  */
 static struct of_device_id cpu_pmu_of_device_ids[] = {
+        {.compatible = "arm,cortex-a17-pmu",    .data = armv7_a17_pmu_init},
         {.compatible = "arm,cortex-a15-pmu",    .data = armv7_a15_pmu_init},
         {.compatible = "arm,cortex-a12-pmu",    .data = armv7_a12_pmu_init},
         {.compatible = "arm,cortex-a9-pmu",     .data = armv7_a9_pmu_init},
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index f4ef3981ed02..2037f7205987 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -1599,6 +1599,13 @@ static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
         return 0;
 }
 
+static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu)
+{
+        armv7_a12_pmu_init(cpu_pmu);
+        cpu_pmu->name = "ARMv7 Cortex-A17";
+        return 0;
+}
+
 /*
  * Krait Performance Monitor Region Event Selection Register (PMRESRn)
  *
@@ -2021,6 +2028,11 @@ static inline int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
         return -ENODEV;
 }
 
+static inline int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu)
+{
+        return -ENODEV;
+}
+
 static inline int krait_pmu_init(struct arm_pmu *cpu_pmu)
 {
         return -ENODEV;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index f5120ca08671..8a16ee5d8a95 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -631,15 +631,8 @@ void __init dump_machine_table(void)
 
 int __init arm_add_memory(u64 start, u64 size)
 {
-        struct membank *bank = &meminfo.bank[meminfo.nr_banks];
         u64 aligned_start;
 
-        if (meminfo.nr_banks >= NR_BANKS) {
-                pr_crit("NR_BANKS too low, ignoring memory at 0x%08llx\n",
-                        (long long)start);
-                return -EINVAL;
-        }
-
         /*
          * Ensure that start/size are aligned to a page boundary.
          * Size is appropriately rounded down, start is rounded up.
@@ -680,17 +673,17 @@ int __init arm_add_memory(u64 start, u64 size)
                 aligned_start = PHYS_OFFSET;
         }
 
-        bank->start = aligned_start;
-        bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1);
+        start = aligned_start;
+        size = size & ~(phys_addr_t)(PAGE_SIZE - 1);
 
         /*
          * Check whether this memory region has non-zero size or
          * invalid node number.
          */
-        if (bank->size == 0)
+        if (size == 0)
                 return -EINVAL;
 
-        meminfo.nr_banks++;
+        memblock_add(start, size);
         return 0;
 }
 
@@ -698,6 +691,7 @@ int __init arm_add_memory(u64 start, u64 size)
  * Pick out the memory size.  We look for mem=size@start,
  * where start and size are "size[KkMm]"
  */
+
 static int __init early_mem(char *p)
 {
         static int usermem __initdata = 0;
@@ -712,7 +706,8 @@ static int __init early_mem(char *p)
          */
         if (usermem == 0) {
                 usermem = 1;
-                meminfo.nr_banks = 0;
+                memblock_remove(memblock_start_of_DRAM(),
+                        memblock_end_of_DRAM() - memblock_start_of_DRAM());
         }
 
         start = PHYS_OFFSET;
@@ -857,13 +852,6 @@ static void __init reserve_crashkernel(void)
 static inline void reserve_crashkernel(void) {}
 #endif /* CONFIG_KEXEC */
 
-static int __init meminfo_cmp(const void *_a, const void *_b)
-{
-        const struct membank *a = _a, *b = _b;
-        long cmp = bank_pfn_start(a) - bank_pfn_start(b);
-        return cmp < 0 ? -1 : cmp > 0 ? 1 : 0;
-}
-
 void __init hyp_mode_check(void)
 {
 #ifdef CONFIG_ARM_VIRT_EXT
@@ -906,12 +894,10 @@ void __init setup_arch(char **cmdline_p)
 
         parse_early_param();
 
-        sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
-
         early_paging_init(mdesc, lookup_processor_type(read_cpuid_id()));
         setup_dma_zone(mdesc);
         sanity_check_meminfo();
-        arm_memblock_init(&meminfo, mdesc);
+        arm_memblock_init(mdesc);
 
         paging_init(mdesc);
         request_standard_resources(mdesc);
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index b907d9b790ab..1b880db2a033 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -127,6 +127,10 @@ ENDPROC(cpu_resume_after_mmu)
         .align
 ENTRY(cpu_resume)
 ARM_BE8(setend be)                      @ ensure we are in BE mode
+#ifdef CONFIG_ARM_VIRT_EXT
+        bl      __hyp_stub_install_secondary
+#endif
+        safe_svcmode_maskall r1
         mov     r1, #0
         ALT_SMP(mrc p15, 0, r0, c0, c0, 5)
         ALT_UP_B(1f)
@@ -144,7 +148,6 @@ ARM_BE8(setend be)			@ ensure we are in BE mode
         ldr     r0, [r0, #SLEEP_SAVE_SP_PHYS]
         ldr     r0, [r0, r1, lsl #2]
 
-        setmode PSR_I_BIT | PSR_F_BIT | SVC_MODE, r1  @ set SVC, irqs off
         @ load phys pgd, stack, resume fn
   ARM(  ldmia   r0!, {r1, sp, pc}       )
 THUMB(  ldmia   r0!, {r1, r2, r3}       )
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index af4e8c8a5422..f065eb05d254 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -3,6 +3,7 @@
 #include <linux/stacktrace.h>
 
 #include <asm/stacktrace.h>
+#include <asm/traps.h>
 
 #if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND)
 /*
@@ -61,6 +62,7 @@ EXPORT_SYMBOL(walk_stackframe);
 #ifdef CONFIG_STACKTRACE
 struct stack_trace_data {
         struct stack_trace *trace;
+        unsigned long last_pc;
         unsigned int no_sched_functions;
         unsigned int skip;
 };
@@ -69,6 +71,7 @@ static int save_trace(struct stackframe *frame, void *d)
 {
         struct stack_trace_data *data = d;
         struct stack_trace *trace = data->trace;
+        struct pt_regs *regs;
         unsigned long addr = frame->pc;
 
         if (data->no_sched_functions && in_sched_functions(addr))
@@ -80,16 +83,39 @@ static int save_trace(struct stackframe *frame, void *d)
 
         trace->entries[trace->nr_entries++] = addr;
 
+        if (trace->nr_entries >= trace->max_entries)
+                return 1;
+
+        /*
+         * in_exception_text() is designed to test if the PC is one of
+         * the functions which has an exception stack above it, but
+         * unfortunately what is in frame->pc is the return LR value,
+         * not the saved PC value.  So, we need to track the previous
+         * frame PC value when doing this.
+         */
+        addr = data->last_pc;
+        data->last_pc = frame->pc;
+        if (!in_exception_text(addr))
+                return 0;
+
+        regs = (struct pt_regs *)frame->sp;
+
+        trace->entries[trace->nr_entries++] = regs->ARM_pc;
+
         return trace->nr_entries >= trace->max_entries;
 }
 
-void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+/* This must be noinline to so that our skip calculation works correctly */
+static noinline void __save_stack_trace(struct task_struct *tsk,
+        struct stack_trace *trace, unsigned int nosched)
 {
         struct stack_trace_data data;
         struct stackframe frame;
 
         data.trace = trace;
+        data.last_pc = ULONG_MAX;
         data.skip = trace->skip;
+        data.no_sched_functions = nosched;
 
         if (tsk != current) {
 #ifdef CONFIG_SMP
@@ -102,7 +128,6 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
                         trace->entries[trace->nr_entries++] = ULONG_MAX;
                 return;
 #else
-                data.no_sched_functions = 1;
                 frame.fp = thread_saved_fp(tsk);
                 frame.sp = thread_saved_sp(tsk);
                 frame.lr = 0;           /* recovered from the stack */
@@ -111,11 +136,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
         } else {
                 register unsigned long current_sp asm ("sp");
 
-                data.no_sched_functions = 0;
+                /* We don't want this function nor the caller */
+                data.skip += 2;
                 frame.fp = (unsigned long)__builtin_frame_address(0);
                 frame.sp = current_sp;
                 frame.lr = (unsigned long)__builtin_return_address(0);
-                frame.pc = (unsigned long)save_stack_trace_tsk;
+                frame.pc = (unsigned long)__save_stack_trace;
         }
 
         walk_stackframe(&frame, save_trace, &data);
@@ -123,9 +149,33 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
                 trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 
+void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
+{
+        struct stack_trace_data data;
+        struct stackframe frame;
+
+        data.trace = trace;
+        data.skip = trace->skip;
+        data.no_sched_functions = 0;
+
+        frame.fp = regs->ARM_fp;
+        frame.sp = regs->ARM_sp;
+        frame.lr = regs->ARM_lr;
+        frame.pc = regs->ARM_pc;
+
+        walk_stackframe(&frame, save_trace, &data);
+        if (trace->nr_entries < trace->max_entries)
+                trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+        __save_stack_trace(tsk, trace, 1);
+}
+
 void save_stack_trace(struct stack_trace *trace)
 {
-        save_stack_trace_tsk(current, trace);
+        __save_stack_trace(current, trace, 0);
 }
 EXPORT_SYMBOL_GPL(save_stack_trace);
 #endif
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 0bc94b1fd1ae..0fa8825cea04 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -91,13 +91,13 @@ static void __init parse_dt_topology(void)
 {
         const struct cpu_efficiency *cpu_eff;
         struct device_node *cn = NULL;
-        unsigned long min_capacity = (unsigned long)(-1);
+        unsigned long min_capacity = ULONG_MAX;
         unsigned long max_capacity = 0;
         unsigned long capacity = 0;
-        int alloc_size, cpu = 0;
+        int cpu = 0;
 
-        alloc_size = nr_cpu_ids * sizeof(*__cpu_capacity);
-        __cpu_capacity = kzalloc(alloc_size, GFP_NOWAIT);
+        __cpu_capacity = kcalloc(nr_cpu_ids, sizeof(*__cpu_capacity),
+                                 GFP_NOWAIT);
 
         for_each_possible_cpu(cpu) {
                 const u32 *rate;
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 3c217694ebec..cb791ac6a003 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -285,7 +285,7 @@ static int unwind_exec_pop_r4_to_rN(struct unwind_ctrl_block *ctrl,
                 if (unwind_pop_register(ctrl, &vsp, reg))
                                 return -URC_FAILURE;
 
-        if (insn & 0x80)
+        if (insn & 0x8)
                 if (unwind_pop_register(ctrl, &vsp, 14))
                                 return -URC_FAILURE;
 
diff --git a/arch/arm/kernel/uprobes.c b/arch/arm/kernel/uprobes.c
index f9bacee973bf..56adf9c1fde0 100644
--- a/arch/arm/kernel/uprobes.c
+++ b/arch/arm/kernel/uprobes.c
@@ -113,6 +113,26 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
         return 0;
 }
 
+void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
+                           void *src, unsigned long len)
+{
+        void *xol_page_kaddr = kmap_atomic(page);
+        void *dst = xol_page_kaddr + (vaddr & ~PAGE_MASK);
+
+        preempt_disable();
+
+        /* Initialize the slot */
+        memcpy(dst, src, len);
+
+        /* flush caches (dcache/icache) */
+        flush_uprobe_xol_access(page, vaddr, dst, len);
+
+        preempt_enable();
+
+        kunmap_atomic(xol_page_kaddr);
+}
+
+
 int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
 {
         struct uprobe_task *utask = current->utask;
diff --git a/arch/arm/mach-bcm/bcm_5301x.c b/arch/arm/mach-bcm/bcm_5301x.c
index edff69761e04..e9bcbdbce555 100644
--- a/arch/arm/mach-bcm/bcm_5301x.c
+++ b/arch/arm/mach-bcm/bcm_5301x.c
@@ -43,19 +43,14 @@ static void __init bcm5301x_init_early(void)
                         "imprecise external abort");
 }
 
-static void __init bcm5301x_dt_init(void)
-{
-        l2x0_of_init(0, ~0UL);
-        of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-}
-
 static const char __initconst *bcm5301x_dt_compat[] = {
         "brcm,bcm4708",
         NULL,
 };
 
 DT_MACHINE_START(BCM5301X, "BCM5301X")
+        .l2c_aux_val    = 0,
+        .l2c_aux_mask   = ~0,
         .init_early     = bcm5301x_init_early,
-        .init_machine   = bcm5301x_dt_init,
         .dt_compat      = bcm5301x_dt_compat,
 MACHINE_END
diff --git a/arch/arm/mach-berlin/berlin.c b/arch/arm/mach-berlin/berlin.c
index 025bcb5473eb..ac181c6797ee 100644
--- a/arch/arm/mach-berlin/berlin.c
+++ b/arch/arm/mach-berlin/berlin.c
@@ -18,16 +18,6 @@
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/mach/arch.h>
 
-static void __init berlin_init_machine(void)
-{
-        /*
-         * with DT probing for L2CCs, berlin_init_machine can be removed.
-         * Note: 88DE3005 (Armada 1500-mini) uses pl310 l2cc
-         */
-        l2x0_of_init(0x70c00000, 0xfeffffff);
-        of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-}
-
 static const char * const berlin_dt_compat[] = {
         "marvell,berlin",
         NULL,
@@ -35,5 +25,10 @@ static const char * const berlin_dt_compat[] = {
 
 DT_MACHINE_START(BERLIN_DT, "Marvell Berlin")
         .dt_compat      = berlin_dt_compat,
-        .init_machine   = berlin_init_machine,
+        /*
+         * with DT probing for L2CCs, berlin_init_machine can be removed.
+         * Note: 88DE3005 (Armada 1500-mini) uses pl310 l2cc
+         */
+        .l2c_aux_val    = 0x30c00000,
+        .l2c_aux_mask   = 0xfeffffff,
 MACHINE_END
diff --git a/arch/arm/mach-clps711x/board-clep7312.c b/arch/arm/mach-clps711x/board-clep7312.c
index 221b9de32dd6..94a7add88a3f 100644
--- a/arch/arm/mach-clps711x/board-clep7312.c
+++ b/arch/arm/mach-clps711x/board-clep7312.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/string.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/mach-types.h>
@@ -26,11 +27,9 @@
 #include "common.h"
 
 static void __init
-fixup_clep7312(struct tag *tags, char **cmdline, struct meminfo *mi)
+fixup_clep7312(struct tag *tags, char **cmdline)
 {
-        mi->nr_banks=1;
-        mi->bank[0].start = 0xc0000000;
-        mi->bank[0].size = 0x01000000;
+        memblock_add(0xc0000000, 0x01000000);
 }
 
 MACHINE_START(CLEP7212, "Cirrus Logic 7212/7312")
diff --git a/arch/arm/mach-clps711x/board-edb7211.c b/arch/arm/mach-clps711x/board-edb7211.c
index 077609841f14..f9828f89972a 100644
--- a/arch/arm/mach-clps711x/board-edb7211.c
+++ b/arch/arm/mach-clps711x/board-edb7211.c
@@ -16,6 +16,7 @@
 #include <linux/interrupt.h>
 #include <linux/backlight.h>
 #include <linux/platform_device.h>
+#include <linux/memblock.h>
 
 #include <linux/mtd/physmap.h>
 #include <linux/mtd/partitions.h>
@@ -133,7 +134,7 @@ static void __init edb7211_reserve(void)
 }
 
 static void __init
-fixup_edb7211(struct tag *tags, char **cmdline, struct meminfo *mi)
+fixup_edb7211(struct tag *tags, char **cmdline)
 {
         /*
          * Bank start addresses are not present in the information
@@ -143,11 +144,8 @@ fixup_edb7211(struct tag *tags, char **cmdline, struct meminfo *mi)
          * Banks sizes _are_ present in the param block, but we're
          * not using that information yet.
          */
-        mi->bank[0].start = 0xc0000000;
-        mi->bank[0].size = SZ_8M;
-        mi->bank[1].start = 0xc1000000;
-        mi->bank[1].size = SZ_8M;
-        mi->nr_banks = 2;
+        memblock_add(0xc0000000, SZ_8M);
+        memblock_add(0xc1000000, SZ_8M);
 }
 
 static void __init edb7211_init(void)
diff --git a/arch/arm/mach-clps711x/board-p720t.c b/arch/arm/mach-clps711x/board-p720t.c
index 67b733744ed7..0cf0e51e6546 100644
--- a/arch/arm/mach-clps711x/board-p720t.c
+++ b/arch/arm/mach-clps711x/board-p720t.c
@@ -295,7 +295,7 @@ static struct generic_bl_info p720t_lcd_backlight_pdata = {
 };
 
 static void __init
-fixup_p720t(struct tag *tag, char **cmdline, struct meminfo *mi)
+fixup_p720t(struct tag *tag, char **cmdline)
 {
         /*
          * Our bootloader doesn't setup any tags (yet).
diff --git a/arch/arm/mach-cns3xxx/core.c b/arch/arm/mach-cns3xxx/core.c
index 2ae28a69e3e5..f85449a6accd 100644
--- a/arch/arm/mach-cns3xxx/core.c
+++ b/arch/arm/mach-cns3xxx/core.c
@@ -272,9 +272,9 @@ void __init cns3xxx_l2x0_init(void)
          *
          * 1 cycle of latency for setup, read and write accesses
          */
-        val = readl(base + L2X0_TAG_LATENCY_CTRL);
+        val = readl(base + L310_TAG_LATENCY_CTRL);
         val &= 0xfffff888;
-        writel(val, base + L2X0_TAG_LATENCY_CTRL);
+        writel(val, base + L310_TAG_LATENCY_CTRL);
 
         /*
          * Data RAM Control register
@@ -285,12 +285,12 @@ void __init cns3xxx_l2x0_init(void)
          *
          * 1 cycle of latency for setup, read and write accesses
          */
-        val = readl(base + L2X0_DATA_LATENCY_CTRL);
+        val = readl(base + L310_DATA_LATENCY_CTRL);
         val &= 0xfffff888;
-        writel(val, base + L2X0_DATA_LATENCY_CTRL);
+        writel(val, base + L310_DATA_LATENCY_CTRL);
 
         /* 32 KiB, 8-way, parity disable */
-        l2x0_init(base, 0x00540000, 0xfe000fff);
+        l2x0_init(base, 0x00500000, 0xfe0f0fff);
 }
 
 #endif /* CONFIG_CACHE_L2X0 */
diff --git a/arch/arm/mach-ep93xx/crunch-bits.S b/arch/arm/mach-ep93xx/crunch-bits.S
index 0ec9bb48fab9..e96923a3017b 100644
--- a/arch/arm/mach-ep93xx/crunch-bits.S
+++ b/arch/arm/mach-ep93xx/crunch-bits.S
@@ -16,6 +16,7 @@
 #include <asm/ptrace.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
+#include <asm/assembler.h>
 #include <mach/ep93xx-regs.h>
 
 /*
@@ -62,14 +63,16 @@
  * r9  = ret_from_exception
  * lr  = undefined instr exit
  *
- * called from prefetch exception handler with interrupts disabled
+ * called from prefetch exception handler with interrupts enabled
  */
 ENTRY(crunch_task_enable)
+        inc_preempt_count r10, r3
+
         ldr     r8, =(EP93XX_APB_VIRT_BASE + 0x00130000)        @ syscon addr
 
         ldr     r1, [r8, #0x80]
         tst     r1, #0x00800000                 @ access to crunch enabled?
-        movne   pc, lr                          @ if so no business here
+        bne     2f                              @ if so no business here
         mov     r3, #0xaa                       @ unlock syscon swlock
         str     r3, [r8, #0xc0]
         orr     r1, r1, #0x00800000             @ enable access to crunch
@@ -142,7 +145,7 @@ crunch_save:
 
         teq             r0, #0                          @ anything to load?
         cfldr64eq       mvdx0, [r1, #CRUNCH_MVDX0]      @ mvdx0 was clobbered
-        moveq           pc, lr
+        beq             1f
 
 crunch_load:
         cfldr64         mvdx0, [r0, #CRUNCH_DSPSC]      @ load status word
@@ -190,6 +193,11 @@ crunch_load:
         cfldr64         mvdx14, [r0, #CRUNCH_MVDX14]
         cfldr64         mvdx15, [r0, #CRUNCH_MVDX15]
 
+1:
+#ifdef CONFIG_PREEMPT_COUNT
+        get_thread_info r10
+#endif
+2:      dec_preempt_count r10, r3
         mov     pc, lr
 
 /*
diff --git a/arch/arm/mach-exynos/common.h b/arch/arm/mach-exynos/common.h
index 9ef3f83efaff..88c619d1e145 100644
--- a/arch/arm/mach-exynos/common.h
+++ b/arch/arm/mach-exynos/common.h
@@ -55,7 +55,6 @@ enum sys_powerdown {
         NUM_SYS_POWERDOWN,
 };
 
-extern unsigned long l2x0_regs_phys;
 struct exynos_pmu_conf {
         void __iomem *reg;
         unsigned int val[NUM_SYS_POWERDOWN];
diff --git a/arch/arm/mach-exynos/exynos.c b/arch/arm/mach-exynos/exynos.c
index b32a907d021d..a763c0862da9 100644
--- a/arch/arm/mach-exynos/exynos.c
+++ b/arch/arm/mach-exynos/exynos.c
@@ -32,9 +32,6 @@
 #include "mfc.h"
 #include "regs-pmu.h"
 
-#define L2_AUX_VAL 0x7C470001
-#define L2_AUX_MASK 0xC200ffff
-
 static struct map_desc exynos4_iodesc[] __initdata = {
         {
                 .virtual        = (unsigned long)S3C_VA_SYS,
@@ -319,22 +316,6 @@ static int __init exynos_core_init(void)
 }
 core_initcall(exynos_core_init);
 
-static int __init exynos4_l2x0_cache_init(void)
-{
-        int ret;
-
-        ret = l2x0_of_init(L2_AUX_VAL, L2_AUX_MASK);
-        if (ret)
-                return ret;
-
-        if (IS_ENABLED(CONFIG_S5P_SLEEP)) {
-                l2x0_regs_phys = virt_to_phys(&l2x0_saved_regs);
-                clean_dcache_area(&l2x0_regs_phys, sizeof(unsigned long));
-        }
-        return 0;
-}
-early_initcall(exynos4_l2x0_cache_init);
-
 static void __init exynos_dt_machine_init(void)
 {
         struct device_node *i2c_np;
@@ -400,6 +381,8 @@ static void __init exynos_reserve(void)
 DT_MACHINE_START(EXYNOS_DT, "SAMSUNG EXYNOS (Flattened Device Tree)")
         /* Maintainer: Thomas Abraham <thomas.abraham@linaro.org> */
         /* Maintainer: Kukjin Kim <kgene.kim@samsung.com> */
+        .l2c_aux_val    = 0x3c400001,
+        .l2c_aux_mask   = 0xc20fffff,
         .smp            = smp_ops(exynos_smp_ops),
         .map_io         = exynos_init_io,
         .init_early     = exynos_firmware_init,
diff --git a/arch/arm/mach-exynos/sleep.S b/arch/arm/mach-exynos/sleep.S
index a2613e944e10..108a45f4bb62 100644
--- a/arch/arm/mach-exynos/sleep.S
+++ b/arch/arm/mach-exynos/sleep.S
@@ -16,8 +16,6 @@
  */
 
 #include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/hardware/cache-l2x0.h>
 
 #define CPU_MASK        0xff0ffff0
 #define CPU_CORTEX_A9   0x410fc090
@@ -53,33 +51,7 @@ ENTRY(exynos_cpu_resume)
         and     r0, r0, r1
         ldr     r1, =CPU_CORTEX_A9
         cmp     r0, r1
-        bne     skip_l2_resume
-        adr     r0, l2x0_regs_phys
-        ldr     r0, [r0]
-        cmp     r0, #0
-        beq     skip_l2_resume
-        ldr     r1, [r0, #L2X0_R_PHY_BASE]
-        ldr     r2, [r1, #L2X0_CTRL]
-        tst     r2, #0x1
-        bne     skip_l2_resume
-        ldr     r2, [r0, #L2X0_R_AUX_CTRL]
-        str     r2, [r1, #L2X0_AUX_CTRL]
-        ldr     r2, [r0, #L2X0_R_TAG_LATENCY]
-        str     r2, [r1, #L2X0_TAG_LATENCY_CTRL]
-        ldr     r2, [r0, #L2X0_R_DATA_LATENCY]
-        str     r2, [r1, #L2X0_DATA_LATENCY_CTRL]
-        ldr     r2, [r0, #L2X0_R_PREFETCH_CTRL]
-        str     r2, [r1, #L2X0_PREFETCH_CTRL]
-        ldr     r2, [r0, #L2X0_R_PWR_CTRL]
-        str     r2, [r1, #L2X0_POWER_CTRL]
-        mov     r2, #1
-        str     r2, [r1, #L2X0_CTRL]
-skip_l2_resume:
+        bleq    l2c310_early_resume
 #endif
         b       cpu_resume
 ENDPROC(exynos_cpu_resume)
-#ifdef CONFIG_CACHE_L2X0
-        .globl l2x0_regs_phys
-l2x0_regs_phys:
-        .long   0
-#endif
diff --git a/arch/arm/mach-footbridge/cats-hw.c b/arch/arm/mach-footbridge/cats-hw.c
index da0415094856..8f05489671b7 100644
--- a/arch/arm/mach-footbridge/cats-hw.c
+++ b/arch/arm/mach-footbridge/cats-hw.c
@@ -76,7 +76,7 @@ __initcall(cats_hw_init);
  * hard reboots fail on early boards.
  */
 static void __init
-fixup_cats(struct tag *tags, char **cmdline, struct meminfo *mi)
+fixup_cats(struct tag *tags, char **cmdline)
 {
 #if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE)
         screen_info.orig_video_lines  = 25;
diff --git a/arch/arm/mach-footbridge/netwinder-hw.c b/arch/arm/mach-footbridge/netwinder-hw.c
index eb1fa5c84723..cdee08c6d239 100644
--- a/arch/arm/mach-footbridge/netwinder-hw.c
+++ b/arch/arm/mach-footbridge/netwinder-hw.c
@@ -620,7 +620,7 @@ __initcall(nw_hw_init);
  * the parameter page.
  */
 static void __init
-fixup_netwinder(struct tag *tags, char **cmdline, struct meminfo *mi)
+fixup_netwinder(struct tag *tags, char **cmdline)
 {
 #ifdef CONFIG_ISAPNP
         extern int isapnp_disable;
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index c7de89b263dd..8c35ae4ff176 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -51,11 +51,13 @@ static void __init highbank_scu_map_io(void)
 }
 
 
-static void highbank_l2x0_disable(void)
+static void highbank_l2c310_write_sec(unsigned long val, unsigned reg)
 {
-        outer_flush_all();
-        /* Disable PL310 L2 Cache controller */
-        highbank_smc1(0x102, 0x0);
+        if (reg == L2X0_CTRL)
+                highbank_smc1(0x102, val);
+        else
+                WARN_ONCE(1, "Highbank L2C310: ignoring write to reg 0x%x\n",
+                          reg);
 }
 
 static void __init highbank_init_irq(void)
@@ -64,14 +66,6 @@ static void __init highbank_init_irq(void)
 
         if (of_find_compatible_node(NULL, NULL, "arm,cortex-a9"))
                 highbank_scu_map_io();
-
-        /* Enable PL310 L2 Cache controller */
-        if (IS_ENABLED(CONFIG_CACHE_L2X0) &&
-            of_find_compatible_node(NULL, NULL, "arm,pl310-cache")) {
-                highbank_smc1(0x102, 0x1);
-                l2x0_of_init(0, ~0UL);
-                outer_cache.disable = highbank_l2x0_disable;
-        }
 }
 
 static void highbank_power_off(void)
@@ -185,6 +179,9 @@ DT_MACHINE_START(HIGHBANK, "Highbank")
 #if defined(CONFIG_ZONE_DMA) && defined(CONFIG_ARM_LPAE)
         .dma_zone_size  = (4ULL * SZ_1G),
 #endif
+        .l2c_aux_val    = 0,
+        .l2c_aux_mask   = ~0,
+        .l2c_write_sec  = highbank_l2c310_write_sec,
         .init_irq       = highbank_init_irq,
         .init_machine   = highbank_init,
         .dt_compat      = highbank_match,
diff --git a/arch/arm/mach-imx/mach-vf610.c b/arch/arm/mach-imx/mach-vf610.c
index 2d8aef5a6efa..c44602758120 100644
--- a/arch/arm/mach-imx/mach-vf610.c
+++ b/arch/arm/mach-imx/mach-vf610.c
@@ -20,19 +20,14 @@ static void __init vf610_init_machine(void)
         of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 }
 
-static void __init vf610_init_irq(void)
-{
-        l2x0_of_init(0, ~0UL);
-        irqchip_init();
-}
-
 static const char *vf610_dt_compat[] __initconst = {
         "fsl,vf610",
         NULL,
 };
 
 DT_MACHINE_START(VYBRID_VF610, "Freescale Vybrid VF610 (Device Tree)")
-        .init_irq       = vf610_init_irq,
+        .l2c_aux_val    = 0,
+        .l2c_aux_mask   = ~0,
         .init_machine   = vf610_init_machine,
         .dt_compat      = vf610_dt_compat,
         .restart        = mxc_restart,
diff --git a/arch/arm/mach-imx/suspend-imx6.S b/arch/arm/mach-imx/suspend-imx6.S
index 20048ff05739..fe123b079c05 100644
--- a/arch/arm/mach-imx/suspend-imx6.S
+++ b/arch/arm/mach-imx/suspend-imx6.S
@@ -334,28 +334,10 @@ ENDPROC(imx6_suspend)
  * turned into relative ones.
  */
 
-#ifdef CONFIG_CACHE_L2X0
-        .macro  pl310_resume
-        adr     r0, l2x0_saved_regs_offset
-        ldr     r2, [r0]
-        add     r2, r2, r0
-        ldr     r0, [r2, #L2X0_R_PHY_BASE]      @ get physical base of l2x0
-        ldr     r1, [r2, #L2X0_R_AUX_CTRL]      @ get aux_ctrl value
-        str     r1, [r0, #L2X0_AUX_CTRL]        @ restore aux_ctrl
-        mov     r1, #0x1
-        str     r1, [r0, #L2X0_CTRL]            @ re-enable L2
-        .endm
-
-l2x0_saved_regs_offset:
-        .word   l2x0_saved_regs - .
-
-#else
-        .macro  pl310_resume
-        .endm
-#endif
-
 ENTRY(v7_cpu_resume)
         bl      v7_invalidate_l1
-        pl310_resume
+#ifdef CONFIG_CACHE_L2X0
+        bl      l2c310_early_resume
+#endif
         b       cpu_resume
 ENDPROC(v7_cpu_resume)
diff --git a/arch/arm/mach-imx/system.c b/arch/arm/mach-imx/system.c
index 5e3027d3692f..3b0733edb68c 100644
--- a/arch/arm/mach-imx/system.c
+++ b/arch/arm/mach-imx/system.c
@@ -124,7 +124,7 @@ void __init imx_init_l2cache(void)
         }
 
         /* Configure the L2 PREFETCH and POWER registers */
-        val = readl_relaxed(l2x0_base + L2X0_PREFETCH_CTRL);
+        val = readl_relaxed(l2x0_base + L310_PREFETCH_CTRL);
         val |= 0x70800000;
         /*
          * The L2 cache controller(PL310) version on the i.MX6D/Q is r3p1-50rel0
@@ -137,14 +137,12 @@ void __init imx_init_l2cache(void)
          */
         if (cpu_is_imx6q())
                 val &= ~(1 << 30 | 1 << 23);
-        writel_relaxed(val, l2x0_base + L2X0_PREFETCH_CTRL);
-        val = L2X0_DYNAMIC_CLK_GATING_EN | L2X0_STNDBY_MODE_EN;
-        writel_relaxed(val, l2x0_base + L2X0_POWER_CTRL);
+        writel_relaxed(val, l2x0_base + L310_PREFETCH_CTRL);
 
         iounmap(l2x0_base);
         of_node_put(np);
 
 out:
-        l2x0_of_init(0, ~0UL);
+        l2x0_of_init(0, ~0);
 }
 #endif
diff --git a/arch/arm/mach-msm/board-halibut.c b/arch/arm/mach-msm/board-halibut.c
index a77529887cbc..61bfe584a9d7 100644
--- a/arch/arm/mach-msm/board-halibut.c
+++ b/arch/arm/mach-msm/board-halibut.c
@@ -83,11 +83,6 @@ static void __init halibut_init(void)
         platform_add_devices(devices, ARRAY_SIZE(devices));
 }
 
-static void __init halibut_fixup(struct tag *tags, char **cmdline,
-                                 struct meminfo *mi)
-{
-}
-
 static void __init halibut_map_io(void)
 {
         msm_map_common_io();
@@ -100,7 +95,6 @@ static void __init halibut_init_late(void)
 
 MACHINE_START(HALIBUT, "Halibut Board (QCT SURF7200A)")
         .atag_offset    = 0x100,
-        .fixup          = halibut_fixup,
         .map_io         = halibut_map_io,
         .init_early     = halibut_init_early,
         .init_irq       = halibut_init_irq,
diff --git a/arch/arm/mach-msm/board-mahimahi.c b/arch/arm/mach-msm/board-mahimahi.c
index 7d9981cb400e..873c3ca3cd7e 100644
--- a/arch/arm/mach-msm/board-mahimahi.c
+++ b/arch/arm/mach-msm/board-mahimahi.c
@@ -22,6 +22,7 @@
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
+#include <linux/memblock.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -52,16 +53,10 @@ static void __init mahimahi_init(void)
         platform_add_devices(devices, ARRAY_SIZE(devices));
 }
 
-static void __init mahimahi_fixup(struct tag *tags, char **cmdline,
-                                  struct meminfo *mi)
+static void __init mahimahi_fixup(struct tag *tags, char **cmdline)
 {
-        mi->nr_banks = 2;
-        mi->bank[0].start = PHYS_OFFSET;
-        mi->bank[0].node = PHYS_TO_NID(PHYS_OFFSET);
-        mi->bank[0].size = (219*1024*1024);
-        mi->bank[1].start = MSM_HIGHMEM_BASE;
-        mi->bank[1].node = PHYS_TO_NID(MSM_HIGHMEM_BASE);
-        mi->bank[1].size = MSM_HIGHMEM_SIZE;
+        memblock_add(PHYS_OFFSET, 219*SZ_1M);
+        memblock_add(MSM_HIGHMEM_BASE, MSM_HIGHMEM_SIZE);
 }
 
 static void __init mahimahi_map_io(void)
diff --git a/arch/arm/mach-msm/board-msm7x30.c b/arch/arm/mach-msm/board-msm7x30.c
index 46de789ad3ae..b621b23a5ecc 100644
--- a/arch/arm/mach-msm/board-msm7x30.c
+++ b/arch/arm/mach-msm/board-msm7x30.c
@@ -40,8 +40,7 @@
 #include "proc_comm.h"
 #include "common.h"
 
-static void __init msm7x30_fixup(struct tag *tag, char **cmdline,
-                struct meminfo *mi)
+static void __init msm7x30_fixup(struct tag *tag, char **cmdline)
 {
         for (; tag->hdr.size; tag = tag_next(tag))
                 if (tag->hdr.tag == ATAG_MEM && tag->u.mem.start == 0x200000) {
diff --git a/arch/arm/mach-msm/board-sapphire.c b/arch/arm/mach-msm/board-sapphire.c
index 327605174d63..e50967926dcd 100644
--- a/arch/arm/mach-msm/board-sapphire.c
+++ b/arch/arm/mach-msm/board-sapphire.c
@@ -35,6 +35,7 @@
 
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
+#include <linux/memblock.h>
 
 #include "gpio_chip.h"
 #include "board-sapphire.h"
@@ -74,22 +75,18 @@ static struct map_desc sapphire_io_desc[] __initdata = {
         }
 };
 
-static void __init sapphire_fixup(struct tag *tags, char **cmdline,
-                                  struct meminfo *mi)
+static void __init sapphire_fixup(struct tag *tags, char **cmdline)
 {
         int smi_sz = parse_tag_smi((const struct tag *)tags);
 
-        mi->nr_banks = 1;
-        mi->bank[0].start = PHYS_OFFSET;
-        mi->bank[0].node = PHYS_TO_NID(PHYS_OFFSET);
         if (smi_sz == 32) {
-                mi->bank[0].size = (84*1024*1024);
+                memblock_add(PHYS_OFFSET, 84*SZ_1M);
         } else if (smi_sz == 64) {
-                mi->bank[0].size = (101*1024*1024);
+                memblock_add(PHYS_OFFSET, 101*SZ_1M);
         } else {
+                memblock_add(PHYS_OFFSET, 101*SZ_1M);
                 /* Give a default value when not get smi size */
                 smi_sz = 64;
-                mi->bank[0].size = (101*1024*1024);
         }
 }
 
diff --git a/arch/arm/mach-msm/board-trout.c b/arch/arm/mach-msm/board-trout.c
index 015d544aa017..58826cfab6b0 100644
--- a/arch/arm/mach-msm/board-trout.c
+++ b/arch/arm/mach-msm/board-trout.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/clkdev.h>
+#include <linux/memblock.h>
 
 #include <asm/system_info.h>
 #include <asm/mach-types.h>
@@ -55,12 +56,9 @@ static void __init trout_init_irq(void)
         msm_init_irq();
 }
 
-static void __init trout_fixup(struct tag *tags, char **cmdline,
-                               struct meminfo *mi)
+static void __init trout_fixup(struct tag *tags, char **cmdline)
 {
-        mi->nr_banks = 1;
-        mi->bank[0].start = PHYS_OFFSET;
-        mi->bank[0].size = (101*1024*1024);
+        memblock_add(PHYS_OFFSET, 101*SZ_1M);
 }
 
 static void __init trout_init(void)
diff --git a/arch/arm/mach-mvebu/board-v7.c b/arch/arm/mach-mvebu/board-v7.c
index 333fca8fdc41..48169caa56ea 100644
--- a/arch/arm/mach-mvebu/board-v7.c
+++ b/arch/arm/mach-mvebu/board-v7.c
@@ -59,9 +59,6 @@ static void __init mvebu_timer_and_clk_init(void)
         clocksource_of_init();
         coherency_init();
         BUG_ON(mvebu_mbus_dt_init());
-#ifdef CONFIG_CACHE_L2X0
-        l2x0_of_init(0, ~0UL);
-#endif
 
         if (of_machine_is_compatible("marvell,armada375"))
                 hook_fault_code(16 + 6, armada_375_external_abort_wa, SIGBUS, 0,
@@ -109,6 +106,8 @@ static const char * const armada_370_xp_dt_compat[] = {
 };
 
 DT_MACHINE_START(ARMADA_370_XP_DT, "Marvell Armada 370/XP (Device Tree)")
+        .l2c_aux_val    = 0,
+        .l2c_aux_mask   = ~0,
         .smp            = smp_ops(armada_xp_smp_ops),
         .init_machine   = mvebu_dt_init,
         .init_time      = mvebu_timer_and_clk_init,
@@ -122,6 +121,8 @@ static const char * const armada_375_dt_compat[] = {
 };
 
 DT_MACHINE_START(ARMADA_375_DT, "Marvell Armada 375 (Device Tree)")
+        .l2c_aux_val    = 0,
+        .l2c_aux_mask   = ~0,
         .init_time      = mvebu_timer_and_clk_init,
         .restart        = mvebu_restart,
         .dt_compat      = armada_375_dt_compat,
@@ -134,6 +135,8 @@ static const char * const armada_38x_dt_compat[] = {
 };
 
 DT_MACHINE_START(ARMADA_38X_DT, "Marvell Armada 380/385 (Device Tree)")
+        .l2c_aux_val    = 0,
+        .l2c_aux_mask   = ~0,
         .init_time      = mvebu_timer_and_clk_init,
         .restart        = mvebu_restart,
         .dt_compat      = armada_38x_dt_compat,
diff --git a/arch/arm/mach-nomadik/cpu-8815.c b/arch/arm/mach-nomadik/cpu-8815.c
index 4a1065e41e9c..9116ca476d7c 100644
--- a/arch/arm/mach-nomadik/cpu-8815.c
+++ b/arch/arm/mach-nomadik/cpu-8815.c
@@ -143,23 +143,16 @@ static int __init cpu8815_mmcsd_init(void)
 }
 device_initcall(cpu8815_mmcsd_init);
 
-static void __init cpu8815_init_of(void)
-{
-#ifdef CONFIG_CACHE_L2X0
-        /* At full speed latency must be >=2, so 0x249 in low bits */
-        l2x0_of_init(0x00730249, 0xfe000fff);
-#endif
-        of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-}
-
 static const char * cpu8815_board_compat[] = {
         "calaosystems,usb-s8815",
         NULL,
 };
 
 DT_MACHINE_START(NOMADIK_DT, "Nomadik STn8815")
+        /* At full speed latency must be >=2, so 0x249 in low bits */
+        .l2c_aux_val    = 0x00700249,
+        .l2c_aux_mask   = 0xfe0fefff,
         .map_io         = cpu8815_map_io,
-        .init_machine   = cpu8815_init_of,
         .restart        = cpu8815_restart,
         .dt_compat      = cpu8815_board_compat,
 MACHINE_END
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index cb31d4390d52..0ba482638ebf 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -65,6 +65,7 @@ config SOC_AM43XX
         select ARCH_HAS_OPP
         select ARM_GIC
         select MACH_OMAP_GENERIC
+        select MIGHT_HAVE_CACHE_L2X0
 
 config SOC_DRA7XX
         bool "TI DRA7XX"
diff --git a/arch/arm/mach-omap2/common.h b/arch/arm/mach-omap2/common.h
index d88aff7baff8..ff029737c8f0 100644
--- a/arch/arm/mach-omap2/common.h
+++ b/arch/arm/mach-omap2/common.h
@@ -91,6 +91,7 @@ extern void omap3_sync32k_timer_init(void);
 extern void omap3_secure_sync32k_timer_init(void);
 extern void omap3_gptimer_timer_init(void);
 extern void omap4_local_timer_init(void);
+int omap_l2_cache_init(void);
 extern void omap5_realtime_timer_init(void);
 
 void omap2420_init_early(void);
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index f14f9ac2dca1..4e2df49991ad 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -609,6 +609,7 @@ void __init am43xx_init_early(void)
         am43xx_clockdomains_init();
         am43xx_hwmod_init();
         omap_hwmod_init_postsetup();
+        omap_l2_cache_init();
         omap_clk_soc_init = am43xx_dt_clk_init;
 }
 
@@ -640,6 +641,7 @@ void __init omap4430_init_early(void)
         omap44xx_clockdomains_init();
         omap44xx_hwmod_init();
         omap_hwmod_init_postsetup();
+        omap_l2_cache_init();
         omap_clk_soc_init = omap4xxx_dt_clk_init;
 }
 
diff --git a/arch/arm/mach-omap2/omap-mpuss-lowpower.c b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
index 667915d236f3..61cb77f8cf12 100644
--- a/arch/arm/mach-omap2/omap-mpuss-lowpower.c
+++ b/arch/arm/mach-omap2/omap-mpuss-lowpower.c
@@ -187,19 +187,15 @@ static void l2x0_pwrst_prepare(unsigned int cpu_id, unsigned int save_state)
  * in every restore MPUSS OFF path.
  */
 #ifdef CONFIG_CACHE_L2X0
-static void save_l2x0_context(void)
+static void __init save_l2x0_context(void)
 {
-        u32 val;
-        void __iomem *l2x0_base = omap4_get_l2cache_base();
-        if (l2x0_base) {
-                val = __raw_readl(l2x0_base + L2X0_AUX_CTRL);
-                __raw_writel(val, sar_base + L2X0_AUXCTRL_OFFSET);
-                val = __raw_readl(l2x0_base + L2X0_PREFETCH_CTRL);
-                __raw_writel(val, sar_base + L2X0_PREFETCH_CTRL_OFFSET);
-        }
+        __raw_writel(l2x0_saved_regs.aux_ctrl,
+                     sar_base + L2X0_AUXCTRL_OFFSET);
+        __raw_writel(l2x0_saved_regs.prefetch_ctrl,
+                     sar_base + L2X0_PREFETCH_CTRL_OFFSET);
 }
 #else
-static void save_l2x0_context(void)
+static void __init save_l2x0_context(void)
 {}
 #endif
 
diff --git a/arch/arm/mach-omap2/omap4-common.c b/arch/arm/mach-omap2/omap4-common.c
index 95e171a055f3..c41ff8b638e1 100644
--- a/arch/arm/mach-omap2/omap4-common.c
+++ b/arch/arm/mach-omap2/omap4-common.c
@@ -167,75 +167,57 @@ void __iomem *omap4_get_l2cache_base(void)
         return l2cache_base;
 }
 
-static void omap4_l2x0_disable(void)
+static void omap4_l2c310_write_sec(unsigned long val, unsigned reg)
 {
-        outer_flush_all();
-        /* Disable PL310 L2 Cache controller */
-        omap_smc1(0x102, 0x0);
-}
+        unsigned smc_op;
 
-static void omap4_l2x0_set_debug(unsigned long val)
-{
-        /* Program PL310 L2 Cache controller debug register */
-        omap_smc1(0x100, val);
+        switch (reg) {
+        case L2X0_CTRL:
+                smc_op = OMAP4_MON_L2X0_CTRL_INDEX;
+                break;
+
+        case L2X0_AUX_CTRL:
+                smc_op = OMAP4_MON_L2X0_AUXCTRL_INDEX;
+                break;
+
+        case L2X0_DEBUG_CTRL:
+                smc_op = OMAP4_MON_L2X0_DBG_CTRL_INDEX;
+                break;
+
+        case L310_PREFETCH_CTRL:
+                smc_op = OMAP4_MON_L2X0_PREFETCH_INDEX;
+                break;
+
+        default:
+                WARN_ONCE(1, "OMAP L2C310: ignoring write to reg 0x%x\n", reg);
+                return;
+        }
+
+        omap_smc1(smc_op, val);
 }
 
-static int __init omap_l2_cache_init(void)
+int __init omap_l2_cache_init(void)
 {
-        u32 aux_ctrl = 0;
-
-        /*
-         * To avoid code running on other OMAPs in
-         * multi-omap builds
-         */
-        if (!cpu_is_omap44xx())
-                return -ENODEV;
+        u32 aux_ctrl;
 
         /* Static mapping, never released */
         l2cache_base = ioremap(OMAP44XX_L2CACHE_BASE, SZ_4K);
         if (WARN_ON(!l2cache_base))
                 return -ENOMEM;
 
-        /*
-         * 16-way associativity, parity disabled
-         * Way size - 32KB (es1.0)
-         * Way size - 64KB (es2.0 +)
-         */
-        aux_ctrl = ((1 << L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT) |
-                        (0x1 << 25) |
-                        (0x1 << L2X0_AUX_CTRL_NS_LOCKDOWN_SHIFT) |
-                        (0x1 << L2X0_AUX_CTRL_NS_INT_CTRL_SHIFT));
-
-        if (omap_rev() == OMAP4430_REV_ES1_0) {
-                aux_ctrl |= 0x2 << L2X0_AUX_CTRL_WAY_SIZE_SHIFT;
-        } else {
-                aux_ctrl |= ((0x3 << L2X0_AUX_CTRL_WAY_SIZE_SHIFT) |
-                        (1 << L2X0_AUX_CTRL_SHARE_OVERRIDE_SHIFT) |
-                        (1 << L2X0_AUX_CTRL_DATA_PREFETCH_SHIFT) |
-                        (1 << L2X0_AUX_CTRL_INSTR_PREFETCH_SHIFT) |
-                        (1 << L2X0_AUX_CTRL_EARLY_BRESP_SHIFT));
-        }
-        if (omap_rev() != OMAP4430_REV_ES1_0)
-                omap_smc1(0x109, aux_ctrl);
-
-        /* Enable PL310 L2 Cache controller */
-        omap_smc1(0x102, 0x1);
+        /* 16-way associativity, parity disabled, way size - 64KB (es2.0 +) */
+        aux_ctrl = L2C_AUX_CTRL_SHARED_OVERRIDE |
+                   L310_AUX_CTRL_DATA_PREFETCH |
+                   L310_AUX_CTRL_INSTR_PREFETCH;
 
+        outer_cache.write_sec = omap4_l2c310_write_sec;
         if (of_have_populated_dt())
-                l2x0_of_init(aux_ctrl, L2X0_AUX_CTRL_MASK);
+                l2x0_of_init(aux_ctrl, 0xcf9fffff);
         else
-                l2x0_init(l2cache_base, aux_ctrl, L2X0_AUX_CTRL_MASK);
-
-        /*
-         * Override default outer_cache.disable with a OMAP4
-         * specific one
-        */
-        outer_cache.disable = omap4_l2x0_disable;
-        outer_cache.set_debug = omap4_l2x0_set_debug;
+                l2x0_init(l2cache_base, aux_ctrl, 0xcf9fffff);
 
         return 0;
 }
-omap_early_initcall(omap_l2_cache_init);
 #endif
 
 void __iomem *omap4_get_sar_ram_base(void)
diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c
index 3f1de1111e0f..6bbb7b55c6d1 100644
--- a/arch/arm/mach-orion5x/common.c
+++ b/arch/arm/mach-orion5x/common.c
@@ -365,8 +365,7 @@ void orion5x_restart(enum reboot_mode mode, const char *cmd)
  * Many orion-based systems have buggy bootloader implementations.
  * This is a common fixup for bogus memory tags.
  */
-void __init tag_fixup_mem32(struct tag *t, char **from,
-                            struct meminfo *meminfo)
+void __init tag_fixup_mem32(struct tag *t, char **from)
 {
         for (; t->hdr.size; t = tag_next(t))
                 if (t->hdr.tag == ATAG_MEM &&
diff --git a/arch/arm/mach-orion5x/common.h b/arch/arm/mach-orion5x/common.h
index 7548db2bfb8a..ca3803017c59 100644
--- a/arch/arm/mach-orion5x/common.h
+++ b/arch/arm/mach-orion5x/common.h
@@ -71,9 +71,8 @@ void edmini_v2_init(void);
 static inline void edmini_v2_init(void) {};
 #endif
 
-struct meminfo;
 struct tag;
-extern void __init tag_fixup_mem32(struct tag *, char **, struct meminfo *);
+extern void __init tag_fixup_mem32(struct tag *, char **);
 
 /*****************************************************************************
  * Helpers to access Orion registers
diff --git a/arch/arm/mach-prima2/Makefile b/arch/arm/mach-prima2/Makefile
index 7a6b4a323125..8846e7d87ea5 100644
--- a/arch/arm/mach-prima2/Makefile
+++ b/arch/arm/mach-prima2/Makefile
@@ -2,7 +2,6 @@ obj-y += rstc.o
 obj-y += common.o
 obj-y += rtciobrg.o
 obj-$(CONFIG_DEBUG_LL) += lluart.o
-obj-$(CONFIG_CACHE_L2X0) += l2x0.o
 obj-$(CONFIG_SUSPEND) += pm.o sleep.o
 obj-$(CONFIG_SMP) += platsmp.o headsmp.o
 obj-$(CONFIG_HOTPLUG_CPU)  += hotplug.o
diff --git a/arch/arm/mach-prima2/common.c b/arch/arm/mach-prima2/common.c
index 47c7819edb9b..a860ea27e8ae 100644
--- a/arch/arm/mach-prima2/common.c
+++ b/arch/arm/mach-prima2/common.c
@@ -34,6 +34,8 @@ static const char *atlas6_dt_match[] __initconst = {
 
 DT_MACHINE_START(ATLAS6_DT, "Generic ATLAS6 (Flattened Device Tree)")
         /* Maintainer: Barry Song <baohua.song@csr.com> */
+        .l2c_aux_val    = 0,
+        .l2c_aux_mask   = ~0,
         .map_io         = sirfsoc_map_io,
         .init_late      = sirfsoc_init_late,
         .dt_compat      = atlas6_dt_match,
@@ -48,6 +50,8 @@ static const char *prima2_dt_match[] __initconst = {
 
 DT_MACHINE_START(PRIMA2_DT, "Generic PRIMA2 (Flattened Device Tree)")
         /* Maintainer: Barry Song <baohua.song@csr.com> */
+        .l2c_aux_val    = 0,
+        .l2c_aux_mask   = ~0,
         .map_io         = sirfsoc_map_io,
         .dma_zone_size  = SZ_256M,
         .init_late      = sirfsoc_init_late,
@@ -63,6 +67,8 @@ static const char *marco_dt_match[] __initconst = {
 
 DT_MACHINE_START(MARCO_DT, "Generic MARCO (Flattened Device Tree)")
         /* Maintainer: Barry Song <baohua.song@csr.com> */
+        .l2c_aux_val    = 0,
+        .l2c_aux_mask   = ~0,
         .smp            = smp_ops(sirfsoc_smp_ops),
         .map_io         = sirfsoc_map_io,
         .init_late      = sirfsoc_init_late,
diff --git a/arch/arm/mach-prima2/l2x0.c b/arch/arm/mach-prima2/l2x0.c
deleted file mode 100644
index c7102539c0b0..000000000000
--- a/arch/arm/mach-prima2/l2x0.c
+++ /dev/null
@@ -1,49 +0,0 @@
-/*
- * l2 cache initialization for CSR SiRFprimaII
- *
- * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company.
- *
- * Licensed under GPLv2 or later.
- */
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <asm/hardware/cache-l2x0.h>
-
-struct l2x0_aux {
-        u32 val;
-        u32 mask;
-};
-
-static const struct l2x0_aux prima2_l2x0_aux __initconst = {
-        .val = 2 << L2X0_AUX_CTRL_WAY_SIZE_SHIFT,
-        .mask = 0,
-};
-
-static const struct l2x0_aux marco_l2x0_aux __initconst = {
-        .val = (2 << L2X0_AUX_CTRL_WAY_SIZE_SHIFT) |
-                (1 << L2X0_AUX_CTRL_ASSOCIATIVITY_SHIFT),
-        .mask = L2X0_AUX_CTRL_MASK,
-};
-
-static const struct of_device_id sirf_l2x0_ids[] __initconst = {
-        { .compatible = "sirf,prima2-pl310-cache", .data = &prima2_l2x0_aux, },
-        { .compatible = "sirf,marco-pl310-cache", .data = &marco_l2x0_aux, },
-        {},
-};
-
-static int __init sirfsoc_l2x0_init(void)
-{
-        struct device_node *np;
-        const struct l2x0_aux *aux;
-
-        np = of_find_matching_node(NULL, sirf_l2x0_ids);
-        if (np) {
-                aux = of_match_node(sirf_l2x0_ids, np)->data;
-                return l2x0_of_init(aux->val, aux->mask);
-        }
-
-        return 0;
-}
-early_initcall(sirfsoc_l2x0_init);
diff --git a/arch/arm/mach-prima2/pm.c b/arch/arm/mach-prima2/pm.c
index c4525a88e5da..96e9bc102117 100644
--- a/arch/arm/mach-prima2/pm.c
+++ b/arch/arm/mach-prima2/pm.c
@@ -71,7 +71,6 @@ static int sirfsoc_pm_enter(suspend_state_t state)
         case PM_SUSPEND_MEM:
                 sirfsoc_pre_suspend_power_off();
 
-                outer_flush_all();
                 outer_disable();
                 /* go zzz */
                 cpu_suspend(0, sirfsoc_finish_suspend);
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index 584439bfa59f..4d3588d26c2a 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -837,8 +837,7 @@ static void __init cm_x300_init(void)
         cm_x300_init_bl();
 }
 
-static void __init cm_x300_fixup(struct tag *tags, char **cmdline,
-                                 struct meminfo *mi)
+static void __init cm_x300_fixup(struct tag *tags, char **cmdline)
 {
         /* Make sure that mi->bank[0].start = PHYS_ADDR */
         for (; tags->hdr.size; tags = tag_next(tags))
diff --git a/arch/arm/mach-pxa/corgi.c b/arch/arm/mach-pxa/corgi.c
index 57d60542f982..91dd1c7cdbcd 100644
--- a/arch/arm/mach-pxa/corgi.c
+++ b/arch/arm/mach-pxa/corgi.c
@@ -34,6 +34,7 @@
 #include <linux/input/matrix_keypad.h>
 #include <linux/gpio_keys.h>
 #include <linux/module.h>
+#include <linux/memblock.h>
 #include <video/w100fb.h>
 
 #include <asm/setup.h>
@@ -753,16 +754,13 @@ static void __init corgi_init(void)
         platform_add_devices(devices, ARRAY_SIZE(devices));
 }
 
-static void __init fixup_corgi(struct tag *tags, char **cmdline,
-                               struct meminfo *mi)
+static void __init fixup_corgi(struct tag *tags, char **cmdline)
 {
         sharpsl_save_param();
-        mi->nr_banks=1;
-        mi->bank[0].start = 0xa0000000;
         if (machine_is_corgi())
-                mi->bank[0].size = (32*1024*1024);
+                memblock_add(0xa0000000, SZ_32M);
         else
-                mi->bank[0].size = (64*1024*1024);
+                memblock_add(0xa0000000, SZ_64M);
 }
 
 #ifdef CONFIG_MACH_CORGI
diff --git a/arch/arm/mach-pxa/eseries.c b/arch/arm/mach-pxa/eseries.c
index 8280ebcaab9f..cfb864173ce3 100644
--- a/arch/arm/mach-pxa/eseries.c
+++ b/arch/arm/mach-pxa/eseries.c
@@ -21,6 +21,7 @@
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
 #include <linux/usb/gpio_vbus.h>
+#include <linux/memblock.h>
 
 #include <video/w100fb.h>
 
@@ -41,14 +42,12 @@
 #include "clock.h"
 
 /* Only e800 has 128MB RAM */
-void __init eseries_fixup(struct tag *tags, char **cmdline, struct meminfo *mi)
+void __init eseries_fixup(struct tag *tags, char **cmdline)
 {
-        mi->nr_banks=1;
-        mi->bank[0].start = 0xa0000000;
         if (machine_is_e800())
-                mi->bank[0].size = (128*1024*1024);
+                memblock_add(0xa0000000, SZ_128M);
         else
-                mi->bank[0].size = (64*1024*1024);
+                memblock_add(0xa0000000, SZ_64M);
 }
 
 struct gpio_vbus_mach_info e7xx_udc_info = {
diff --git a/arch/arm/mach-pxa/poodle.c b/arch/arm/mach-pxa/poodle.c
index aedf053a1de5..131991629116 100644
--- a/arch/arm/mach-pxa/poodle.c
+++ b/arch/arm/mach-pxa/poodle.c
@@ -29,6 +29,7 @@
 #include <linux/spi/ads7846.h>
 #include <linux/spi/pxa2xx_spi.h>
 #include <linux/mtd/sharpsl.h>
+#include <linux/memblock.h>
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
@@ -456,13 +457,10 @@ static void __init poodle_init(void)
         poodle_init_spi();
 }
 
-static void __init fixup_poodle(struct tag *tags, char **cmdline,
-                                struct meminfo *mi)
+static void __init fixup_poodle(struct tag *tags, char **cmdline)
 {
         sharpsl_save_param();
-        mi->nr_banks=1;
-        mi->bank[0].start = 0xa0000000;
-        mi->bank[0].size = (32*1024*1024);
+        memblock_add(0xa0000000, SZ_32M);
 }
 
 MACHINE_START(POODLE, "SHARP Poodle")
diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
index 0b11c1af51c4..840c3a48e720 100644
--- a/arch/arm/mach-pxa/spitz.c
+++ b/arch/arm/mach-pxa/spitz.c
@@ -32,6 +32,7 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/reboot.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/mach-types.h>
@@ -971,13 +972,10 @@ static void __init spitz_init(void)
         spitz_i2c_init();
 }
 
-static void __init spitz_fixup(struct tag *tags, char **cmdline,
-                               struct meminfo *mi)
+static void __init spitz_fixup(struct tag *tags, char **cmdline)
 {
         sharpsl_save_param();
-        mi->nr_banks = 1;
-        mi->bank[0].start = 0xa0000000;
-        mi->bank[0].size = (64*1024*1024);
+        memblock_add(0xa0000000, SZ_64M);
 }
 
 #ifdef CONFIG_MACH_SPITZ
diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index ef5557b807ed..c158a6e3e0aa 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -37,6 +37,7 @@
 #include <linux/i2c/pxa-i2c.h>
 #include <linux/usb/gpio_vbus.h>
 #include <linux/reboot.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/mach-types.h>
@@ -960,13 +961,10 @@ static void __init tosa_init(void)
         platform_add_devices(devices, ARRAY_SIZE(devices));
 }
 
-static void __init fixup_tosa(struct tag *tags, char **cmdline,
-                              struct meminfo *mi)
+static void __init fixup_tosa(struct tag *tags, char **cmdline)
 {
         sharpsl_save_param();
-        mi->nr_banks=1;
-        mi->bank[0].start = 0xa0000000;
-        mi->bank[0].size = (64*1024*1024);
+        memblock_add(0xa0000000, SZ_64M);
 }
 
 MACHINE_START(TOSA, "SHARP Tosa")
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index 1d5ee5c9a1dc..c2fae3a5aad8 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -31,6 +31,7 @@
 #include <linux/amba/mmci.h>
 #include <linux/gfp.h>
 #include <linux/mtd/physmap.h>
+#include <linux/memblock.h>
 
 #include <mach/hardware.h>
 #include <asm/irq.h>
@@ -370,19 +371,15 @@ void __init realview_timer_init(unsigned int timer_irq)
 /*
  * Setup the memory banks.
  */
-void realview_fixup(struct tag *tags, char **from, struct meminfo *meminfo)
+void realview_fixup(struct tag *tags, char **from)
 {
         /*
          * Most RealView platforms have 512MB contiguous RAM at 0x70000000.
          * Half of this is mirrored at 0.
          */
 #ifdef CONFIG_REALVIEW_HIGH_PHYS_OFFSET
-        meminfo->bank[0].start = 0x70000000;
-        meminfo->bank[0].size = SZ_512M;
-        meminfo->nr_banks = 1;
+        memblock_add(0x70000000, SZ_512M);
 #else
-        meminfo->bank[0].start = 0;
-        meminfo->bank[0].size = SZ_256M;
-        meminfo->nr_banks = 1;
+        memblock_add(0, SZ_256M);
 #endif
 }
diff --git a/arch/arm/mach-realview/core.h b/arch/arm/mach-realview/core.h
index 602ca5ec52c5..844946da3c66 100644
--- a/arch/arm/mach-realview/core.h
+++ b/arch/arm/mach-realview/core.h
@@ -51,8 +51,7 @@ extern int realview_flash_register(struct resource *res, u32 num);
 extern int realview_eth_register(const char *name, struct resource *res);
 extern int realview_usb_register(struct resource *res);
 extern void realview_init_early(void);
-extern void realview_fixup(struct tag *tags, char **from,
-                           struct meminfo *meminfo);
+extern void realview_fixup(struct tag *tags, char **from);
 
 extern struct smp_operations realview_smp_ops;
 extern void realview_cpu_die(unsigned int cpu);
diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c
index c85ddb2a0ad0..b575895037b8 100644
--- a/arch/arm/mach-realview/realview_eb.c
+++ b/arch/arm/mach-realview/realview_eb.c
@@ -442,8 +442,13 @@ static void __init realview_eb_init(void)
                 realview_eb11mp_fixup();
 
 #ifdef CONFIG_CACHE_L2X0
-                /* 1MB (128KB/way), 8-way associativity, evmon/parity/share enabled
-                 * Bits:  .... ...0 0111 1001 0000 .... .... .... */
+                /*
+                 * The PL220 needs to be manually configured as the hardware
+                 * doesn't report the correct sizes.
+                 * 1MB (128KB/way), 8-way associativity, event monitor and
+                 * parity enabled, ignore share bit, no force write allocate
+                 * Bits:  .... ...0 0111 1001 0000 .... .... ....
+                 */
                 l2x0_init(__io_address(REALVIEW_EB11MP_L220_BASE), 0x00790000, 0xfe000fff);
 #endif
                 platform_device_register(&pmu_device);
diff --git a/arch/arm/mach-realview/realview_pb1176.c b/arch/arm/mach-realview/realview_pb1176.c
index c5eade76461b..aad9c5a40d47 100644
--- a/arch/arm/mach-realview/realview_pb1176.c
+++ b/arch/arm/mach-realview/realview_pb1176.c
@@ -32,6 +32,7 @@
 #include <linux/irqchip/arm-gic.h>
 #include <linux/platform_data/clk-realview.h>
 #include <linux/reboot.h>
+#include <linux/memblock.h>
 
 #include <mach/hardware.h>
 #include <asm/irq.h>
@@ -339,15 +340,12 @@ static void realview_pb1176_restart(enum reboot_mode mode, const char *cmd)
         dsb();
 }
 
-static void realview_pb1176_fixup(struct tag *tags, char **from,
-                                  struct meminfo *meminfo)
+static void realview_pb1176_fixup(struct tag *tags, char **from)
 {
         /*
          * RealView PB1176 only has 128MB of RAM mapped at 0.
          */
-        meminfo->bank[0].start = 0;
-        meminfo->bank[0].size = SZ_128M;
-        meminfo->nr_banks = 1;
+        memblock_add(0, SZ_128M);
 }
 
 static void __init realview_pb1176_init(void)
@@ -355,7 +353,13 @@ static void __init realview_pb1176_init(void)
         int i;
 
 #ifdef CONFIG_CACHE_L2X0
-        /* 128Kb (16Kb/way) 8-way associativity. evmon/parity/share enabled. */
+        /*
+         * The PL220 needs to be manually configured as the hardware
+         * doesn't report the correct sizes.
+         * 128kB (16kB/way), 8-way associativity, event monitor and
+         * parity enabled, ignore share bit, no force write allocate
+         * Bits:  .... ...0 0111 0011 0000 .... .... ....
+         */
         l2x0_init(__io_address(REALVIEW_PB1176_L220_BASE), 0x00730000, 0xfe000fff);
 #endif
 
diff --git a/arch/arm/mach-realview/realview_pb11mp.c b/arch/arm/mach-realview/realview_pb11mp.c
index f4b0962578fe..101deaf2630b 100644
--- a/arch/arm/mach-realview/realview_pb11mp.c
+++ b/arch/arm/mach-realview/realview_pb11mp.c
@@ -337,8 +337,13 @@ static void __init realview_pb11mp_init(void)
         int i;
 
 #ifdef CONFIG_CACHE_L2X0
-        /* 1MB (128KB/way), 8-way associativity, evmon/parity/share enabled
-         * Bits:  .... ...0 0111 1001 0000 .... .... .... */
+        /*
+         * The PL220 needs to be manually configured as the hardware
+         * doesn't report the correct sizes.
+         * 1MB (128KB/way), 8-way associativity, event monitor and
+         * parity enabled, ignore share bit, no force write allocate
+         * Bits:  .... ...0 0111 1001 0000 .... .... ....
+         */
         l2x0_init(__io_address(REALVIEW_TC11MP_L220_BASE), 0x00790000, 0xfe000fff);
 #endif
 
diff --git a/arch/arm/mach-realview/realview_pbx.c b/arch/arm/mach-realview/realview_pbx.c
index 9d75493e3f0c..535697abfd91 100644
--- a/arch/arm/mach-realview/realview_pbx.c
+++ b/arch/arm/mach-realview/realview_pbx.c
@@ -29,6 +29,7 @@
 #include <linux/irqchip/arm-gic.h>
 #include <linux/platform_data/clk-realview.h>
 #include <linux/reboot.h>
+#include <linux/memblock.h>
 
 #include <asm/irq.h>
 #include <asm/mach-types.h>
@@ -325,23 +326,19 @@ static void __init realview_pbx_timer_init(void)
         realview_pbx_twd_init();
 }
 
-static void realview_pbx_fixup(struct tag *tags, char **from,
-                               struct meminfo *meminfo)
+static void realview_pbx_fixup(struct tag *tags, char **from)
 {
 #ifdef CONFIG_SPARSEMEM
         /*
          * Memory configuration with SPARSEMEM enabled on RealView PBX (see
          * asm/mach/memory.h for more information).
          */
-        meminfo->bank[0].start = 0;
-        meminfo->bank[0].size = SZ_256M;
-        meminfo->bank[1].start = 0x20000000;
-        meminfo->bank[1].size = SZ_512M;
-        meminfo->bank[2].start = 0x80000000;
-        meminfo->bank[2].size = SZ_256M;
-        meminfo->nr_banks = 3;
+
+        memblock_add(0, SZ_256M);
+        memblock_add(0x20000000, SZ_512M);
+        memblock_add(0x80000000, SZ_256M);
 #else
-        realview_fixup(tags, from, meminfo);
+        realview_fixup(tags, from);
 #endif
 }
 
@@ -370,8 +367,8 @@ static void __init realview_pbx_init(void)
                         __io_address(REALVIEW_PBX_TILE_L220_BASE);
 
                 /* set RAM latencies to 1 cycle for eASIC */
-                writel(0, l2x0_base + L2X0_TAG_LATENCY_CTRL);
-                writel(0, l2x0_base + L2X0_DATA_LATENCY_CTRL);
+                writel(0, l2x0_base + L310_TAG_LATENCY_CTRL);
+                writel(0, l2x0_base + L310_DATA_LATENCY_CTRL);
 
                 /* 16KB way size, 8-way associativity, parity disabled
                  * Bits:  .. 0 0 0 0 1 00 1 0 1 001 0 000 0 .... .... .... */
diff --git a/arch/arm/mach-rockchip/rockchip.c b/arch/arm/mach-rockchip/rockchip.c
index d211d6fa0d98..138b9975313a 100644
--- a/arch/arm/mach-rockchip/rockchip.c
+++ b/arch/arm/mach-rockchip/rockchip.c
@@ -24,12 +24,6 @@
 #include <asm/hardware/cache-l2x0.h>
 #include "core.h"
 
-static void __init rockchip_dt_init(void)
-{
-        l2x0_of_init(0, ~0UL);
-        of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-}
-
 static const char * const rockchip_board_dt_compat[] = {
         "rockchip,rk2928",
         "rockchip,rk3066a",
@@ -39,7 +33,8 @@ static const char * const rockchip_board_dt_compat[] = {
 };
 
 DT_MACHINE_START(ROCKCHIP_DT, "Rockchip Cortex-A9 (Device Tree)")
+        .l2c_aux_val    = 0,
+        .l2c_aux_mask   = ~0,
         .smp            = smp_ops(rockchip_smp_ops),
-        .init_machine   = rockchip_dt_init,
         .dt_compat      = rockchip_board_dt_compat,
 MACHINE_END
diff --git a/arch/arm/mach-s3c24xx/mach-smdk2413.c b/arch/arm/mach-s3c24xx/mach-smdk2413.c
index 233fe52d2015..a03c855ee854 100644
--- a/arch/arm/mach-s3c24xx/mach-smdk2413.c
+++ b/arch/arm/mach-s3c24xx/mach-smdk2413.c
@@ -22,6 +22,7 @@
 #include <linux/serial_s3c.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
+#include <linux/memblock.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -93,13 +94,10 @@ static struct platform_device *smdk2413_devices[] __initdata = {
         &s3c2412_device_dma,
 };
 
-static void __init smdk2413_fixup(struct tag *tags, char **cmdline,
-                                  struct meminfo *mi)
+static void __init smdk2413_fixup(struct tag *tags, char **cmdline)
 {
         if (tags != phys_to_virt(S3C2410_SDRAM_PA + 0x100)) {
-                mi->nr_banks=1;
-                mi->bank[0].start = 0x30000000;
-                mi->bank[0].size = SZ_64M;
+                memblock_add(0x30000000, SZ_64M);
         }
 }
 
diff --git a/arch/arm/mach-s3c24xx/mach-vstms.c b/arch/arm/mach-s3c24xx/mach-vstms.c
index 40868c0e0a68..a79af7843aed 100644
--- a/arch/arm/mach-s3c24xx/mach-vstms.c
+++ b/arch/arm/mach-s3c24xx/mach-vstms.c
@@ -23,6 +23,7 @@
 #include <linux/mtd/nand.h>
 #include <linux/mtd/nand_ecc.h>
 #include <linux/mtd/partitions.h>
+#include <linux/memblock.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -129,13 +130,10 @@ static struct platform_device *vstms_devices[] __initdata = {
         &s3c2412_device_dma,
 };
 
-static void __init vstms_fixup(struct tag *tags, char **cmdline,
-                               struct meminfo *mi)
+static void __init vstms_fixup(struct tag *tags, char **cmdline)
 {
         if (tags != phys_to_virt(S3C2410_SDRAM_PA + 0x100)) {
-                mi->nr_banks=1;
-                mi->bank[0].start = 0x30000000;
-                mi->bank[0].size = SZ_64M;
+                memblock_add(0x30000000, SZ_64M);
         }
 }
 
diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index 8443a27bca2f..7dd894ece9ae 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -531,7 +531,7 @@ static void __init get_assabet_scr(void)
 }
 
 static void __init
-fixup_assabet(struct tag *tags, char **cmdline, struct meminfo *mi)
+fixup_assabet(struct tag *tags, char **cmdline)
 {
         /* This must be done before any call to machine_has_neponset() */
         map_sa1100_gpio_regs();
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva-reference.c b/arch/arm/mach-shmobile/board-armadillo800eva-reference.c
index 57d1a78367b6..39e11f48e8bc 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva-reference.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva-reference.c
@@ -164,8 +164,8 @@ static void __init eva_init(void)
         r8a7740_meram_workaround();
 
 #ifdef CONFIG_CACHE_L2X0
-        /* Early BRESP enable, Shared attribute override enable, 32K*8way */
-        l2x0_init(IOMEM(0xf0002000), 0x40440000, 0x82000fff);
+        /* Shared attribute override enable, 32K*8way */
+        l2x0_init(IOMEM(0xf0002000), 0x00400000, 0xc20f0fff);
 #endif
 
         r8a7740_add_standard_devices_dt();
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index 486063db2a2f..f8e25fd29b79 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -1271,8 +1271,8 @@ static void __init eva_init(void)
 
 
 #ifdef CONFIG_CACHE_L2X0
-        /* Early BRESP enable, Shared attribute override enable, 32K*8way */
-        l2x0_init(IOMEM(0xf0002000), 0x40440000, 0x82000fff);
+        /* Shared attribute override enable, 32K*8way */
+        l2x0_init(IOMEM(0xf0002000), 0x00400000, 0xc20f0fff);
 #endif
 
         i2c_register_board_info(0, i2c0_devices, ARRAY_SIZE(i2c0_devices));
diff --git a/arch/arm/mach-shmobile/board-kzm9g-reference.c b/arch/arm/mach-shmobile/board-kzm9g-reference.c
index 598e32488410..a735a1d80c28 100644
--- a/arch/arm/mach-shmobile/board-kzm9g-reference.c
+++ b/arch/arm/mach-shmobile/board-kzm9g-reference.c
@@ -36,8 +36,8 @@ static void __init kzm_init(void)
         sh73a0_add_standard_devices_dt();
 
 #ifdef CONFIG_CACHE_L2X0
-        /* Early BRESP enable, Shared attribute override enable, 64K*8way */
-        l2x0_init(IOMEM(0xf0100000), 0x40460000, 0x82000fff);
+        /* Shared attribute override enable, 64K*8way */
+        l2x0_init(IOMEM(0xf0100000), 0x00400000, 0xc20f0fff);
 #endif
 }
 
diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c
index 03dc3ac84502..f94ec8ca42c1 100644
--- a/arch/arm/mach-shmobile/board-kzm9g.c
+++ b/arch/arm/mach-shmobile/board-kzm9g.c
@@ -876,8 +876,8 @@ static void __init kzm_init(void)
         gpio_request_one(223, GPIOF_IN, NULL); /* IRQ8 */
 
 #ifdef CONFIG_CACHE_L2X0
-        /* Early BRESP enable, Shared attribute override enable, 64K*8way */
-        l2x0_init(IOMEM(0xf0100000), 0x40460000, 0x82000fff);
+        /* Shared attribute override enable, 64K*8way */
+        l2x0_init(IOMEM(0xf0100000), 0x00400000, 0xc20f0fff);
 #endif
 
         i2c_register_board_info(0, i2c0_devices, ARRAY_SIZE(i2c0_devices));
diff --git a/arch/arm/mach-shmobile/setup-r8a7778.c b/arch/arm/mach-shmobile/setup-r8a7778.c
index 6d694526e4ca..6dd7ddf88741 100644
--- a/arch/arm/mach-shmobile/setup-r8a7778.c
+++ b/arch/arm/mach-shmobile/setup-r8a7778.c
@@ -298,10 +298,10 @@ void __init r8a7778_add_dt_devices(void)
         void __iomem *base = ioremap_nocache(0xf0100000, 0x1000);
         if (base) {
                 /*
-                 * Early BRESP enable, Shared attribute override enable, 64K*16way
+                 * Shared attribute override enable, 64K*16way
                  * don't call iounmap(base)
                  */
-                l2x0_init(base, 0x40470000, 0x82000fff);
+                l2x0_init(base, 0x00400000, 0xc20f0fff);
         }
 #endif
 
diff --git a/arch/arm/mach-shmobile/setup-r8a7779.c b/arch/arm/mach-shmobile/setup-r8a7779.c
index 8e860b36997a..a6630fccfc45 100644
--- a/arch/arm/mach-shmobile/setup-r8a7779.c
+++ b/arch/arm/mach-shmobile/setup-r8a7779.c
@@ -700,8 +700,8 @@ static struct platform_device *r8a7779_standard_devices[] __initdata = {
 void __init r8a7779_add_standard_devices(void)
 {
 #ifdef CONFIG_CACHE_L2X0
-        /* Early BRESP enable, Shared attribute override enable, 64K*16way */
-        l2x0_init(IOMEM(0xf0100000), 0x40470000, 0x82000fff);
+        /* Shared attribute override enable, 64K*16way */
+        l2x0_init(IOMEM(0xf0100000), 0x00400000, 0xc20f0fff);
 #endif
         r8a7779_pm_init();
 
diff --git a/arch/arm/mach-socfpga/socfpga.c b/arch/arm/mach-socfpga/socfpga.c
index d86231e11b34..adbf38314ca8 100644
--- a/arch/arm/mach-socfpga/socfpga.c
+++ b/arch/arm/mach-socfpga/socfpga.c
@@ -98,22 +98,17 @@ static void socfpga_cyclone5_restart(enum reboot_mode mode, const char *cmd)
         writel(temp, rst_manager_base_addr + SOCFPGA_RSTMGR_CTRL);
 }
 
-static void __init socfpga_cyclone5_init(void)
-{
-        l2x0_of_init(0, ~0UL);
-        of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-}
-
 static const char *altera_dt_match[] = {
         "altr,socfpga",
         NULL
 };
 
 DT_MACHINE_START(SOCFPGA, "Altera SOCFPGA")
+        .l2c_aux_val    = 0,
+        .l2c_aux_mask   = ~0,
         .smp            = smp_ops(socfpga_smp_ops),
         .map_io         = socfpga_map_io,
         .init_irq       = socfpga_init_irq,
-        .init_machine   = socfpga_cyclone5_init,
         .restart        = socfpga_cyclone5_restart,
         .dt_compat      = altera_dt_match,
 MACHINE_END
diff --git a/arch/arm/mach-spear/platsmp.c b/arch/arm/mach-spear/platsmp.c
index c19751fff2c6..fd4297713d67 100644
--- a/arch/arm/mach-spear/platsmp.c
+++ b/arch/arm/mach-spear/platsmp.c
@@ -20,6 +20,18 @@
 #include <mach/spear.h>
 #include "generic.h"
 
+/*
+ * Write pen_release in a way that is guaranteed to be visible to all
+ * observers, irrespective of whether they're taking part in coherency
+ * or not.  This is necessary for the hotplug code to work reliably.
+ */
+static void write_pen_release(int val)
+{
+        pen_release = val;
+        smp_wmb();
+        sync_cache_w(&pen_release);
+}
+
 static DEFINE_SPINLOCK(boot_lock);
 
 static void __iomem *scu_base = IOMEM(VA_SCU_BASE);
@@ -30,8 +42,7 @@ static void spear13xx_secondary_init(unsigned int cpu)
          * let the primary processor know we're out of the
          * pen, then head off into the C entry point
          */
-        pen_release = -1;
-        smp_wmb();
+        write_pen_release(-1);
 
         /*
          * Synchronise with the boot thread.
@@ -58,9 +69,7 @@ static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle)
          * Note that "pen_release" is the hardware CPU ID, whereas
          * "cpu" is Linux's internal ID.
          */
-        pen_release = cpu;
-        flush_cache_all();
-        outer_flush_all();
+        write_pen_release(cpu);
 
         timeout = jiffies + (1 * HZ);
         while (time_before(jiffies, timeout)) {
diff --git a/arch/arm/mach-spear/spear13xx.c b/arch/arm/mach-spear/spear13xx.c
index 7aa6e8cf830f..c9897ea38980 100644
--- a/arch/arm/mach-spear/spear13xx.c
+++ b/arch/arm/mach-spear/spear13xx.c
@@ -38,15 +38,15 @@ void __init spear13xx_l2x0_init(void)
         if (!IS_ENABLED(CONFIG_CACHE_L2X0))
                 return;
 
-        writel_relaxed(0x06, VA_L2CC_BASE + L2X0_PREFETCH_CTRL);
+        writel_relaxed(0x06, VA_L2CC_BASE + L310_PREFETCH_CTRL);
 
         /*
          * Program following latencies in order to make
          * SPEAr1340 work at 600 MHz
          */
-        writel_relaxed(0x221, VA_L2CC_BASE + L2X0_TAG_LATENCY_CTRL);
-        writel_relaxed(0x441, VA_L2CC_BASE + L2X0_DATA_LATENCY_CTRL);
-        l2x0_init(VA_L2CC_BASE, 0x70A60001, 0xfe00ffff);
+        writel_relaxed(0x221, VA_L2CC_BASE + L310_TAG_LATENCY_CTRL);
+        writel_relaxed(0x441, VA_L2CC_BASE + L310_DATA_LATENCY_CTRL);
+        l2x0_init(VA_L2CC_BASE, 0x30a00001, 0xfe0fffff);
 }
 
 /*
diff --git a/arch/arm/mach-sti/board-dt.c b/arch/arm/mach-sti/board-dt.c
index 1217fb598cfd..910e978dfbc0 100644
--- a/arch/arm/mach-sti/board-dt.c
+++ b/arch/arm/mach-sti/board-dt.c
@@ -14,25 +14,6 @@
 
 #include "smp.h"
 
-void __init stih41x_l2x0_init(void)
-{
-        u32 way_size = 0x4;
-        u32 aux_ctrl;
-        /* may be this can be encoded in macros like BIT*() */
-        aux_ctrl = (0x1 << L2X0_AUX_CTRL_SHARE_OVERRIDE_SHIFT) |
-                (0x1 << L2X0_AUX_CTRL_DATA_PREFETCH_SHIFT) |
-                (0x1 << L2X0_AUX_CTRL_INSTR_PREFETCH_SHIFT) |
-                (way_size << L2X0_AUX_CTRL_WAY_SIZE_SHIFT);
-
-        l2x0_of_init(aux_ctrl, L2X0_AUX_CTRL_MASK);
-}
-
-static void __init stih41x_machine_init(void)
-{
-        stih41x_l2x0_init();
-        of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
-}
-
 static const char *stih41x_dt_match[] __initdata = {
         "st,stih415",
         "st,stih416",
@@ -40,7 +21,11 @@ static const char *stih41x_dt_match[] __initdata = {
 };
 
 DT_MACHINE_START(STM, "STiH415/416 SoC with Flattened Device Tree")
-        .init_machine   = stih41x_machine_init,
-        .smp            = smp_ops(sti_smp_ops),
         .dt_compat      = stih41x_dt_match,
+        .l2c_aux_val    = L2C_AUX_CTRL_SHARED_OVERRIDE |
+                          L310_AUX_CTRL_DATA_PREFETCH |
+                          L310_AUX_CTRL_INSTR_PREFETCH |
+                          L2C_AUX_CTRL_WAY_SIZE(4),
+        .l2c_aux_mask   = 0xc0000fff,
+        .smp            = smp_ops(sti_smp_ops),
 MACHINE_END
diff --git a/arch/arm/mach-tegra/pm.h b/arch/arm/mach-tegra/pm.h
index 6e92a7c2ecbd..f4a89698e5b0 100644
--- a/arch/arm/mach-tegra/pm.h
+++ b/arch/arm/mach-tegra/pm.h
@@ -35,8 +35,6 @@ void tegra20_sleep_core_init(void);
 void tegra30_lp1_iram_hook(void);
 void tegra30_sleep_core_init(void);
 
-extern unsigned long l2x0_saved_regs_addr;
-
 void tegra_clear_cpu_in_lp2(void);
 bool tegra_set_cpu_in_lp2(void);
 
diff --git a/arch/arm/mach-tegra/reset-handler.S b/arch/arm/mach-tegra/reset-handler.S
index 8c1ba4fea384..578d4d1ad648 100644
--- a/arch/arm/mach-tegra/reset-handler.S
+++ b/arch/arm/mach-tegra/reset-handler.S
@@ -19,7 +19,6 @@
 
 #include <asm/cache.h>
 #include <asm/asm-offsets.h>
-#include <asm/hardware/cache-l2x0.h>
 
 #include "flowctrl.h"
 #include "fuse.h"
@@ -78,8 +77,10 @@ ENTRY(tegra_resume)
         str     r1, [r0]
 #endif
 
+#ifdef CONFIG_CACHE_L2X0
         /* L2 cache resume & re-enable */
-        l2_cache_resume r0, r1, r2, l2x0_saved_regs_addr
+        bl      l2c310_early_resume
+#endif
 end_ca9_scu_l2_resume:
         mov32   r9, 0xc0f
         cmp     r8, r9
@@ -89,12 +90,6 @@ end_ca9_scu_l2_resume:
 ENDPROC(tegra_resume)
 #endif
 
-#ifdef CONFIG_CACHE_L2X0
-        .globl  l2x0_saved_regs_addr
-l2x0_saved_regs_addr:
-        .long   0
-#endif
-
         .align L1_CACHE_SHIFT
 ENTRY(__tegra_cpu_reset_handler_start)
 
diff --git a/arch/arm/mach-tegra/sleep.h b/arch/arm/mach-tegra/sleep.h
index a4edbb3abd3d..339fe42cd6fb 100644
--- a/arch/arm/mach-tegra/sleep.h
+++ b/arch/arm/mach-tegra/sleep.h
@@ -120,37 +120,6 @@
         mov     \tmp1, \tmp1, lsr #8
 .endm
 
-/* Macro to resume & re-enable L2 cache */
-#ifndef L2X0_CTRL_EN
-#define L2X0_CTRL_EN    1
-#endif
-
-#ifdef CONFIG_CACHE_L2X0
-.macro l2_cache_resume, tmp1, tmp2, tmp3, phys_l2x0_saved_regs
-        W(adr)  \tmp1, \phys_l2x0_saved_regs
-        ldr     \tmp1, [\tmp1]
-        ldr     \tmp2, [\tmp1, #L2X0_R_PHY_BASE]
-        ldr     \tmp3, [\tmp2, #L2X0_CTRL]
-        tst     \tmp3, #L2X0_CTRL_EN
-        bne     exit_l2_resume
-        ldr     \tmp3, [\tmp1, #L2X0_R_TAG_LATENCY]
-        str     \tmp3, [\tmp2, #L2X0_TAG_LATENCY_CTRL]
-        ldr     \tmp3, [\tmp1, #L2X0_R_DATA_LATENCY]
-        str     \tmp3, [\tmp2, #L2X0_DATA_LATENCY_CTRL]
-        ldr     \tmp3, [\tmp1, #L2X0_R_PREFETCH_CTRL]
-        str     \tmp3, [\tmp2, #L2X0_PREFETCH_CTRL]
-        ldr     \tmp3, [\tmp1, #L2X0_R_PWR_CTRL]
-        str     \tmp3, [\tmp2, #L2X0_POWER_CTRL]
-        ldr     \tmp3, [\tmp1, #L2X0_R_AUX_CTRL]
-        str     \tmp3, [\tmp2, #L2X0_AUX_CTRL]
-        mov     \tmp3, #L2X0_CTRL_EN
-        str     \tmp3, [\tmp2, #L2X0_CTRL]
-exit_l2_resume:
-.endm
-#else /* CONFIG_CACHE_L2X0 */
-.macro l2_cache_resume, tmp1, tmp2, tmp3, phys_l2x0_saved_regs
-.endm
-#endif /* CONFIG_CACHE_L2X0 */
 #else
 void tegra_pen_lock(void);
 void tegra_pen_unlock(void);
diff --git a/arch/arm/mach-tegra/tegra.c b/arch/arm/mach-tegra/tegra.c
index 6191603379e1..15ac9fcc96b1 100644
--- a/arch/arm/mach-tegra/tegra.c
+++ b/arch/arm/mach-tegra/tegra.c
@@ -70,40 +70,12 @@ u32 tegra_uart_config[3] = {
         0,
 };
 
-static void __init tegra_init_cache(void)
-{
-#ifdef CONFIG_CACHE_L2X0
-        static const struct of_device_id pl310_ids[] __initconst = {
-                { .compatible = "arm,pl310-cache",  },
-                {}
-        };
-
-        struct device_node *np;
-        int ret;
-        void __iomem *p = IO_ADDRESS(TEGRA_ARM_PERIF_BASE) + 0x3000;
-        u32 aux_ctrl, cache_type;
-
-        np = of_find_matching_node(NULL, pl310_ids);
-        if (!np)
-                return;
-
-        cache_type = readl(p + L2X0_CACHE_TYPE);
-        aux_ctrl = (cache_type & 0x700) << (17-8);
-        aux_ctrl |= 0x7C400001;
-
-        ret = l2x0_of_init(aux_ctrl, 0x8200c3fe);
-        if (!ret)
-                l2x0_saved_regs_addr = virt_to_phys(&l2x0_saved_regs);
-#endif
-}
-
 static void __init tegra_init_early(void)
 {
         of_register_trusted_foundations();
         tegra_apb_io_init();
         tegra_init_fuse();
         tegra_cpu_reset_handler_init();
-        tegra_init_cache();
         tegra_powergate_init();
         tegra_hotplug_init();
 }
@@ -191,8 +163,10 @@ static const char * const tegra_dt_board_compat[] = {
 };
 
 DT_MACHINE_START(TEGRA_DT, "NVIDIA Tegra SoC (Flattened Device Tree)")
-        .map_io         = tegra_map_common_io,
+        .l2c_aux_val    = 0x3c400001,
+        .l2c_aux_mask   = 0xc20fc3fe,
         .smp            = smp_ops(tegra_smp_ops),
+        .map_io         = tegra_map_common_io,
         .init_early     = tegra_init_early,
         .init_irq       = tegra_dt_init_irq,
         .init_machine   = tegra_dt_init,
diff --git a/arch/arm/mach-ux500/cache-l2x0.c b/arch/arm/mach-ux500/cache-l2x0.c
index 264f894c0e3d..842ebedbdd1c 100644
--- a/arch/arm/mach-ux500/cache-l2x0.c
+++ b/arch/arm/mach-ux500/cache-l2x0.c
@@ -35,10 +35,16 @@ static int __init ux500_l2x0_unlock(void)
         return 0;
 }
 
-static int __init ux500_l2x0_init(void)
+static void ux500_l2c310_write_sec(unsigned long val, unsigned reg)
 {
-        u32 aux_val = 0x3e000000;
+        /*
+         * We can't write to secure registers as we are in non-secure
+         * mode, until we have some SMI service available.
+         */
+}
 
+static int __init ux500_l2x0_init(void)
+{
         if (cpu_is_u8500_family() || cpu_is_ux540_family())
                 l2x0_base = __io_address(U8500_L2CC_BASE);
         else
@@ -48,28 +54,12 @@ static int __init ux500_l2x0_init(void)
         /* Unlock before init */
         ux500_l2x0_unlock();
 
-        /* DBx540's L2 has 128KB way size */
-        if (cpu_is_ux540_family())
-                /* 128KB way size */
-                aux_val |= (0x4 << L2X0_AUX_CTRL_WAY_SIZE_SHIFT);
-        else
-                /* 64KB way size */
-                aux_val |= (0x3 << L2X0_AUX_CTRL_WAY_SIZE_SHIFT);
+        outer_cache.write_sec = ux500_l2c310_write_sec;
 
-        /* 64KB way size, 8 way associativity, force WA */
         if (of_have_populated_dt())
-                l2x0_of_init(aux_val, 0xc0000fff);
+                l2x0_of_init(0, ~0);
         else
-                l2x0_init(l2x0_base, aux_val, 0xc0000fff);
-
-        /*
-         * We can't disable l2 as we are in non secure mode, currently
-         * this seems be called only during kexec path. So let's
-         * override outer.disable with nasty assignment until we have
-         * some SMI service available.
-         */
-        outer_cache.disable = NULL;
-        outer_cache.set_debug = NULL;
+                l2x0_init(l2x0_base, 0, ~0);
 
         return 0;
 }
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
index 6f34497a4245..204038ef3795 100644
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ b/arch/arm/mach-vexpress/ct-ca9x4.c
@@ -45,6 +45,23 @@ static void __init ct_ca9x4_map_io(void)
         iotable_init(ct_ca9x4_io_desc, ARRAY_SIZE(ct_ca9x4_io_desc));
 }
 
+static void __init ca9x4_l2_init(void)
+{
+#ifdef CONFIG_CACHE_L2X0
+        void __iomem *l2x0_base = ioremap(CT_CA9X4_L2CC, SZ_4K);
+
+        if (l2x0_base) {
+                /* set RAM latencies to 1 cycle for this core tile. */
+                writel(0, l2x0_base + L310_TAG_LATENCY_CTRL);
+                writel(0, l2x0_base + L310_DATA_LATENCY_CTRL);
+
+                l2x0_init(l2x0_base, 0x00400000, 0xfe0fffff);
+        } else {
+                pr_err("L2C: unable to map L2 cache controller\n");
+        }
+#endif
+}
+
 #ifdef CONFIG_HAVE_ARM_TWD
 static DEFINE_TWD_LOCAL_TIMER(twd_local_timer, A9_MPCORE_TWD, IRQ_LOCALTIMER);
 
@@ -63,6 +80,7 @@ static void __init ct_ca9x4_init_irq(void)
         gic_init(0, 29, ioremap(A9_MPCORE_GIC_DIST, SZ_4K),
                  ioremap(A9_MPCORE_GIC_CPU, SZ_256));
         ca9x4_twd_init();
+        ca9x4_l2_init();
 }
 
 static int ct_ca9x4_clcd_setup(struct clcd_fb *fb)
@@ -141,16 +159,6 @@ static void __init ct_ca9x4_init(void)
 {
         int i;
 
-#ifdef CONFIG_CACHE_L2X0
-        void __iomem *l2x0_base = ioremap(CT_CA9X4_L2CC, SZ_4K);
-
-        /* set RAM latencies to 1 cycle for this core tile. */
-        writel(0, l2x0_base + L2X0_TAG_LATENCY_CTRL);
-        writel(0, l2x0_base + L2X0_DATA_LATENCY_CTRL);
-
-        l2x0_init(l2x0_base, 0x00400000, 0xfe0fffff);
-#endif
-
         for (i = 0; i < ARRAY_SIZE(ct_ca9x4_amba_devs); i++)
                 amba_device_register(ct_ca9x4_amba_devs[i], &iomem_resource);
 
diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c
index 29e7785a54bc..b743a0ae02ce 100644
--- a/arch/arm/mach-vexpress/tc2_pm.c
+++ b/arch/arm/mach-vexpress/tc2_pm.c
@@ -209,7 +209,7 @@ static int tc2_core_in_reset(unsigned int cpu, unsigned int cluster)
 #define POLL_MSEC 10
 #define TIMEOUT_MSEC 1000
 
-static int tc2_pm_power_down_finish(unsigned int cpu, unsigned int cluster)
+static int tc2_pm_wait_for_powerdown(unsigned int cpu, unsigned int cluster)
 {
         unsigned tries;
 
@@ -290,7 +290,7 @@ static void tc2_pm_powered_up(void)
 static const struct mcpm_platform_ops tc2_pm_power_ops = {
         .power_up               = tc2_pm_power_up,
         .power_down             = tc2_pm_power_down,
-        .power_down_finish      = tc2_pm_power_down_finish,
+        .wait_for_powerdown     = tc2_pm_wait_for_powerdown,
         .suspend                = tc2_pm_suspend,
         .powered_up             = tc2_pm_powered_up,
 };
diff --git a/arch/arm/mach-vexpress/v2m.c b/arch/arm/mach-vexpress/v2m.c
index 4f8b8cb17ff5..b2fea70d412d 100644
--- a/arch/arm/mach-vexpress/v2m.c
+++ b/arch/arm/mach-vexpress/v2m.c
@@ -432,7 +432,6 @@ static const struct of_device_id v2m_dt_bus_match[] __initconst = {
 
 static void __init v2m_dt_init(void)
 {
-        l2x0_of_init(0x00400000, 0xfe0fffff);
         of_platform_populate(NULL, v2m_dt_bus_match, NULL, NULL);
 }
 
@@ -443,6 +442,8 @@ static const char * const v2m_dt_match[] __initconst = {
 
 DT_MACHINE_START(VEXPRESS_DT, "ARM-Versatile Express")
         .dt_compat      = v2m_dt_match,
+        .l2c_aux_val    = 0x00400000,
+        .l2c_aux_mask   = 0xfe0fffff,
         .smp            = smp_ops(vexpress_smp_ops),
         .smp_init       = smp_init_ops(vexpress_smp_init_ops),
         .map_io         = v2m_dt_map_io,
diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c
index 6fcc584c1a11..d1e992e6403e 100644
--- a/arch/arm/mach-zynq/common.c
+++ b/arch/arm/mach-zynq/common.c
@@ -67,11 +67,6 @@ static void __init zynq_init_machine(void)
 {
         struct platform_device_info devinfo = { .name = "cpufreq-cpu0", };
 
-        /*
-         * 64KB way size, 8-way associativity, parity disabled
-         */
-        l2x0_of_init(0x02060000, 0xF0F0FFFF);
-
         of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 
         platform_device_register(&zynq_cpuidle_device);
@@ -133,6 +128,9 @@ static const char * const zynq_dt_match[] = {
 };
 
 DT_MACHINE_START(XILINX_EP107, "Xilinx Zynq Platform")
+        /* 64KB way size, 8-way associativity, parity disabled */
+        .l2c_aux_val    = 0x02000000,
+        .l2c_aux_mask   = 0xf0ffffff,
         .smp            = smp_ops(zynq_smp_ops),
         .map_io         = zynq_map_io,
         .init_irq       = zynq_irq_init,
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 5bf7c3c3b301..eda0dd0ab97b 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -897,6 +897,57 @@ config CACHE_PL310
           This option enables optimisations for the PL310 cache
           controller.
 
+config PL310_ERRATA_588369
+        bool "PL310 errata: Clean & Invalidate maintenance operations do not invalidate clean lines"
+        depends on CACHE_L2X0
+        help
+           The PL310 L2 cache controller implements three types of Clean &
+           Invalidate maintenance operations: by Physical Address
+           (offset 0x7F0), by Index/Way (0x7F8) and by Way (0x7FC).
+           They are architecturally defined to behave as the execution of a
+           clean operation followed immediately by an invalidate operation,
+           both performing to the same memory location. This functionality
+           is not correctly implemented in PL310 as clean lines are not
+           invalidated as a result of these operations.
+
+config PL310_ERRATA_727915
+        bool "PL310 errata: Background Clean & Invalidate by Way operation can cause data corruption"
+        depends on CACHE_L2X0
+        help
+          PL310 implements the Clean & Invalidate by Way L2 cache maintenance
+          operation (offset 0x7FC). This operation runs in background so that
+          PL310 can handle normal accesses while it is in progress. Under very
+          rare circumstances, due to this erratum, write data can be lost when
+          PL310 treats a cacheable write transaction during a Clean &
+          Invalidate by Way operation.
+
+config PL310_ERRATA_753970
+        bool "PL310 errata: cache sync operation may be faulty"
+        depends on CACHE_PL310
+        help
+          This option enables the workaround for the 753970 PL310 (r3p0) erratum.
+
+          Under some condition the effect of cache sync operation on
+          the store buffer still remains when the operation completes.
+          This means that the store buffer is always asked to drain and
+          this prevents it from merging any further writes. The workaround
+          is to replace the normal offset of cache sync operation (0x730)
+          by another offset targeting an unmapped PL310 register 0x740.
+          This has the same effect as the cache sync operation: store buffer
+          drain and waiting for all buffers empty.
+
+config PL310_ERRATA_769419
+        bool "PL310 errata: no automatic Store Buffer drain"
+        depends on CACHE_L2X0
+        help
+          On revisions of the PL310 prior to r3p2, the Store Buffer does
+          not automatically drain. This can cause normal, non-cacheable
+          writes to be retained when the memory system is idle, leading
+          to suboptimal I/O performance for drivers using coherent DMA.
+          This option adds a write barrier to the cpu_idle loop so that,
+          on systems with an outer cache, the store buffer is drained
+          explicitly.
+
 config CACHE_TAUROS2
         bool "Enable the Tauros2 L2 cache controller"
         depends on (ARCH_DOVE || ARCH_MMP || CPU_PJ4)
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 7f39ce2f841f..91da64de440f 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -95,7 +95,8 @@ obj-$(CONFIG_CPU_V7M)		+= proc-v7m.o
 AFLAGS_proc-v6.o        :=-Wa,-march=armv6
 AFLAGS_proc-v7.o        :=-Wa,-march=armv7-a
 
+obj-$(CONFIG_OUTER_CACHE)       += l2c-common.o
 obj-$(CONFIG_CACHE_FEROCEON_L2) += cache-feroceon-l2.o
-obj-$(CONFIG_CACHE_L2X0)        += cache-l2x0.o
+obj-$(CONFIG_CACHE_L2X0)        += cache-l2x0.o l2c-l2x0-resume.o
 obj-$(CONFIG_CACHE_XSC3L2)      += cache-xsc3l2.o
 obj-$(CONFIG_CACHE_TAUROS2)     += cache-tauros2.o
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index dc814a548056..e028a7f2ebcc 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -350,7 +350,6 @@ void __init feroceon_l2_init(int __l2_wt_override)
         outer_cache.inv_range = feroceon_l2_inv_range;
         outer_cache.clean_range = feroceon_l2_clean_range;
         outer_cache.flush_range = feroceon_l2_flush_range;
-        outer_cache.inv_all = l2_inv_all;
 
         enable_l2();
 
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 7abde2ce8973..efc5cabf70e0 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -16,18 +16,33 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
+#include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/init.h>
+#include <linux/smp.h>
 #include <linux/spinlock.h>
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cp15.h>
+#include <asm/cputype.h>
 #include <asm/hardware/cache-l2x0.h>
 #include "cache-tauros3.h"
 #include "cache-aurora-l2.h"
 
+struct l2c_init_data {
+        const char *type;
+        unsigned way_size_0;
+        unsigned num_lock;
+        void (*of_parse)(const struct device_node *, u32 *, u32 *);
+        void (*enable)(void __iomem *, u32, unsigned);
+        void (*fixup)(void __iomem *, u32, struct outer_cache_fns *);
+        void (*save)(void __iomem *);
+        struct outer_cache_fns outer_cache;
+};
+
 #define CACHE_LINE_SIZE         32
 
 static void __iomem *l2x0_base;
@@ -36,96 +51,116 @@ static u32 l2x0_way_mask;	/* Bitmask of active ways */
 static u32 l2x0_size;
 static unsigned long sync_reg_offset = L2X0_CACHE_SYNC;
 
-/* Aurora don't have the cache ID register available, so we have to
- * pass it though the device tree */
-static u32  cache_id_part_number_from_dt;
-
 struct l2x0_regs l2x0_saved_regs;
 
-struct l2x0_of_data {
-        void (*setup)(const struct device_node *, u32 *, u32 *);
-        void (*save)(void);
-        struct outer_cache_fns outer_cache;
-};
-
-static bool of_init = false;
-
-static inline void cache_wait_way(void __iomem *reg, unsigned long mask)
+/*
+ * Common code for all cache controllers.
+ */
+static inline void l2c_wait_mask(void __iomem *reg, unsigned long mask)
 {
         /* wait for cache operation by line or way to complete */
         while (readl_relaxed(reg) & mask)
                 cpu_relax();
 }
 
-#ifdef CONFIG_CACHE_PL310
-static inline void cache_wait(void __iomem *reg, unsigned long mask)
+/*
+ * By default, we write directly to secure registers.  Platforms must
+ * override this if they are running non-secure.
+ */
+static void l2c_write_sec(unsigned long val, void __iomem *base, unsigned reg)
 {
-        /* cache operations by line are atomic on PL310 */
+        if (val == readl_relaxed(base + reg))
+                return;
+        if (outer_cache.write_sec)
+                outer_cache.write_sec(val, reg);
+        else
+                writel_relaxed(val, base + reg);
 }
-#else
-#define cache_wait      cache_wait_way
-#endif
 
-static inline void cache_sync(void)
+/*
+ * This should only be called when we have a requirement that the
+ * register be written due to a work-around, as platforms running
+ * in non-secure mode may not be able to access this register.
+ */
+static inline void l2c_set_debug(void __iomem *base, unsigned long val)
 {
-        void __iomem *base = l2x0_base;
-
-        writel_relaxed(0, base + sync_reg_offset);
-        cache_wait(base + L2X0_CACHE_SYNC, 1);
+        l2c_write_sec(val, base, L2X0_DEBUG_CTRL);
 }
 
-static inline void l2x0_clean_line(unsigned long addr)
+static void __l2c_op_way(void __iomem *reg)
 {
-        void __iomem *base = l2x0_base;
-        cache_wait(base + L2X0_CLEAN_LINE_PA, 1);
-        writel_relaxed(addr, base + L2X0_CLEAN_LINE_PA);
+        writel_relaxed(l2x0_way_mask, reg);
+        l2c_wait_mask(reg, l2x0_way_mask);
 }
 
-static inline void l2x0_inv_line(unsigned long addr)
+static inline void l2c_unlock(void __iomem *base, unsigned num)
 {
-        void __iomem *base = l2x0_base;
-        cache_wait(base + L2X0_INV_LINE_PA, 1);
-        writel_relaxed(addr, base + L2X0_INV_LINE_PA);
+        unsigned i;
+
+        for (i = 0; i < num; i++) {
+                writel_relaxed(0, base + L2X0_LOCKDOWN_WAY_D_BASE +
+                               i * L2X0_LOCKDOWN_STRIDE);
+                writel_relaxed(0, base + L2X0_LOCKDOWN_WAY_I_BASE +
+                               i * L2X0_LOCKDOWN_STRIDE);
+        }
 }
 
-#if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915)
-static inline void debug_writel(unsigned long val)
+/*
+ * Enable the L2 cache controller.  This function must only be
+ * called when the cache controller is known to be disabled.
+ */
+static void l2c_enable(void __iomem *base, u32 aux, unsigned num_lock)
 {
-        if (outer_cache.set_debug)
-                outer_cache.set_debug(val);
+        unsigned long flags;
+
+        l2c_write_sec(aux, base, L2X0_AUX_CTRL);
+
+        l2c_unlock(base, num_lock);
+
+        local_irq_save(flags);
+        __l2c_op_way(base + L2X0_INV_WAY);
+        writel_relaxed(0, base + sync_reg_offset);
+        l2c_wait_mask(base + sync_reg_offset, 1);
+        local_irq_restore(flags);
+
+        l2c_write_sec(L2X0_CTRL_EN, base, L2X0_CTRL);
 }
 
-static void pl310_set_debug(unsigned long val)
+static void l2c_disable(void)
 {
-        writel_relaxed(val, l2x0_base + L2X0_DEBUG_CTRL);
+        void __iomem *base = l2x0_base;
+
+        outer_cache.flush_all();
+        l2c_write_sec(0, base, L2X0_CTRL);
+        dsb(st);
 }
-#else
-/* Optimised out for non-errata case */
-static inline void debug_writel(unsigned long val)
+
+#ifdef CONFIG_CACHE_PL310
+static inline void cache_wait(void __iomem *reg, unsigned long mask)
 {
+        /* cache operations by line are atomic on PL310 */
 }
-
-#define pl310_set_debug NULL
+#else
+#define cache_wait      l2c_wait_mask
 #endif
 
-#ifdef CONFIG_PL310_ERRATA_588369
-static inline void l2x0_flush_line(unsigned long addr)
+static inline void cache_sync(void)
 {
         void __iomem *base = l2x0_base;
 
-        /* Clean by PA followed by Invalidate by PA */
-        cache_wait(base + L2X0_CLEAN_LINE_PA, 1);
-        writel_relaxed(addr, base + L2X0_CLEAN_LINE_PA);
-        cache_wait(base + L2X0_INV_LINE_PA, 1);
-        writel_relaxed(addr, base + L2X0_INV_LINE_PA);
+        writel_relaxed(0, base + sync_reg_offset);
+        cache_wait(base + L2X0_CACHE_SYNC, 1);
 }
-#else
 
-static inline void l2x0_flush_line(unsigned long addr)
+#if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915)
+static inline void debug_writel(unsigned long val)
+{
+        l2c_set_debug(l2x0_base, val);
+}
+#else
+/* Optimised out for non-errata case */
+static inline void debug_writel(unsigned long val)
 {
-        void __iomem *base = l2x0_base;
-        cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1);
-        writel_relaxed(addr, base + L2X0_CLEAN_INV_LINE_PA);
 }
 #endif
 
@@ -141,8 +176,7 @@ static void l2x0_cache_sync(void)
 static void __l2x0_flush_all(void)
 {
         debug_writel(0x03);
-        writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_INV_WAY);
-        cache_wait_way(l2x0_base + L2X0_CLEAN_INV_WAY, l2x0_way_mask);
+        __l2c_op_way(l2x0_base + L2X0_CLEAN_INV_WAY);
         cache_sync();
         debug_writel(0x00);
 }
@@ -157,275 +191,883 @@ static void l2x0_flush_all(void)
         raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
-static void l2x0_clean_all(void)
+static void l2x0_disable(void)
 {
         unsigned long flags;
 
-        /* clean all ways */
         raw_spin_lock_irqsave(&l2x0_lock, flags);
-        writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_WAY);
-        cache_wait_way(l2x0_base + L2X0_CLEAN_WAY, l2x0_way_mask);
-        cache_sync();
+        __l2x0_flush_all();
+        l2c_write_sec(0, l2x0_base, L2X0_CTRL);
+        dsb(st);
         raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
-static void l2x0_inv_all(void)
+static void l2c_save(void __iomem *base)
 {
-        unsigned long flags;
+        l2x0_saved_regs.aux_ctrl = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
+}
 
-        /* invalidate all ways */
-        raw_spin_lock_irqsave(&l2x0_lock, flags);
-        /* Invalidating when L2 is enabled is a nono */
-        BUG_ON(readl(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN);
-        writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY);
-        cache_wait_way(l2x0_base + L2X0_INV_WAY, l2x0_way_mask);
-        cache_sync();
-        raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+/*
+ * L2C-210 specific code.
+ *
+ * The L2C-2x0 PA, set/way and sync operations are atomic, but we must
+ * ensure that no background operation is running.  The way operations
+ * are all background tasks.
+ *
+ * While a background operation is in progress, any new operation is
+ * ignored (unspecified whether this causes an error.)  Thankfully, not
+ * used on SMP.
+ *
+ * Never has a different sync register other than L2X0_CACHE_SYNC, but
+ * we use sync_reg_offset here so we can share some of this with L2C-310.
+ */
+static void __l2c210_cache_sync(void __iomem *base)
+{
+        writel_relaxed(0, base + sync_reg_offset);
 }
 
-static void l2x0_inv_range(unsigned long start, unsigned long end)
+static void __l2c210_op_pa_range(void __iomem *reg, unsigned long start,
+        unsigned long end)
+{
+        while (start < end) {
+                writel_relaxed(start, reg);
+                start += CACHE_LINE_SIZE;
+        }
+}
+
+static void l2c210_inv_range(unsigned long start, unsigned long end)
 {
         void __iomem *base = l2x0_base;
-        unsigned long flags;
 
-        raw_spin_lock_irqsave(&l2x0_lock, flags);
         if (start & (CACHE_LINE_SIZE - 1)) {
                 start &= ~(CACHE_LINE_SIZE - 1);
-                debug_writel(0x03);
-                l2x0_flush_line(start);
-                debug_writel(0x00);
+                writel_relaxed(start, base + L2X0_CLEAN_INV_LINE_PA);
                 start += CACHE_LINE_SIZE;
         }
 
         if (end & (CACHE_LINE_SIZE - 1)) {
                 end &= ~(CACHE_LINE_SIZE - 1);
-                debug_writel(0x03);
-                l2x0_flush_line(end);
-                debug_writel(0x00);
+                writel_relaxed(end, base + L2X0_CLEAN_INV_LINE_PA);
         }
 
+        __l2c210_op_pa_range(base + L2X0_INV_LINE_PA, start, end);
+        __l2c210_cache_sync(base);
+}
+
+static void l2c210_clean_range(unsigned long start, unsigned long end)
+{
+        void __iomem *base = l2x0_base;
+
+        start &= ~(CACHE_LINE_SIZE - 1);
+        __l2c210_op_pa_range(base + L2X0_CLEAN_LINE_PA, start, end);
+        __l2c210_cache_sync(base);
+}
+
+static void l2c210_flush_range(unsigned long start, unsigned long end)
+{
+        void __iomem *base = l2x0_base;
+
+        start &= ~(CACHE_LINE_SIZE - 1);
+        __l2c210_op_pa_range(base + L2X0_CLEAN_INV_LINE_PA, start, end);
+        __l2c210_cache_sync(base);
+}
+
+static void l2c210_flush_all(void)
+{
+        void __iomem *base = l2x0_base;
+
+        BUG_ON(!irqs_disabled());
+
+        __l2c_op_way(base + L2X0_CLEAN_INV_WAY);
+        __l2c210_cache_sync(base);
+}
+
+static void l2c210_sync(void)
+{
+        __l2c210_cache_sync(l2x0_base);
+}
+
+static void l2c210_resume(void)
+{
+        void __iomem *base = l2x0_base;
+
+        if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN))
+                l2c_enable(base, l2x0_saved_regs.aux_ctrl, 1);
+}
+
+static const struct l2c_init_data l2c210_data __initconst = {
+        .type = "L2C-210",
+        .way_size_0 = SZ_8K,
+        .num_lock = 1,
+        .enable = l2c_enable,
+        .save = l2c_save,
+        .outer_cache = {
+                .inv_range = l2c210_inv_range,
+                .clean_range = l2c210_clean_range,
+                .flush_range = l2c210_flush_range,
+                .flush_all = l2c210_flush_all,
+                .disable = l2c_disable,
+                .sync = l2c210_sync,
+                .resume = l2c210_resume,
+        },
+};
+
+/*
+ * L2C-220 specific code.
+ *
+ * All operations are background operations: they have to be waited for.
+ * Conflicting requests generate a slave error (which will cause an
+ * imprecise abort.)  Never uses sync_reg_offset, so we hard-code the
+ * sync register here.
+ *
+ * However, we can re-use the l2c210_resume call.
+ */
+static inline void __l2c220_cache_sync(void __iomem *base)
+{
+        writel_relaxed(0, base + L2X0_CACHE_SYNC);
+        l2c_wait_mask(base + L2X0_CACHE_SYNC, 1);
+}
+
+static void l2c220_op_way(void __iomem *base, unsigned reg)
+{
+        unsigned long flags;
+
+        raw_spin_lock_irqsave(&l2x0_lock, flags);
+        __l2c_op_way(base + reg);
+        __l2c220_cache_sync(base);
+        raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+}
+
+static unsigned long l2c220_op_pa_range(void __iomem *reg, unsigned long start,
+        unsigned long end, unsigned long flags)
+{
+        raw_spinlock_t *lock = &l2x0_lock;
+
         while (start < end) {
                 unsigned long blk_end = start + min(end - start, 4096UL);
 
                 while (start < blk_end) {
-                        l2x0_inv_line(start);
+                        l2c_wait_mask(reg, 1);
+                        writel_relaxed(start, reg);
                         start += CACHE_LINE_SIZE;
                 }
 
                 if (blk_end < end) {
-                        raw_spin_unlock_irqrestore(&l2x0_lock, flags);
-                        raw_spin_lock_irqsave(&l2x0_lock, flags);
+                        raw_spin_unlock_irqrestore(lock, flags);
+                        raw_spin_lock_irqsave(lock, flags);
                 }
         }
-        cache_wait(base + L2X0_INV_LINE_PA, 1);
-        cache_sync();
-        raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+
+        return flags;
 }
 
-static void l2x0_clean_range(unsigned long start, unsigned long end)
+static void l2c220_inv_range(unsigned long start, unsigned long end)
 {
         void __iomem *base = l2x0_base;
         unsigned long flags;
 
-        if ((end - start) >= l2x0_size) {
-                l2x0_clean_all();
-                return;
-        }
-
         raw_spin_lock_irqsave(&l2x0_lock, flags);
-        start &= ~(CACHE_LINE_SIZE - 1);
-        while (start < end) {
-                unsigned long blk_end = start + min(end - start, 4096UL);
-
-                while (start < blk_end) {
-                        l2x0_clean_line(start);
+        if ((start | end) & (CACHE_LINE_SIZE - 1)) {
+                if (start & (CACHE_LINE_SIZE - 1)) {
+                        start &= ~(CACHE_LINE_SIZE - 1);
+                        writel_relaxed(start, base + L2X0_CLEAN_INV_LINE_PA);
                         start += CACHE_LINE_SIZE;
                 }
 
-                if (blk_end < end) {
-                        raw_spin_unlock_irqrestore(&l2x0_lock, flags);
-                        raw_spin_lock_irqsave(&l2x0_lock, flags);
+                if (end & (CACHE_LINE_SIZE - 1)) {
+                        end &= ~(CACHE_LINE_SIZE - 1);
+                        l2c_wait_mask(base + L2X0_CLEAN_INV_LINE_PA, 1);
+                        writel_relaxed(end, base + L2X0_CLEAN_INV_LINE_PA);
                 }
         }
-        cache_wait(base + L2X0_CLEAN_LINE_PA, 1);
-        cache_sync();
+
+        flags = l2c220_op_pa_range(base + L2X0_INV_LINE_PA,
+                                   start, end, flags);
+        l2c_wait_mask(base + L2X0_INV_LINE_PA, 1);
+        __l2c220_cache_sync(base);
         raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
-static void l2x0_flush_range(unsigned long start, unsigned long end)
+static void l2c220_clean_range(unsigned long start, unsigned long end)
 {
         void __iomem *base = l2x0_base;
         unsigned long flags;
 
+        start &= ~(CACHE_LINE_SIZE - 1);
         if ((end - start) >= l2x0_size) {
-                l2x0_flush_all();
+                l2c220_op_way(base, L2X0_CLEAN_WAY);
                 return;
         }
 
         raw_spin_lock_irqsave(&l2x0_lock, flags);
+        flags = l2c220_op_pa_range(base + L2X0_CLEAN_LINE_PA,
+                                   start, end, flags);
+        l2c_wait_mask(base + L2X0_CLEAN_INV_LINE_PA, 1);
+        __l2c220_cache_sync(base);
+        raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+}
+
+static void l2c220_flush_range(unsigned long start, unsigned long end)
+{
+        void __iomem *base = l2x0_base;
+        unsigned long flags;
+
         start &= ~(CACHE_LINE_SIZE - 1);
+        if ((end - start) >= l2x0_size) {
+                l2c220_op_way(base, L2X0_CLEAN_INV_WAY);
+                return;
+        }
+
+        raw_spin_lock_irqsave(&l2x0_lock, flags);
+        flags = l2c220_op_pa_range(base + L2X0_CLEAN_INV_LINE_PA,
+                                   start, end, flags);
+        l2c_wait_mask(base + L2X0_CLEAN_INV_LINE_PA, 1);
+        __l2c220_cache_sync(base);
+        raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+}
+
+static void l2c220_flush_all(void)
+{
+        l2c220_op_way(l2x0_base, L2X0_CLEAN_INV_WAY);
+}
+
+static void l2c220_sync(void)
+{
+        unsigned long flags;
+
+        raw_spin_lock_irqsave(&l2x0_lock, flags);
+        __l2c220_cache_sync(l2x0_base);
+        raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+}
+
+static void l2c220_enable(void __iomem *base, u32 aux, unsigned num_lock)
+{
+        /*
+         * Always enable non-secure access to the lockdown registers -
+         * we write to them as part of the L2C enable sequence so they
+         * need to be accessible.
+         */
+        aux |= L220_AUX_CTRL_NS_LOCKDOWN;
+
+        l2c_enable(base, aux, num_lock);
+}
+
+static const struct l2c_init_data l2c220_data = {
+        .type = "L2C-220",
+        .way_size_0 = SZ_8K,
+        .num_lock = 1,
+        .enable = l2c220_enable,
+        .save = l2c_save,
+        .outer_cache = {
+                .inv_range = l2c220_inv_range,
+                .clean_range = l2c220_clean_range,
+                .flush_range = l2c220_flush_range,
+                .flush_all = l2c220_flush_all,
+                .disable = l2c_disable,
+                .sync = l2c220_sync,
+                .resume = l2c210_resume,
+        },
+};
+
+/*
+ * L2C-310 specific code.
+ *
+ * Very similar to L2C-210, the PA, set/way and sync operations are atomic,
+ * and the way operations are all background tasks.  However, issuing an
+ * operation while a background operation is in progress results in a
+ * SLVERR response.  We can reuse:
+ *
+ *  __l2c210_cache_sync (using sync_reg_offset)
+ *  l2c210_sync
+ *  l2c210_inv_range (if 588369 is not applicable)
+ *  l2c210_clean_range
+ *  l2c210_flush_range (if 588369 is not applicable)
+ *  l2c210_flush_all (if 727915 is not applicable)
+ *
+ * Errata:
+ * 588369: PL310 R0P0->R1P0, fixed R2P0.
+ *      Affects: all clean+invalidate operations
+ *      clean and invalidate skips the invalidate step, so we need to issue
+ *      separate operations.  We also require the above debug workaround
+ *      enclosing this code fragment on affected parts.  On unaffected parts,
+ *      we must not use this workaround without the debug register writes
+ *      to avoid exposing a problem similar to 727915.
+ *
+ * 727915: PL310 R2P0->R3P0, fixed R3P1.
+ *      Affects: clean+invalidate by way
+ *      clean and invalidate by way runs in the background, and a store can
+ *      hit the line between the clean operation and invalidate operation,
+ *      resulting in the store being lost.
+ *
+ * 752271: PL310 R3P0->R3P1-50REL0, fixed R3P2.
+ *      Affects: 8x64-bit (double fill) line fetches
+ *      double fill line fetches can fail to cause dirty data to be evicted
+ *      from the cache before the new data overwrites the second line.
+ *
+ * 753970: PL310 R3P0, fixed R3P1.
+ *      Affects: sync
+ *      prevents merging writes after the sync operation, until another L2C
+ *      operation is performed (or a number of other conditions.)
+ *
+ * 769419: PL310 R0P0->R3P1, fixed R3P2.
+ *      Affects: store buffer
+ *      store buffer is not automatically drained.
+ */
+static void l2c310_inv_range_erratum(unsigned long start, unsigned long end)
+{
+        void __iomem *base = l2x0_base;
+
+        if ((start | end) & (CACHE_LINE_SIZE - 1)) {
+                unsigned long flags;
+
+                /* Erratum 588369 for both clean+invalidate operations */
+                raw_spin_lock_irqsave(&l2x0_lock, flags);
+                l2c_set_debug(base, 0x03);
+
+                if (start & (CACHE_LINE_SIZE - 1)) {
+                        start &= ~(CACHE_LINE_SIZE - 1);
+                        writel_relaxed(start, base + L2X0_CLEAN_LINE_PA);
+                        writel_relaxed(start, base + L2X0_INV_LINE_PA);
+                        start += CACHE_LINE_SIZE;
+                }
+
+                if (end & (CACHE_LINE_SIZE - 1)) {
+                        end &= ~(CACHE_LINE_SIZE - 1);
+                        writel_relaxed(end, base + L2X0_CLEAN_LINE_PA);
+                        writel_relaxed(end, base + L2X0_INV_LINE_PA);
+                }
+
+                l2c_set_debug(base, 0x00);
+                raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+        }
+
+        __l2c210_op_pa_range(base + L2X0_INV_LINE_PA, start, end);
+        __l2c210_cache_sync(base);
+}
+
+static void l2c310_flush_range_erratum(unsigned long start, unsigned long end)
+{
+        raw_spinlock_t *lock = &l2x0_lock;
+        unsigned long flags;
+        void __iomem *base = l2x0_base;
+
+        raw_spin_lock_irqsave(lock, flags);
         while (start < end) {
                 unsigned long blk_end = start + min(end - start, 4096UL);
 
-                debug_writel(0x03);
+                l2c_set_debug(base, 0x03);
                 while (start < blk_end) {
-                        l2x0_flush_line(start);
+                        writel_relaxed(start, base + L2X0_CLEAN_LINE_PA);
+                        writel_relaxed(start, base + L2X0_INV_LINE_PA);
                         start += CACHE_LINE_SIZE;
                 }
-                debug_writel(0x00);
+                l2c_set_debug(base, 0x00);
 
                 if (blk_end < end) {
-                        raw_spin_unlock_irqrestore(&l2x0_lock, flags);
-                        raw_spin_lock_irqsave(&l2x0_lock, flags);
+                        raw_spin_unlock_irqrestore(lock, flags);
+                        raw_spin_lock_irqsave(lock, flags);
                 }
         }
-        cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1);
-        cache_sync();
-        raw_spin_unlock_irqrestore(&l2x0_lock, flags);
+        raw_spin_unlock_irqrestore(lock, flags);
+        __l2c210_cache_sync(base);
 }
 
-static void l2x0_disable(void)
+static void l2c310_flush_all_erratum(void)
 {
+        void __iomem *base = l2x0_base;
         unsigned long flags;
 
         raw_spin_lock_irqsave(&l2x0_lock, flags);
-        __l2x0_flush_all();
-        writel_relaxed(0, l2x0_base + L2X0_CTRL);
-        dsb(st);
+        l2c_set_debug(base, 0x03);
+        __l2c_op_way(base + L2X0_CLEAN_INV_WAY);
+        l2c_set_debug(base, 0x00);
+        __l2c210_cache_sync(base);
         raw_spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
-static void l2x0_unlock(u32 cache_id)
+static void __init l2c310_save(void __iomem *base)
 {
-        int lockregs;
-        int i;
+        unsigned revision;
 
-        switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
-        case L2X0_CACHE_ID_PART_L310:
-                lockregs = 8;
-                break;
-        case AURORA_CACHE_ID:
-                lockregs = 4;
+        l2c_save(base);
+
+        l2x0_saved_regs.tag_latency = readl_relaxed(base +
+                L310_TAG_LATENCY_CTRL);
+        l2x0_saved_regs.data_latency = readl_relaxed(base +
+                L310_DATA_LATENCY_CTRL);
+        l2x0_saved_regs.filter_end = readl_relaxed(base +
+                L310_ADDR_FILTER_END);
+        l2x0_saved_regs.filter_start = readl_relaxed(base +
+                L310_ADDR_FILTER_START);
+
+        revision = readl_relaxed(base + L2X0_CACHE_ID) &
+                        L2X0_CACHE_ID_RTL_MASK;
+
+        /* From r2p0, there is Prefetch offset/control register */
+        if (revision >= L310_CACHE_ID_RTL_R2P0)
+                l2x0_saved_regs.prefetch_ctrl = readl_relaxed(base +
+                                                        L310_PREFETCH_CTRL);
+
+        /* From r3p0, there is Power control register */
+        if (revision >= L310_CACHE_ID_RTL_R3P0)
+                l2x0_saved_regs.pwr_ctrl = readl_relaxed(base +
+                                                        L310_POWER_CTRL);
+}
+
+static void l2c310_resume(void)
+{
+        void __iomem *base = l2x0_base;
+
+        if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)) {
+                unsigned revision;
+
+                /* restore pl310 setup */
+                writel_relaxed(l2x0_saved_regs.tag_latency,
+                               base + L310_TAG_LATENCY_CTRL);
+                writel_relaxed(l2x0_saved_regs.data_latency,
+                               base + L310_DATA_LATENCY_CTRL);
+                writel_relaxed(l2x0_saved_regs.filter_end,
+                               base + L310_ADDR_FILTER_END);
+                writel_relaxed(l2x0_saved_regs.filter_start,
+                               base + L310_ADDR_FILTER_START);
+
+                revision = readl_relaxed(base + L2X0_CACHE_ID) &
+                                L2X0_CACHE_ID_RTL_MASK;
+
+                if (revision >= L310_CACHE_ID_RTL_R2P0)
+                        l2c_write_sec(l2x0_saved_regs.prefetch_ctrl, base,
+                                      L310_PREFETCH_CTRL);
+                if (revision >= L310_CACHE_ID_RTL_R3P0)
+                        l2c_write_sec(l2x0_saved_regs.pwr_ctrl, base,
+                                      L310_POWER_CTRL);
+
+                l2c_enable(base, l2x0_saved_regs.aux_ctrl, 8);
+
+                /* Re-enable full-line-of-zeros for Cortex-A9 */
+                if (l2x0_saved_regs.aux_ctrl & L310_AUX_CTRL_FULL_LINE_ZERO)
+                        set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1));
+        }
+}
+
+static int l2c310_cpu_enable_flz(struct notifier_block *nb, unsigned long act, void *data)
+{
+        switch (act & ~CPU_TASKS_FROZEN) {
+        case CPU_STARTING:
+                set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1));
                 break;
-        default:
-                /* L210 and unknown types */
-                lockregs = 1;
+        case CPU_DYING:
+                set_auxcr(get_auxcr() & ~(BIT(3) | BIT(2) | BIT(1)));
                 break;
         }
+        return NOTIFY_OK;
+}
 
-        for (i = 0; i < lockregs; i++) {
-                writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE +
-                               i * L2X0_LOCKDOWN_STRIDE);
-                writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_I_BASE +
-                               i * L2X0_LOCKDOWN_STRIDE);
+static void __init l2c310_enable(void __iomem *base, u32 aux, unsigned num_lock)
+{
+        unsigned rev = readl_relaxed(base + L2X0_CACHE_ID) & L2X0_CACHE_ID_PART_MASK;
+        bool cortex_a9 = read_cpuid_part_number() == ARM_CPU_PART_CORTEX_A9;
+
+        if (rev >= L310_CACHE_ID_RTL_R2P0) {
+                if (cortex_a9) {
+                        aux |= L310_AUX_CTRL_EARLY_BRESP;
+                        pr_info("L2C-310 enabling early BRESP for Cortex-A9\n");
+                } else if (aux & L310_AUX_CTRL_EARLY_BRESP) {
+                        pr_warn("L2C-310 early BRESP only supported with Cortex-A9\n");
+                        aux &= ~L310_AUX_CTRL_EARLY_BRESP;
+                }
+        }
+
+        if (cortex_a9) {
+                u32 aux_cur = readl_relaxed(base + L2X0_AUX_CTRL);
+                u32 acr = get_auxcr();
+
+                pr_debug("Cortex-A9 ACR=0x%08x\n", acr);
+
+                if (acr & BIT(3) && !(aux_cur & L310_AUX_CTRL_FULL_LINE_ZERO))
+                        pr_err("L2C-310: full line of zeros enabled in Cortex-A9 but not L2C-310 - invalid\n");
+
+                if (aux & L310_AUX_CTRL_FULL_LINE_ZERO && !(acr & BIT(3)))
+                        pr_err("L2C-310: enabling full line of zeros but not enabled in Cortex-A9\n");
+
+                if (!(aux & L310_AUX_CTRL_FULL_LINE_ZERO) && !outer_cache.write_sec) {
+                        aux |= L310_AUX_CTRL_FULL_LINE_ZERO;
+                        pr_info("L2C-310 full line of zeros enabled for Cortex-A9\n");
+                }
+        } else if (aux & (L310_AUX_CTRL_FULL_LINE_ZERO | L310_AUX_CTRL_EARLY_BRESP)) {
+                pr_err("L2C-310: disabling Cortex-A9 specific feature bits\n");
+                aux &= ~(L310_AUX_CTRL_FULL_LINE_ZERO | L310_AUX_CTRL_EARLY_BRESP);
+        }
+
+        if (aux & (L310_AUX_CTRL_DATA_PREFETCH | L310_AUX_CTRL_INSTR_PREFETCH)) {
+                u32 prefetch = readl_relaxed(base + L310_PREFETCH_CTRL);
+
+                pr_info("L2C-310 %s%s prefetch enabled, offset %u lines\n",
+                        aux & L310_AUX_CTRL_INSTR_PREFETCH ? "I" : "",
+                        aux & L310_AUX_CTRL_DATA_PREFETCH ? "D" : "",
+                        1 + (prefetch & L310_PREFETCH_CTRL_OFFSET_MASK));
+        }
+
+        /* r3p0 or later has power control register */
+        if (rev >= L310_CACHE_ID_RTL_R3P0) {
+                u32 power_ctrl;
+
+                l2c_write_sec(L310_DYNAMIC_CLK_GATING_EN | L310_STNDBY_MODE_EN,
+                              base, L310_POWER_CTRL);
+                power_ctrl = readl_relaxed(base + L310_POWER_CTRL);
+                pr_info("L2C-310 dynamic clock gating %sabled, standby mode %sabled\n",
+                        power_ctrl & L310_DYNAMIC_CLK_GATING_EN ? "en" : "dis",
+                        power_ctrl & L310_STNDBY_MODE_EN ? "en" : "dis");
+        }
+
+        /*
+         * Always enable non-secure access to the lockdown registers -
+         * we write to them as part of the L2C enable sequence so they
+         * need to be accessible.
+         */
+        aux |= L310_AUX_CTRL_NS_LOCKDOWN;
+
+        l2c_enable(base, aux, num_lock);
+
+        if (aux & L310_AUX_CTRL_FULL_LINE_ZERO) {
+                set_auxcr(get_auxcr() | BIT(3) | BIT(2) | BIT(1));
+                cpu_notifier(l2c310_cpu_enable_flz, 0);
         }
 }
 
-void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
+static void __init l2c310_fixup(void __iomem *base, u32 cache_id,
+        struct outer_cache_fns *fns)
 {
-        u32 aux;
-        u32 cache_id;
-        u32 way_size = 0;
-        int ways;
-        int way_size_shift = L2X0_WAY_SIZE_SHIFT;
-        const char *type;
+        unsigned revision = cache_id & L2X0_CACHE_ID_RTL_MASK;
+        const char *errata[8];
+        unsigned n = 0;
+
+        if (IS_ENABLED(CONFIG_PL310_ERRATA_588369) &&
+            revision < L310_CACHE_ID_RTL_R2P0 &&
+            /* For bcm compatibility */
+            fns->inv_range == l2c210_inv_range) {
+                fns->inv_range = l2c310_inv_range_erratum;
+                fns->flush_range = l2c310_flush_range_erratum;
+                errata[n++] = "588369";
+        }
 
-        l2x0_base = base;
-        if (cache_id_part_number_from_dt)
-                cache_id = cache_id_part_number_from_dt;
-        else
-                cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID);
-        aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
+        if (IS_ENABLED(CONFIG_PL310_ERRATA_727915) &&
+            revision >= L310_CACHE_ID_RTL_R2P0 &&
+            revision < L310_CACHE_ID_RTL_R3P1) {
+                fns->flush_all = l2c310_flush_all_erratum;
+                errata[n++] = "727915";
+        }
+
+        if (revision >= L310_CACHE_ID_RTL_R3P0 &&
+            revision < L310_CACHE_ID_RTL_R3P2) {
+                u32 val = readl_relaxed(base + L310_PREFETCH_CTRL);
+                /* I don't think bit23 is required here... but iMX6 does so */
+                if (val & (BIT(30) | BIT(23))) {
+                        val &= ~(BIT(30) | BIT(23));
+                        l2c_write_sec(val, base, L310_PREFETCH_CTRL);
+                        errata[n++] = "752271";
+                }
+        }
+
+        if (IS_ENABLED(CONFIG_PL310_ERRATA_753970) &&
+            revision == L310_CACHE_ID_RTL_R3P0) {
+                sync_reg_offset = L2X0_DUMMY_REG;
+                errata[n++] = "753970";
+        }
+
+        if (IS_ENABLED(CONFIG_PL310_ERRATA_769419))
+                errata[n++] = "769419";
+
+        if (n) {
+                unsigned i;
 
+                pr_info("L2C-310 errat%s", n > 1 ? "a" : "um");
+                for (i = 0; i < n; i++)
+                        pr_cont(" %s", errata[i]);
+                pr_cont(" enabled\n");
+        }
+}
+
+static void l2c310_disable(void)
+{
+        /*
+         * If full-line-of-zeros is enabled, we must first disable it in the
+         * Cortex-A9 auxiliary control register before disabling the L2 cache.
+         */
+        if (l2x0_saved_regs.aux_ctrl & L310_AUX_CTRL_FULL_LINE_ZERO)
+                set_auxcr(get_auxcr() & ~(BIT(3) | BIT(2) | BIT(1)));
+
+        l2c_disable();
+}
+
+static const struct l2c_init_data l2c310_init_fns __initconst = {
+        .type = "L2C-310",
+        .way_size_0 = SZ_8K,
+        .num_lock = 8,
+        .enable = l2c310_enable,
+        .fixup = l2c310_fixup,
+        .save = l2c310_save,
+        .outer_cache = {
+                .inv_range = l2c210_inv_range,
+                .clean_range = l2c210_clean_range,
+                .flush_range = l2c210_flush_range,
+                .flush_all = l2c210_flush_all,
+                .disable = l2c310_disable,
+                .sync = l2c210_sync,
+                .resume = l2c310_resume,
+        },
+};
+
+static void __init __l2c_init(const struct l2c_init_data *data,
+        u32 aux_val, u32 aux_mask, u32 cache_id)
+{
+        struct outer_cache_fns fns;
+        unsigned way_size_bits, ways;
+        u32 aux, old_aux;
+
+        /*
+         * Sanity check the aux values.  aux_mask is the bits we preserve
+         * from reading the hardware register, and aux_val is the bits we
+         * set.
+         */
+        if (aux_val & aux_mask)
+                pr_alert("L2C: platform provided aux values permit register corruption.\n");
+
+        old_aux = aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
         aux &= aux_mask;
         aux |= aux_val;
 
+        if (old_aux != aux)
+                pr_warn("L2C: DT/platform modifies aux control register: 0x%08x -> 0x%08x\n",
+                        old_aux, aux);
+
         /* Determine the number of ways */
         switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
         case L2X0_CACHE_ID_PART_L310:
+                if ((aux_val | ~aux_mask) & (L2C_AUX_CTRL_WAY_SIZE_MASK | L310_AUX_CTRL_ASSOCIATIVITY_16))
+                        pr_warn("L2C: DT/platform tries to modify or specify cache size\n");
                 if (aux & (1 << 16))
                         ways = 16;
                 else
                         ways = 8;
-                type = "L310";
-#ifdef CONFIG_PL310_ERRATA_753970
-                /* Unmapped register. */
-                sync_reg_offset = L2X0_DUMMY_REG;
-#endif
-                if ((cache_id & L2X0_CACHE_ID_RTL_MASK) <= L2X0_CACHE_ID_RTL_R3P0)
-                        outer_cache.set_debug = pl310_set_debug;
                 break;
+
         case L2X0_CACHE_ID_PART_L210:
+        case L2X0_CACHE_ID_PART_L220:
                 ways = (aux >> 13) & 0xf;
-                type = "L210";
                 break;
 
         case AURORA_CACHE_ID:
-                sync_reg_offset = AURORA_SYNC_REG;
                 ways = (aux >> 13) & 0xf;
                 ways = 2 << ((ways + 1) >> 2);
-                way_size_shift = AURORA_WAY_SIZE_SHIFT;
-                type = "Aurora";
                 break;
+
         default:
                 /* Assume unknown chips have 8 ways */
                 ways = 8;
-                type = "L2x0 series";
                 break;
         }
 
         l2x0_way_mask = (1 << ways) - 1;
 
         /*
-         * L2 cache Size =  Way size * Number of ways
+         * way_size_0 is the size that a way_size value of zero would be
+         * given the calculation: way_size = way_size_0 << way_size_bits.
+         * So, if way_size_bits=0 is reserved, but way_size_bits=1 is 16k,
+         * then way_size_0 would be 8k.
+         *
+         * L2 cache size = number of ways * way size.
          */
-        way_size = (aux & L2X0_AUX_CTRL_WAY_SIZE_MASK) >> 17;
-        way_size = 1 << (way_size + way_size_shift);
+        way_size_bits = (aux & L2C_AUX_CTRL_WAY_SIZE_MASK) >>
+                        L2C_AUX_CTRL_WAY_SIZE_SHIFT;
+        l2x0_size = ways * (data->way_size_0 << way_size_bits);
 
-        l2x0_size = ways * way_size * SZ_1K;
+        fns = data->outer_cache;
+        fns.write_sec = outer_cache.write_sec;
+        if (data->fixup)
+                data->fixup(l2x0_base, cache_id, &fns);
 
         /*
-         * Check if l2x0 controller is already enabled.
-         * If you are booting from non-secure mode
-         * accessing the below registers will fault.
+         * Check if l2x0 controller is already enabled.  If we are booting
+         * in non-secure mode accessing the below registers will fault.
          */
-        if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
-                /* Make sure that I&D is not locked down when starting */
-                l2x0_unlock(cache_id);
+        if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN))
+                data->enable(l2x0_base, aux, data->num_lock);
 
-                /* l2x0 controller is disabled */
-                writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL);
+        outer_cache = fns;
 
-                l2x0_inv_all();
-
-                /* enable L2X0 */
-                writel_relaxed(L2X0_CTRL_EN, l2x0_base + L2X0_CTRL);
-        }
+        /*
+         * It is strange to save the register state before initialisation,
+         * but hey, this is what the DT implementations decided to do.
+         */
+        if (data->save)
+                data->save(l2x0_base);
 
         /* Re-read it in case some bits are reserved. */
         aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
 
-        /* Save the value for resuming. */
-        l2x0_saved_regs.aux_ctrl = aux;
+        pr_info("%s cache controller enabled, %d ways, %d kB\n",
+                data->type, ways, l2x0_size >> 10);
+        pr_info("%s: CACHE_ID 0x%08x, AUX_CTRL 0x%08x\n",
+                data->type, cache_id, aux);
+}
+
+void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask)
+{
+        const struct l2c_init_data *data;
+        u32 cache_id;
+
+        l2x0_base = base;
+
+        cache_id = readl_relaxed(base + L2X0_CACHE_ID);
+
+        switch (cache_id & L2X0_CACHE_ID_PART_MASK) {
+        default:
+        case L2X0_CACHE_ID_PART_L210:
+                data = &l2c210_data;
+                break;
 
-        if (!of_init) {
-                outer_cache.inv_range = l2x0_inv_range;
-                outer_cache.clean_range = l2x0_clean_range;
-                outer_cache.flush_range = l2x0_flush_range;
-                outer_cache.sync = l2x0_cache_sync;
-                outer_cache.flush_all = l2x0_flush_all;
-                outer_cache.inv_all = l2x0_inv_all;
-                outer_cache.disable = l2x0_disable;
+        case L2X0_CACHE_ID_PART_L220:
+                data = &l2c220_data;
+                break;
+
+        case L2X0_CACHE_ID_PART_L310:
+                data = &l2c310_init_fns;
+                break;
         }
 
-        pr_info("%s cache controller enabled\n", type);
-        pr_info("l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d kB\n",
-                ways, cache_id, aux, l2x0_size >> 10);
+        __l2c_init(data, aux_val, aux_mask, cache_id);
 }
 
 #ifdef CONFIG_OF
 static int l2_wt_override;
 
+/* Aurora don't have the cache ID register available, so we have to
+ * pass it though the device tree */
+static u32 cache_id_part_number_from_dt;
+
+static void __init l2x0_of_parse(const struct device_node *np,
+                                 u32 *aux_val, u32 *aux_mask)
+{
+        u32 data[2] = { 0, 0 };
+        u32 tag = 0;
+        u32 dirty = 0;
+        u32 val = 0, mask = 0;
+
+        of_property_read_u32(np, "arm,tag-latency", &tag);
+        if (tag) {
+                mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK;
+                val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT;
+        }
+
+        of_property_read_u32_array(np, "arm,data-latency",
+                                   data, ARRAY_SIZE(data));
+        if (data[0] && data[1]) {
+                mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK |
+                        L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK;
+                val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) |
+                       ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT);
+        }
+
+        of_property_read_u32(np, "arm,dirty-latency", &dirty);
+        if (dirty) {
+                mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK;
+                val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT;
+        }
+
+        *aux_val &= ~mask;
+        *aux_val |= val;
+        *aux_mask &= ~mask;
+}
+
+static const struct l2c_init_data of_l2c210_data __initconst = {
+        .type = "L2C-210",
+        .way_size_0 = SZ_8K,
+        .num_lock = 1,
+        .of_parse = l2x0_of_parse,
+        .enable = l2c_enable,
+        .save = l2c_save,
+        .outer_cache = {
+                .inv_range   = l2c210_inv_range,
+                .clean_range = l2c210_clean_range,
+                .flush_range = l2c210_flush_range,
+                .flush_all   = l2c210_flush_all,
+                .disable     = l2c_disable,
+                .sync        = l2c210_sync,
+                .resume      = l2c210_resume,
+        },
+};
+
+static const struct l2c_init_data of_l2c220_data __initconst = {
+        .type = "L2C-220",
+        .way_size_0 = SZ_8K,
+        .num_lock = 1,
+        .of_parse = l2x0_of_parse,
+        .enable = l2c220_enable,
+        .save = l2c_save,
+        .outer_cache = {
+                .inv_range   = l2c220_inv_range,
+                .clean_range = l2c220_clean_range,
+                .flush_range = l2c220_flush_range,
+                .flush_all   = l2c220_flush_all,
+                .disable     = l2c_disable,
+                .sync        = l2c220_sync,
+                .resume      = l2c210_resume,
+        },
+};
+
+static void __init l2c310_of_parse(const struct device_node *np,
+        u32 *aux_val, u32 *aux_mask)
+{
+        u32 data[3] = { 0, 0, 0 };
+        u32 tag[3] = { 0, 0, 0 };
+        u32 filter[2] = { 0, 0 };
+
+        of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag));
+        if (tag[0] && tag[1] && tag[2])
+                writel_relaxed(
+                        L310_LATENCY_CTRL_RD(tag[0] - 1) |
+                        L310_LATENCY_CTRL_WR(tag[1] - 1) |
+                        L310_LATENCY_CTRL_SETUP(tag[2] - 1),
+                        l2x0_base + L310_TAG_LATENCY_CTRL);
+
+        of_property_read_u32_array(np, "arm,data-latency",
+                                   data, ARRAY_SIZE(data));
+        if (data[0] && data[1] && data[2])
+                writel_relaxed(
+                        L310_LATENCY_CTRL_RD(data[0] - 1) |
+                        L310_LATENCY_CTRL_WR(data[1] - 1) |
+                        L310_LATENCY_CTRL_SETUP(data[2] - 1),
+                        l2x0_base + L310_DATA_LATENCY_CTRL);
+
+        of_property_read_u32_array(np, "arm,filter-ranges",
+                                   filter, ARRAY_SIZE(filter));
+        if (filter[1]) {
+                writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M),
+                               l2x0_base + L310_ADDR_FILTER_END);
+                writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L310_ADDR_FILTER_EN,
+                               l2x0_base + L310_ADDR_FILTER_START);
+        }
+}
+
+static const struct l2c_init_data of_l2c310_data __initconst = {
+        .type = "L2C-310",
+        .way_size_0 = SZ_8K,
+        .num_lock = 8,
+        .of_parse = l2c310_of_parse,
+        .enable = l2c310_enable,
+        .fixup = l2c310_fixup,
+        .save  = l2c310_save,
+        .outer_cache = {
+                .inv_range   = l2c210_inv_range,
+                .clean_range = l2c210_clean_range,
+                .flush_range = l2c210_flush_range,
+                .flush_all   = l2c210_flush_all,
+                .disable     = l2c310_disable,
+                .sync        = l2c210_sync,
+                .resume      = l2c310_resume,
+        },
+};
+
 /*
  * Note that the end addresses passed to Linux primitives are
  * noninclusive, while the hardware cache range operations use
@@ -524,6 +1166,100 @@ static void aurora_flush_range(unsigned long start, unsigned long end)
         }
 }
 
+static void aurora_save(void __iomem *base)
+{
+        l2x0_saved_regs.ctrl = readl_relaxed(base + L2X0_CTRL);
+        l2x0_saved_regs.aux_ctrl = readl_relaxed(base + L2X0_AUX_CTRL);
+}
+
+static void aurora_resume(void)
+{
+        void __iomem *base = l2x0_base;
+
+        if (!(readl(base + L2X0_CTRL) & L2X0_CTRL_EN)) {
+                writel_relaxed(l2x0_saved_regs.aux_ctrl, base + L2X0_AUX_CTRL);
+                writel_relaxed(l2x0_saved_regs.ctrl, base + L2X0_CTRL);
+        }
+}
+
+/*
+ * For Aurora cache in no outer mode, enable via the CP15 coprocessor
+ * broadcasting of cache commands to L2.
+ */
+static void __init aurora_enable_no_outer(void __iomem *base, u32 aux,
+        unsigned num_lock)
+{
+        u32 u;
+
+        asm volatile("mrc p15, 1, %0, c15, c2, 0" : "=r" (u));
+        u |= AURORA_CTRL_FW;            /* Set the FW bit */
+        asm volatile("mcr p15, 1, %0, c15, c2, 0" : : "r" (u));
+
+        isb();
+
+        l2c_enable(base, aux, num_lock);
+}
+
+static void __init aurora_fixup(void __iomem *base, u32 cache_id,
+        struct outer_cache_fns *fns)
+{
+        sync_reg_offset = AURORA_SYNC_REG;
+}
+
+static void __init aurora_of_parse(const struct device_node *np,
+                                u32 *aux_val, u32 *aux_mask)
+{
+        u32 val = AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU;
+        u32 mask =  AURORA_ACR_REPLACEMENT_MASK;
+
+        of_property_read_u32(np, "cache-id-part",
+                        &cache_id_part_number_from_dt);
+
+        /* Determine and save the write policy */
+        l2_wt_override = of_property_read_bool(np, "wt-override");
+
+        if (l2_wt_override) {
+                val |= AURORA_ACR_FORCE_WRITE_THRO_POLICY;
+                mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK;
+        }
+
+        *aux_val &= ~mask;
+        *aux_val |= val;
+        *aux_mask &= ~mask;
+}
+
+static const struct l2c_init_data of_aurora_with_outer_data __initconst = {
+        .type = "Aurora",
+        .way_size_0 = SZ_4K,
+        .num_lock = 4,
+        .of_parse = aurora_of_parse,
+        .enable = l2c_enable,
+        .fixup = aurora_fixup,
+        .save  = aurora_save,
+        .outer_cache = {
+                .inv_range   = aurora_inv_range,
+                .clean_range = aurora_clean_range,
+                .flush_range = aurora_flush_range,
+                .flush_all   = l2x0_flush_all,
+                .disable     = l2x0_disable,
+                .sync        = l2x0_cache_sync,
+                .resume      = aurora_resume,
+        },
+};
+
+static const struct l2c_init_data of_aurora_no_outer_data __initconst = {
+        .type = "Aurora",
+        .way_size_0 = SZ_4K,
+        .num_lock = 4,
+        .of_parse = aurora_of_parse,
+        .enable = aurora_enable_no_outer,
+        .fixup = aurora_fixup,
+        .save  = aurora_save,
+        .outer_cache = {
+                .resume      = aurora_resume,
+        },
+};
+
 /*
  * For certain Broadcom SoCs, depending on the address range, different offsets
  * need to be added to the address before passing it to L2 for
@@ -588,16 +1324,16 @@ static void bcm_inv_range(unsigned long start, unsigned long end)
 
         /* normal case, no cross section between start and end */
         if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) {
-                l2x0_inv_range(new_start, new_end);
+                l2c210_inv_range(new_start, new_end);
                 return;
         }
 
         /* They cross sections, so it can only be a cross from section
          * 2 to section 3
          */
-        l2x0_inv_range(new_start,
+        l2c210_inv_range(new_start,
                 bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1));
-        l2x0_inv_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
+        l2c210_inv_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
                 new_end);
 }
 
@@ -610,26 +1346,21 @@ static void bcm_clean_range(unsigned long start, unsigned long end)
         if (unlikely(end <= start))
                 return;
 
-        if ((end - start) >= l2x0_size) {
-                l2x0_clean_all();
-                return;
-        }
-
         new_start = bcm_l2_phys_addr(start);
         new_end = bcm_l2_phys_addr(end);
 
         /* normal case, no cross section between start and end */
         if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) {
-                l2x0_clean_range(new_start, new_end);
+                l2c210_clean_range(new_start, new_end);
                 return;
         }
 
         /* They cross sections, so it can only be a cross from section
          * 2 to section 3
          */
-        l2x0_clean_range(new_start,
+        l2c210_clean_range(new_start,
                 bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1));
-        l2x0_clean_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
+        l2c210_clean_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
                 new_end);
 }
 
@@ -643,7 +1374,7 @@ static void bcm_flush_range(unsigned long start, unsigned long end)
                 return;
 
         if ((end - start) >= l2x0_size) {
-                l2x0_flush_all();
+                outer_cache.flush_all();
                 return;
         }
 
@@ -652,283 +1383,67 @@ static void bcm_flush_range(unsigned long start, unsigned long end)
 
         /* normal case, no cross section between start and end */
         if (likely(bcm_addr_is_sys_emi(end) || !bcm_addr_is_sys_emi(start))) {
-                l2x0_flush_range(new_start, new_end);
+                l2c210_flush_range(new_start, new_end);
                 return;
         }
 
         /* They cross sections, so it can only be a cross from section
          * 2 to section 3
          */
-        l2x0_flush_range(new_start,
+        l2c210_flush_range(new_start,
                 bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR-1));
-        l2x0_flush_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
+        l2c210_flush_range(bcm_l2_phys_addr(BCM_VC_EMI_SEC3_START_ADDR),
                 new_end);
 }
 
-static void __init l2x0_of_setup(const struct device_node *np,
-                                 u32 *aux_val, u32 *aux_mask)
-{
-        u32 data[2] = { 0, 0 };
-        u32 tag = 0;
-        u32 dirty = 0;
-        u32 val = 0, mask = 0;
-
-        of_property_read_u32(np, "arm,tag-latency", &tag);
-        if (tag) {
-                mask |= L2X0_AUX_CTRL_TAG_LATENCY_MASK;
-                val |= (tag - 1) << L2X0_AUX_CTRL_TAG_LATENCY_SHIFT;
-        }
-
-        of_property_read_u32_array(np, "arm,data-latency",
-                                   data, ARRAY_SIZE(data));
-        if (data[0] && data[1]) {
-                mask |= L2X0_AUX_CTRL_DATA_RD_LATENCY_MASK |
-                        L2X0_AUX_CTRL_DATA_WR_LATENCY_MASK;
-                val |= ((data[0] - 1) << L2X0_AUX_CTRL_DATA_RD_LATENCY_SHIFT) |
-                       ((data[1] - 1) << L2X0_AUX_CTRL_DATA_WR_LATENCY_SHIFT);
-        }
-
-        of_property_read_u32(np, "arm,dirty-latency", &dirty);
-        if (dirty) {
-                mask |= L2X0_AUX_CTRL_DIRTY_LATENCY_MASK;
-                val |= (dirty - 1) << L2X0_AUX_CTRL_DIRTY_LATENCY_SHIFT;
-        }
-
-        *aux_val &= ~mask;
-        *aux_val |= val;
-        *aux_mask &= ~mask;
-}
-
-static void __init pl310_of_setup(const struct device_node *np,
-                                  u32 *aux_val, u32 *aux_mask)
-{
-        u32 data[3] = { 0, 0, 0 };
-        u32 tag[3] = { 0, 0, 0 };
-        u32 filter[2] = { 0, 0 };
-
-        of_property_read_u32_array(np, "arm,tag-latency", tag, ARRAY_SIZE(tag));
-        if (tag[0] && tag[1] && tag[2])
-                writel_relaxed(
-                        ((tag[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) |
-                        ((tag[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) |
-                        ((tag[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT),
-                        l2x0_base + L2X0_TAG_LATENCY_CTRL);
-
-        of_property_read_u32_array(np, "arm,data-latency",
-                                   data, ARRAY_SIZE(data));
-        if (data[0] && data[1] && data[2])
-                writel_relaxed(
-                        ((data[0] - 1) << L2X0_LATENCY_CTRL_RD_SHIFT) |
-                        ((data[1] - 1) << L2X0_LATENCY_CTRL_WR_SHIFT) |
-                        ((data[2] - 1) << L2X0_LATENCY_CTRL_SETUP_SHIFT),
-                        l2x0_base + L2X0_DATA_LATENCY_CTRL);
-
-        of_property_read_u32_array(np, "arm,filter-ranges",
-                                   filter, ARRAY_SIZE(filter));
-        if (filter[1]) {
-                writel_relaxed(ALIGN(filter[0] + filter[1], SZ_1M),
-                               l2x0_base + L2X0_ADDR_FILTER_END);
-                writel_relaxed((filter[0] & ~(SZ_1M - 1)) | L2X0_ADDR_FILTER_EN,
-                               l2x0_base + L2X0_ADDR_FILTER_START);
-        }
-}
-
-static void __init pl310_save(void)
-{
-        u32 l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) &
-                L2X0_CACHE_ID_RTL_MASK;
-
-        l2x0_saved_regs.tag_latency = readl_relaxed(l2x0_base +
-                L2X0_TAG_LATENCY_CTRL);
-        l2x0_saved_regs.data_latency = readl_relaxed(l2x0_base +
-                L2X0_DATA_LATENCY_CTRL);
-        l2x0_saved_regs.filter_end = readl_relaxed(l2x0_base +
-                L2X0_ADDR_FILTER_END);
-        l2x0_saved_regs.filter_start = readl_relaxed(l2x0_base +
-                L2X0_ADDR_FILTER_START);
-
-        if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) {
-                /*
-                 * From r2p0, there is Prefetch offset/control register
-                 */
-                l2x0_saved_regs.prefetch_ctrl = readl_relaxed(l2x0_base +
-                        L2X0_PREFETCH_CTRL);
-                /*
-                 * From r3p0, there is Power control register
-                 */
-                if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0)
-                        l2x0_saved_regs.pwr_ctrl = readl_relaxed(l2x0_base +
-                                L2X0_POWER_CTRL);
-        }
-}
+/* Broadcom L2C-310 start from ARMs R3P2 or later, and require no fixups */
+static const struct l2c_init_data of_bcm_l2x0_data __initconst = {
+        .type = "BCM-L2C-310",
+        .way_size_0 = SZ_8K,
+        .num_lock = 8,
+        .of_parse = l2c310_of_parse,
+        .enable = l2c310_enable,
+        .save  = l2c310_save,
+        .outer_cache = {
+                .inv_range   = bcm_inv_range,
+                .clean_range = bcm_clean_range,
+                .flush_range = bcm_flush_range,
+                .flush_all   = l2c210_flush_all,
+                .disable     = l2c310_disable,
+                .sync        = l2c210_sync,
+                .resume      = l2c310_resume,
+        },
+};
 
-static void aurora_save(void)
+static void __init tauros3_save(void __iomem *base)
 {
-        l2x0_saved_regs.ctrl = readl_relaxed(l2x0_base + L2X0_CTRL);
-        l2x0_saved_regs.aux_ctrl = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
-}
+        l2c_save(base);
 
-static void __init tauros3_save(void)
-{
         l2x0_saved_regs.aux2_ctrl =
-                readl_relaxed(l2x0_base + TAUROS3_AUX2_CTRL);
+                readl_relaxed(base + TAUROS3_AUX2_CTRL);
         l2x0_saved_regs.prefetch_ctrl =
-                readl_relaxed(l2x0_base + L2X0_PREFETCH_CTRL);
-}
-
-static void l2x0_resume(void)
-{
-        if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
-                /* restore aux ctrl and enable l2 */
-                l2x0_unlock(readl_relaxed(l2x0_base + L2X0_CACHE_ID));
-
-                writel_relaxed(l2x0_saved_regs.aux_ctrl, l2x0_base +
-                        L2X0_AUX_CTRL);
-
-                l2x0_inv_all();
-
-                writel_relaxed(L2X0_CTRL_EN, l2x0_base + L2X0_CTRL);
-        }
-}
-
-static void pl310_resume(void)
-{
-        u32 l2x0_revision;
-
-        if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
-                /* restore pl310 setup */
-                writel_relaxed(l2x0_saved_regs.tag_latency,
-                        l2x0_base + L2X0_TAG_LATENCY_CTRL);
-                writel_relaxed(l2x0_saved_regs.data_latency,
-                        l2x0_base + L2X0_DATA_LATENCY_CTRL);
-                writel_relaxed(l2x0_saved_regs.filter_end,
-                        l2x0_base + L2X0_ADDR_FILTER_END);
-                writel_relaxed(l2x0_saved_regs.filter_start,
-                        l2x0_base + L2X0_ADDR_FILTER_START);
-
-                l2x0_revision = readl_relaxed(l2x0_base + L2X0_CACHE_ID) &
-                        L2X0_CACHE_ID_RTL_MASK;
-
-                if (l2x0_revision >= L2X0_CACHE_ID_RTL_R2P0) {
-                        writel_relaxed(l2x0_saved_regs.prefetch_ctrl,
-                                l2x0_base + L2X0_PREFETCH_CTRL);
-                        if (l2x0_revision >= L2X0_CACHE_ID_RTL_R3P0)
-                                writel_relaxed(l2x0_saved_regs.pwr_ctrl,
-                                        l2x0_base + L2X0_POWER_CTRL);
-                }
-        }
-
-        l2x0_resume();
-}
-
-static void aurora_resume(void)
-{
-        if (!(readl(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
-                writel_relaxed(l2x0_saved_regs.aux_ctrl,
-                                l2x0_base + L2X0_AUX_CTRL);
-                writel_relaxed(l2x0_saved_regs.ctrl, l2x0_base + L2X0_CTRL);
-        }
+                readl_relaxed(base + L310_PREFETCH_CTRL);
 }
 
 static void tauros3_resume(void)
 {
-        if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
+        void __iomem *base = l2x0_base;
+
+        if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)) {
                 writel_relaxed(l2x0_saved_regs.aux2_ctrl,
-                               l2x0_base + TAUROS3_AUX2_CTRL);
+                               base + TAUROS3_AUX2_CTRL);
                 writel_relaxed(l2x0_saved_regs.prefetch_ctrl,
-                               l2x0_base + L2X0_PREFETCH_CTRL);
-        }
+                               base + L310_PREFETCH_CTRL);
 
-        l2x0_resume();
-}
-
-static void __init aurora_broadcast_l2_commands(void)
-{
-        __u32 u;
-        /* Enable Broadcasting of cache commands to L2*/
-        __asm__ __volatile__("mrc p15, 1, %0, c15, c2, 0" : "=r"(u));
-        u |= AURORA_CTRL_FW;            /* Set the FW bit */
-        __asm__ __volatile__("mcr p15, 1, %0, c15, c2, 0\n" : : "r"(u));
-        isb();
-}
-
-static void __init aurora_of_setup(const struct device_node *np,
-                                u32 *aux_val, u32 *aux_mask)
-{
-        u32 val = AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU;
-        u32 mask =  AURORA_ACR_REPLACEMENT_MASK;
-
-        of_property_read_u32(np, "cache-id-part",
-                        &cache_id_part_number_from_dt);
-
-        /* Determine and save the write policy */
-        l2_wt_override = of_property_read_bool(np, "wt-override");
-
-        if (l2_wt_override) {
-                val |= AURORA_ACR_FORCE_WRITE_THRO_POLICY;
-                mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK;
+                l2c_enable(base, l2x0_saved_regs.aux_ctrl, 8);
         }
-
-        *aux_val &= ~mask;
-        *aux_val |= val;
-        *aux_mask &= ~mask;
 }
 
-static const struct l2x0_of_data pl310_data = {
-        .setup = pl310_of_setup,
-        .save  = pl310_save,
-        .outer_cache = {
-                .resume      = pl310_resume,
-                .inv_range   = l2x0_inv_range,
-                .clean_range = l2x0_clean_range,
-                .flush_range = l2x0_flush_range,
-                .sync        = l2x0_cache_sync,
-                .flush_all   = l2x0_flush_all,
-                .inv_all     = l2x0_inv_all,
-                .disable     = l2x0_disable,
-        },
-};
-
-static const struct l2x0_of_data l2x0_data = {
-        .setup = l2x0_of_setup,
-        .save  = NULL,
-        .outer_cache = {
-                .resume      = l2x0_resume,
-                .inv_range   = l2x0_inv_range,
-                .clean_range = l2x0_clean_range,
-                .flush_range = l2x0_flush_range,
-                .sync        = l2x0_cache_sync,
-                .flush_all   = l2x0_flush_all,
-                .inv_all     = l2x0_inv_all,
-                .disable     = l2x0_disable,
-        },
-};
-
-static const struct l2x0_of_data aurora_with_outer_data = {
-        .setup = aurora_of_setup,
-        .save  = aurora_save,
-        .outer_cache = {
-                .resume      = aurora_resume,
-                .inv_range   = aurora_inv_range,
-                .clean_range = aurora_clean_range,
-                .flush_range = aurora_flush_range,
-                .sync        = l2x0_cache_sync,
-                .flush_all   = l2x0_flush_all,
-                .inv_all     = l2x0_inv_all,
-                .disable     = l2x0_disable,
-        },
-};
-
-static const struct l2x0_of_data aurora_no_outer_data = {
-        .setup = aurora_of_setup,
-        .save  = aurora_save,
-        .outer_cache = {
-                .resume      = aurora_resume,
-        },
-};
-
-static const struct l2x0_of_data tauros3_data = {
-        .setup = NULL,
+static const struct l2c_init_data of_tauros3_data __initconst = {
+        .type = "Tauros3",
+        .way_size_0 = SZ_8K,
+        .num_lock = 8,
+        .enable = l2c_enable,
         .save  = tauros3_save,
         /* Tauros3 broadcasts L1 cache operations to L2 */
         .outer_cache = {
@@ -936,43 +1451,26 @@ static const struct l2x0_of_data tauros3_data = {
         },
 };
 
-static const struct l2x0_of_data bcm_l2x0_data = {
-        .setup = pl310_of_setup,
-        .save  = pl310_save,
-        .outer_cache = {
-                .resume      = pl310_resume,
-                .inv_range   = bcm_inv_range,
-                .clean_range = bcm_clean_range,
-                .flush_range = bcm_flush_range,
-                .sync        = l2x0_cache_sync,
-                .flush_all   = l2x0_flush_all,
-                .inv_all     = l2x0_inv_all,
-                .disable     = l2x0_disable,
-        },
-};
-
+#define L2C_ID(name, fns) { .compatible = name, .data = (void *)&fns }
 static const struct of_device_id l2x0_ids[] __initconst = {
-        { .compatible = "arm,l210-cache", .data = (void *)&l2x0_data },
-        { .compatible = "arm,l220-cache", .data = (void *)&l2x0_data },
-        { .compatible = "arm,pl310-cache", .data = (void *)&pl310_data },
-        { .compatible = "bcm,bcm11351-a2-pl310-cache", /* deprecated name */
-          .data = (void *)&bcm_l2x0_data},
-        { .compatible = "brcm,bcm11351-a2-pl310-cache",
-          .data = (void *)&bcm_l2x0_data},
-        { .compatible = "marvell,aurora-outer-cache",
-          .data = (void *)&aurora_with_outer_data},
-        { .compatible = "marvell,aurora-system-cache",
-          .data = (void *)&aurora_no_outer_data},
-        { .compatible = "marvell,tauros3-cache",
-          .data = (void *)&tauros3_data },
+        L2C_ID("arm,l210-cache", of_l2c210_data),
+        L2C_ID("arm,l220-cache", of_l2c220_data),
+        L2C_ID("arm,pl310-cache", of_l2c310_data),
+        L2C_ID("brcm,bcm11351-a2-pl310-cache", of_bcm_l2x0_data),
+        L2C_ID("marvell,aurora-outer-cache", of_aurora_with_outer_data),
+        L2C_ID("marvell,aurora-system-cache", of_aurora_no_outer_data),
+        L2C_ID("marvell,tauros3-cache", of_tauros3_data),
+        /* Deprecated IDs */
+        L2C_ID("bcm,bcm11351-a2-pl310-cache", of_bcm_l2x0_data),
         {}
 };
 
 int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 {
+        const struct l2c_init_data *data;
         struct device_node *np;
-        const struct l2x0_of_data *data;
         struct resource res;
+        u32 cache_id, old_aux;
 
         np = of_find_matching_node(NULL, l2x0_ids);
         if (!np)
@@ -989,23 +1487,29 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 
         data = of_match_node(l2x0_ids, np)->data;
 
-        /* L2 configuration can only be changed if the cache is disabled */
-        if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) {
-                if (data->setup)
-                        data->setup(np, &aux_val, &aux_mask);
-
-                /* For aurora cache in no outer mode select the
-                 * correct mode using the coprocessor*/
-                if (data == &aurora_no_outer_data)
-                        aurora_broadcast_l2_commands();
+        old_aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL);
+        if (old_aux != ((old_aux & aux_mask) | aux_val)) {
+                pr_warn("L2C: platform modifies aux control register: 0x%08x -> 0x%08x\n",
+                        old_aux, (old_aux & aux_mask) | aux_val);
+        } else if (aux_mask != ~0U && aux_val != 0) {
+                pr_alert("L2C: platform provided aux values match the hardware, so have no effect.  Please remove them.\n");
         }
 
-        if (data->save)
-                data->save();
+        /* All L2 caches are unified, so this property should be specified */
+        if (!of_property_read_bool(np, "cache-unified"))
+                pr_err("L2C: device tree omits to specify unified cache\n");
+
+        /* L2 configuration can only be changed if the cache is disabled */
+        if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN))
+                if (data->of_parse)
+                        data->of_parse(np, &aux_val, &aux_mask);
+
+        if (cache_id_part_number_from_dt)
+                cache_id = cache_id_part_number_from_dt;
+        else
+                cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID);
 
-        of_init = true;
-        memcpy(&outer_cache, &data->outer_cache, sizeof(outer_cache));
-        l2x0_init(l2x0_base, aux_val, aux_mask);
+        __l2c_init(data, aux_val, aux_mask, cache_id);
 
         return 0;
 }
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 778bcf88ee79..615c99e38ba1 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -59,7 +59,7 @@ ENTRY(v7_invalidate_l1)
        bgt     2b
        cmp     r2, #0
        bgt     1b
-       dsb
+       dsb     st
        isb
        mov     pc, lr
 ENDPROC(v7_invalidate_l1)
@@ -166,7 +166,7 @@ skip:
 finished:
         mov     r10, #0                         @ swith back to cache level 0
         mcr     p15, 2, r10, c0, c0, 0          @ select current cache level in cssr
-        dsb
+        dsb     st
         isb
         mov     pc, lr
 ENDPROC(v7_flush_dcache_all)
@@ -335,7 +335,7 @@ ENTRY(v7_flush_kern_dcache_area)
         add     r0, r0, r2
         cmp     r0, r1
         blo     1b
-        dsb
+        dsb     st
         mov     pc, lr
 ENDPROC(v7_flush_kern_dcache_area)
 
@@ -368,7 +368,7 @@ v7_dma_inv_range:
         add     r0, r0, r2
         cmp     r0, r1
         blo     1b
-        dsb
+        dsb     st
         mov     pc, lr
 ENDPROC(v7_dma_inv_range)
 
@@ -390,7 +390,7 @@ v7_dma_clean_range:
         add     r0, r0, r2
         cmp     r0, r1
         blo     1b
-        dsb
+        dsb     st
         mov     pc, lr
 ENDPROC(v7_dma_clean_range)
 
@@ -412,7 +412,7 @@ ENTRY(v7_dma_flush_range)
         add     r0, r0, r2
         cmp     r0, r1
         blo     1b
-        dsb
+        dsb     st
         mov     pc, lr
 ENDPROC(v7_dma_flush_range)
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 6b00be1f971e..b05e08c4734c 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -904,11 +904,12 @@ static void __dma_page_dev_to_cpu(struct page *page, unsigned long off,
         unsigned long paddr = page_to_phys(page) + off;
 
         /* FIXME: non-speculating: not required */
-        /* don't bother invalidating if DMA to device */
-        if (dir != DMA_TO_DEVICE)
+        /* in any case, don't bother invalidating if DMA to device */
+        if (dir != DMA_TO_DEVICE) {
                 outer_inv_range(paddr, paddr + size);
 
-        dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
+                dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
+        }
 
         /*
          * Mark the D-cache clean for these pages to avoid extra flushing.
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 3387e60e4ea3..43d54f5b26b9 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -104,17 +104,20 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsig
 #define flush_icache_alias(pfn,vaddr,len)       do { } while (0)
 #endif
 
+#define FLAG_PA_IS_EXEC 1
+#define FLAG_PA_CORE_IN_MM 2
+
 static void flush_ptrace_access_other(void *args)
 {
         __flush_icache_all();
 }
 
-static
-void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
-                         unsigned long uaddr, void *kaddr, unsigned long len)
+static inline
+void __flush_ptrace_access(struct page *page, unsigned long uaddr, void *kaddr,
+                           unsigned long len, unsigned int flags)
 {
         if (cache_is_vivt()) {
-                if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm))) {
+                if (flags & FLAG_PA_CORE_IN_MM) {
                         unsigned long addr = (unsigned long)kaddr;
                         __cpuc_coherent_kern_range(addr, addr + len);
                 }
@@ -128,7 +131,7 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
         }
 
         /* VIPT non-aliasing D-cache */
-        if (vma->vm_flags & VM_EXEC) {
+        if (flags & FLAG_PA_IS_EXEC) {
                 unsigned long addr = (unsigned long)kaddr;
                 if (icache_is_vipt_aliasing())
                         flush_icache_alias(page_to_pfn(page), uaddr, len);
@@ -140,6 +143,26 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
         }
 }
 
+static
+void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
+                         unsigned long uaddr, void *kaddr, unsigned long len)
+{
+        unsigned int flags = 0;
+        if (cpumask_test_cpu(smp_processor_id(), mm_cpumask(vma->vm_mm)))
+                flags |= FLAG_PA_CORE_IN_MM;
+        if (vma->vm_flags & VM_EXEC)
+                flags |= FLAG_PA_IS_EXEC;
+        __flush_ptrace_access(page, uaddr, kaddr, len, flags);
+}
+
+void flush_uprobe_xol_access(struct page *page, unsigned long uaddr,
+                             void *kaddr, unsigned long len)
+{
+        unsigned int flags = FLAG_PA_CORE_IN_MM|FLAG_PA_IS_EXEC;
+
+        __flush_ptrace_access(page, uaddr, kaddr, len, flags);
+}
+
 /*
  * Copy user data from/to a page which is mapped into a different
  * processes address space.  Really, we want to allow our "user
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index 21b9e1bf9b77..45aeaaca9052 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -18,6 +18,21 @@
 #include <asm/tlbflush.h>
 #include "mm.h"
 
+pte_t *fixmap_page_table;
+
+static inline void set_fixmap_pte(int idx, pte_t pte)
+{
+        unsigned long vaddr = __fix_to_virt(idx);
+        set_pte_ext(fixmap_page_table + idx, pte, 0);
+        local_flush_tlb_kernel_page(vaddr);
+}
+
+static inline pte_t get_fixmap_pte(unsigned long vaddr)
+{
+        unsigned long idx = __virt_to_fix(vaddr);
+        return *(fixmap_page_table + idx);
+}
+
 void *kmap(struct page *page)
 {
         might_sleep();
@@ -63,20 +78,20 @@ void *kmap_atomic(struct page *page)
         type = kmap_atomic_idx_push();
 
         idx = type + KM_TYPE_NR * smp_processor_id();
-        vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+        vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
         /*
          * With debugging enabled, kunmap_atomic forces that entry to 0.
          * Make sure it was indeed properly unmapped.
          */
-        BUG_ON(!pte_none(get_top_pte(vaddr)));
+        BUG_ON(!pte_none(*(fixmap_page_table + idx)));
 #endif
         /*
          * When debugging is off, kunmap_atomic leaves the previous mapping
          * in place, so the contained TLB flush ensures the TLB is updated
          * with the new mapping.
          */
-        set_top_pte(vaddr, mk_pte(page, kmap_prot));
+        set_fixmap_pte(idx, mk_pte(page, kmap_prot));
 
         return (void *)vaddr;
 }
@@ -94,8 +109,8 @@ void __kunmap_atomic(void *kvaddr)
                 if (cache_is_vivt())
                         __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
 #ifdef CONFIG_DEBUG_HIGHMEM
-                BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
-                set_top_pte(vaddr, __pte(0));
+                BUG_ON(vaddr != __fix_to_virt(idx));
+                set_fixmap_pte(idx, __pte(0));
 #else
                 (void) idx;  /* to kill a warning */
 #endif
@@ -117,11 +132,11 @@ void *kmap_atomic_pfn(unsigned long pfn)
 
         type = kmap_atomic_idx_push();
         idx = type + KM_TYPE_NR * smp_processor_id();
-        vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
+        vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
-        BUG_ON(!pte_none(get_top_pte(vaddr)));
+        BUG_ON(!pte_none(*(fixmap_page_table + idx)));
 #endif
-        set_top_pte(vaddr, pfn_pte(pfn, kmap_prot));
+        set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot));
 
         return (void *)vaddr;
 }
@@ -133,5 +148,5 @@ struct page *kmap_atomic_to_page(const void *ptr)
         if (vaddr < FIXADDR_START)
                 return virt_to_page(ptr);
 
-        return pte_page(get_top_pte(vaddr));
+        return pte_page(get_fixmap_pte(vaddr));
 }
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 13ce33e096b5..5958ac05181e 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -90,24 +90,21 @@ __tagtable(ATAG_INITRD2, parse_tag_initrd2);
  * initialization functions, as well as show_mem() for the skipping
  * of holes in the memory map.  It is populated by arm_add_memory().
  */
-struct meminfo meminfo;
-
 void show_mem(unsigned int filter)
 {
         int free = 0, total = 0, reserved = 0;
-        int shared = 0, cached = 0, slab = 0, i;
-        struct meminfo * mi = &meminfo;
+        int shared = 0, cached = 0, slab = 0;
+        struct memblock_region *reg;
 
         printk("Mem-info:\n");
         show_free_areas(filter);
 
-        for_each_bank (i, mi) {
-                struct membank *bank = &mi->bank[i];
+        for_each_memblock (memory, reg) {
                 unsigned int pfn1, pfn2;
                 struct page *page, *end;
 
-                pfn1 = bank_pfn_start(bank);
-                pfn2 = bank_pfn_end(bank);
+                pfn1 = memblock_region_memory_base_pfn(reg);
+                pfn2 = memblock_region_memory_end_pfn(reg);
 
                 page = pfn_to_page(pfn1);
                 end  = pfn_to_page(pfn2 - 1) + 1;
@@ -124,8 +121,9 @@ void show_mem(unsigned int filter)
                                 free++;
                         else
                                 shared += page_count(page) - 1;
-                        page++;
-                } while (page < end);
+                        pfn1++;
+                        page = pfn_to_page(pfn1);
+                } while (pfn1 < pfn2);
         }
 
         printk("%d pages of RAM\n", total);
@@ -139,16 +137,9 @@ void show_mem(unsigned int filter)
 static void __init find_limits(unsigned long *min, unsigned long *max_low,
                                unsigned long *max_high)
 {
-        struct meminfo *mi = &meminfo;
-        int i;
-
-        /* This assumes the meminfo array is properly sorted */
-        *min = bank_pfn_start(&mi->bank[0]);
-        for_each_bank (i, mi)
-                if (mi->bank[i].highmem)
-                                break;
-        *max_low = bank_pfn_end(&mi->bank[i - 1]);
-        *max_high = bank_pfn_end(&mi->bank[mi->nr_banks - 1]);
+        *max_low = PFN_DOWN(memblock_get_current_limit());
+        *min = PFN_UP(memblock_start_of_DRAM());
+        *max_high = PFN_DOWN(memblock_end_of_DRAM());
 }
 
 #ifdef CONFIG_ZONE_DMA
@@ -283,14 +274,8 @@ phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align)
         return phys;
 }
 
-void __init arm_memblock_init(struct meminfo *mi,
-        const struct machine_desc *mdesc)
+void __init arm_memblock_init(const struct machine_desc *mdesc)
 {
-        int i;
-
-        for (i = 0; i < mi->nr_banks; i++)
-                memblock_add(mi->bank[i].start, mi->bank[i].size);
-
         /* Register the kernel text, kernel data and initrd with memblock. */
 #ifdef CONFIG_XIP_KERNEL
         memblock_reserve(__pa(_sdata), _end - _sdata);
@@ -422,54 +407,53 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 /*
  * The mem_map array can get very big.  Free the unused area of the memory map.
  */
-static void __init free_unused_memmap(struct meminfo *mi)
+static void __init free_unused_memmap(void)
 {
-        unsigned long bank_start, prev_bank_end = 0;
-        unsigned int i;
+        unsigned long start, prev_end = 0;
+        struct memblock_region *reg;
 
         /*
          * This relies on each bank being in address order.
          * The banks are sorted previously in bootmem_init().
          */
-        for_each_bank(i, mi) {
-                struct membank *bank = &mi->bank[i];
-
-                bank_start = bank_pfn_start(bank);
+        for_each_memblock(memory, reg) {
+                start = memblock_region_memory_base_pfn(reg);
 
 #ifdef CONFIG_SPARSEMEM
                 /*
                  * Take care not to free memmap entries that don't exist
                  * due to SPARSEMEM sections which aren't present.
                  */
-                bank_start = min(bank_start,
-                                 ALIGN(prev_bank_end, PAGES_PER_SECTION));
+                start = min(start,
+                                 ALIGN(prev_end, PAGES_PER_SECTION));
 #else
                 /*
                  * Align down here since the VM subsystem insists that the
                  * memmap entries are valid from the bank start aligned to
                  * MAX_ORDER_NR_PAGES.
                  */
-                bank_start = round_down(bank_start, MAX_ORDER_NR_PAGES);
+                start = round_down(start, MAX_ORDER_NR_PAGES);
 #endif
                 /*
                  * If we had a previous bank, and there is a space
                  * between the current bank and the previous, free it.
                  */
-                if (prev_bank_end && prev_bank_end < bank_start)
-                        free_memmap(prev_bank_end, bank_start);
+                if (prev_end && prev_end < start)
+                        free_memmap(prev_end, start);
 
                 /*
                  * Align up here since the VM subsystem insists that the
                  * memmap entries are valid from the bank end aligned to
                  * MAX_ORDER_NR_PAGES.
                  */
-                prev_bank_end = ALIGN(bank_pfn_end(bank), MAX_ORDER_NR_PAGES);
+                prev_end = ALIGN(memblock_region_memory_end_pfn(reg),
+                                 MAX_ORDER_NR_PAGES);
         }
 
 #ifdef CONFIG_SPARSEMEM
-        if (!IS_ALIGNED(prev_bank_end, PAGES_PER_SECTION))
-                free_memmap(prev_bank_end,
-                            ALIGN(prev_bank_end, PAGES_PER_SECTION));
+        if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION))
+                free_memmap(prev_end,
+                            ALIGN(prev_end, PAGES_PER_SECTION));
 #endif
 }
 
@@ -545,7 +529,7 @@ void __init mem_init(void)
         set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
 
         /* this will put all unused low memory onto the freelists */
-        free_unused_memmap(&meminfo);
+        free_unused_memmap();
         free_all_bootmem();
 
 #ifdef CONFIG_SA1111
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index f9c32ba73544..d1e5ad7ab3bc 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -438,6 +438,13 @@ void __arm_iounmap(volatile void __iomem *io_addr)
 EXPORT_SYMBOL(__arm_iounmap);
 
 #ifdef CONFIG_PCI
+static int pci_ioremap_mem_type = MT_DEVICE;
+
+void pci_ioremap_set_mem_type(int mem_type)
+{
+        pci_ioremap_mem_type = mem_type;
+}
+
 int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr)
 {
         BUG_ON(offset + SZ_64K > IO_SPACE_LIMIT);
@@ -445,7 +452,7 @@ int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr)
         return ioremap_page_range(PCI_IO_VIRT_BASE + offset,
                                   PCI_IO_VIRT_BASE + offset + SZ_64K,
                                   phys_addr,
-                                  __pgprot(get_mem_type(MT_DEVICE)->prot_pte));
+                                  __pgprot(get_mem_type(pci_ioremap_mem_type)->prot_pte));
 }
 EXPORT_SYMBOL_GPL(pci_ioremap_io);
 #endif
diff --git a/arch/arm/mm/l2c-common.c b/arch/arm/mm/l2c-common.c
new file mode 100644
index 000000000000..10a3cf28c362
--- /dev/null
+++ b/arch/arm/mm/l2c-common.c
@@ -0,0 +1,20 @@
+/*
+ * Copyright (C) 2010 ARM Ltd.
+ * Written by Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * 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.
+ */
+#include <linux/bug.h>
+#include <linux/smp.h>
+#include <asm/outercache.h>
+
+void outer_disable(void)
+{
+        WARN_ON(!irqs_disabled());
+        WARN_ON(num_online_cpus() > 1);
+
+        if (outer_cache.disable)
+                outer_cache.disable();
+}
diff --git a/arch/arm/mm/l2c-l2x0-resume.S b/arch/arm/mm/l2c-l2x0-resume.S
new file mode 100644
index 000000000000..99b05f21a59a
--- /dev/null
+++ b/arch/arm/mm/l2c-l2x0-resume.S
@@ -0,0 +1,58 @@
+/*
+ * L2C-310 early resume code.  This can be used by platforms to restore
+ * the settings of their L2 cache controller before restoring the
+ * processor state.
+ *
+ * This code can only be used to if you are running in the secure world.
+ */
+#include <linux/linkage.h>
+#include <asm/hardware/cache-l2x0.h>
+
+        .text
+
+ENTRY(l2c310_early_resume)
+        adr     r0, 1f
+        ldr     r2, [r0]
+        add     r0, r2, r0
+
+        ldmia   r0, {r1, r2, r3, r4, r5, r6, r7, r8}
+        @ r1 = phys address of L2C-310 controller
+        @ r2 = aux_ctrl
+        @ r3 = tag_latency
+        @ r4 = data_latency
+        @ r5 = filter_start
+        @ r6 = filter_end
+        @ r7 = prefetch_ctrl
+        @ r8 = pwr_ctrl
+
+        @ Check that the address has been initialised
+        teq     r1, #0
+        moveq   pc, lr
+
+        @ The prefetch and power control registers are revision dependent
+        @ and can be written whether or not the L2 cache is enabled
+        ldr     r0, [r1, #L2X0_CACHE_ID]
+        and     r0, r0, #L2X0_CACHE_ID_RTL_MASK
+        cmp     r0, #L310_CACHE_ID_RTL_R2P0
+        strcs   r7, [r1, #L310_PREFETCH_CTRL]
+        cmp     r0, #L310_CACHE_ID_RTL_R3P0
+        strcs   r8, [r1, #L310_POWER_CTRL]
+
+        @ Don't setup the L2 cache if it is already enabled
+        ldr     r0, [r1, #L2X0_CTRL]
+        tst     r0, #L2X0_CTRL_EN
+        movne   pc, lr
+
+        str     r3, [r1, #L310_TAG_LATENCY_CTRL]
+        str     r4, [r1, #L310_DATA_LATENCY_CTRL]
+        str     r6, [r1, #L310_ADDR_FILTER_END]
+        str     r5, [r1, #L310_ADDR_FILTER_START]
+
+        str     r2, [r1, #L2X0_AUX_CTRL]
+        mov     r9, #L2X0_CTRL_EN
+        str     r9, [r1, #L2X0_CTRL]
+        mov     pc, lr
+ENDPROC(l2c310_early_resume)
+
+        .align
+1:      .long   l2x0_saved_regs - .
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index df875c457068..ab14b79b03f0 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -35,6 +35,7 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/pci.h>
+#include <asm/fixmap.h>
 
 #include "mm.h"
 #include "tcm.h"
@@ -1074,74 +1075,47 @@ phys_addr_t arm_lowmem_limit __initdata = 0;
 void __init sanity_check_meminfo(void)
 {
         phys_addr_t memblock_limit = 0;
-        int i, j, highmem = 0;
+        int highmem = 0;
         phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;
+        struct memblock_region *reg;
 
-        for (i = 0, j = 0; i < meminfo.nr_banks; i++) {
-                struct membank *bank = &meminfo.bank[j];
-                phys_addr_t size_limit;
-
-                *bank = meminfo.bank[i];
-                size_limit = bank->size;
+        for_each_memblock(memory, reg) {
+                phys_addr_t block_start = reg->base;
+                phys_addr_t block_end = reg->base + reg->size;
+                phys_addr_t size_limit = reg->size;
 
-                if (bank->start >= vmalloc_limit)
+                if (reg->base >= vmalloc_limit)
                         highmem = 1;
                 else
-                        size_limit = vmalloc_limit - bank->start;
+                        size_limit = vmalloc_limit - reg->base;
 
-                bank->highmem = highmem;
 
-#ifdef CONFIG_HIGHMEM
-                /*
-                 * Split those memory banks which are partially overlapping
-                 * the vmalloc area greatly simplifying things later.
-                 */
-                if (!highmem && bank->size > size_limit) {
-                        if (meminfo.nr_banks >= NR_BANKS) {
-                                printk(KERN_CRIT "NR_BANKS too low, "
-                                                 "ignoring high memory\n");
-                        } else {
-                                memmove(bank + 1, bank,
-                                        (meminfo.nr_banks - i) * sizeof(*bank));
-                                meminfo.nr_banks++;
-                                i++;
-                                bank[1].size -= size_limit;
-                                bank[1].start = vmalloc_limit;
-                                bank[1].highmem = highmem = 1;
-                                j++;
+                if (!IS_ENABLED(CONFIG_HIGHMEM) || cache_is_vipt_aliasing()) {
+
+                        if (highmem) {
+                                pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n",
+                                        &block_start, &block_end);
+                                memblock_remove(reg->base, reg->size);
+                                continue;
                         }
-                        bank->size = size_limit;
-                }
-#else
-                /*
-                 * Highmem banks not allowed with !CONFIG_HIGHMEM.
-                 */
-                if (highmem) {
-                        printk(KERN_NOTICE "Ignoring RAM at %.8llx-%.8llx "
-                               "(!CONFIG_HIGHMEM).\n",
-                               (unsigned long long)bank->start,
-                               (unsigned long long)bank->start + bank->size - 1);
-                        continue;
-                }
 
-                /*
-                 * Check whether this memory bank would partially overlap
-                 * the vmalloc area.
-                 */
-                if (bank->size > size_limit) {
-                        printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx "
-                               "to -%.8llx (vmalloc region overlap).\n",
-                               (unsigned long long)bank->start,
-                               (unsigned long long)bank->start + bank->size - 1,
-                               (unsigned long long)bank->start + size_limit - 1);
-                        bank->size = size_limit;
+                        if (reg->size > size_limit) {
+                                phys_addr_t overlap_size = reg->size - size_limit;
+
+                                pr_notice("Truncating RAM at %pa-%pa to -%pa",
+                                      &block_start, &block_end, &vmalloc_limit);
+                                memblock_remove(vmalloc_limit, overlap_size);
+                                block_end = vmalloc_limit;
+                        }
                 }
-#endif
-                if (!bank->highmem) {
-                        phys_addr_t bank_end = bank->start + bank->size;
 
-                        if (bank_end > arm_lowmem_limit)
-                                arm_lowmem_limit = bank_end;
+                if (!highmem) {
+                        if (block_end > arm_lowmem_limit) {
+                                if (reg->size > size_limit)
+                                        arm_lowmem_limit = vmalloc_limit;
+                                else
+                                        arm_lowmem_limit = block_end;
+                        }
 
                         /*
                          * Find the first non-section-aligned page, and point
@@ -1157,35 +1131,15 @@ void __init sanity_check_meminfo(void)
                          * occurs before any free memory is mapped.
                          */
                         if (!memblock_limit) {
-                                if (!IS_ALIGNED(bank->start, SECTION_SIZE))
-                                        memblock_limit = bank->start;
-                                else if (!IS_ALIGNED(bank_end, SECTION_SIZE))
-                                        memblock_limit = bank_end;
+                                if (!IS_ALIGNED(block_start, SECTION_SIZE))
+                                        memblock_limit = block_start;
+                                else if (!IS_ALIGNED(block_end, SECTION_SIZE))
+                                        memblock_limit = arm_lowmem_limit;
                         }
-                }
-                j++;
-        }
-#ifdef CONFIG_HIGHMEM
-        if (highmem) {
-                const char *reason = NULL;
 
-                if (cache_is_vipt_aliasing()) {
-                        /*
-                         * Interactions between kmap and other mappings
-                         * make highmem support with aliasing VIPT caches
-                         * rather difficult.
-                         */
-                        reason = "with VIPT aliasing cache";
-                }
-                if (reason) {
-                        printk(KERN_CRIT "HIGHMEM is not supported %s, ignoring high memory\n",
-                                reason);
-                        while (j > 0 && meminfo.bank[j - 1].highmem)
-                                j--;
                 }
         }
-#endif
-        meminfo.nr_banks = j;
+
         high_memory = __va(arm_lowmem_limit - 1) + 1;
 
         /*
@@ -1372,6 +1326,9 @@ static void __init kmap_init(void)
 #ifdef CONFIG_HIGHMEM
         pkmap_page_table = early_pte_alloc(pmd_off_k(PKMAP_BASE),
                 PKMAP_BASE, _PAGE_KERNEL_TABLE);
+
+        fixmap_page_table = early_pte_alloc(pmd_off_k(FIXADDR_START),
+                FIXADDR_START, _PAGE_KERNEL_TABLE);
 #endif
 }
 
@@ -1474,7 +1431,7 @@ void __init early_paging_init(const struct machine_desc *mdesc,
          * just complicate the code.
          */
         flush_cache_louis();
-        dsb();
+        dsb(ishst);
         isb();
 
         /* remap level 1 table */
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 55764a7ef1f0..da1874f9f8cf 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -88,30 +88,35 @@ static unsigned long irbar_read(void)
 void __init sanity_check_meminfo_mpu(void)
 {
         int i;
-        struct membank *bank = meminfo.bank;
         phys_addr_t phys_offset = PHYS_OFFSET;
         phys_addr_t aligned_region_size, specified_mem_size, rounded_mem_size;
-
-        /* Initially only use memory continuous from PHYS_OFFSET */
-        if (bank_phys_start(&bank[0]) != phys_offset)
-                panic("First memory bank must be contiguous from PHYS_OFFSET");
-
-        /* Banks have already been sorted by start address */
-        for (i = 1; i < meminfo.nr_banks; i++) {
-                if (bank[i].start <= bank_phys_end(&bank[0]) &&
-                    bank_phys_end(&bank[i]) > bank_phys_end(&bank[0])) {
-                        bank[0].size = bank_phys_end(&bank[i]) - bank[0].start;
+        struct memblock_region *reg;
+        bool first = true;
+        phys_addr_t mem_start;
+        phys_addr_t mem_end;
+
+        for_each_memblock(memory, reg) {
+                if (first) {
+                        /*
+                         * Initially only use memory continuous from
+                         * PHYS_OFFSET */
+                        if (reg->base != phys_offset)
+                                panic("First memory bank must be contiguous from PHYS_OFFSET");
+
+                        mem_start = reg->base;
+                        mem_end = reg->base + reg->size;
+                        specified_mem_size = reg->size;
+                        first = false;
                 } else {
-                        pr_notice("Ignoring RAM after 0x%.8lx. "
-                        "First non-contiguous (ignored) bank start: 0x%.8lx\n",
-                                (unsigned long)bank_phys_end(&bank[0]),
-                                (unsigned long)bank_phys_start(&bank[i]));
-                        break;
+                        /*
+                         * memblock auto merges contiguous blocks, remove
+                         * all blocks afterwards
+                         */
+                        pr_notice("Ignoring RAM after %pa, memory at %pa ignored\n",
+                                  &mem_start, &reg->base);
+                        memblock_remove(reg->base, reg->size);
                 }
         }
-        /* All contiguous banks are now merged in to the first bank */
-        meminfo.nr_banks = 1;
-        specified_mem_size = bank[0].size;
 
         /*
          * MPU has curious alignment requirements: Size must be power of 2, and
@@ -128,23 +133,24 @@ void __init sanity_check_meminfo_mpu(void)
          */
         aligned_region_size = (phys_offset - 1) ^ (phys_offset);
         /* Find the max power-of-two sized region that fits inside our bank */
-        rounded_mem_size = (1 <<  __fls(bank[0].size)) - 1;
+        rounded_mem_size = (1 <<  __fls(specified_mem_size)) - 1;
 
         /* The actual region size is the smaller of the two */
         aligned_region_size = aligned_region_size < rounded_mem_size
                                 ? aligned_region_size + 1
                                 : rounded_mem_size + 1;
 
-        if (aligned_region_size != specified_mem_size)
-                pr_warn("Truncating memory from 0x%.8lx to 0x%.8lx (MPU region constraints)",
-                                (unsigned long)specified_mem_size,
-                                (unsigned long)aligned_region_size);
+        if (aligned_region_size != specified_mem_size) {
+                pr_warn("Truncating memory from %pa to %pa (MPU region constraints)",
+                                &specified_mem_size, &aligned_region_size);
+                memblock_remove(mem_start + aligned_region_size,
+                                specified_mem_size - aligned_round_size);
+
+                mem_end = mem_start + aligned_region_size;
+        }
 
-        meminfo.bank[0].size = aligned_region_size;
-        pr_debug("MPU Region from 0x%.8lx size 0x%.8lx (end 0x%.8lx))\n",
-                (unsigned long)phys_offset,
-                (unsigned long)aligned_region_size,
-                (unsigned long)bank_phys_end(&bank[0]));
+        pr_debug("MPU Region from %pa size %pa (end %pa))\n",
+                &phys_offset, &aligned_region_size, &mem_end);
 
 }
 
@@ -292,7 +298,7 @@ void __init sanity_check_meminfo(void)
 {
         phys_addr_t end;
         sanity_check_meminfo_mpu();
-        end = bank_phys_end(&meminfo.bank[meminfo.nr_banks - 1]);
+        end = memblock_end_of_DRAM();
         high_memory = __va(end - 1) + 1;
 }
 
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 01a719e18bb0..22e3ad63500c 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -64,6 +64,14 @@ ENTRY(cpu_v7_switch_mm)
         mov     pc, lr
 ENDPROC(cpu_v7_switch_mm)
 
+#ifdef __ARMEB__
+#define rl r3
+#define rh r2
+#else
+#define rl r2
+#define rh r3
+#endif
+
 /*
  * cpu_v7_set_pte_ext(ptep, pte)
  *
@@ -73,13 +81,13 @@ ENDPROC(cpu_v7_switch_mm)
  */
 ENTRY(cpu_v7_set_pte_ext)
 #ifdef CONFIG_MMU
-        tst     r2, #L_PTE_VALID
+        tst     rl, #L_PTE_VALID
         beq     1f
-        tst     r3, #1 << (57 - 32)             @ L_PTE_NONE
-        bicne   r2, #L_PTE_VALID
+        tst     rh, #1 << (57 - 32)             @ L_PTE_NONE
+        bicne   rl, #L_PTE_VALID
         bne     1f
-        tst     r3, #1 << (55 - 32)             @ L_PTE_DIRTY
-        orreq   r2, #L_PTE_RDONLY
+        tst     rh, #1 << (55 - 32)             @ L_PTE_DIRTY
+        orreq   rl, #L_PTE_RDONLY
 1:      strd    r2, r3, [r0]
         ALT_SMP(W(nop))
         ALT_UP (mcr     p15, 0, r0, c7, c10, 1)         @ flush_pte
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 195731d3813b..3db2c2f04a30 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -169,9 +169,31 @@ ENDPROC(cpu_pj4b_do_idle)
         globl_equ       cpu_pj4b_do_idle,       cpu_v7_do_idle
 #endif
         globl_equ       cpu_pj4b_dcache_clean_area,     cpu_v7_dcache_clean_area
-        globl_equ       cpu_pj4b_do_suspend,    cpu_v7_do_suspend
-        globl_equ       cpu_pj4b_do_resume,     cpu_v7_do_resume
-        globl_equ       cpu_pj4b_suspend_size,  cpu_v7_suspend_size
+#ifdef CONFIG_ARM_CPU_SUSPEND
+ENTRY(cpu_pj4b_do_suspend)
+        stmfd   sp!, {r6 - r10}
+        mrc     p15, 1, r6, c15, c1, 0  @ save CP15 - extra features
+        mrc     p15, 1, r7, c15, c2, 0  @ save CP15 - Aux Func Modes Ctrl 0
+        mrc     p15, 1, r8, c15, c1, 2  @ save CP15 - Aux Debug Modes Ctrl 2
+        mrc     p15, 1, r9, c15, c1, 1  @ save CP15 - Aux Debug Modes Ctrl 1
+        mrc     p15, 0, r10, c9, c14, 0  @ save CP15 - PMC
+        stmia   r0!, {r6 - r10}
+        ldmfd   sp!, {r6 - r10}
+        b cpu_v7_do_suspend
+ENDPROC(cpu_pj4b_do_suspend)
+
+ENTRY(cpu_pj4b_do_resume)
+        ldmia   r0!, {r6 - r10}
+        mcr     p15, 1, r6, c15, c1, 0  @ save CP15 - extra features
+        mcr     p15, 1, r7, c15, c2, 0  @ save CP15 - Aux Func Modes Ctrl 0
+        mcr     p15, 1, r8, c15, c1, 2  @ save CP15 - Aux Debug Modes Ctrl 2
+        mcr     p15, 1, r9, c15, c1, 1  @ save CP15 - Aux Debug Modes Ctrl 1
+        mcr     p15, 0, r10, c9, c14, 0  @ save CP15 - PMC
+        b cpu_v7_do_resume
+ENDPROC(cpu_pj4b_do_resume)
+#endif
+.globl  cpu_pj4b_suspend_size
+.equ    cpu_pj4b_suspend_size, 4 * 14
 
 #endif
 
@@ -194,6 +216,7 @@ __v7_cr7mp_setup:
 __v7_ca7mp_setup:
 __v7_ca12mp_setup:
 __v7_ca15mp_setup:
+__v7_ca17mp_setup:
         mov     r10, #0
 1:
 #ifdef CONFIG_SMP
@@ -505,6 +528,16 @@ __v7_ca15mp_proc_info:
         .size   __v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info
 
         /*
+         * ARM Ltd. Cortex A17 processor.
+         */
+        .type   __v7_ca17mp_proc_info, #object
+__v7_ca17mp_proc_info:
+        .long   0x410fc0e0
+        .long   0xff0ffff0
+        __v7_proc __v7_ca17mp_setup
+        .size   __v7_ca17mp_proc_info, . - __v7_ca17mp_proc_info
+
+        /*
          * Qualcomm Inc. Krait processors.
          */
         .type   __krait_proc_info, #object
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 0c93588fcb91..1ca37c72f12f 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -123,6 +123,11 @@ __v7m_setup:
         mov     pc, lr
 ENDPROC(__v7m_setup)
 
+        .align 2
+__v7m_setup_stack:
+        .space  4 * 8                           @ 8 registers
+__v7m_setup_stack_top:
+
         define_processor_functions v7m, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1
 
         .section ".rodata"
@@ -152,6 +157,3 @@ __v7m_proc_info:
         .long   nop_cache_fns           @ proc_info_list.cache
         .size   __v7m_proc_info, . - __v7m_proc_info
 
-__v7m_setup_stack:
-        .space  4 * 8                           @ 8 registers
-__v7m_setup_stack_top:
diff --git a/arch/arm/plat-samsung/s5p-sleep.S b/arch/arm/plat-samsung/s5p-sleep.S
index c5001659bdf8..25c68ceb9e2b 100644
--- a/arch/arm/plat-samsung/s5p-sleep.S
+++ b/arch/arm/plat-samsung/s5p-sleep.S
@@ -22,7 +22,6 @@
 */
 
 #include <linux/linkage.h>
-#include <asm/asm-offsets.h>
 
         .data
         .align
diff --git a/arch/arm/vfp/entry.S b/arch/arm/vfp/entry.S
index f0759e70fb86..fe6ca574d093 100644
--- a/arch/arm/vfp/entry.S
+++ b/arch/arm/vfp/entry.S
@@ -22,11 +22,10 @@
 @  r9  = normal "successful" return address
 @  r10 = this threads thread_info structure
 @  lr  = unrecognised instruction return address
-@  IRQs disabled.
+@  IRQs enabled.
 @
 ENTRY(do_vfp)
         inc_preempt_count r10, r4
-        enable_irq
         ldr     r4, .LCvfp
         ldr     r11, [r10, #TI_CPU]     @ CPU number
         add     r10, r10, #TI_VFPSTATE  @ r10 = workspace
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 63b5eff0a80f..fdd7e1b61f60 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -47,6 +47,7 @@ struct amba_driver {
 enum amba_vendor {
         AMBA_VENDOR_ARM = 0x41,
         AMBA_VENDOR_ST = 0x80,
+        AMBA_VENDOR_QCOM = 0x51,
 };
 
 extern struct bus_type amba_bustype;
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index f73cabf59012..38bbf95109da 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -320,6 +320,8 @@ extern unsigned long get_safe_page(gfp_t gfp_mask);
 extern void hibernation_set_ops(const struct platform_hibernation_ops *ops);
 extern int hibernate(void);
 extern bool system_entering_hibernation(void);
+asmlinkage int swsusp_save(void);
+extern struct pbe *restore_pblist;
 #else /* CONFIG_HIBERNATION */
 static inline void register_nosave_region(unsigned long b, unsigned long e) {}
 static inline void register_nosave_region_late(unsigned long b, unsigned long e) {}
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index edff2b97b864..c52f827ba6ce 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -32,6 +32,7 @@ struct vm_area_struct;
 struct mm_struct;
 struct inode;
 struct notifier_block;
+struct page;
 
 #define UPROBE_HANDLER_REMOVE           1
 #define UPROBE_HANDLER_MASK             1
@@ -127,6 +128,8 @@ extern int  arch_uprobe_exception_notify(struct notifier_block *self, unsigned l
 extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
 extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
 extern bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs);
+extern void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
+                                         void *src, unsigned long len);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 04709b66369d..4968213c63fa 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1296,14 +1296,8 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe)
         if (unlikely(!xol_vaddr))
                 return 0;
 
-        /* Initialize the slot */
-        copy_to_page(area->page, xol_vaddr,
-                        &uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
-        /*
-         * We probably need flush_icache_user_range() but it needs vma.
-         * This should work on supported architectures too.
-         */
-        flush_dcache_page(area->page);
+        arch_uprobe_copy_ixol(area->page, xol_vaddr,
+                              &uprobe->arch.ixol, sizeof(uprobe->arch.ixol));
 
         return xol_vaddr;
 }
@@ -1346,6 +1340,21 @@ static void xol_free_insn_slot(struct task_struct *tsk)
         }
 }
 
+void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
+                                  void *src, unsigned long len)
+{
+        /* Initialize the slot */
+        copy_to_page(page, vaddr, src, len);
+
+        /*
+         * We probably need flush_icache_user_range() but it needs vma.
+         * This should work on most of architectures by default. If
+         * architecture needs to do something different it can define
+         * its own version of the function.
+         */
+        flush_dcache_page(page);
+}
+
 /**
  * uprobe_get_swbp_addr - compute address of swbp given post-swbp regs
  * @regs: Reflects the saved state of the task after it has hit a breakpoint