Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm

Pull ARM changes from Russell King:

 - Perf updates from Will Deacon:
   - Support for Qualcomm Krait processors (run perf on your phone!)
   - Support for Cortex-A12 (run perf stat on your FPGA!)
   - Support for perf_sample_event_took, allowing us to automatically decrease
     the sample rate if we can't handle the PMU interrupts quickly enough
     (run perf record on your FPGA!).

 - Basic uprobes support from David Long:
     This patch series adds basic uprobes support to ARM. It is based on
     patches developed earlier by Rabin Vincent. That approach of adding
     hooks into the kprobes instruction parsing code was not well received.
     This approach separates the ARM instruction parsing code in kprobes out
     into a separate set of functions which can be used by both kprobes and
     uprobes. Both kprobes and uprobes then provide their own semantic action
     tables to process the results of the parsing.

 - ARMv7M (microcontroller) updates from Uwe Kleine-König

 - OMAP DMA updates (recently added Vinod's Ack even though they've been
   sitting in linux-next for a few months) to reduce the reliance of
   omap-dma on the code in arch/arm.

 - SA11x0 changes from Dmitry Eremin-Solenikov and Alexander Shiyan

 - Support for Cortex-A12 CPU

 - Align support for ARMv6 with ARMv7 so they can cooperate better in a
   single zImage.

 - Addition of first AT_HWCAP2 feature bits for ARMv8 crypto support.

 - Removal of IRQ_DISABLED from various ARM files

 - Improved efficiency of virt_to_page() for single zImage

 - Patch from Ulf Hansson to permit runtime PM callbacks to be available for
   AMBA devices for suspend/resume as well.

 - Finally kill asm/system.h on ARM.

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (89 commits)
  dmaengine: omap-dma: more consolidation of CCR register setup
  dmaengine: omap-dma: move IRQ handling to omap-dma
  dmaengine: omap-dma: move register read/writes into omap-dma.c
  ARM: omap: dma: get rid of 'p' allocation and clean up
  ARM: omap: move dma channel allocation into plat-omap code
  ARM: omap: dma: get rid of errata global
  ARM: omap: clean up DMA register accesses
  ARM: omap: remove almost-const variables
  ARM: omap: remove references to disable_irq_lch
  dmaengine: omap-dma: cleanup errata 3.3 handling
  dmaengine: omap-dma: provide register read/write functions
  dmaengine: omap-dma: use cached CCR value when enabling DMA
  dmaengine: omap-dma: move barrier to omap_dma_start_desc()
  dmaengine: omap-dma: move clnk_ctrl setting to preparation functions
  dmaengine: omap-dma: improve efficiency loading C.SA/C.EI/C.FI registers
  dmaengine: omap-dma: consolidate clearing channel status register
  dmaengine: omap-dma: move CCR buffering disable errata out of the fast path
  dmaengine: omap-dma: provide register definitions
  dmaengine: omap-dma: consolidate setup of CCR
  dmaengine: omap-dma: consolidate setup of CSDP
  ...

1 files changed, 100 insertions, 37 deletions

diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 00df012c4678..3c217694ebec 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -68,6 +68,12 @@ EXPORT_SYMBOL(__aeabi_unwind_cpp_pr2);
 struct unwind_ctrl_block {
 	unsigned long vrs[16];		/* virtual register set */
 	const unsigned long *insn;	/* pointer to the current instructions word */
+	unsigned long sp_high;		/* highest value of sp allowed */
+	/*
+	 * 1 : check for stack overflow for each register pop.
+	 * 0 : save overhead if there is plenty of stack remaining.
+	 */
+	int check_each_pop;
 	int entries;			/* number of entries left to interpret */
 	int byte;			/* current byte number in the instructions word */
 };
@@ -235,12 +241,85 @@ static unsigned long unwind_get_byte(struct unwind_ctrl_block *ctrl)
 	return ret;
 }
 
+/* Before poping a register check whether it is feasible or not */
+static int unwind_pop_register(struct unwind_ctrl_block *ctrl,
+				unsigned long **vsp, unsigned int reg)
+{
+	if (unlikely(ctrl->check_each_pop))
+		if (*vsp >= (unsigned long *)ctrl->sp_high)
+			return -URC_FAILURE;
+
+	ctrl->vrs[reg] = *(*vsp)++;
+	return URC_OK;
+}
+
+/* Helper functions to execute the instructions */
+static int unwind_exec_pop_subset_r4_to_r13(struct unwind_ctrl_block *ctrl,
+						unsigned long mask)
+{
+	unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
+	int load_sp, reg = 4;
+
+	load_sp = mask & (1 << (13 - 4));
+	while (mask) {
+		if (mask & 1)
+			if (unwind_pop_register(ctrl, &vsp, reg))
+				return -URC_FAILURE;
+		mask >>= 1;
+		reg++;
+	}
+	if (!load_sp)
+		ctrl->vrs[SP] = (unsigned long)vsp;
+
+	return URC_OK;
+}
+
+static int unwind_exec_pop_r4_to_rN(struct unwind_ctrl_block *ctrl,
+					unsigned long insn)
+{
+	unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
+	int reg;
+
+	/* pop R4-R[4+bbb] */
+	for (reg = 4; reg <= 4 + (insn & 7); reg++)
+		if (unwind_pop_register(ctrl, &vsp, reg))
+				return -URC_FAILURE;
+
+	if (insn & 0x80)
+		if (unwind_pop_register(ctrl, &vsp, 14))
+				return -URC_FAILURE;
+
+	ctrl->vrs[SP] = (unsigned long)vsp;
+
+	return URC_OK;
+}
+
+static int unwind_exec_pop_subset_r0_to_r3(struct unwind_ctrl_block *ctrl,
+						unsigned long mask)
+{
+	unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
+	int reg = 0;
+
+	/* pop R0-R3 according to mask */
+	while (mask) {
+		if (mask & 1)
+			if (unwind_pop_register(ctrl, &vsp, reg))
+				return -URC_FAILURE;
+		mask >>= 1;
+		reg++;
+	}
+	ctrl->vrs[SP] = (unsigned long)vsp;
+
+	return URC_OK;
+}
+
 /*
  * Execute the current unwind instruction.
  */
 static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 {
 	unsigned long insn = unwind_get_byte(ctrl);
+	int ret = URC_OK;
 
 	pr_debug("%s: insn = %08lx\n", __func__, insn);
 
@@ -250,8 +329,6 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 		ctrl->vrs[SP] -= ((insn & 0x3f) << 2) + 4;
 	else if ((insn & 0xf0) == 0x80) {
 		unsigned long mask;
-		unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
-		int load_sp, reg = 4;
 
 		insn = (insn << 8) | unwind_get_byte(ctrl);
 		mask = insn & 0x0fff;
@@ -261,29 +338,16 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 			return -URC_FAILURE;
 		}
 
-		/* pop R4-R15 according to mask */
-		load_sp = mask & (1 << (13 - 4));
-		while (mask) {
-			if (mask & 1)
-				ctrl->vrs[reg] = *vsp++;
-			mask >>= 1;
-			reg++;
-		}
-		if (!load_sp)
-			ctrl->vrs[SP] = (unsigned long)vsp;
+		ret = unwind_exec_pop_subset_r4_to_r13(ctrl, mask);
+		if (ret)
+			goto error;
 	} else if ((insn & 0xf0) == 0x90 &&
 		   (insn & 0x0d) != 0x0d)
 		ctrl->vrs[SP] = ctrl->vrs[insn & 0x0f];
 	else if ((insn & 0xf0) == 0xa0) {
-		unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
-		int reg;
-
-		/* pop R4-R[4+bbb] */
-		for (reg = 4; reg <= 4 + (insn & 7); reg++)
-			ctrl->vrs[reg] = *vsp++;
-		if (insn & 0x80)
-			ctrl->vrs[14] = *vsp++;
-		ctrl->vrs[SP] = (unsigned long)vsp;
+		ret = unwind_exec_pop_r4_to_rN(ctrl, insn);
+		if (ret)
+			goto error;
 	} else if (insn == 0xb0) {
 		if (ctrl->vrs[PC] == 0)
 			ctrl->vrs[PC] = ctrl->vrs[LR];
@@ -291,8 +355,6 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 		ctrl->entries = 0;
 	} else if (insn == 0xb1) {
 		unsigned long mask = unwind_get_byte(ctrl);
-		unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
-		int reg = 0;
 
 		if (mask == 0 || mask & 0xf0) {
 			pr_warning("unwind: Spare encoding %04lx\n",
@@ -300,14 +362,9 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 			return -URC_FAILURE;
 		}
 
-		/* pop R0-R3 according to mask */
-		while (mask) {
-			if (mask & 1)
-				ctrl->vrs[reg] = *vsp++;
-			mask >>= 1;
-			reg++;
-		}
-		ctrl->vrs[SP] = (unsigned long)vsp;
+		ret = unwind_exec_pop_subset_r0_to_r3(ctrl, mask);
+		if (ret)
+			goto error;
 	} else if (insn == 0xb2) {
 		unsigned long uleb128 = unwind_get_byte(ctrl);
 
@@ -320,7 +377,8 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 	pr_debug("%s: fp = %08lx sp = %08lx lr = %08lx pc = %08lx\n", __func__,
 		 ctrl->vrs[FP], ctrl->vrs[SP], ctrl->vrs[LR], ctrl->vrs[PC]);
 
-	return URC_OK;
+error:
+	return ret;
 }
 
 /*
@@ -329,13 +387,13 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
  */
 int unwind_frame(struct stackframe *frame)
 {
-	unsigned long high, low;
+	unsigned long low;
 	const struct unwind_idx *idx;
 	struct unwind_ctrl_block ctrl;
 
-	/* only go to a higher address on the stack */
+	/* store the highest address on the stack to avoid crossing it*/
 	low = frame->sp;
-	high = ALIGN(low, THREAD_SIZE);
+	ctrl.sp_high = ALIGN(low, THREAD_SIZE);
 
 	pr_debug("%s(pc = %08lx lr = %08lx sp = %08lx)\n", __func__,
 		 frame->pc, frame->lr, frame->sp);
@@ -382,11 +440,16 @@ int unwind_frame(struct stackframe *frame)
 		return -URC_FAILURE;
 	}
 
+	ctrl.check_each_pop = 0;
+
 	while (ctrl.entries > 0) {
-		int urc = unwind_exec_insn(&ctrl);
+		int urc;
+		if ((ctrl.sp_high - ctrl.vrs[SP]) < sizeof(ctrl.vrs))
+			ctrl.check_each_pop = 1;
+		urc = unwind_exec_insn(&ctrl);
 		if (urc < 0)
 			return urc;
-		if (ctrl.vrs[SP] < low || ctrl.vrs[SP] >= high)
+		if (ctrl.vrs[SP] < low || ctrl.vrs[SP] >= ctrl.sp_high)
 			return -URC_FAILURE;
 	}