Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (34 commits)
  powerpc: Wireup new syscalls
  Move update_mmu_cache() declaration from tlbflush.h to pgtable.h
  powerpc/pseries: Remove kmalloc call in handling writes to lparcfg
  powerpc/pseries: Update arch vector to indicate support for CMO
  ibmvfc: Add support for collaborative memory overcommit
  ibmvscsi: driver enablement for CMO
  ibmveth: enable driver for CMO
  ibmveth: Automatically enable larger rx buffer pools for larger mtu
  powerpc/pseries: Verify CMO memory entitlement updates with virtual I/O
  powerpc/pseries: vio bus support for CMO
  powerpc/pseries: iommu enablement for CMO
  powerpc/pseries: Add CMO paging statistics
  powerpc/pseries: Add collaborative memory manager
  powerpc/pseries: Utilities to set firmware page state
  powerpc/pseries: Enable CMO feature during platform setup
  powerpc/pseries: Split retrieval of processor entitlement data into a helper routine
  powerpc/pseries: Add memory entitlement capabilities to /proc/ppc64/lparcfg
  powerpc/pseries: Split processor entitlement retrieval and gathering to helper routines
  powerpc/pseries: Remove extraneous error reporting for hcall failures in lparcfg
  powerpc: Fix compile error with binutils 2.15
  ...

Fixed up conflict in arch/powerpc/platforms/52xx/Kconfig manually.

Documentation/powerpc/booting-without-of.txt

@@ -59,6 +59,7 @@ Table of Contents
       p) Freescale Synchronous Serial Interface
 	  q) USB EHCI controllers
       r) MDIO on GPIOs
+      s) SPI busses
 
   VII - Marvell Discovery mv64[345]6x System Controller chips
     1) The /system-controller node
@@ -1883,6 +1884,62 @@ platforms are moved over to use the flattened-device-tree model.
 			 &qe_pio_c 6>;
 	};
 
+    s) SPI (Serial Peripheral Interface) busses
+
+    SPI busses can be described with a node for the SPI master device
+    and a set of child nodes for each SPI slave on the bus.  For this
+    discussion, it is assumed that the system's SPI controller is in
+    SPI master mode.  This binding does not describe SPI controllers
+    in slave mode.
+
+    The SPI master node requires the following properties:
+    - #address-cells  - number of cells required to define a chip select
+			address on the SPI bus.
+    - #size-cells     - should be zero.
+    - compatible      - name of SPI bus controller following generic names
+			recommended practice.
+    No other properties are required in the SPI bus node.  It is assumed
+    that a driver for an SPI bus device will understand that it is an SPI bus.
+    However, the binding does not attempt to define the specific method for
+    assigning chip select numbers.  Since SPI chip select configuration is
+    flexible and non-standardized, it is left out of this binding with the
+    assumption that board specific platform code will be used to manage
+    chip selects.  Individual drivers can define additional properties to
+    support describing the chip select layout.
+
+    SPI slave nodes must be children of the SPI master node and can
+    contain the following properties.
+    - reg             - (required) chip select address of device.
+    - compatible      - (required) name of SPI device following generic names
+			recommended practice
+    - spi-max-frequency - (required) Maximum SPI clocking speed of device in Hz
+    - spi-cpol        - (optional) Empty property indicating device requires
+			inverse clock polarity (CPOL) mode
+    - spi-cpha        - (optional) Empty property indicating device requires
+			shifted clock phase (CPHA) mode
+
+    SPI example for an MPC5200 SPI bus:
+		spi@f00 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "fsl,mpc5200b-spi","fsl,mpc5200-spi";
+			reg = <0xf00 0x20>;
+			interrupts = <2 13 0 2 14 0>;
+			interrupt-parent = <&mpc5200_pic>;
+
+			ethernet-switch@0 {
+				compatible = "micrel,ks8995m";
+				spi-max-frequency = <1000000>;
+				reg = <0>;
+			};
+
+			codec@1 {
+				compatible = "ti,tlv320aic26";
+				spi-max-frequency = <100000>;
+				reg = <1>;
+			};
+		};
+
 VII - Marvell Discovery mv64[345]6x System Controller chips
 ===========================================================
 

arch/powerpc/kernel/cputable.c

@@ -23,6 +23,9 @@
 struct cpu_spec* cur_cpu_spec = NULL;
 EXPORT_SYMBOL(cur_cpu_spec);
 
+/* The platform string corresponding to the real PVR */
+const char *powerpc_base_platform;
+
 /* NOTE:
  * Unlike ppc32, ppc64 will only call this once for the boot CPU, it's
  * the responsibility of the appropriate CPU save/restore functions to
@@ -1652,6 +1655,14 @@ struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr)
 			} else
 				*t = *s;
 			*PTRRELOC(&cur_cpu_spec) = &the_cpu_spec;
+
+			/*
+			 * Set the base platform string once; assumes
+			 * we're called with real pvr first.
+			 */
+			if (powerpc_base_platform == NULL)
+				powerpc_base_platform = t->platform;
+
 #if defined(CONFIG_PPC64) || defined(CONFIG_BOOKE)
 			/* ppc64 and booke expect identify_cpu to also call
 			 * setup_cpu for that processor. I will consolidate

arch/powerpc/kernel/entry_32.S

@@ -148,7 +148,7 @@ transfer_to_handler:
 	/* Check to see if the dbcr0 register is set up to debug.  Use the
 	   internal debug mode bit to do this. */
 	lwz	r12,THREAD_DBCR0(r12)
-	andis.	r12,r12,DBCR0_IDM@h
+	andis.	r12,r12,(DBCR0_IDM  | DBSR_DAC1R | DBSR_DAC1W)@h
 	beq+	3f
 	/* From user and task is ptraced - load up global dbcr0 */
 	li	r12,-1			/* clear all pending debug events */
@@ -292,7 +292,7 @@ syscall_exit_cont:
 	/* If the process has its own DBCR0 value, load it up.  The internal
 	   debug mode bit tells us that dbcr0 should be loaded. */
 	lwz	r0,THREAD+THREAD_DBCR0(r2)
-	andis.	r10,r0,DBCR0_IDM@h
+	andis.	r10,r0,(DBCR0_IDM  | DBSR_DAC1R | DBSR_DAC1W)@h
 	bnel-	load_dbcr0
 #endif
 #ifdef CONFIG_44x
@@ -720,7 +720,7 @@ restore_user:
 	/* Check whether this process has its own DBCR0 value.  The internal
 	   debug mode bit tells us that dbcr0 should be loaded. */
 	lwz	r0,THREAD+THREAD_DBCR0(r2)
-	andis.	r10,r0,DBCR0_IDM@h
+	andis.	r10,r0,(DBCR0_IDM  | DBSR_DAC1R | DBSR_DAC1W)@h
 	bnel-	load_dbcr0
 #endif
 

arch/powerpc/kernel/iommu.c

@@ -49,6 +49,8 @@ static int novmerge = 1;
 
 static int protect4gb = 1;
 
+static void __iommu_free(struct iommu_table *, dma_addr_t, unsigned int);
+
 static inline unsigned long iommu_num_pages(unsigned long vaddr,
 					    unsigned long slen)
 {
@@ -191,6 +193,7 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 {
 	unsigned long entry, flags;
 	dma_addr_t ret = DMA_ERROR_CODE;
+	int build_fail;
 
 	spin_lock_irqsave(&(tbl->it_lock), flags);
 
@@ -205,9 +208,21 @@ static dma_addr_t iommu_alloc(struct device *dev, struct iommu_table *tbl,
 	ret = entry << IOMMU_PAGE_SHIFT;	/* Set the return dma address */
 
 	/* Put the TCEs in the HW table */
-	ppc_md.tce_build(tbl, entry, npages, (unsigned long)page & IOMMU_PAGE_MASK,
-			 direction, attrs);
+	build_fail = ppc_md.tce_build(tbl, entry, npages,
+	                              (unsigned long)page & IOMMU_PAGE_MASK,
+	                              direction, attrs);
+
+	/* ppc_md.tce_build() only returns non-zero for transient errors.
+	 * Clean up the table bitmap in this case and return
+	 * DMA_ERROR_CODE. For all other errors the functionality is
+	 * not altered.
+	 */
+	if (unlikely(build_fail)) {
+		__iommu_free(tbl, ret, npages);
 
+		spin_unlock_irqrestore(&(tbl->it_lock), flags);
+		return DMA_ERROR_CODE;
+	}
 
 	/* Flush/invalidate TLB caches if necessary */
 	if (ppc_md.tce_flush)
@@ -276,7 +291,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 	dma_addr_t dma_next = 0, dma_addr;
 	unsigned long flags;
 	struct scatterlist *s, *outs, *segstart;
-	int outcount, incount, i;
+	int outcount, incount, i, build_fail = 0;
 	unsigned int align;
 	unsigned long handle;
 	unsigned int max_seg_size;
@@ -337,8 +352,11 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 			    npages, entry, dma_addr);
 
 		/* Insert into HW table */
-		ppc_md.tce_build(tbl, entry, npages, vaddr & IOMMU_PAGE_MASK,
-				 direction, attrs);
+		build_fail = ppc_md.tce_build(tbl, entry, npages,
+		                              vaddr & IOMMU_PAGE_MASK,
+		                              direction, attrs);
+		if(unlikely(build_fail))
+			goto failure;
 
 		/* If we are in an open segment, try merging */
 		if (segstart != s) {

arch/powerpc/kernel/process.c

@@ -47,6 +47,8 @@
 #ifdef CONFIG_PPC64
 #include <asm/firmware.h>
 #endif
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
 
 extern unsigned long _get_SP(void);
 
@@ -239,6 +241,35 @@ void discard_lazy_cpu_state(void)
 }
 #endif /* CONFIG_SMP */
 
+void do_dabr(struct pt_regs *regs, unsigned long address,
+		    unsigned long error_code)
+{
+	siginfo_t info;
+
+	if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
+			11, SIGSEGV) == NOTIFY_STOP)
+		return;
+
+	if (debugger_dabr_match(regs))
+		return;
+
+	/* Clear the DAC and struct entries.  One shot trigger */
+#if (defined(CONFIG_44x) || defined(CONFIG_BOOKE))
+	mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~(DBSR_DAC1R | DBSR_DAC1W
+							| DBCR0_IDM));
+#endif
+
+	/* Clear the DABR */
+	set_dabr(0);
+
+	/* Deliver the signal to userspace */
+	info.si_signo = SIGTRAP;
+	info.si_errno = 0;
+	info.si_code = TRAP_HWBKPT;
+	info.si_addr = (void __user *)address;
+	force_sig_info(SIGTRAP, &info, current);
+}
+
 static DEFINE_PER_CPU(unsigned long, current_dabr);
 
 int set_dabr(unsigned long dabr)
@@ -254,6 +285,11 @@ int set_dabr(unsigned long dabr)
 #if defined(CONFIG_PPC64) || defined(CONFIG_6xx)
 	mtspr(SPRN_DABR, dabr);
 #endif
+
+#if defined(CONFIG_44x) || defined(CONFIG_BOOKE)
+	mtspr(SPRN_DAC1, dabr);
+#endif
+
 	return 0;
 }
 
@@ -337,6 +373,12 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr))
 		set_dabr(new->thread.dabr);
 
+#if defined(CONFIG_44x) || defined(CONFIG_BOOKE)
+	/* If new thread DAC (HW breakpoint) is the same then leave it */
+	if (new->thread.dabr)
+		set_dabr(new->thread.dabr);
+#endif
+
 	new_thread = &new->thread;
 	old_thread = &current->thread;
 
@@ -525,6 +567,10 @@ void flush_thread(void)
 	if (current->thread.dabr) {
 		current->thread.dabr = 0;
 		set_dabr(0);
+
+#if defined(CONFIG_44x) || defined(CONFIG_BOOKE)
+		current->thread.dbcr0 &= ~(DBSR_DAC1R | DBSR_DAC1W);
+#endif
 	}
 }
 

arch/powerpc/kernel/prom_init.c

@@ -643,6 +643,11 @@ static void __init early_cmdline_parse(void)
 #else
 #define OV5_MSI			0x00
 #endif /* CONFIG_PCI_MSI */
+#ifdef CONFIG_PPC_SMLPAR
+#define OV5_CMO			0x80	/* Cooperative Memory Overcommitment */
+#else
+#define OV5_CMO			0x00
+#endif
 
 /*
  * The architecture vector has an array of PVR mask/value pairs,
@@ -687,10 +692,12 @@ static unsigned char ibm_architecture_vec[] = {
 	0,				/* don't halt */
 
 	/* option vector 5: PAPR/OF options */
-	3 - 2,				/* length */
+	5 - 2,				/* length */
 	0,				/* don't ignore, don't halt */
 	OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY |
 	OV5_DONATE_DEDICATE_CPU | OV5_MSI,
+	0,
+	OV5_CMO,
 };
 
 /* Old method - ELF header with PT_NOTE sections */

arch/powerpc/kernel/ptrace.c

@@ -703,7 +703,7 @@ void user_enable_single_step(struct task_struct *task)
 
 	if (regs != NULL) {
 #if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
-		task->thread.dbcr0 = DBCR0_IDM | DBCR0_IC;
+		task->thread.dbcr0 |= DBCR0_IDM | DBCR0_IC;
 		regs->msr |= MSR_DE;
 #else
 		regs->msr |= MSR_SE;
@@ -716,9 +716,16 @@ void user_disable_single_step(struct task_struct *task)
 {
 	struct pt_regs *regs = task->thread.regs;
 
+
+#if defined(CONFIG_44x) || defined(CONFIG_BOOKE)
+	/* If DAC then do not single step, skip */
+	if (task->thread.dabr)
+		return;
+#endif
+
 	if (regs != NULL) {
 #if defined(CONFIG_40x) || defined(CONFIG_BOOKE)
-		task->thread.dbcr0 = 0;
+		task->thread.dbcr0 &= ~(DBCR0_IC | DBCR0_IDM);
 		regs->msr &= ~MSR_DE;
 #else
 		regs->msr &= ~MSR_SE;
@@ -727,22 +734,75 @@ void user_disable_single_step(struct task_struct *task)
 	clear_tsk_thread_flag(task, TIF_SINGLESTEP);
 }
 
-static int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
+int ptrace_set_debugreg(struct task_struct *task, unsigned long addr,
 			       unsigned long data)
 {
-	/* We only support one DABR and no IABRS at the moment */
+	/* For ppc64 we support one DABR and no IABR's at the moment (ppc64).
+	 *  For embedded processors we support one DAC and no IAC's at the
+	 *  moment.
+	 */
 	if (addr > 0)
 		return -EINVAL;
 
-	/* The bottom 3 bits are flags */
 	if ((data & ~0x7UL) >= TASK_SIZE)
 		return -EIO;
 
-	/* Ensure translation is on */
+#ifdef CONFIG_PPC64
+
+	/* For processors using DABR (i.e. 970), the bottom 3 bits are flags.
+	 *  It was assumed, on previous implementations, that 3 bits were
+	 *  passed together with the data address, fitting the design of the
+	 *  DABR register, as follows:
+	 *
+	 *  bit 0: Read flag
+	 *  bit 1: Write flag
+	 *  bit 2: Breakpoint translation
+	 *
+	 *  Thus, we use them here as so.
+	 */
+
+	/* Ensure breakpoint translation bit is set */
 	if (data && !(data & DABR_TRANSLATION))
 		return -EIO;
 
+	/* Move contents to the DABR register */
 	task->thread.dabr = data;
+
+#endif
+#if defined(CONFIG_44x) || defined(CONFIG_BOOKE)
+
+	/* As described above, it was assumed 3 bits were passed with the data
+	 *  address, but we will assume only the mode bits will be passed
+	 *  as to not cause alignment restrictions for DAC-based processors.
+	 */
+
+	/* DAC's hold the whole address without any mode flags */
+	task->thread.dabr = data & ~0x3UL;
+
+	if (task->thread.dabr == 0) {
+		task->thread.dbcr0 &= ~(DBSR_DAC1R | DBSR_DAC1W | DBCR0_IDM);
+		task->thread.regs->msr &= ~MSR_DE;
+		return 0;
+	}
+
+	/* Read or Write bits must be set */
+
+	if (!(data & 0x3UL))
+		return -EINVAL;
+
+	/* Set the Internal Debugging flag (IDM bit 1) for the DBCR0
+	   register */
+	task->thread.dbcr0 = DBCR0_IDM;
+
+	/* Check for write and read flags and set DBCR0
+	   accordingly */
+	if (data & 0x1UL)
+		task->thread.dbcr0 |= DBSR_DAC1R;
+	if (data & 0x2UL)
+		task->thread.dbcr0 |= DBSR_DAC1W;
+
+	task->thread.regs->msr |= MSR_DE;
+#endif
 	return 0;
 }
 

arch/powerpc/kernel/signal.c

@@ -145,8 +145,12 @@ int do_signal(sigset_t *oldset, struct pt_regs *regs)
 	 * user space. The DABR will have been cleared if it
 	 * triggered inside the kernel.
 	 */
-	if (current->thread.dabr)
+	if (current->thread.dabr) {
 		set_dabr(current->thread.dabr);
+#if defined(CONFIG_44x) || defined(CONFIG_BOOKE)
+		mtspr(SPRN_DBCR0, current->thread.dbcr0);
+#endif
+	}
 
 	if (is32) {
         	if (ka.sa.sa_flags & SA_SIGINFO)

arch/powerpc/kernel/sysfs.c

@@ -529,7 +529,8 @@ static void register_nodes(void)
 #endif
 
 /* Only valid if CPU is present. */
-static ssize_t show_physical_id(struct sys_device *dev, char *buf)
+static ssize_t show_physical_id(struct sys_device *dev,
+				struct sysdev_attribute *attr, char *buf)
 {
 	struct cpu *cpu = container_of(dev, struct cpu, sysdev);
 

arch/powerpc/kernel/traps.c

@@ -1067,6 +1067,22 @@ void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status)
 		}
 
 		_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
+	} else if (debug_status & (DBSR_DAC1R | DBSR_DAC1W)) {
+		regs->msr &= ~MSR_DE;
+
+		if (user_mode(regs)) {
+			current->thread.dbcr0 &= ~(DBSR_DAC1R | DBSR_DAC1W |
+								DBCR0_IDM);
+		} else {
+			/* Disable DAC interupts */
+			mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) & ~(DBSR_DAC1R |
+						DBSR_DAC1W | DBCR0_IDM));
+
+			/* Clear the DAC event */
+			mtspr(SPRN_DBSR, (DBSR_DAC1R | DBSR_DAC1W));
+		}
+		/* Setup and send the trap to the handler */
+		do_dabr(regs, mfspr(SPRN_DAC1), debug_status);
 	}
 }
 #endif /* CONFIG_4xx || CONFIG_BOOKE */

arch/powerpc/kernel/vmlinux.lds.S

@@ -85,7 +85,7 @@ SECTIONS
 
 	/* The dummy segment contents for the bug workaround mentioned above
 	   near PHDRS.  */
-	.dummy : {
+	.dummy : AT(ADDR(.dummy) - LOAD_OFFSET) {
 		LONG(0xf177)
 	} :kernel :dummy
 

arch/powerpc/mm/fault.c

@@ -100,31 +100,6 @@ static int store_updates_sp(struct pt_regs *regs)
 	return 0;
 }
 
-#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE))
-static void do_dabr(struct pt_regs *regs, unsigned long address,
-		    unsigned long error_code)
-{
-	siginfo_t info;
-
-	if (notify_die(DIE_DABR_MATCH, "dabr_match", regs, error_code,
-			11, SIGSEGV) == NOTIFY_STOP)
-		return;
-
-	if (debugger_dabr_match(regs))
-		return;
-
-	/* Clear the DABR */
-	set_dabr(0);
-
-	/* Deliver the signal to userspace */
-	info.si_signo = SIGTRAP;
-	info.si_errno = 0;
-	info.si_code = TRAP_HWBKPT;
-	info.si_addr = (void __user *)address;
-	force_sig_info(SIGTRAP, &info, current);
-}
-#endif /* !(CONFIG_4xx || CONFIG_BOOKE)*/
-
 /*
  * For 600- and 800-family processors, the error_code parameter is DSISR
  * for a data fault, SRR1 for an instruction fault. For 400-family processors

arch/powerpc/platforms/52xx/Kconfig

 config PPC_MPC52xx
 	bool "52xx-based boards"
 	depends on PPC_MULTIPLATFORM && PPC32
-	select FSL_SOC
 	select PPC_CLOCK
 	select PPC_PCI_CHOICE
 
@@ -49,5 +48,6 @@ config PPC_MPC5200_GPIO
 	bool "MPC5200 GPIO support"
 	depends on PPC_MPC52xx
 	select ARCH_REQUIRE_GPIOLIB
+	select GENERIC_GPIO
 	help
 	  Enable gpiolib support for mpc5200 based boards

arch/powerpc/platforms/cell/iommu.c

@@ -172,7 +172,7 @@ static void invalidate_tce_cache(struct cbe_iommu *iommu, unsigned long *pte,
 	}
 }
 
-static void tce_build_cell(struct iommu_table *tbl, long index, long npages,
+static int tce_build_cell(struct iommu_table *tbl, long index, long npages,
 		unsigned long uaddr, enum dma_data_direction direction,
 		struct dma_attrs *attrs)
 {
@@ -213,6 +213,7 @@ static void tce_build_cell(struct iommu_table *tbl, long index, long npages,
 
 	pr_debug("tce_build_cell(index=%lx,n=%lx,dir=%d,base_pte=%lx)\n",
 		 index, npages, direction, base_pte);
+	return 0;
 }
 
 static void tce_free_cell(struct iommu_table *tbl, long index, long npages)
@@ -1150,12 +1151,23 @@ static int iommu_fixed_disabled;
 
 static int __init setup_iommu_fixed(char *str)
 {
+	struct device_node *pciep;
+
 	if (strcmp(str, "off") == 0)
 		iommu_fixed_disabled = 1;
 
-	else if (strcmp(str, "weak") == 0)
+	/* If we can find a pcie-endpoint in the device tree assume that
+	 * we're on a triblade or a CAB so by default the fixed mapping
+	 * should be set to be weakly ordered; but only if the boot
+	 * option WASN'T set for strong ordering
+	 */
+	pciep = of_find_node_by_type(NULL, "pcie-endpoint");
+
+	if (strcmp(str, "weak") == 0 || (pciep && strcmp(str, "strong") != 0))
 		iommu_fixed_is_weak = 1;
 
+	of_node_put(pciep);
+
 	return 1;
 }
 __setup("iommu_fixed=", setup_iommu_fixed);

arch/powerpc/platforms/cell/spufs/sched.c

@@ -312,10 +312,27 @@ static struct spu *aff_ref_location(struct spu_context *ctx, int mem_aff,
 	 */
 	node = cpu_to_node(raw_smp_processor_id());
 	for (n = 0; n < MAX_NUMNODES; n++, node++) {
+		int available_spus;
+
 		node = (node < MAX_NUMNODES) ? node : 0;
 		if (!node_allowed(ctx, node))
 			continue;
+
+		available_spus = 0;
 		mutex_lock(&cbe_spu_info[node].list_mutex);
+		list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) {
+			if (spu->ctx && spu->ctx->gang
+					&& spu->ctx->aff_offset == 0)
+				available_spus -=
+					(spu->ctx->gang->contexts - 1);
+			else
+				available_spus++;
+		}
+		if (available_spus < ctx->gang->contexts) {
+			mutex_unlock(&cbe_spu_info[node].list_mutex);
+			continue;
+		}
+
 		list_for_each_entry(spu, &cbe_spu_info[node].spus, cbe_list) {
 			if ((!mem_aff || spu->has_mem_affinity) &&
 							sched_spu(spu)) {
@@ -389,6 +406,9 @@ static int has_affinity(struct spu_context *ctx)
 	if (list_empty(&ctx->aff_list))
 		return 0;
 
+	if (atomic_read(&ctx->gang->aff_sched_count) == 0)
+		ctx->gang->aff_ref_spu = NULL;
+
 	if (!gang->aff_ref_spu) {
 		if (!(gang->aff_flags & AFF_MERGED))
 			aff_merge_remaining_ctxs(gang);
@@ -416,14 +436,8 @@ static void spu_unbind_context(struct spu *spu, struct spu_context *ctx)
  	if (spu->ctx->flags & SPU_CREATE_NOSCHED)
 		atomic_dec(&cbe_spu_info[spu->node].reserved_spus);
 
-	if (ctx->gang){
-		mutex_lock(&ctx->gang->aff_mutex);
-		if (has_affinity(ctx)) {
-			if (atomic_dec_and_test(&ctx->gang->aff_sched_count))
-				ctx->gang->aff_ref_spu = NULL;
-		}
-		mutex_unlock(&ctx->gang->aff_mutex);
-	}
+	if (ctx->gang)
+		atomic_dec_if_positive(&ctx->gang->aff_sched_count);
 
 	spu_switch_notify(spu, NULL);
 	spu_unmap_mappings(ctx);
@@ -562,10 +576,7 @@ static struct spu *spu_get_idle(struct spu_context *ctx)
 				goto found;
 			mutex_unlock(&cbe_spu_info[node].list_mutex);
 
-			mutex_lock(&ctx->gang->aff_mutex);
-			if (atomic_dec_and_test(&ctx->gang->aff_sched_count))
-				ctx->gang->aff_ref_spu = NULL;
-			mutex_unlock(&ctx->gang->aff_mutex);
+			atomic_dec(&ctx->gang->aff_sched_count);
 			goto not_found;
 		}
 		mutex_unlock(&ctx->gang->aff_mutex);

arch/powerpc/platforms/cell/spufs/sputrace.c

@@ -196,8 +196,7 @@ static int __init sputrace_init(void)
 	struct proc_dir_entry *entry;
 	int i, error = -ENOMEM;
 
-	sputrace_log = kcalloc(sizeof(struct sputrace),
-				bufsize, GFP_KERNEL);
+	sputrace_log = kcalloc(bufsize, sizeof(struct sputrace), GFP_KERNEL);
 	if (!sputrace_log)
 		goto out;
 

arch/powerpc/platforms/iseries/iommu.c

@@ -41,7 +41,7 @@
 #include <asm/iseries/hv_call_event.h>
 #include <asm/iseries/iommu.h>
 
-static void tce_build_iSeries(struct iommu_table *tbl, long index, long npages,
+static int tce_build_iSeries(struct iommu_table *tbl, long index, long npages,
 		unsigned long uaddr, enum dma_data_direction direction,
 		struct dma_attrs *attrs)
 {
@@ -71,6 +71,7 @@ static void tce_build_iSeries(struct iommu_table *tbl, long index, long npages,
 		index++;
 		uaddr += TCE_PAGE_SIZE;
 	}
+	return 0;
 }
 
 static void tce_free_iSeries(struct iommu_table *tbl, long index, long npages)

arch/powerpc/platforms/pasemi/iommu.c

@@ -83,7 +83,7 @@ static u32 *iob_l2_base;
 static struct iommu_table iommu_table_iobmap;
 static int iommu_table_iobmap_inited;
 
-static void iobmap_build(struct iommu_table *tbl, long index,
+static int iobmap_build(struct iommu_table *tbl, long index,
 			 long npages, unsigned long uaddr,
 			 enum dma_data_direction direction,
 			 struct dma_attrs *attrs)
@@ -108,6 +108,7 @@ static void iobmap_build(struct iommu_table *tbl, long index,
 		uaddr += IOBMAP_PAGE_SIZE;
 		bus_addr += IOBMAP_PAGE_SIZE;
 	}
+	return 0;
 }
 
 

arch/powerpc/platforms/pseries/Kconfig

@@ -40,3 +40,26 @@ config PPC_PSERIES_DEBUG
 	depends on PPC_PSERIES && PPC_EARLY_DEBUG
 	bool "Enable extra debug logging in platforms/pseries"
 	default y
+
+config PPC_SMLPAR
+	bool "Support for shared-memory logical partitions"
+	depends on PPC_PSERIES
+	select LPARCFG
+	default n
+	help
+	  Select this option to enable shared memory partition support.
+	  With this option a system running in an LPAR can be given more
+	  memory than physically available and will allow firmware to
+	  balance memory across many LPARs.
+
+config CMM
+	tristate "Collaborative memory management"
+	depends on PPC_SMLPAR
+	default y
+	help
+	  Select this option, if you want to enable the kernel interface
+	  to reduce the memory size of the system. This is accomplished
+	  by allocating pages of memory and put them "on hold". This only
+	  makes sense for a system running in an LPAR where the unused pages
+	  will be reused for other LPARs. The interface allows firmware to
+	  balance memory across many LPARs.

arch/powerpc/platforms/pseries/Makefile

@@ -24,3 +24,4 @@ obj-$(CONFIG_HVC_CONSOLE)	+= hvconsole.o
 obj-$(CONFIG_HVCS)		+= hvcserver.o
 obj-$(CONFIG_HCALL_STATS)	+= hvCall_inst.o
 obj-$(CONFIG_PHYP_DUMP)	+= phyp_dump.o
+obj-$(CONFIG_CMM)		+= cmm.o

arch/powerpc/platforms/pseries/iommu.c

@@ -48,7 +48,7 @@
 #include "plpar_wrappers.h"
 
 
-static void tce_build_pSeries(struct iommu_table *tbl, long index,
+static int tce_build_pSeries(struct iommu_table *tbl, long index,
 			      long npages, unsigned long uaddr,
 			      enum dma_data_direction direction,
 			      struct dma_attrs *attrs)
@@ -72,6 +72,7 @@ static void tce_build_pSeries(struct iommu_table *tbl, long index,
 		uaddr += TCE_PAGE_SIZE;
 		tcep++;
 	}
+	return 0;
 }
 
 
@@ -94,14 +95,19 @@ static unsigned long tce_get_pseries(struct iommu_table *tbl, long index)
 	return *tcep;
 }
 
-static void tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
+static void tce_free_pSeriesLP(struct iommu_table*, long, long);
+static void tce_freemulti_pSeriesLP(struct iommu_table*, long, long);
+
+static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				long npages, unsigned long uaddr,
 				enum dma_data_direction direction,
 				struct dma_attrs *attrs)
 {
-	u64 rc;
+	u64 rc = 0;
 	u64 proto_tce, tce;
 	u64 rpn;
+	int ret = 0;
+	long tcenum_start = tcenum, npages_start = npages;
 
 	rpn = (virt_to_abs(uaddr)) >> TCE_SHIFT;
 	proto_tce = TCE_PCI_READ;
@@ -112,6 +118,13 @@ static void tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tce = proto_tce | (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
 		rc = plpar_tce_put((u64)tbl->it_index, (u64)tcenum << 12, tce);
 
+		if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
+			ret = (int)rc;
+			tce_free_pSeriesLP(tbl, tcenum_start,
+			                   (npages_start - (npages + 1)));
+			break;
+		}
+
 		if (rc && printk_ratelimit()) {
 			printk("tce_build_pSeriesLP: plpar_tce_put failed. rc=%ld\n", rc);
 			printk("\tindex   = 0x%lx\n", (u64)tbl->it_index);
@@ -123,25 +136,27 @@ static void tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcenum++;
 		rpn++;
 	}
+	return ret;
 }
 
 static DEFINE_PER_CPU(u64 *, tce_page) = NULL;
 
-static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
+static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				     long npages, unsigned long uaddr,
 				     enum dma_data_direction direction,
 				     struct dma_attrs *attrs)
 {
-	u64 rc;
+	u64 rc = 0;
 	u64 proto_tce;
 	u64 *tcep;
 	u64 rpn;
 	long l, limit;
+	long tcenum_start = tcenum, npages_start = npages;
+	int ret = 0;
 
 	if (npages == 1) {
-		tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
-				    direction, attrs);
-		return;
+		return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
+		                           direction, attrs);
 	}
 
 	tcep = __get_cpu_var(tce_page);
@@ -153,9 +168,8 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcep = (u64 *)__get_free_page(GFP_ATOMIC);
 		/* If allocation fails, fall back to the loop implementation */
 		if (!tcep) {
-			tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
+			return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
 					    direction, attrs);
-			return;
 		}
 		__get_cpu_var(tce_page) = tcep;
 	}
@@ -187,6 +201,13 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcenum += limit;
 	} while (npages > 0 && !rc);
 
+	if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
+		ret = (int)rc;
+		tce_freemulti_pSeriesLP(tbl, tcenum_start,
+		                        (npages_start - (npages + limit)));
+		return ret;
+	}
+
 	if (rc && printk_ratelimit()) {
 		printk("tce_buildmulti_pSeriesLP: plpar_tce_put failed. rc=%ld\n", rc);
 		printk("\tindex   = 0x%lx\n", (u64)tbl->it_index);
@@ -194,6 +215,7 @@ static void tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		printk("\ttce[0] val = 0x%lx\n", tcep[0]);
 		show_stack(current, (unsigned long *)__get_SP());
 	}
+	return ret;
 }
 
 static void tce_free_pSeriesLP(struct iommu_table *tbl, long tcenum, long npages)

arch/powerpc/platforms/pseries/plpar_wrappers.h

@@ -42,6 +42,16 @@ static inline long register_slb_shadow(unsigned long cpu, unsigned long vpa)
 	return vpa_call(0x3, cpu, vpa);
 }
 
+static inline long plpar_page_set_loaned(unsigned long vpa)
+{
+	return plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_LOANED, vpa, 0);
+}
+
+static inline long plpar_page_set_active(unsigned long vpa)
+{
+	return plpar_hcall_norets(H_PAGE_INIT, H_PAGE_SET_ACTIVE, vpa, 0);
+}
+
 extern void vpa_init(int cpu);
 
 static inline long plpar_pte_enter(unsigned long flags,

arch/powerpc/platforms/pseries/setup.c

@@ -314,6 +314,76 @@ static int pseries_set_xdabr(unsigned long dabr)
 			H_DABRX_KERNEL | H_DABRX_USER);
 }
 
+#define CMO_CHARACTERISTICS_TOKEN 44
+#define CMO_MAXLENGTH 1026
+
+/**
+ * fw_cmo_feature_init - FW_FEATURE_CMO is not stored in ibm,hypertas-functions,
+ * handle that here. (Stolen from parse_system_parameter_string)
+ */
+void pSeries_cmo_feature_init(void)
+{
+	char *ptr, *key, *value, *end;
+	int call_status;
+	int PrPSP = -1;
+	int SecPSP = -1;
+
+	pr_debug(" -> fw_cmo_feature_init()\n");
+	spin_lock(&rtas_data_buf_lock);
+	memset(rtas_data_buf, 0, RTAS_DATA_BUF_SIZE);
+	call_status = rtas_call(rtas_token("ibm,get-system-parameter"), 3, 1,
+				NULL,
+				CMO_CHARACTERISTICS_TOKEN,
+				__pa(rtas_data_buf),
+				RTAS_DATA_BUF_SIZE);
+
+	if (call_status != 0) {
+		spin_unlock(&rtas_data_buf_lock);
+		pr_debug("CMO not available\n");
+		pr_debug(" <- fw_cmo_feature_init()\n");
+		return;
+	}
+
+	end = rtas_data_buf + CMO_MAXLENGTH - 2;
+	ptr = rtas_data_buf + 2;	/* step over strlen value */
+	key = value = ptr;
+
+	while (*ptr && (ptr <= end)) {
+		/* Separate the key and value by replacing '=' with '\0' and
+		 * point the value at the string after the '='
+		 */
+		if (ptr[0] == '=') {
+			ptr[0] = '\0';
+			value = ptr + 1;
+		} else if (ptr[0] == '\0' || ptr[0] == ',') {
+			/* Terminate the string containing the key/value pair */
+			ptr[0] = '\0';
+
+			if (key == value) {
+				pr_debug("Malformed key/value pair\n");
+				/* Never found a '=', end processing */
+				break;
+			}
+
+			if (0 == strcmp(key, "PrPSP"))
+				PrPSP = simple_strtol(value, NULL, 10);
+			else if (0 == strcmp(key, "SecPSP"))
+				SecPSP = simple_strtol(value, NULL, 10);
+			value = key = ptr + 1;
+		}
+		ptr++;
+	}
+
+	if (PrPSP != -1 || SecPSP != -1) {
+		pr_info("CMO enabled\n");
+		pr_debug("CMO enabled, PrPSP=%d, SecPSP=%d\n", PrPSP, SecPSP);
+		powerpc_firmware_features |= FW_FEATURE_CMO;
+	} else
+		pr_debug("CMO not enabled, PrPSP=%d, SecPSP=%d\n", PrPSP, SecPSP);
+	spin_unlock(&rtas_data_buf_lock);
+	pr_debug(" <- fw_cmo_feature_init()\n");
+}
+
 /*
  * Early initialization.  Relocation is on but do not reference unbolted pages
  */
@@ -329,6 +399,7 @@ static void __init pSeries_init_early(void)
 	else if (firmware_has_feature(FW_FEATURE_XDABR))
 		ppc_md.set_dabr = pseries_set_xdabr;
 
+	pSeries_cmo_feature_init();
 	iommu_init_early_pSeries();
 
 	pr_debug(" <- pSeries_init_early()\n");

arch/powerpc/sysdev/dart_iommu.c

@@ -147,7 +147,7 @@ static void dart_flush(struct iommu_table *tbl)
 	}
 }
 
-static void dart_build(struct iommu_table *tbl, long index,
+static int dart_build(struct iommu_table *tbl, long index,
 		       long npages, unsigned long uaddr,
 		       enum dma_data_direction direction,
 		       struct dma_attrs *attrs)
@@ -184,6 +184,7 @@ static void dart_build(struct iommu_table *tbl, long index,
 	} else {
 		dart_dirty = 1;
 	}
+	return 0;
 }
 
 

drivers/net/ibmveth.h

@@ -93,9 +93,12 @@ static inline long h_illan_attributes(unsigned long unit_address,
   plpar_hcall_norets(H_CHANGE_LOGICAL_LAN_MAC, ua, mac)
 
 #define IbmVethNumBufferPools 5
+#define IBMVETH_IO_ENTITLEMENT_DEFAULT 4243456 /* MTU of 1500 needs 4.2Mb */
 #define IBMVETH_BUFF_OH 22 /* Overhead: 14 ethernet header + 8 opaque handle */
 #define IBMVETH_MAX_MTU 68
 #define IBMVETH_MAX_POOL_COUNT 4096
+#define IBMVETH_BUFF_LIST_SIZE 4096
+#define IBMVETH_FILT_LIST_SIZE 4096
 #define IBMVETH_MAX_BUF_SIZE (1024 * 128)
 
 static int pool_size[] = { 512, 1024 * 2, 1024 * 16, 1024 * 32, 1024 * 64 };
@@ -143,6 +146,8 @@ struct ibmveth_adapter {
     struct ibmveth_rx_q rx_queue;
     int pool_config;
     int rx_csum;
+    void *bounce_buffer;
+    dma_addr_t bounce_buffer_dma;
 
     /* adapter specific stats */
     u64 replenish_task_cycles;

drivers/of/of_i2c.c

@@ -91,8 +91,6 @@ void of_register_i2c_devices(struct i2c_adapter *adap,
 		}
 
 		info.irq = irq_of_parse_and_map(node, 0);
-		if (info.irq == NO_IRQ)
-			info.irq = -1;
 
 		if (of_find_i2c_driver(node, &info) < 0) {
 			irq_dispose_mapping(info.irq);

drivers/scsi/ibmvscsi/ibmvfc.c

@@ -3819,6 +3819,20 @@ static int ibmvfc_remove(struct vio_dev *vdev)
 	return 0;
 }
 
+/**
+ * ibmvfc_get_desired_dma - Calculate DMA resources needed by the driver
+ * @vdev:	vio device struct
+ *
+ * Return value:
+ *	Number of bytes the driver will need to DMA map at the same time in
+ *	order to perform well.
+ */
+static unsigned long ibmvfc_get_desired_dma(struct vio_dev *vdev)
+{
+	unsigned long pool_dma = max_requests * sizeof(union ibmvfc_iu);
+	return pool_dma + ((512 * 1024) * driver_template.cmd_per_lun);
+}
+
 static struct vio_device_id ibmvfc_device_table[] __devinitdata = {
 	{"fcp", "IBM,vfc-client"},
 	{ "", "" }
@@ -3829,6 +3843,7 @@ static struct vio_driver ibmvfc_driver = {
 	.id_table = ibmvfc_device_table,
 	.probe = ibmvfc_probe,
 	.remove = ibmvfc_remove,
+	.get_desired_dma = ibmvfc_get_desired_dma,
 	.driver = {
 		.name = IBMVFC_NAME,
 		.owner = THIS_MODULE,

drivers/scsi/ibmvscsi/ibmvscsi.c

@@ -72,6 +72,7 @@
 #include <linux/delay.h>
 #include <asm/firmware.h>
 #include <asm/vio.h>
+#include <asm/firmware.h>
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_host.h>
@@ -426,8 +427,10 @@ static int map_sg_data(struct scsi_cmnd *cmd,
 					   SG_ALL * sizeof(struct srp_direct_buf),
 					   &evt_struct->ext_list_token, 0);
 		if (!evt_struct->ext_list) {
-			sdev_printk(KERN_ERR, cmd->device,
-				    "Can't allocate memory for indirect table\n");
+			if (!firmware_has_feature(FW_FEATURE_CMO))
+				sdev_printk(KERN_ERR, cmd->device,
+				            "Can't allocate memory "
+				            "for indirect table\n");
 			return 0;
 		}
 	}
@@ -743,7 +746,9 @@ static int ibmvscsi_queuecommand(struct scsi_cmnd *cmnd,
 	srp_cmd->lun = ((u64) lun) << 48;
 
 	if (!map_data_for_srp_cmd(cmnd, evt_struct, srp_cmd, hostdata->dev)) {
-		sdev_printk(KERN_ERR, cmnd->device, "couldn't convert cmd to srp_cmd\n");
+		if (!firmware_has_feature(FW_FEATURE_CMO))
+			sdev_printk(KERN_ERR, cmnd->device,
+			            "couldn't convert cmd to srp_cmd\n");
 		free_event_struct(&hostdata->pool, evt_struct);
 		return SCSI_MLQUEUE_HOST_BUSY;
 	}
@@ -855,7 +860,10 @@ static void send_mad_adapter_info(struct ibmvscsi_host_data *hostdata)
 					    DMA_BIDIRECTIONAL);
 
 	if (dma_mapping_error(req->buffer)) {
-		dev_err(hostdata->dev, "Unable to map request_buffer for adapter_info!\n");
+		if (!firmware_has_feature(FW_FEATURE_CMO))
+			dev_err(hostdata->dev,
+			        "Unable to map request_buffer for "
+			        "adapter_info!\n");
 		free_event_struct(&hostdata->pool, evt_struct);
 		return;
 	}
@@ -1400,7 +1408,9 @@ static int ibmvscsi_do_host_config(struct ibmvscsi_host_data *hostdata,
 						    DMA_BIDIRECTIONAL);
 
 	if (dma_mapping_error(host_config->buffer)) {
-		dev_err(hostdata->dev, "dma_mapping error getting host config\n");
+		if (!firmware_has_feature(FW_FEATURE_CMO))
+			dev_err(hostdata->dev,
+			        "dma_mapping error getting host config\n");
 		free_event_struct(&hostdata->pool, evt_struct);
 		return -1;
 	}
@@ -1604,7 +1614,7 @@ static struct scsi_host_template driver_template = {
 	.eh_host_reset_handler = ibmvscsi_eh_host_reset_handler,
 	.slave_configure = ibmvscsi_slave_configure,
 	.change_queue_depth = ibmvscsi_change_queue_depth,
-	.cmd_per_lun = 16,
+	.cmd_per_lun = IBMVSCSI_CMDS_PER_LUN_DEFAULT,
 	.can_queue = IBMVSCSI_MAX_REQUESTS_DEFAULT,
 	.this_id = -1,
 	.sg_tablesize = SG_ALL,
@@ -1612,6 +1622,26 @@ static struct scsi_host_template driver_template = {
 	.shost_attrs = ibmvscsi_attrs,
 };
 
+/**
+ * ibmvscsi_get_desired_dma - Calculate IO memory desired by the driver
+ *
+ * @vdev: struct vio_dev for the device whose desired IO mem is to be returned
+ *
+ * Return value:
+ *	Number of bytes of IO data the driver will need to perform well.
+ */
+static unsigned long ibmvscsi_get_desired_dma(struct vio_dev *vdev)
+{
+	/* iu_storage data allocated in initialize_event_pool */
+	unsigned long desired_io = max_requests * sizeof(union viosrp_iu);
+
+	/* add io space for sg data */
+	desired_io += (IBMVSCSI_MAX_SECTORS_DEFAULT *
+	                     IBMVSCSI_CMDS_PER_LUN_DEFAULT);
+
+	return desired_io;
+}
+
 /**
  * Called by bus code for each adapter
  */
@@ -1641,7 +1671,7 @@ static int ibmvscsi_probe(struct vio_dev *vdev, const struct vio_device_id *id)
 	hostdata->host = host;
 	hostdata->dev = dev;
 	atomic_set(&hostdata->request_limit, -1);
-	hostdata->host->max_sectors = 32 * 8; /* default max I/O 32 pages */
+	hostdata->host->max_sectors = IBMVSCSI_MAX_SECTORS_DEFAULT;
 
 	rc = ibmvscsi_ops->init_crq_queue(&hostdata->queue, hostdata, max_requests);
 	if (rc != 0 && rc != H_RESOURCE) {
@@ -1735,6 +1765,7 @@ static struct vio_driver ibmvscsi_driver = {
 	.id_table = ibmvscsi_device_table,
 	.probe = ibmvscsi_probe,
 	.remove = ibmvscsi_remove,
+	.get_desired_dma = ibmvscsi_get_desired_dma,
 	.driver = {
 		.name = "ibmvscsi",
 		.owner = THIS_MODULE,

drivers/scsi/ibmvscsi/ibmvscsi.h

@@ -45,6 +45,8 @@ struct Scsi_Host;
 #define MAX_INDIRECT_BUFS 10
 
 #define IBMVSCSI_MAX_REQUESTS_DEFAULT 100
+#define IBMVSCSI_CMDS_PER_LUN_DEFAULT 16
+#define IBMVSCSI_MAX_SECTORS_DEFAULT 256 /* 32 * 8 = default max I/O 32 pages */
 #define IBMVSCSI_MAX_CMDS_PER_LUN 64
 
 /* ------------------------------------------------------------

fs/binfmt_elf.c

@@ -131,6 +131,15 @@ static int padzero(unsigned long elf_bss)
 #define STACK_ALLOC(sp, len) ({ sp -= len ; sp; })
 #endif
 
+#ifndef ELF_BASE_PLATFORM
+/*
+ * AT_BASE_PLATFORM indicates the "real" hardware/microarchitecture.
+ * If the arch defines ELF_BASE_PLATFORM (in asm/elf.h), the value
+ * will be copied to the user stack in the same manner as AT_PLATFORM.
+ */
+#define ELF_BASE_PLATFORM NULL
+#endif
+
 static int
 create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 		unsigned long load_addr, unsigned long interp_load_addr)
@@ -142,7 +151,9 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 	elf_addr_t __user *envp;
 	elf_addr_t __user *sp;
 	elf_addr_t __user *u_platform;
+	elf_addr_t __user *u_base_platform;
 	const char *k_platform = ELF_PLATFORM;
+	const char *k_base_platform = ELF_BASE_PLATFORM;
 	int items;
 	elf_addr_t *elf_info;
 	int ei_index = 0;
@@ -172,6 +183,19 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 			return -EFAULT;
 	}
 
+	/*
+	 * If this architecture has a "base" platform capability
+	 * string, copy it to userspace.
+	 */
+	u_base_platform = NULL;
+	if (k_base_platform) {
+		size_t len = strlen(k_base_platform) + 1;
+
+		u_base_platform = (elf_addr_t __user *)STACK_ALLOC(p, len);
+		if (__copy_to_user(u_base_platform, k_base_platform, len))
+			return -EFAULT;
+	}
+
 	/* Create the ELF interpreter info */
 	elf_info = (elf_addr_t *)current->mm->saved_auxv;
 	/* update AT_VECTOR_SIZE_BASE if the number of NEW_AUX_ENT() changes */
@@ -209,6 +233,10 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 		NEW_AUX_ENT(AT_PLATFORM,
 			    (elf_addr_t)(unsigned long)u_platform);
 	}
+	if (k_base_platform) {
+		NEW_AUX_ENT(AT_BASE_PLATFORM,
+			    (elf_addr_t)(unsigned long)u_base_platform);
+	}
 	if (bprm->interp_flags & BINPRM_FLAGS_EXECFD) {
 		NEW_AUX_ENT(AT_EXECFD, bprm->interp_data);
 	}

include/asm-powerpc/cputable.h

@@ -127,6 +127,8 @@ extern struct cpu_spec *identify_cpu(unsigned long offset, unsigned int pvr);
 extern void do_feature_fixups(unsigned long value, void *fixup_start,
 			      void *fixup_end);
 
+extern const char *powerpc_base_platform;
+
 #endif /* __ASSEMBLY__ */
 
 /* CPU kernel features */

include/asm-powerpc/elf.h

@@ -217,6 +217,14 @@ typedef elf_vrregset_t elf_fpxregset_t;
 
 #define ELF_PLATFORM	(cur_cpu_spec->platform)
 
+/* While ELF_PLATFORM indicates the ISA supported by the platform, it
+ * may not accurately reflect the underlying behavior of the hardware
+ * (as in the case of running in Power5+ compatibility mode on a
+ * Power6 machine).  ELF_BASE_PLATFORM allows ld.so to load libraries
+ * that are tuned for the real hardware.
+ */
+#define ELF_BASE_PLATFORM (powerpc_base_platform)
+
 #ifdef __powerpc64__
 # define ELF_PLAT_INIT(_r, load_addr)	do {	\
 	_r->gpr[2] = load_addr; 		\

include/asm-powerpc/firmware.h

@@ -46,6 +46,7 @@
 #define FW_FEATURE_PS3_LV1	ASM_CONST(0x0000000000800000)
 #define FW_FEATURE_BEAT		ASM_CONST(0x0000000001000000)
 #define FW_FEATURE_BULK_REMOVE	ASM_CONST(0x0000000002000000)
+#define FW_FEATURE_CMO		ASM_CONST(0x0000000004000000)
 
 #ifndef __ASSEMBLY__
 
@@ -58,7 +59,7 @@ enum {
 		FW_FEATURE_MIGRATE | FW_FEATURE_PERFMON | FW_FEATURE_CRQ |
 		FW_FEATURE_VIO | FW_FEATURE_RDMA | FW_FEATURE_LLAN |
 		FW_FEATURE_BULK | FW_FEATURE_XDABR | FW_FEATURE_MULTITCE |
-		FW_FEATURE_SPLPAR | FW_FEATURE_LPAR,
+		FW_FEATURE_SPLPAR | FW_FEATURE_LPAR | FW_FEATURE_CMO,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
 	FW_FEATURE_ISERIES_POSSIBLE = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,
 	FW_FEATURE_ISERIES_ALWAYS = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,

include/asm-powerpc/hvcall.h

@@ -92,6 +92,11 @@
 #define H_EXACT			(1UL<<(63-24))	/* Use exact PTE or return H_PTEG_FULL */
 #define H_R_XLATE		(1UL<<(63-25))	/* include a valid logical page num in the pte if the valid bit is set */
 #define H_READ_4		(1UL<<(63-26))	/* Return 4 PTEs */
+#define H_PAGE_STATE_CHANGE	(1UL<<(63-28))
+#define H_PAGE_UNUSED		((1UL<<(63-29)) | (1UL<<(63-30)))
+#define H_PAGE_SET_UNUSED	(H_PAGE_STATE_CHANGE | H_PAGE_UNUSED)
+#define H_PAGE_SET_LOANED	(H_PAGE_SET_UNUSED | (1UL<<(63-31)))
+#define H_PAGE_SET_ACTIVE	H_PAGE_STATE_CHANGE
 #define H_AVPN			(1UL<<(63-32))	/* An avpn is provided as a sanity test */
 #define H_ANDCOND		(1UL<<(63-33))
 #define H_ICACHE_INVALIDATE	(1UL<<(63-40))	/* icbi, etc.  (ignored for IO pages) */
@@ -210,7 +215,9 @@
 #define H_JOIN			0x298
 #define H_VASI_STATE            0x2A4
 #define H_ENABLE_CRQ		0x2B0
-#define MAX_HCALL_OPCODE	H_ENABLE_CRQ
+#define H_SET_MPP		0x2D0
+#define H_GET_MPP		0x2D4
+#define MAX_HCALL_OPCODE	H_GET_MPP
 
 #ifndef __ASSEMBLY__
 
@@ -270,6 +277,20 @@ struct hcall_stats {
 };
 #define HCALL_STAT_ARRAY_SIZE	((MAX_HCALL_OPCODE >> 2) + 1)
 
+struct hvcall_mpp_data {
+	unsigned long entitled_mem;
+	unsigned long mapped_mem;
+	unsigned short group_num;
+	unsigned short pool_num;
+	unsigned char mem_weight;
+	unsigned char unallocated_mem_weight;
+	unsigned long unallocated_entitlement;  /* value in bytes */
+	unsigned long pool_size;
+	signed long loan_request;
+	unsigned long backing_mem;
+};
+
+int h_get_mpp(struct hvcall_mpp_data *);
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 #endif /* _ASM_POWERPC_HVCALL_H */

include/asm-powerpc/lppaca.h

@@ -125,7 +125,10 @@ struct lppaca {
 	// NOTE: This value will ALWAYS be zero for dedicated processors and
 	// will NEVER be zero for shared processors (ie, initialized to a 1).
 	volatile u32 yield_count;	// PLIC increments each dispatchx00-x03
-	u8	reserved6[124];		// Reserved                     x04-x7F
+	u32 reserved6;
+	volatile u64 cmo_faults;	// CMO page fault count         x08-x0F
+	volatile u64 cmo_fault_time;	// CMO page fault time          x10-x17
+	u8	reserved7[104];		// Reserved                     x18-x7F
 
 //=============================================================================
 // CACHE_LINE_4-5 0x0180 - 0x027F Contains PMC interrupt data

include/asm-powerpc/machdep.h

@@ -76,7 +76,7 @@ struct machdep_calls {
 	 * destroyed as well */
 	void		(*hpte_clear_all)(void);
 
-	void		(*tce_build)(struct iommu_table * tbl,
+	int		(*tce_build)(struct iommu_table *tbl,
 				     long index,
 				     long npages,
 				     unsigned long uaddr,

include/asm-powerpc/mpc52xx_psc.h

@@ -60,10 +60,12 @@
 #define MPC52xx_PSC_RXTX_FIFO_ALARM	0x0002
 #define MPC52xx_PSC_RXTX_FIFO_EMPTY	0x0001
 
-/* PSC interrupt mask bits */
+/* PSC interrupt status/mask bits */
 #define MPC52xx_PSC_IMR_TXRDY		0x0100
 #define MPC52xx_PSC_IMR_RXRDY		0x0200
 #define MPC52xx_PSC_IMR_DB		0x0400
+#define MPC52xx_PSC_IMR_TXEMP		0x0800
+#define MPC52xx_PSC_IMR_ORERR		0x1000
 #define MPC52xx_PSC_IMR_IPC		0x8000
 
 /* PSC input port change bit */
@@ -92,6 +94,34 @@
 
 #define MPC52xx_PSC_RFNUM_MASK	0x01ff
 
+#define MPC52xx_PSC_SICR_DTS1			(1 << 29)
+#define MPC52xx_PSC_SICR_SHDR			(1 << 28)
+#define MPC52xx_PSC_SICR_SIM_MASK		(0xf << 24)
+#define MPC52xx_PSC_SICR_SIM_UART		(0x0 << 24)
+#define MPC52xx_PSC_SICR_SIM_UART_DCD		(0x8 << 24)
+#define MPC52xx_PSC_SICR_SIM_CODEC_8		(0x1 << 24)
+#define MPC52xx_PSC_SICR_SIM_CODEC_16		(0x2 << 24)
+#define MPC52xx_PSC_SICR_SIM_AC97		(0x3 << 24)
+#define MPC52xx_PSC_SICR_SIM_SIR		(0x8 << 24)
+#define MPC52xx_PSC_SICR_SIM_SIR_DCD		(0xc << 24)
+#define MPC52xx_PSC_SICR_SIM_MIR		(0x5 << 24)
+#define MPC52xx_PSC_SICR_SIM_FIR		(0x6 << 24)
+#define MPC52xx_PSC_SICR_SIM_CODEC_24		(0x7 << 24)
+#define MPC52xx_PSC_SICR_SIM_CODEC_32		(0xf << 24)
+#define MPC52xx_PSC_SICR_GENCLK			(1 << 23)
+#define MPC52xx_PSC_SICR_I2S			(1 << 22)
+#define MPC52xx_PSC_SICR_CLKPOL			(1 << 21)
+#define MPC52xx_PSC_SICR_SYNCPOL		(1 << 20)
+#define MPC52xx_PSC_SICR_CELLSLAVE		(1 << 19)
+#define MPC52xx_PSC_SICR_CELL2XCLK		(1 << 18)
+#define MPC52xx_PSC_SICR_ESAI			(1 << 17)
+#define MPC52xx_PSC_SICR_ENAC97			(1 << 16)
+#define MPC52xx_PSC_SICR_SPI			(1 << 15)
+#define MPC52xx_PSC_SICR_MSTR			(1 << 14)
+#define MPC52xx_PSC_SICR_CPOL			(1 << 13)
+#define MPC52xx_PSC_SICR_CPHA			(1 << 12)
+#define MPC52xx_PSC_SICR_USEEOF			(1 << 11)
+#define MPC52xx_PSC_SICR_DISABLEEOF		(1 << 10)
 
 /* Structure of the hardware registers */
 struct mpc52xx_psc {
@@ -132,8 +162,12 @@ struct mpc52xx_psc {
 	u8		reserved5[3];
 	u8		ctlr;		/* PSC + 0x1c */
 	u8		reserved6[3];
-	u16		ccr;		/* PSC + 0x20 */
-	u8		reserved7[14];
+	/* BitClkDiv field of CCR is byte swapped in
+	 * the hardware for mpc5200/b compatibility */
+	u32		ccr;		/* PSC + 0x20 */
+	u32		ac97_slots;	/* PSC + 0x24 */
+	u32		ac97_cmd;	/* PSC + 0x28 */
+	u32		ac97_data;	/* PSC + 0x2c */
 	u8		ivr;		/* PSC + 0x30 */
 	u8		reserved8[3];
 	u8		ip;		/* PSC + 0x34 */

include/asm-powerpc/pgtable.h

@@ -38,6 +38,19 @@ extern void paging_init(void);
 		remap_pfn_range(vma, vaddr, pfn, size, prot)
 
 #include <asm-generic/pgtable.h>
+
+
+/*
+ * This gets called at the end of handling a page fault, when
+ * the kernel has put a new PTE into the page table for the process.
+ * We use it to ensure coherency between the i-cache and d-cache
+ * for the page which has just been mapped in.
+ * On machines which use an MMU hash table, we use this to put a
+ * corresponding HPTE into the hash table ahead of time, instead of
+ * waiting for the inevitable extra hash-table miss exception.
+ */
+extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */

include/asm-powerpc/syscalls.h

@@ -31,6 +31,7 @@ asmlinkage int sys_vfork(unsigned long p1, unsigned long p2,
 		unsigned long p3, unsigned long p4, unsigned long p5,
 		unsigned long p6, struct pt_regs *regs);
 asmlinkage long sys_pipe(int __user *fildes);
+asmlinkage long sys_pipe2(int __user *fildes, int flags);
 asmlinkage long sys_rt_sigaction(int sig,
 		const struct sigaction __user *act,
 		struct sigaction __user *oact, size_t sigsetsize);

include/asm-powerpc/systbl.h

@@ -316,3 +316,9 @@ COMPAT_SYS(fallocate)
 SYSCALL(subpage_prot)
 COMPAT_SYS_SPU(timerfd_settime)
 COMPAT_SYS_SPU(timerfd_gettime)
+COMPAT_SYS_SPU(signalfd4)
+SYSCALL_SPU(eventfd2)
+SYSCALL_SPU(epoll_create1)
+SYSCALL_SPU(dup3)
+SYSCALL_SPU(pipe2)
+SYSCALL(inotify_init1)

include/asm-powerpc/system.h

@@ -110,6 +110,8 @@ static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; }
 #endif
 
 extern int set_dabr(unsigned long dabr);
+extern void do_dabr(struct pt_regs *regs, unsigned long address,
+		    unsigned long error_code);
 extern void print_backtrace(unsigned long *);
 extern void show_regs(struct pt_regs * regs);
 extern void flush_instruction_cache(void);

include/asm-powerpc/tlbflush.h

@@ -162,16 +162,5 @@ extern void __flush_hash_table_range(struct mm_struct *mm, unsigned long start,
 
 #endif
 
-/*
- * This gets called at the end of handling a page fault, when
- * the kernel has put a new PTE into the page table for the process.
- * We use it to ensure coherency between the i-cache and d-cache
- * for the page which has just been mapped in.
- * On machines which use an MMU hash table, we use this to put a
- * corresponding HPTE into the hash table ahead of time, instead of
- * waiting for the inevitable extra hash-table miss exception.
- */
-extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t);
-
 #endif /*__KERNEL__ */
 #endif /* _ASM_POWERPC_TLBFLUSH_H */

include/asm-powerpc/unistd.h

@@ -335,10 +335,16 @@
 #define __NR_subpage_prot	310
 #define __NR_timerfd_settime	311
 #define __NR_timerfd_gettime	312
+#define __NR_signalfd4		313
+#define __NR_eventfd2		314
+#define __NR_epoll_create1	315
+#define __NR_dup3		316
+#define __NR_pipe2		317
+#define __NR_inotify_init1	318
 
 #ifdef __KERNEL__
 
-#define __NR_syscalls		313
+#define __NR_syscalls		319
 
 #define __NR__exit __NR_exit
 #define NR_syscalls	__NR_syscalls

include/asm-powerpc/vio.h

@@ -39,16 +39,32 @@
 #define VIO_IRQ_DISABLE		0UL
 #define VIO_IRQ_ENABLE		1UL
 
+/*
+ * VIO CMO minimum entitlement for all devices and spare entitlement
+ */
+#define VIO_CMO_MIN_ENT 1562624
+
 struct iommu_table;
 
-/*
- * The vio_dev structure is used to describe virtual I/O devices.
+/**
+ * vio_dev - This structure is used to describe virtual I/O devices.
+ *
+ * @desired: set from return of driver's get_desired_dma() function
+ * @entitled: bytes of IO data that has been reserved for this device.
+ * @allocated: bytes of IO data currently in use by the device.
+ * @allocs_failed: number of DMA failures due to insufficient entitlement.
  */
 struct vio_dev {
 	const char *name;
 	const char *type;
 	uint32_t unit_address;
 	unsigned int irq;
+	struct {
+		size_t desired;
+		size_t entitled;
+		size_t allocated;
+		atomic_t allocs_failed;
+	} cmo;
 	struct device dev;
 };
 
@@ -56,12 +72,19 @@ struct vio_driver {
 	const struct vio_device_id *id_table;
 	int (*probe)(struct vio_dev *dev, const struct vio_device_id *id);
 	int (*remove)(struct vio_dev *dev);
+	/* A driver must have a get_desired_dma() function to
+	 * be loaded in a CMO environment if it uses DMA.
+	 */
+	unsigned long (*get_desired_dma)(struct vio_dev *dev);
 	struct device_driver driver;
 };
 
 extern int vio_register_driver(struct vio_driver *drv);
 extern void vio_unregister_driver(struct vio_driver *drv);
 
+extern int vio_cmo_entitlement_update(size_t);
+extern void vio_cmo_set_dev_desired(struct vio_dev *viodev, size_t desired);
+
 extern void __devinit vio_unregister_device(struct vio_dev *dev);
 
 struct device_node;

include/linux/auxvec.h

@@ -26,9 +26,13 @@
 
 #define AT_SECURE 23   /* secure mode boolean */
 
+#define AT_BASE_PLATFORM 24	/* string identifying real platform, may
+				 * differ from AT_PLATFORM. */
+
 #define AT_EXECFN  31	/* filename of program */
+
 #ifdef __KERNEL__
-#define AT_VECTOR_SIZE_BASE 17 /* NEW_AUX_ENT entries in auxiliary table */
+#define AT_VECTOR_SIZE_BASE 18 /* NEW_AUX_ENT entries in auxiliary table */
   /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */
 #endif