17 files changed, 65 insertions, 17 deletions

diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 73eddda53b8e..4eec430d8fa8 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -28,6 +28,9 @@ BOOTCFLAGS	+= -m64
 endif
 ifdef CONFIG_CPU_BIG_ENDIAN
 BOOTCFLAGS      += -mbig-endian
+else
+BOOTCFLAGS      += -mlittle-endian
+BOOTCFLAGS      += $(call cc-option,-mabi=elfv2)
 endif
 
 BOOTAFLAGS      := -D__ASSEMBLY__ $(BOOTCFLAGS) -traditional -nostdinc
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 71f2b3f02cf8..4d65499ee1c1 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -368,3 +368,4 @@ SYSCALL_SPU(memfd_create)
 SYSCALL_SPU(bpf)
 COMPAT_SYS(execveat)
 PPC64ONLY(switch_endian)
+SYSCALL_SPU(userfaultfd)
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index f4f8b667d75b..4a055b6c2a64 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -12,7 +12,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define __NR_syscalls           364
+#define __NR_syscalls           365
 
 #define __NR__exit __NR_exit
 #define NR_syscalls     __NR_syscalls
diff --git a/arch/powerpc/include/uapi/asm/unistd.h b/arch/powerpc/include/uapi/asm/unistd.h
index e4aa173dae62..6ad58d4c879b 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -386,5 +386,6 @@
 #define __NR_bpf                361
 #define __NR_execveat           362
 #define __NR_switch_endian      363
+#define __NR_userfaultfd        364
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index bb02e9f6944e..ad8c9db61237 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -38,6 +38,7 @@
 #include <asm/udbg.h>
 #include <asm/mmu_context.h>
 #include <asm/epapr_hcalls.h>
+#include <asm/code-patching.h>
 
 #define DBG(fmt...)
 
@@ -109,6 +110,8 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
  * This is called very early on the boot process, after a minimal
  * MMU environment has been set up but before MMU_init is called.
  */
+extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */
+
 notrace void __init machine_init(u64 dt_ptr)
 {
         lockdep_init();
@@ -116,6 +119,9 @@ notrace void __init machine_init(u64 dt_ptr)
         /* Enable early debugging if any specified (see udbg.h) */
         udbg_early_init();
 
+        patch_instruction((unsigned int *)&memcpy, PPC_INST_NOP);
+        patch_instruction(&memset_nocache_branch, PPC_INST_NOP);
+
         /* Do some early initialization based on the flat device tree */
         early_init_devtree(__va(dt_ptr));
 
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index 2ef50c629470..c44df2dbedd5 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -73,6 +73,10 @@ CACHELINE_MASK = (L1_CACHE_BYTES-1)
  * Use dcbz on the complete cache lines in the destination
  * to set them to zero.  This requires that the destination
  * area is cacheable.  -- paulus
+ *
+ * During early init, cache might not be active yet, so dcbz cannot be used.
+ * We therefore skip the optimised bloc that uses dcbz. This jump is
+ * replaced by a nop once cache is active. This is done in machine_init()
  */
 _GLOBAL(memset)
         rlwimi  r4,r4,8,16,23
@@ -88,6 +92,8 @@ _GLOBAL(memset)
         subf    r6,r0,r6
         cmplwi  0,r4,0
         bne     2f      /* Use normal procedure if r4 is not zero */
+_GLOBAL(memset_nocache_branch)
+        b       2f      /* Skip optimised bloc until cache is enabled */
 
         clrlwi  r7,r6,32-LG_CACHELINE_BYTES
         add     r8,r7,r5
@@ -128,6 +134,10 @@ _GLOBAL(memset)
  * the destination area is cacheable.
  * We only use this version if the source and dest don't overlap.
  * -- paulus.
+ *
+ * During early init, cache might not be active yet, so dcbz cannot be used.
+ * We therefore jump to generic_memcpy which doesn't use dcbz. This jump is
+ * replaced by a nop once cache is active. This is done in machine_init()
  */
 _GLOBAL(memmove)
         cmplw   0,r3,r4
@@ -135,6 +145,7 @@ _GLOBAL(memmove)
         /* fall through */
 
 _GLOBAL(memcpy)
+        b       generic_memcpy
         add     r7,r3,r5                /* test if the src & dst overlap */
         add     r8,r4,r5
         cmplw   0,r4,r7
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 43dafb9d6a46..4d87122cf6a7 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -85,7 +85,6 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
         BUG_ON(index >= 4096);
 
         vpn = hpt_vpn(ea, vsid, ssize);
-        hash = hpt_hash(vpn, shift, ssize);
         hpte_slot_array = get_hpte_slot_array(pmdp);
         if (psize == MMU_PAGE_4K) {
                 /*
@@ -101,6 +100,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
         valid = hpte_valid(hpte_slot_array, index);
         if (valid) {
                 /* update the hpte bits */
+                hash = hpt_hash(vpn, shift, ssize);
                 hidx =  hpte_hash_index(hpte_slot_array, index);
                 if (hidx & _PTEIDX_SECONDARY)
                         hash = ~hash;
@@ -126,6 +126,7 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
         if (!valid) {
                 unsigned long hpte_group;
 
+                hash = hpt_hash(vpn, shift, ssize);
                 /* insert new entry */
                 pa = pmd_pfn(__pmd(old_pmd)) << PAGE_SHIFT;
                 new_pmd |= _PAGE_HASHPTE;
diff --git a/arch/powerpc/platforms/pasemi/msi.c b/arch/powerpc/platforms/pasemi/msi.c
index e66ef1943338..b304a9fe55cc 100644
--- a/arch/powerpc/platforms/pasemi/msi.c
+++ b/arch/powerpc/platforms/pasemi/msi.c
@@ -63,6 +63,7 @@ static struct irq_chip mpic_pasemi_msi_chip = {
 static void pasemi_msi_teardown_msi_irqs(struct pci_dev *pdev)
 {
         struct msi_desc *entry;
+        irq_hw_number_t hwirq;
 
         pr_debug("pasemi_msi_teardown_msi_irqs, pdev %p\n", pdev);
 
@@ -70,10 +71,10 @@ static void pasemi_msi_teardown_msi_irqs(struct pci_dev *pdev)
                 if (entry->irq == NO_IRQ)
                         continue;
 
+                hwirq = virq_to_hw(entry->irq);
                 irq_set_msi_desc(entry->irq, NULL);
-                msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap,
-                                       virq_to_hw(entry->irq), ALLOC_CHUNK);
                 irq_dispose_mapping(entry->irq);
+                msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap, hwirq, ALLOC_CHUNK);
         }
 
         return;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 2927cd5c8303..414fd1a00fda 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2049,9 +2049,23 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
         struct iommu_table *tbl = NULL;
         long rc;
 
+        /*
+         * crashkernel= specifies the kdump kernel's maximum memory at
+         * some offset and there is no guaranteed the result is a power
+         * of 2, which will cause errors later.
+         */
+        const u64 max_memory = __rounddown_pow_of_two(memory_hotplug_max());
+
+        /*
+         * In memory constrained environments, e.g. kdump kernel, the
+         * DMA window can be larger than available memory, which will
+         * cause errors later.
+         */
+        const u64 window_size = min((u64)pe->table_group.tce32_size, max_memory);
+
         rc = pnv_pci_ioda2_create_table(&pe->table_group, 0,
                         IOMMU_PAGE_SHIFT_4K,
-                        pe->table_group.tce32_size,
+                        window_size,
                         POWERNV_IOMMU_DEFAULT_LEVELS, &tbl);
         if (rc) {
                 pe_err(pe, "Failed to create 32-bit TCE table, err %ld",
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 9b2480b265c0..f2dd77234240 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -99,6 +99,7 @@ void pnv_teardown_msi_irqs(struct pci_dev *pdev)
         struct pci_controller *hose = pci_bus_to_host(pdev->bus);
         struct pnv_phb *phb = hose->private_data;
         struct msi_desc *entry;
+        irq_hw_number_t hwirq;
 
         if (WARN_ON(!phb))
                 return;
@@ -106,10 +107,10 @@ void pnv_teardown_msi_irqs(struct pci_dev *pdev)
         for_each_pci_msi_entry(entry, pdev) {
                 if (entry->irq == NO_IRQ)
                         continue;
+                hwirq = virq_to_hw(entry->irq);
                 irq_set_msi_desc(entry->irq, NULL);
-                msi_bitmap_free_hwirqs(&phb->msi_bmp,
-                        virq_to_hw(entry->irq) - phb->msi_base, 1);
                 irq_dispose_mapping(entry->irq);
+                msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, 1);
         }
 }
 #endif /* CONFIG_PCI_MSI */
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 47d9cebe7159..db17827eb746 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -422,8 +422,10 @@ static ssize_t dlpar_cpu_probe(const char *buf, size_t count)
 
         dn = dlpar_configure_connector(cpu_to_be32(drc_index), parent);
         of_node_put(parent);
-        if (!dn)
+        if (!dn) {
+                dlpar_release_drc(drc_index);
                 return -EINVAL;
+        }
 
         rc = dlpar_attach_node(dn);
         if (rc) {
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 5916da1856a7..48a576aa47b9 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -128,15 +128,16 @@ static void fsl_teardown_msi_irqs(struct pci_dev *pdev)
 {
         struct msi_desc *entry;
         struct fsl_msi *msi_data;
+        irq_hw_number_t hwirq;
 
         for_each_pci_msi_entry(entry, pdev) {
                 if (entry->irq == NO_IRQ)
                         continue;
+                hwirq = virq_to_hw(entry->irq);
                 msi_data = irq_get_chip_data(entry->irq);
                 irq_set_msi_desc(entry->irq, NULL);
-                msi_bitmap_free_hwirqs(&msi_data->bitmap,
-                                       virq_to_hw(entry->irq), 1);
                 irq_dispose_mapping(entry->irq);
+                msi_bitmap_free_hwirqs(&msi_data->bitmap, hwirq, 1);
         }
 
         return;
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index 70fbd5694a8b..2cbc7e29b85f 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -107,15 +107,16 @@ static u64 find_u4_magic_addr(struct pci_dev *pdev, unsigned int hwirq)
 static void u3msi_teardown_msi_irqs(struct pci_dev *pdev)
 {
         struct msi_desc *entry;
+        irq_hw_number_t hwirq;
 
         for_each_pci_msi_entry(entry, pdev) {
                 if (entry->irq == NO_IRQ)
                         continue;
 
+                hwirq = virq_to_hw(entry->irq);
                 irq_set_msi_desc(entry->irq, NULL);
-                msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap,
-                                       virq_to_hw(entry->irq), 1);
                 irq_dispose_mapping(entry->irq);
+                msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap, hwirq, 1);
         }
 
         return;
diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c
index 24d0470c1698..8fb806135043 100644
--- a/arch/powerpc/sysdev/ppc4xx_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_msi.c
@@ -124,16 +124,17 @@ void ppc4xx_teardown_msi_irqs(struct pci_dev *dev)
 {
         struct msi_desc *entry;
         struct ppc4xx_msi *msi_data = &ppc4xx_msi;
+        irq_hw_number_t hwirq;
 
         dev_dbg(&dev->dev, "PCIE-MSI: tearing down msi irqs\n");
 
         for_each_pci_msi_entry(entry, dev) {
                 if (entry->irq == NO_IRQ)
                         continue;
+                hwirq = virq_to_hw(entry->irq);
                 irq_set_msi_desc(entry->irq, NULL);
-                msi_bitmap_free_hwirqs(&msi_data->bitmap,
-                                virq_to_hw(entry->irq), 1);
                 irq_dispose_mapping(entry->irq);
+                msi_bitmap_free_hwirqs(&msi_data->bitmap, hwirq, 1);
         }
 }
 
diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile
index 6f484dfe78f9..6982f603fadc 100644
--- a/drivers/misc/cxl/Makefile
+++ b/drivers/misc/cxl/Makefile
@@ -1,4 +1,4 @@
-ccflags-y := -Werror
+ccflags-y := -Werror -Wno-unused-const-variable
 
 cxl-y                           += main.o file.o irq.o fault.o native.o
 cxl-y                           += context.o sysfs.o debugfs.o pci.o trace.o
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 02c85160bfe9..a5e977192b61 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -1249,8 +1249,6 @@ static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
         int slice;
         int rc;
 
-        pci_dev_get(dev);
-
         if (cxl_verbose)
                 dump_cxl_config_space(dev);
 
diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c
index 6dd16a6d153f..94b520896b18 100644
--- a/drivers/misc/cxl/vphb.c
+++ b/drivers/misc/cxl/vphb.c
@@ -48,6 +48,12 @@ static bool cxl_pci_enable_device_hook(struct pci_dev *dev)
 
         phb = pci_bus_to_host(dev->bus);
         afu = (struct cxl_afu *)phb->private_data;
+
+        if (!cxl_adapter_link_ok(afu->adapter)) {
+                dev_warn(&dev->dev, "%s: Device link is down, refusing to enable AFU\n", __func__);
+                return false;
+        }
+
         set_dma_ops(&dev->dev, &dma_direct_ops);
         set_dma_offset(&dev->dev, PAGE_OFFSET);