Merge tag 'powerpc-5.5-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc fixes from Michael Ellerman:
 "Two weeks worth of accumulated fixes:

   - A fix for a performance regression seen on PowerVM LPARs using
     dedicated CPUs, caused by our vcpu_is_preempted() returning true
     even for idle CPUs.

   - One of the ultravisor support patches broke KVM on big endian hosts
     in v5.4.

   - Our KUAP (Kernel User Access Prevention) code missed allowing
     access in __clear_user(), which could lead to an oops or erroneous
     SEGV when triggered via PTRACE_GETREGSET.

   - Two fixes for the ocxl driver, an open/remove race, and a memory
     leak in an error path.

   - A handful of other small fixes.

  Thanks to: Andrew Donnellan, Christian Zigotzky, Christophe Leroy,
  Christoph Hellwig, Daniel Axtens, David Hildenbrand, Frederic Barrat,
  Gautham R. Shenoy, Greg Kurz, Ihor Pasichnyk, Juri Lelli, Marcus
  Comstedt, Mike Rapoport, Parth Shah, Srikar Dronamraju, Vaidyanathan
  Srinivasan"

* tag 'powerpc-5.5-4' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  KVM: PPC: Book3S HV: Fix regression on big endian hosts
  powerpc: Fix __clear_user() with KUAP enabled
  powerpc/pseries/cmm: fix managed page counts when migrating pages between zones
  powerpc/8xx: fix bogus __init on mmu_mapin_ram_chunk()
  ocxl: Fix potential memory leak on context creation
  powerpc/irq: fix stack overflow verification
  powerpc: Ensure that swiotlb buffer is allocated from low memory
  powerpc/shared: Use static key to detect shared processor
  powerpc/vcpu: Assume dedicated processors as non-preempt
  ocxl: Fix concurrent AFU open and device removal

12 files changed, 62 insertions, 36 deletions

diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index e9a960e28f3c..1b55fc08f853 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -36,10 +36,12 @@
 #endif
 
 #ifdef CONFIG_PPC_PSERIES
+DECLARE_STATIC_KEY_FALSE(shared_processor);
+
 #define vcpu_is_preempted vcpu_is_preempted
 static inline bool vcpu_is_preempted(int cpu)
 {
-	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
+	if (!static_branch_unlikely(&shared_processor))
 		return false;
 	return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1);
 }
@@ -110,13 +112,8 @@ static inline void splpar_rw_yield(arch_rwlock_t *lock) {};
 
 static inline bool is_shared_processor(void)
 {
-/*
- * LPPACA is only available on Pseries so guard anything LPPACA related to
- * allow other platforms (which include this common header) to compile.
- */
-#ifdef CONFIG_PPC_PSERIES
-	return (IS_ENABLED(CONFIG_PPC_SPLPAR) &&
-		lppaca_shared_proc(local_paca->lppaca_ptr));
+#ifdef CONFIG_PPC_SPLPAR
+	return static_branch_unlikely(&shared_processor);
 #else
 	return false;
 #endif
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index 15002b51ff18..c92fe7fe9692 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -401,7 +401,7 @@ copy_to_user_mcsafe(void __user *to, const void *from, unsigned long n)
 	return n;
 }
 
-extern unsigned long __clear_user(void __user *addr, unsigned long size);
+unsigned long __arch_clear_user(void __user *addr, unsigned long size);
 
 static inline unsigned long clear_user(void __user *addr, unsigned long size)
 {
@@ -409,12 +409,17 @@ static inline unsigned long clear_user(void __user *addr, unsigned long size)
 	might_fault();
 	if (likely(access_ok(addr, size))) {
 		allow_write_to_user(addr, size);
-		ret = __clear_user(addr, size);
+		ret = __arch_clear_user(addr, size);
 		prevent_write_to_user(addr, size);
 	}
 	return ret;
 }
 
+static inline unsigned long __clear_user(void __user *addr, unsigned long size)
+{
+	return clear_user(addr, size);
+}
+
 extern long strncpy_from_user(char *dst, const char __user *src, long count);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 5645bc9cbc09..add67498c126 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -619,8 +619,6 @@ void __do_irq(struct pt_regs *regs)
 
 	trace_irq_entry(regs);
 
-	check_stack_overflow();
-
 	/*
 	 * Query the platform PIC for the interrupt & ack it.
 	 *
@@ -652,6 +650,8 @@ void do_IRQ(struct pt_regs *regs)
 	irqsp = hardirq_ctx[raw_smp_processor_id()];
 	sirqsp = softirq_ctx[raw_smp_processor_id()];
 
+	check_stack_overflow();
+
 	/* Already there ? */
 	if (unlikely(cursp == irqsp || cursp == sirqsp)) {
 		__do_irq(regs);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 0496e66aaa56..c6fbbd29bd87 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1117,7 +1117,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	ld	r7, VCPU_GPR(R7)(r4)
 	bne	ret_to_ultra
 
-	lwz	r0, VCPU_CR(r4)
+	ld	r0, VCPU_CR(r4)
 	mtcr	r0
 
 	ld	r0, VCPU_GPR(R0)(r4)
@@ -1137,7 +1137,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
  *   R3 = UV_RETURN
  */
 ret_to_ultra:
-	lwz	r0, VCPU_CR(r4)
+	ld	r0, VCPU_CR(r4)
 	mtcr	r0
 
 	ld	r0, VCPU_GPR(R3)(r4)
diff --git a/arch/powerpc/lib/string_32.S b/arch/powerpc/lib/string_32.S
index f69a6aab7bfb..1ddb26394e8a 100644
--- a/arch/powerpc/lib/string_32.S
+++ b/arch/powerpc/lib/string_32.S
@@ -17,7 +17,7 @@ CACHELINE_BYTES = L1_CACHE_BYTES
 LG_CACHELINE_BYTES = L1_CACHE_SHIFT
 CACHELINE_MASK = (L1_CACHE_BYTES-1)
 
-_GLOBAL(__clear_user)
+_GLOBAL(__arch_clear_user)
 /*
  * Use dcbz on the complete cache lines in the destination
  * to set them to zero.  This requires that the destination
@@ -87,4 +87,4 @@ _GLOBAL(__clear_user)
 	EX_TABLE(8b, 91b)
 	EX_TABLE(9b, 91b)
 
-EXPORT_SYMBOL(__clear_user)
+EXPORT_SYMBOL(__arch_clear_user)
diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S
index 507b18b1660e..169872bc0892 100644
--- a/arch/powerpc/lib/string_64.S
+++ b/arch/powerpc/lib/string_64.S
@@ -17,7 +17,7 @@ PPC64_CACHES:
 	.section	".text"
 
 /**
- * __clear_user: - Zero a block of memory in user space, with less checking.
+ * __arch_clear_user: - Zero a block of memory in user space, with less checking.
  * @to:   Destination address, in user space.
  * @n:    Number of bytes to zero.
  *
@@ -58,7 +58,7 @@ err3;	stb	r0,0(r3)
 	mr	r3,r4
 	blr
 
-_GLOBAL_TOC(__clear_user)
+_GLOBAL_TOC(__arch_clear_user)
 	cmpdi	r4,32
 	neg	r6,r3
 	li	r0,0
@@ -181,4 +181,4 @@ err1;	dcbz	0,r3
 	cmpdi	r4,32
 	blt	.Lshort_clear
 	b	.Lmedium_clear
-EXPORT_SYMBOL(__clear_user)
+EXPORT_SYMBOL(__arch_clear_user)
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 9488b63dfc87..617c2777926f 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -289,6 +289,14 @@ void __init mem_init(void)
 	BUILD_BUG_ON(MMU_PAGE_COUNT > 16);
 
 #ifdef CONFIG_SWIOTLB
+	/*
+	 * Some platforms (e.g. 85xx) limit DMA-able memory way below
+	 * 4G. We force memblock to bottom-up mode to ensure that the
+	 * memory allocated in swiotlb_init() is DMA-able.
+	 * As it's the last memblock allocation, no need to reset it
+	 * back to to-down.
+	 */
+	memblock_set_bottom_up(true);
 	swiotlb_init(0);
 #endif
 
diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
index 090af2d2d3e4..96eb8e43f39b 100644
--- a/arch/powerpc/mm/nohash/8xx.c
+++ b/arch/powerpc/mm/nohash/8xx.c
@@ -103,7 +103,7 @@ static void mmu_patch_addis(s32 *site, long simm)
 	patch_instruction_site(site, instr);
 }
 
-void __init mmu_mapin_ram_chunk(unsigned long offset, unsigned long top, pgprot_t prot)
+static void mmu_mapin_ram_chunk(unsigned long offset, unsigned long top, pgprot_t prot)
 {
 	unsigned long s = offset;
 	unsigned long v = PAGE_OFFSET + s;
diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index 91571841df8a..9dba7e880885 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -539,6 +539,16 @@ static int cmm_migratepage(struct balloon_dev_info *b_dev_info,
 	/* balloon page list reference */
 	get_page(newpage);
 
+	/*
+	 * When we migrate a page to a different zone, we have to fixup the
+	 * count of both involved zones as we adjusted the managed page count
+	 * when inflating.
+	 */
+	if (page_zone(page) != page_zone(newpage)) {
+		adjust_managed_page_count(page, 1);
+		adjust_managed_page_count(newpage, -1);
+	}
+
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
 	balloon_page_insert(b_dev_info, newpage);
 	balloon_page_delete(page);
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 0a40201f315f..0c8421dd01ab 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -74,6 +74,9 @@
 #include "pseries.h"
 #include "../../../../drivers/pci/pci.h"
 
+DEFINE_STATIC_KEY_FALSE(shared_processor);
+EXPORT_SYMBOL_GPL(shared_processor);
+
 int CMO_PrPSP = -1;
 int CMO_SecPSP = -1;
 unsigned long CMO_PageSize = (ASM_CONST(1) << IOMMU_PAGE_SHIFT_4K);
@@ -758,6 +761,10 @@ static void __init pSeries_setup_arch(void)
 
 	if (firmware_has_feature(FW_FEATURE_LPAR)) {
 		vpa_init(boot_cpuid);
+
+		if (lppaca_shared_proc(get_lppaca()))
+			static_branch_enable(&shared_processor);
+
 		ppc_md.power_save = pseries_lpar_idle;
 		ppc_md.enable_pmcs = pseries_lpar_enable_pmcs;
 #ifdef CONFIG_PCI_IOV
diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c
index 994563a078eb..de8a66b9d76b 100644
--- a/drivers/misc/ocxl/context.c
+++ b/drivers/misc/ocxl/context.c
@@ -10,18 +10,17 @@ int ocxl_context_alloc(struct ocxl_context **context, struct ocxl_afu *afu,
 	int pasid;
 	struct ocxl_context *ctx;
 
-	*context = kzalloc(sizeof(struct ocxl_context), GFP_KERNEL);
-	if (!*context)
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
 		return -ENOMEM;
 
-	ctx = *context;
-
 	ctx->afu = afu;
 	mutex_lock(&afu->contexts_lock);
 	pasid = idr_alloc(&afu->contexts_idr, ctx, afu->pasid_base,
 			afu->pasid_base + afu->pasid_max, GFP_KERNEL);
 	if (pasid < 0) {
 		mutex_unlock(&afu->contexts_lock);
+		kfree(ctx);
 		return pasid;
 	}
 	afu->pasid_count++;
@@ -43,6 +42,7 @@ int ocxl_context_alloc(struct ocxl_context **context, struct ocxl_afu *afu,
 	 * duration of the life of the context
 	 */
 	ocxl_afu_get(afu);
+	*context = ctx;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ocxl_context_alloc);
diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c
index 2870c25da166..4d1b44de1492 100644
--- a/drivers/misc/ocxl/file.c
+++ b/drivers/misc/ocxl/file.c
@@ -18,18 +18,15 @@ static struct class *ocxl_class;
 static struct mutex minors_idr_lock;
 static struct idr minors_idr;
 
-static struct ocxl_file_info *find_file_info(dev_t devno)
+static struct ocxl_file_info *find_and_get_file_info(dev_t devno)
 {
 	struct ocxl_file_info *info;
 
-	/*
-	 * We don't declare an RCU critical section here, as our AFU
-	 * is protected by a reference counter on the device. By the time the
-	 * info reference is removed from the idr, the ref count of
-	 * the device is already at 0, so no user API will access that AFU and
-	 * this function can't return it.
-	 */
+	mutex_lock(&minors_idr_lock);
 	info = idr_find(&minors_idr, MINOR(devno));
+	if (info)
+		get_device(&info->dev);
+	mutex_unlock(&minors_idr_lock);
 	return info;
 }
 
@@ -58,14 +55,16 @@ static int afu_open(struct inode *inode, struct file *file)
 
 	pr_debug("%s for device %x\n", __func__, inode->i_rdev);
 
-	info = find_file_info(inode->i_rdev);
+	info = find_and_get_file_info(inode->i_rdev);
 	if (!info)
 		return -ENODEV;
 
 	rc = ocxl_context_alloc(&ctx, info->afu, inode->i_mapping);
-	if (rc)
+	if (rc) {
+		put_device(&info->dev);
 		return rc;
-
+	}
+	put_device(&info->dev);
 	file->private_data = ctx;
 	return 0;
 }
@@ -487,7 +486,6 @@ static void info_release(struct device *dev)
 {
 	struct ocxl_file_info *info = container_of(dev, struct ocxl_file_info, dev);
 
-	free_minor(info);
 	ocxl_afu_put(info->afu);
 	kfree(info);
 }
@@ -577,6 +575,7 @@ void ocxl_file_unregister_afu(struct ocxl_afu *afu)
 
 	ocxl_file_make_invisible(info);
 	ocxl_sysfs_unregister_afu(info);
+	free_minor(info);
 	device_unregister(&info->dev);
 }