LinuxPPC-Dev Archive on lore.kernel.org
 help / color / mirror / Atom feed

* [PATCH v6 09/12] mm: Move vmap_range from mm/ioremap.c to mm/vmalloc.c
From: Nicholas Piggin @ 2020-08-21 15:12 UTC (permalink / raw)
  To: linux-mm, Andrew Morton
  Cc: linux-arch, linux-kernel, Nicholas Piggin, Christoph Hellwig,
	Zefan Li, Jonathan Cameron, linuxppc-dev
In-Reply-To: <20200821151216.1005117-1-npiggin@gmail.com>

This is a generic kernel virtual memory mapper, not specific to ioremap.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 include/linux/vmalloc.h |   3 +
 mm/ioremap.c            | 197 ----------------------------------------
 mm/vmalloc.c            | 196 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 199 insertions(+), 197 deletions(-)

diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 3f6bba4cc9bc..15adb9a14fb6 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -177,6 +177,9 @@ extern struct vm_struct *remove_vm_area(const void *addr);
 extern struct vm_struct *find_vm_area(const void *addr);
 
 #ifdef CONFIG_MMU
+int vmap_range(unsigned long addr, unsigned long end,
+			phys_addr_t phys_addr, pgprot_t prot,
+			unsigned int max_page_shift);
 extern int map_kernel_range_noflush(unsigned long start, unsigned long size,
 				    pgprot_t prot, struct page **pages);
 int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot,
diff --git a/mm/ioremap.c b/mm/ioremap.c
index c67f91164401..d1dcc7e744ac 100644
--- a/mm/ioremap.c
+++ b/mm/ioremap.c
@@ -28,203 +28,6 @@ early_param("nohugeiomap", set_nohugeiomap);
 static const bool iomap_max_page_shift = PAGE_SHIFT;
 #endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
 
-static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
-			phys_addr_t phys_addr, pgprot_t prot,
-			pgtbl_mod_mask *mask)
-{
-	pte_t *pte;
-	u64 pfn;
-
-	pfn = phys_addr >> PAGE_SHIFT;
-	pte = pte_alloc_kernel_track(pmd, addr, mask);
-	if (!pte)
-		return -ENOMEM;
-	do {
-		BUG_ON(!pte_none(*pte));
-		set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
-		pfn++;
-	} while (pte++, addr += PAGE_SIZE, addr != end);
-	*mask |= PGTBL_PTE_MODIFIED;
-	return 0;
-}
-
-static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
-			phys_addr_t phys_addr, pgprot_t prot,
-			unsigned int max_page_shift)
-{
-	if (max_page_shift < PMD_SHIFT)
-		return 0;
-
-	if (!arch_vmap_pmd_supported(prot))
-		return 0;
-
-	if ((end - addr) != PMD_SIZE)
-		return 0;
-
-	if (!IS_ALIGNED(addr, PMD_SIZE))
-		return 0;
-
-	if (!IS_ALIGNED(phys_addr, PMD_SIZE))
-		return 0;
-
-	if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr))
-		return 0;
-
-	return pmd_set_huge(pmd, phys_addr, prot);
-}
-
-static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
-			phys_addr_t phys_addr, pgprot_t prot,
-			unsigned int max_page_shift, pgtbl_mod_mask *mask)
-{
-	pmd_t *pmd;
-	unsigned long next;
-
-	pmd = pmd_alloc_track(&init_mm, pud, addr, mask);
-	if (!pmd)
-		return -ENOMEM;
-	do {
-		next = pmd_addr_end(addr, end);
-
-		if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot, max_page_shift)) {
-			*mask |= PGTBL_PMD_MODIFIED;
-			continue;
-		}
-
-		if (vmap_pte_range(pmd, addr, next, phys_addr, prot, mask))
-			return -ENOMEM;
-	} while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
-	return 0;
-}
-
-static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
-			phys_addr_t phys_addr, pgprot_t prot,
-			unsigned int max_page_shift)
-{
-	if (max_page_shift < PUD_SHIFT)
-		return 0;
-
-	if (!arch_vmap_pud_supported(prot))
-		return 0;
-
-	if ((end - addr) != PUD_SIZE)
-		return 0;
-
-	if (!IS_ALIGNED(addr, PUD_SIZE))
-		return 0;
-
-	if (!IS_ALIGNED(phys_addr, PUD_SIZE))
-		return 0;
-
-	if (pud_present(*pud) && !pud_free_pmd_page(pud, addr))
-		return 0;
-
-	return pud_set_huge(pud, phys_addr, prot);
-}
-
-static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
-			phys_addr_t phys_addr, pgprot_t prot,
-			unsigned int max_page_shift, pgtbl_mod_mask *mask)
-{
-	pud_t *pud;
-	unsigned long next;
-
-	pud = pud_alloc_track(&init_mm, p4d, addr, mask);
-	if (!pud)
-		return -ENOMEM;
-	do {
-		next = pud_addr_end(addr, end);
-
-		if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot, max_page_shift)) {
-			*mask |= PGTBL_PUD_MODIFIED;
-			continue;
-		}
-
-		if (vmap_pmd_range(pud, addr, next, phys_addr, prot, max_page_shift, mask))
-			return -ENOMEM;
-	} while (pud++, phys_addr += (next - addr), addr = next, addr != end);
-	return 0;
-}
-
-static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
-			phys_addr_t phys_addr, pgprot_t prot,
-			unsigned int max_page_shift)
-{
-	if (max_page_shift < P4D_SHIFT)
-		return 0;
-
-	if (!arch_vmap_p4d_supported(prot))
-		return 0;
-
-	if ((end - addr) != P4D_SIZE)
-		return 0;
-
-	if (!IS_ALIGNED(addr, P4D_SIZE))
-		return 0;
-
-	if (!IS_ALIGNED(phys_addr, P4D_SIZE))
-		return 0;
-
-	if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr))
-		return 0;
-
-	return p4d_set_huge(p4d, phys_addr, prot);
-}
-
-static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
-			phys_addr_t phys_addr, pgprot_t prot,
-			unsigned int max_page_shift, pgtbl_mod_mask *mask)
-{
-	p4d_t *p4d;
-	unsigned long next;
-
-	p4d = p4d_alloc_track(&init_mm, pgd, addr, mask);
-	if (!p4d)
-		return -ENOMEM;
-	do {
-		next = p4d_addr_end(addr, end);
-
-		if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot, max_page_shift)) {
-			*mask |= PGTBL_P4D_MODIFIED;
-			continue;
-		}
-
-		if (vmap_pud_range(p4d, addr, next, phys_addr, prot, max_page_shift, mask))
-			return -ENOMEM;
-	} while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
-	return 0;
-}
-
-static int vmap_range(unsigned long addr, unsigned long end,
-			phys_addr_t phys_addr, pgprot_t prot,
-			unsigned int max_page_shift)
-{
-	pgd_t *pgd;
-	unsigned long start;
-	unsigned long next;
-	int err;
-	pgtbl_mod_mask mask = 0;
-
-	might_sleep();
-	BUG_ON(addr >= end);
-
-	start = addr;
-	pgd = pgd_offset_k(addr);
-	do {
-		next = pgd_addr_end(addr, end);
-		err = vmap_p4d_range(pgd, addr, next, phys_addr, prot, max_page_shift, &mask);
-		if (err)
-			break;
-	} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
-
-	flush_cache_vmap(start, end);
-
-	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
-		arch_sync_kernel_mappings(start, end);
-
-	return err;
-}
-
 int ioremap_page_range(unsigned long addr,
 		       unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
 {
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 45cd80ec7eeb..256554d598e6 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -70,6 +70,202 @@ static void free_work(struct work_struct *w)
 }
 
 /*** Page table manipulation functions ***/
+static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+			phys_addr_t phys_addr, pgprot_t prot,
+			pgtbl_mod_mask *mask)
+{
+	pte_t *pte;
+	u64 pfn;
+
+	pfn = phys_addr >> PAGE_SHIFT;
+	pte = pte_alloc_kernel_track(pmd, addr, mask);
+	if (!pte)
+		return -ENOMEM;
+	do {
+		BUG_ON(!pte_none(*pte));
+		set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
+		pfn++;
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+	*mask |= PGTBL_PTE_MODIFIED;
+	return 0;
+}
+
+static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
+			phys_addr_t phys_addr, pgprot_t prot,
+			unsigned int max_page_shift)
+{
+	if (max_page_shift < PMD_SHIFT)
+		return 0;
+
+	if (!arch_vmap_pmd_supported(prot))
+		return 0;
+
+	if ((end - addr) != PMD_SIZE)
+		return 0;
+
+	if (!IS_ALIGNED(addr, PMD_SIZE))
+		return 0;
+
+	if (!IS_ALIGNED(phys_addr, PMD_SIZE))
+		return 0;
+
+	if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr))
+		return 0;
+
+	return pmd_set_huge(pmd, phys_addr, prot);
+}
+
+static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
+			phys_addr_t phys_addr, pgprot_t prot,
+			unsigned int max_page_shift, pgtbl_mod_mask *mask)
+{
+	pmd_t *pmd;
+	unsigned long next;
+
+	pmd = pmd_alloc_track(&init_mm, pud, addr, mask);
+	if (!pmd)
+		return -ENOMEM;
+	do {
+		next = pmd_addr_end(addr, end);
+
+		if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot, max_page_shift)) {
+			*mask |= PGTBL_PMD_MODIFIED;
+			continue;
+		}
+
+		if (vmap_pte_range(pmd, addr, next, phys_addr, prot, mask))
+			return -ENOMEM;
+	} while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
+	return 0;
+}
+
+static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
+			phys_addr_t phys_addr, pgprot_t prot,
+			unsigned int max_page_shift)
+{
+	if (max_page_shift < PUD_SHIFT)
+		return 0;
+
+	if (!arch_vmap_pud_supported(prot))
+		return 0;
+
+	if ((end - addr) != PUD_SIZE)
+		return 0;
+
+	if (!IS_ALIGNED(addr, PUD_SIZE))
+		return 0;
+
+	if (!IS_ALIGNED(phys_addr, PUD_SIZE))
+		return 0;
+
+	if (pud_present(*pud) && !pud_free_pmd_page(pud, addr))
+		return 0;
+
+	return pud_set_huge(pud, phys_addr, prot);
+}
+
+static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
+			phys_addr_t phys_addr, pgprot_t prot,
+			unsigned int max_page_shift, pgtbl_mod_mask *mask)
+{
+	pud_t *pud;
+	unsigned long next;
+
+	pud = pud_alloc_track(&init_mm, p4d, addr, mask);
+	if (!pud)
+		return -ENOMEM;
+	do {
+		next = pud_addr_end(addr, end);
+
+		if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot, max_page_shift)) {
+			*mask |= PGTBL_PUD_MODIFIED;
+			continue;
+		}
+
+		if (vmap_pmd_range(pud, addr, next, phys_addr, prot, max_page_shift, mask))
+			return -ENOMEM;
+	} while (pud++, phys_addr += (next - addr), addr = next, addr != end);
+	return 0;
+}
+
+static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
+			phys_addr_t phys_addr, pgprot_t prot,
+			unsigned int max_page_shift)
+{
+	if (max_page_shift < P4D_SHIFT)
+		return 0;
+
+	if (!arch_vmap_p4d_supported(prot))
+		return 0;
+
+	if ((end - addr) != P4D_SIZE)
+		return 0;
+
+	if (!IS_ALIGNED(addr, P4D_SIZE))
+		return 0;
+
+	if (!IS_ALIGNED(phys_addr, P4D_SIZE))
+		return 0;
+
+	if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr))
+		return 0;
+
+	return p4d_set_huge(p4d, phys_addr, prot);
+}
+
+static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
+			phys_addr_t phys_addr, pgprot_t prot,
+			unsigned int max_page_shift, pgtbl_mod_mask *mask)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	p4d = p4d_alloc_track(&init_mm, pgd, addr, mask);
+	if (!p4d)
+		return -ENOMEM;
+	do {
+		next = p4d_addr_end(addr, end);
+
+		if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot, max_page_shift)) {
+			*mask |= PGTBL_P4D_MODIFIED;
+			continue;
+		}
+
+		if (vmap_pud_range(p4d, addr, next, phys_addr, prot, max_page_shift, mask))
+			return -ENOMEM;
+	} while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
+	return 0;
+}
+
+int vmap_range(unsigned long addr, unsigned long end,
+			phys_addr_t phys_addr, pgprot_t prot,
+			unsigned int max_page_shift)
+{
+	pgd_t *pgd;
+	unsigned long start;
+	unsigned long next;
+	int err;
+	pgtbl_mod_mask mask = 0;
+
+	might_sleep();
+	BUG_ON(addr >= end);
+
+	start = addr;
+	pgd = pgd_offset_k(addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		err = vmap_p4d_range(pgd, addr, next, phys_addr, prot, max_page_shift, &mask);
+		if (err)
+			break;
+	} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
+
+	flush_cache_vmap(start, end);
+
+	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
+		arch_sync_kernel_mappings(start, end);
+
+	return err;
+}
 
 static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			     pgtbl_mod_mask *mask)
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 10/12] mm/vmalloc: add vmap_range_noflush variant
From: Nicholas Piggin @ 2020-08-21 15:12 UTC (permalink / raw)
  To: linux-mm, Andrew Morton
  Cc: linux-arch, linux-kernel, Nicholas Piggin, Christoph Hellwig,
	Zefan Li, Jonathan Cameron, linuxppc-dev
In-Reply-To: <20200821151216.1005117-1-npiggin@gmail.com>

As a side-effect, the order of flush_cache_vmap() and
arch_sync_kernel_mappings() calls are switched, but that now matches
the other callers in this file.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 mm/vmalloc.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 256554d598e6..1d6cad16bda3 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -237,7 +237,7 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 	return 0;
 }
 
-int vmap_range(unsigned long addr, unsigned long end,
+static int vmap_range_noflush(unsigned long addr, unsigned long end,
 			phys_addr_t phys_addr, pgprot_t prot,
 			unsigned int max_page_shift)
 {
@@ -259,14 +259,24 @@ int vmap_range(unsigned long addr, unsigned long end,
 			break;
 	} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
 
-	flush_cache_vmap(start, end);
-
 	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
 		arch_sync_kernel_mappings(start, end);
 
 	return err;
 }
 
+int vmap_range(unsigned long addr, unsigned long end,
+			phys_addr_t phys_addr, pgprot_t prot,
+			unsigned int max_page_shift)
+{
+	int err;
+
+	err = vmap_range_noflush(addr, end, phys_addr, prot, max_page_shift);
+	flush_cache_vmap(addr, end);
+
+	return err;
+}
+
 static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			     pgtbl_mod_mask *mask)
 {
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 11/12] mm/vmalloc: Hugepage vmalloc mappings
From: Nicholas Piggin @ 2020-08-21 15:12 UTC (permalink / raw)
  To: linux-mm, Andrew Morton
  Cc: linux-arch, linux-kernel, Nicholas Piggin, Christoph Hellwig,
	Zefan Li, Jonathan Cameron, linuxppc-dev
In-Reply-To: <20200821151216.1005117-1-npiggin@gmail.com>

Support huge page vmalloc mappings. Config option HAVE_ARCH_HUGE_VMALLOC
enables support on architectures that define HAVE_ARCH_HUGE_VMAP and
supports PMD sized vmap mappings.

vmalloc will attempt to allocate PMD-sized pages if allocating PMD size or
larger, and fall back to small pages if that was unsuccessful.

Allocations that do not use PAGE_KERNEL prot are not permitted to use huge
pages, because not all callers expect this (e.g., module allocations vs
strict module rwx).

This reduces TLB misses by nearly 30x on a `git diff` workload on a 2-node
POWER9 (59,800 -> 2,100) and reduces CPU cycles by 0.54%.

This can result in more internal fragmentation and memory overhead for a
given allocation, an option nohugevmalloc is added to disable at boot.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/Kconfig            |   4 +
 include/linux/vmalloc.h |   1 +
 mm/page_alloc.c         |   5 +-
 mm/vmalloc.c            | 180 ++++++++++++++++++++++++++++++----------
 4 files changed, 145 insertions(+), 45 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index af14a567b493..b2b89d629317 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -616,6 +616,10 @@ config HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 config HAVE_ARCH_HUGE_VMAP
 	bool
 
+config HAVE_ARCH_HUGE_VMALLOC
+	depends on HAVE_ARCH_HUGE_VMAP
+	bool
+
 config ARCH_WANT_HUGE_PMD_SHARE
 	bool
 
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 15adb9a14fb6..a7449064fe35 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -58,6 +58,7 @@ struct vm_struct {
 	unsigned long		size;
 	unsigned long		flags;
 	struct page		**pages;
+	unsigned int		page_order;
 	unsigned int		nr_pages;
 	phys_addr_t		phys_addr;
 	const void		*caller;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0e2bab486fea..b6427cc7b838 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -69,6 +69,7 @@
 #include <linux/nmi.h>
 #include <linux/psi.h>
 #include <linux/padata.h>
+#include <linux/vmalloc.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -8102,6 +8103,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 	void *table = NULL;
 	gfp_t gfp_flags;
 	bool virt;
+	bool huge;
 
 	/* allow the kernel cmdline to have a say */
 	if (!numentries) {
@@ -8169,6 +8171,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 		} else if (get_order(size) >= MAX_ORDER || hashdist) {
 			table = __vmalloc(size, gfp_flags);
 			virt = true;
+			huge = (find_vm_area(table)->page_order > 0);
 		} else {
 			/*
 			 * If bucketsize is not a power-of-two, we may free
@@ -8185,7 +8188,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 
 	pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n",
 		tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size,
-		virt ? "vmalloc" : "linear");
+		virt ? (huge ? "vmalloc hugepage" : "vmalloc") : "linear");
 
 	if (_hash_shift)
 		*_hash_shift = log2qty;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 1d6cad16bda3..8db53c2d7f72 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -44,6 +44,19 @@
 #include "internal.h"
 #include "pgalloc-track.h"
 
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+static bool __ro_after_init vmap_allow_huge = true;
+
+static int __init set_nohugevmalloc(char *str)
+{
+	vmap_allow_huge = false;
+	return 0;
+}
+early_param("nohugevmalloc", set_nohugevmalloc);
+#else /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */
+static const bool vmap_allow_huge = false;
+#endif	/* CONFIG_HAVE_ARCH_HUGE_VMALLOC */
+
 bool is_vmalloc_addr(const void *x)
 {
 	unsigned long addr = (unsigned long)x;
@@ -477,31 +490,12 @@ static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr,
 	return 0;
 }
 
-/**
- * map_kernel_range_noflush - map kernel VM area with the specified pages
- * @addr: start of the VM area to map
- * @size: size of the VM area to map
- * @prot: page protection flags to use
- * @pages: pages to map
- *
- * Map PFN_UP(@size) pages at @addr.  The VM area @addr and @size specify should
- * have been allocated using get_vm_area() and its friends.
- *
- * NOTE:
- * This function does NOT do any cache flushing.  The caller is responsible for
- * calling flush_cache_vmap() on to-be-mapped areas before calling this
- * function.
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int map_kernel_range_noflush(unsigned long addr, unsigned long size,
-			     pgprot_t prot, struct page **pages)
+static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end,
+		pgprot_t prot, struct page **pages)
 {
 	unsigned long start = addr;
-	unsigned long end = addr + size;
-	unsigned long next;
 	pgd_t *pgd;
+	unsigned long next;
 	int err = 0;
 	int nr = 0;
 	pgtbl_mod_mask mask = 0;
@@ -523,6 +517,65 @@ int map_kernel_range_noflush(unsigned long addr, unsigned long size,
 	return 0;
 }
 
+static int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
+		pgprot_t prot, struct page **pages, unsigned int page_shift)
+{
+	unsigned int i, nr = (end - addr) >> PAGE_SHIFT;
+
+	WARN_ON(page_shift < PAGE_SHIFT);
+
+	if (page_shift == PAGE_SHIFT)
+		return vmap_small_pages_range_noflush(addr, end, prot, pages);
+
+	for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) {
+		int err;
+
+		err = vmap_range_noflush(addr, addr + (1UL << page_shift),
+					__pa(page_address(pages[i])), prot,
+					page_shift);
+		if (err)
+			return err;
+
+		addr += 1UL << page_shift;
+	}
+
+	return 0;
+}
+
+static int vmap_pages_range(unsigned long addr, unsigned long end,
+		pgprot_t prot, struct page **pages, unsigned int page_shift)
+{
+	int err;
+
+	err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift);
+	flush_cache_vmap(addr, end);
+	return err;
+}
+
+/**
+ * map_kernel_range_noflush - map kernel VM area with the specified pages
+ * @addr: start of the VM area to map
+ * @size: size of the VM area to map
+ * @prot: page protection flags to use
+ * @pages: pages to map
+ *
+ * Map PFN_UP(@size) pages at @addr.  The VM area @addr and @size specify should
+ * have been allocated using get_vm_area() and its friends.
+ *
+ * NOTE:
+ * This function does NOT do any cache flushing.  The caller is responsible for
+ * calling flush_cache_vmap() on to-be-mapped areas before calling this
+ * function.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int map_kernel_range_noflush(unsigned long addr, unsigned long size,
+			     pgprot_t prot, struct page **pages)
+{
+	return vmap_pages_range_noflush(addr, addr + size, prot, pages, PAGE_SHIFT);
+}
+
 int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot,
 		struct page **pages)
 {
@@ -2400,6 +2453,7 @@ static inline void set_area_direct_map(const struct vm_struct *area,
 {
 	int i;
 
+	/* HUGE_VMALLOC passes small pages to set_direct_map */
 	for (i = 0; i < area->nr_pages; i++)
 		if (page_address(area->pages[i]))
 			set_direct_map(area->pages[i]);
@@ -2433,11 +2487,12 @@ static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
 	 * map. Find the start and end range of the direct mappings to make sure
 	 * the vm_unmap_aliases() flush includes the direct map.
 	 */
-	for (i = 0; i < area->nr_pages; i++) {
+	for (i = 0; i < area->nr_pages; i += 1U << area->page_order) {
 		unsigned long addr = (unsigned long)page_address(area->pages[i]);
 		if (addr) {
+			unsigned long page_size = PAGE_SIZE << area->page_order;
 			start = min(addr, start);
-			end = max(addr + PAGE_SIZE, end);
+			end = max(addr + page_size, end);
 			flush_dmap = 1;
 		}
 	}
@@ -2480,11 +2535,11 @@ static void __vunmap(const void *addr, int deallocate_pages)
 	if (deallocate_pages) {
 		int i;
 
-		for (i = 0; i < area->nr_pages; i++) {
+		for (i = 0; i < area->nr_pages; i += 1U << area->page_order) {
 			struct page *page = area->pages[i];
 
 			BUG_ON(!page);
-			__free_pages(page, 0);
+			__free_pages(page, area->page_order);
 		}
 		atomic_long_sub(area->nr_pages, &nr_vmalloc_pages);
 
@@ -2623,9 +2678,12 @@ void *vmap(struct page **pages, unsigned int count,
 EXPORT_SYMBOL(vmap);
 
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
-				 pgprot_t prot, int node)
+				 pgprot_t prot, unsigned int page_shift, int node)
 {
 	struct page **pages;
+	unsigned long addr = (unsigned long)area->addr;
+	unsigned long size = get_vm_area_size(area);
+	unsigned int page_order = page_shift - PAGE_SHIFT;
 	unsigned int nr_pages, array_size, i;
 	const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
 	const gfp_t alloc_mask = gfp_mask | __GFP_NOWARN;
@@ -2633,7 +2691,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 					0 :
 					__GFP_HIGHMEM;
 
-	nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
+	nr_pages = size >> PAGE_SHIFT;
 	array_size = (nr_pages * sizeof(struct page *));
 
 	/* Please note that the recursion is strictly bounded. */
@@ -2652,29 +2710,29 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 
 	area->pages = pages;
 	area->nr_pages = nr_pages;
+	area->page_order = page_order;
 
-	for (i = 0; i < area->nr_pages; i++) {
+	for (i = 0; i < area->nr_pages; i += 1U << page_order) {
 		struct page *page;
+		int p;
 
-		if (node == NUMA_NO_NODE)
-			page = alloc_page(alloc_mask|highmem_mask);
-		else
-			page = alloc_pages_node(node, alloc_mask|highmem_mask, 0);
-
+		page = alloc_pages_node(node, alloc_mask|highmem_mask, page_order);
 		if (unlikely(!page)) {
 			/* Successfully allocated i pages, free them in __vunmap() */
 			area->nr_pages = i;
 			atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
 			goto fail;
 		}
-		area->pages[i] = page;
+
+		for (p = 0; p < (1U << page_order); p++)
+			area->pages[i + p] = page + p;
+
 		if (gfpflags_allow_blocking(gfp_mask))
 			cond_resched();
 	}
 	atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
 
-	if (map_kernel_range((unsigned long)area->addr, get_vm_area_size(area),
-			prot, pages) < 0)
+	if (vmap_pages_range(addr, addr + size, prot, pages, page_shift) < 0)
 		goto fail;
 
 	return area->addr;
@@ -2682,7 +2740,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 fail:
 	warn_alloc(gfp_mask, NULL,
 			  "vmalloc: allocation failure, allocated %ld of %ld bytes",
-			  (area->nr_pages*PAGE_SIZE), area->size);
+			  (area->nr_pages*PAGE_SIZE), size);
 	__vfree(area->addr);
 	return NULL;
 }
@@ -2713,19 +2771,42 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	struct vm_struct *area;
 	void *addr;
 	unsigned long real_size = size;
+	unsigned long real_align = align;
+	unsigned int shift = PAGE_SHIFT;
 
-	size = PAGE_ALIGN(size);
 	if (!size || (size >> PAGE_SHIFT) > totalram_pages())
 		goto fail;
 
-	area = __get_vm_area_node(real_size, align, VM_ALLOC | VM_UNINITIALIZED |
+	if (vmap_allow_huge && (pgprot_val(prot) == pgprot_val(PAGE_KERNEL))) {
+		unsigned long size_per_node;
+
+		/*
+		 * Try huge pages. Only try for PAGE_KERNEL allocations,
+		 * others like modules don't yet expect huge pages in
+		 * their allocations due to apply_to_page_range not
+		 * supporting them.
+		 */
+
+		size_per_node = size;
+		if (node == NUMA_NO_NODE)
+			size_per_node /= num_online_nodes();
+		if (size_per_node >= PMD_SIZE) {
+			shift = PMD_SHIFT;
+			align = max(real_align, 1UL << shift);
+			size = ALIGN(real_size, 1UL << shift);
+		}
+	}
+
+again:
+	size = PAGE_ALIGN(size);
+	area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED |
 				vm_flags, start, end, node, gfp_mask, caller);
 	if (!area)
 		goto fail;
 
-	addr = __vmalloc_area_node(area, gfp_mask, prot, node);
+	addr = __vmalloc_area_node(area, gfp_mask, prot, shift, node);
 	if (!addr)
-		return NULL;
+		goto fail;
 
 	/*
 	 * In this function, newly allocated vm_struct has VM_UNINITIALIZED
@@ -2739,8 +2820,19 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
 	return addr;
 
 fail:
-	warn_alloc(gfp_mask, NULL,
+	if (shift > PAGE_SHIFT) {
+		free_vm_area(area);
+		shift = PAGE_SHIFT;
+		align = real_align;
+		size = real_size;
+		goto again;
+	}
+
+	if (!area) {
+		/* Warn for area allocation, page allocations already warn */
+		warn_alloc(gfp_mask, NULL,
 			  "vmalloc: allocation failure: %lu bytes", real_size);
+	}
 	return NULL;
 }
 
@@ -3739,7 +3831,7 @@ static int s_show(struct seq_file *m, void *p)
 		seq_printf(m, " %pS", v->caller);
 
 	if (v->nr_pages)
-		seq_printf(m, " pages=%d", v->nr_pages);
+		seq_printf(m, " pages=%d order=%d", v->nr_pages, v->page_order);
 
 	if (v->phys_addr)
 		seq_printf(m, " phys=%pa", &v->phys_addr);
-- 
2.23.0


^ permalink raw reply related

* [PATCH v6 12/12] powerpc/64s/radix: Enable huge vmalloc mappings
From: Nicholas Piggin @ 2020-08-21 15:12 UTC (permalink / raw)
  To: linux-mm, Andrew Morton
  Cc: linux-arch, linux-kernel, Nicholas Piggin, Christoph Hellwig,
	Zefan Li, Jonathan Cameron, linuxppc-dev
In-Reply-To: <20200821151216.1005117-1-npiggin@gmail.com>

Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 Documentation/admin-guide/kernel-parameters.txt | 2 ++
 arch/powerpc/Kconfig                            | 1 +
 2 files changed, 3 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index bdc1f33fd3d1..6f0b41289a90 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3190,6 +3190,8 @@
 
 	nohugeiomap	[KNL,X86,PPC] Disable kernel huge I/O mappings.
 
+	nohugevmalloc	[PPC] Disable kernel huge vmalloc mappings.
+
 	nosmt		[KNL,S390] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1f48bbfb3ce9..9171d25ad7dc 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -175,6 +175,7 @@ config PPC
 	select GENERIC_TIME_VSYSCALL
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMAP		if PPC_BOOK3S_64 && PPC_RADIX_MMU
+	select HAVE_ARCH_HUGE_VMALLOC		if HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_KASAN			if PPC32 && PPC_PAGE_SHIFT <= 14
 	select HAVE_ARCH_KASAN_VMALLOC		if PPC32 && PPC_PAGE_SHIFT <= 14
-- 
2.23.0


^ permalink raw reply related

* Re: [PATCH v6 11/12] mm/vmalloc: Hugepage vmalloc mappings
From: Eric Dumazet @ 2020-08-21 15:38 UTC (permalink / raw)
  To: Nicholas Piggin, linux-mm, Andrew Morton
  Cc: linux-arch, linux-kernel, Christoph Hellwig, Zefan Li,
	Jonathan Cameron, linuxppc-dev
In-Reply-To: <20200821151216.1005117-12-npiggin@gmail.com>


On 8/21/20 8:12 AM, Nicholas Piggin wrote:
> Support huge page vmalloc mappings. Config option HAVE_ARCH_HUGE_VMALLOC
> enables support on architectures that define HAVE_ARCH_HUGE_VMAP and
> supports PMD sized vmap mappings.
> 
> vmalloc will attempt to allocate PMD-sized pages if allocating PMD size or
> larger, and fall back to small pages if that was unsuccessful.
> 
> Allocations that do not use PAGE_KERNEL prot are not permitted to use huge
> pages, because not all callers expect this (e.g., module allocations vs
> strict module rwx).
> 
> This reduces TLB misses by nearly 30x on a `git diff` workload on a 2-node
> POWER9 (59,800 -> 2,100) and reduces CPU cycles by 0.54%.
> 
> This can result in more internal fragmentation and memory overhead for a
> given allocation, an option nohugevmalloc is added to disable at boot.
> 
>

Thanks for working on this stuff, I tried something similar in the past,
but could not really do more than a hack.
( https://lkml.org/lkml/2016/12/21/285 )

Note that __init alloc_large_system_hash() is used at boot time,
when NUMA policy is spreading allocations over all NUMA nodes.

This means that on a dual node system, a hash table should be 50/50 spread.

With your patch, if a hashtable is exactly the size of one huge page,
the location of this hashtable will be not balanced, this might have some
unwanted impact.

Thanks !


^ permalink raw reply

* Re: kernel since 5.6 do not boot anymore on Apple PowerBook
From: Giuseppe Sacco @ 2020-08-21 15:44 UTC (permalink / raw)
  To: Christophe Leroy, linuxppc-dev@lists.ozlabs.org
In-Reply-To: <5158eae8-6809-ae07-0d16-58f2a766f534@csgroup.eu>

Hello,

Il giorno ven, 21/08/2020 alle 16.03 +0200, Christophe Leroy ha
scritto:
[...]
> Thanks.
> 
> The Oops in the video shows that the issue is at 0x1bcac and msr
> value 
> shows that Instruction MMU is disabled. So this corresponds to
> address 
> 0xc001bcac. In the vmlinux you sent me this address is in 
> power_save_ppc32_restore()
> 
> This issue is fixed by 
> https://patchwork.ozlabs.org/project/linuxppc-dev/patch/7bce32ccbab3ba3e3e0f27da6961bf6313df97ed.1581663140.git.christophe.leroy@c-s.fr/
> 
> 
> You also said in a previous mail that your original issue also
> happens 
> when CONFIG_VMAP_STACK is not selected. The above bug being linked
> to 
> CONFIG_VMAP_STACK, maybe it would be easier to bisect with 
> CONFIG_VMAP_STACK unselected.

I rebuilt the same kernel that I would otherwise have skipped because
of the other bug, and it worked, indeed.
I will continue my "bisect quest" unselecting VMAP_STACK in order to
speed up the bisecting.

Thank you very much,
Giuseppe


^ permalink raw reply

* Re: [PATCH v6 11/12] mm/vmalloc: Hugepage vmalloc mappings
From: Nicholas Piggin @ 2020-08-21 16:05 UTC (permalink / raw)
  To: Andrew Morton, Eric Dumazet, linux-mm
  Cc: linux-arch, linux-kernel, Christoph Hellwig, Zefan Li,
	Jonathan Cameron, linuxppc-dev
In-Reply-To: <1e001c2c-6c47-21a9-e920-caf78933b713@gmail.com>

Excerpts from Eric Dumazet's message of August 22, 2020 1:38 am:
> 
> On 8/21/20 8:12 AM, Nicholas Piggin wrote:
>> Support huge page vmalloc mappings. Config option HAVE_ARCH_HUGE_VMALLOC
>> enables support on architectures that define HAVE_ARCH_HUGE_VMAP and
>> supports PMD sized vmap mappings.
>> 
>> vmalloc will attempt to allocate PMD-sized pages if allocating PMD size or
>> larger, and fall back to small pages if that was unsuccessful.
>> 
>> Allocations that do not use PAGE_KERNEL prot are not permitted to use huge
>> pages, because not all callers expect this (e.g., module allocations vs
>> strict module rwx).
>> 
>> This reduces TLB misses by nearly 30x on a `git diff` workload on a 2-node
>> POWER9 (59,800 -> 2,100) and reduces CPU cycles by 0.54%.
>> 
>> This can result in more internal fragmentation and memory overhead for a
>> given allocation, an option nohugevmalloc is added to disable at boot.
>> 
>>
> 
> Thanks for working on this stuff, I tried something similar in the past,
> but could not really do more than a hack.
> ( https://lkml.org/lkml/2016/12/21/285 )

Oh nice. It might be possible to do some ideas from your patch
still. Higher order pages smaller than PMD size, or the memory
policy stuff, perhaps.

> Note that __init alloc_large_system_hash() is used at boot time,
> when NUMA policy is spreading allocations over all NUMA nodes.
> 
> This means that on a dual node system, a hash table should be 50/50 spread.
> 
> With your patch, if a hashtable is exactly the size of one huge page,
> the location of this hashtable will be not balanced, this might have some
> unwanted impact.

In that case it shouldn't because it divides by the number of nodes,
but it will in general have a bit larger granularity in balancing than
smaller pages of course.

There's probably a better way to size these important hashes on NUMA. I
suspect most of the time you have a NUMA machine you actually would
prefer to use large pages now, even if it means taking up to 2MB more
memory per node per hash. It's not a great amount and the allocation 
size is rather arbitrary anyway.

Thanks,
Nick

^ permalink raw reply

* [PATCH AUTOSEL 5.8 12/62] powerpc/xive: Ignore kmemleak false positives
From: Sasha Levin @ 2020-08-21 16:13 UTC (permalink / raw)
  To: linux-kernel, stable; +Cc: Alexey Kardashevskiy, linuxppc-dev, Sasha Levin
In-Reply-To: <20200821161423.347071-1-sashal@kernel.org>

From: Alexey Kardashevskiy <aik@ozlabs.ru>

[ Upstream commit f0993c839e95dd6c7f054a1015e693c87e33e4fb ]

xive_native_provision_pages() allocates memory and passes the pointer to
OPAL so kmemleak cannot find the pointer usage in the kernel memory and
produces a false positive report (below) (even if the kernel did scan
OPAL memory, it is unable to deal with __pa() addresses anyway).

This silences the warning.

unreferenced object 0xc000200350c40000 (size 65536):
  comm "qemu-system-ppc", pid 2725, jiffies 4294946414 (age 70776.530s)
  hex dump (first 32 bytes):
    02 00 00 00 50 00 00 00 00 00 00 00 00 00 00 00  ....P...........
    01 00 08 07 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<0000000081ff046c>] xive_native_alloc_vp_block+0x120/0x250
    [<00000000d555d524>] kvmppc_xive_compute_vp_id+0x248/0x350 [kvm]
    [<00000000d69b9c9f>] kvmppc_xive_connect_vcpu+0xc0/0x520 [kvm]
    [<000000006acbc81c>] kvm_arch_vcpu_ioctl+0x308/0x580 [kvm]
    [<0000000089c69580>] kvm_vcpu_ioctl+0x19c/0xae0 [kvm]
    [<00000000902ae91e>] ksys_ioctl+0x184/0x1b0
    [<00000000f3e68bd7>] sys_ioctl+0x48/0xb0
    [<0000000001b2c127>] system_call_exception+0x124/0x1f0
    [<00000000d2b2ee40>] system_call_common+0xe8/0x214

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200612043303.84894-1-aik@ozlabs.ru
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/sysdev/xive/native.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index 71b881e554fcb..cb58ec7ce77ac 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -18,6 +18,7 @@
 #include <linux/delay.h>
 #include <linux/cpumask.h>
 #include <linux/mm.h>
+#include <linux/kmemleak.h>
 
 #include <asm/machdep.h>
 #include <asm/prom.h>
@@ -647,6 +648,7 @@ static bool xive_native_provision_pages(void)
 			pr_err("Failed to allocate provisioning page\n");
 			return false;
 		}
+		kmemleak_ignore(p);
 		opal_xive_donate_page(chip, __pa(p));
 	}
 	return true;
-- 
2.25.1


^ permalink raw reply related

* [PATCH AUTOSEL 5.8 33/62] selftests/powerpc: Purge extra count_pmc() calls of ebb selftests
From: Sasha Levin @ 2020-08-21 16:13 UTC (permalink / raw)
  To: linux-kernel, stable
  Cc: Sachin Sant, Sasha Levin, Desnes A. Nunes do Rosario,
	linux-kselftest, linuxppc-dev
In-Reply-To: <20200821161423.347071-1-sashal@kernel.org>

From: "Desnes A. Nunes do Rosario" <desnesn@linux.ibm.com>

[ Upstream commit 3337bf41e0dd70b4064cdf60acdfcdc2d050066c ]

An extra count on ebb_state.stats.pmc_count[PMC_INDEX(pmc)] is being per-
formed when count_pmc() is used to reset PMCs on a few selftests. This
extra pmc_count can occasionally invalidate results, such as the ones from
cycles_test shown hereafter. The ebb_check_count() failed with an above
the upper limit error due to the extra value on ebb_state.stats.pmc_count.

Furthermore, this extra count is also indicated by extra PMC1 trace_log on
the output of the cycle test (as well as on pmc56_overflow_test):

==========
   ...
   [21]: counter = 8
   [22]: register SPRN_MMCR0 = 0x0000000080000080
   [23]: register SPRN_PMC1  = 0x0000000080000004
   [24]: counter = 9
   [25]: register SPRN_MMCR0 = 0x0000000080000080
   [26]: register SPRN_PMC1  = 0x0000000080000004
   [27]: counter = 10
   [28]: register SPRN_MMCR0 = 0x0000000080000080
   [29]: register SPRN_PMC1  = 0x0000000080000004
>> [30]: register SPRN_PMC1  = 0x000000004000051e
PMC1 count (0x280000546) above upper limit 0x2800003e8 (+0x15e)
[FAIL] Test FAILED on line 52
failure: cycles
==========

Signed-off-by: Desnes A. Nunes do Rosario <desnesn@linux.ibm.com>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200626164737.21943-1-desnesn@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c      | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c    | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/ebb.c              | 2 --
 .../selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c  | 2 --
 .../selftests/powerpc/pmu/ebb/lost_exception_test.c        | 1 -
 .../testing/selftests/powerpc/pmu/ebb/multi_counter_test.c | 7 -------
 .../selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c       | 2 --
 .../testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c | 2 --
 .../selftests/powerpc/pmu/ebb/pmc56_overflow_test.c        | 2 --
 11 files changed, 26 deletions(-)

diff --git a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
index a2d7b0e3dca97..a26ac122c759f 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
@@ -91,8 +91,6 @@ int back_to_back_ebbs(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
index bc893813483ee..bb9f587fa76e8 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
@@ -42,8 +42,6 @@ int cycles(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
index dcd351d203289..9ae795ce314e6 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
@@ -99,8 +99,6 @@ int cycles_with_freeze(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	printf("EBBs while frozen %d\n", ebbs_while_frozen);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
index 94c99c12c0f23..4b45a2e70f62b 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
@@ -71,8 +71,6 @@ int cycles_with_mmcr2(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index dfbc5c3ad52d7..21537d6eb6b7d 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -396,8 +396,6 @@ int ebb_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
index ca2f7d729155b..b208bf6ad58d3 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
@@ -38,8 +38,6 @@ static int victim_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	FAIL_IF(ebb_state.stats.ebb_count == 0);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
index ac3e6e182614a..ba2681a12cc7b 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
@@ -75,7 +75,6 @@ static int test_body(void)
 	ebb_freeze_pmcs();
 	ebb_global_disable();
 
-	count_pmc(4, sample_period);
 	mtspr(SPRN_PMC4, 0xdead);
 
 	dump_summary_ebb_state();
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
index b8242e9d97d2d..791d37ba327b5 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
@@ -70,13 +70,6 @@ int multi_counter(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-	count_pmc(2, sample_period);
-	count_pmc(3, sample_period);
-	count_pmc(4, sample_period);
-	count_pmc(5, sample_period);
-	count_pmc(6, sample_period);
-
 	dump_ebb_state();
 
 	for (i = 0; i < 6; i++)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
index a05c0e18ded63..9b0f70d597020 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
@@ -61,8 +61,6 @@ static int cycles_child(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_summary_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
index 153ebc92234fd..2904c741e04e5 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
@@ -82,8 +82,6 @@ static int test_body(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	if (mmcr0_mismatch)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index eadad75ed7e6f..b29f8ba22d1e6 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -76,8 +76,6 @@ int pmc56_overflow(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(2, sample_period);
-
 	dump_ebb_state();
 
 	printf("PMC5/6 overflow %d\n", pmc56_overflowed);
-- 
2.25.1


^ permalink raw reply related

* [PATCH AUTOSEL 5.7 12/61] powerpc/xive: Ignore kmemleak false positives
From: Sasha Levin @ 2020-08-21 16:14 UTC (permalink / raw)
  To: linux-kernel, stable; +Cc: Alexey Kardashevskiy, linuxppc-dev, Sasha Levin
In-Reply-To: <20200821161545.347622-1-sashal@kernel.org>

From: Alexey Kardashevskiy <aik@ozlabs.ru>

[ Upstream commit f0993c839e95dd6c7f054a1015e693c87e33e4fb ]

xive_native_provision_pages() allocates memory and passes the pointer to
OPAL so kmemleak cannot find the pointer usage in the kernel memory and
produces a false positive report (below) (even if the kernel did scan
OPAL memory, it is unable to deal with __pa() addresses anyway).

This silences the warning.

unreferenced object 0xc000200350c40000 (size 65536):
  comm "qemu-system-ppc", pid 2725, jiffies 4294946414 (age 70776.530s)
  hex dump (first 32 bytes):
    02 00 00 00 50 00 00 00 00 00 00 00 00 00 00 00  ....P...........
    01 00 08 07 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<0000000081ff046c>] xive_native_alloc_vp_block+0x120/0x250
    [<00000000d555d524>] kvmppc_xive_compute_vp_id+0x248/0x350 [kvm]
    [<00000000d69b9c9f>] kvmppc_xive_connect_vcpu+0xc0/0x520 [kvm]
    [<000000006acbc81c>] kvm_arch_vcpu_ioctl+0x308/0x580 [kvm]
    [<0000000089c69580>] kvm_vcpu_ioctl+0x19c/0xae0 [kvm]
    [<00000000902ae91e>] ksys_ioctl+0x184/0x1b0
    [<00000000f3e68bd7>] sys_ioctl+0x48/0xb0
    [<0000000001b2c127>] system_call_exception+0x124/0x1f0
    [<00000000d2b2ee40>] system_call_common+0xe8/0x214

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200612043303.84894-1-aik@ozlabs.ru
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/sysdev/xive/native.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index 5218fdc4b29a9..82860c7b58353 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -18,6 +18,7 @@
 #include <linux/delay.h>
 #include <linux/cpumask.h>
 #include <linux/mm.h>
+#include <linux/kmemleak.h>
 
 #include <asm/machdep.h>
 #include <asm/prom.h>
@@ -647,6 +648,7 @@ static bool xive_native_provision_pages(void)
 			pr_err("Failed to allocate provisioning page\n");
 			return false;
 		}
+		kmemleak_ignore(p);
 		opal_xive_donate_page(chip, __pa(p));
 	}
 	return true;
-- 
2.25.1


^ permalink raw reply related

* [PATCH AUTOSEL 5.7 33/61] selftests/powerpc: Purge extra count_pmc() calls of ebb selftests
From: Sasha Levin @ 2020-08-21 16:15 UTC (permalink / raw)
  To: linux-kernel, stable
  Cc: Sachin Sant, Sasha Levin, Desnes A. Nunes do Rosario,
	linux-kselftest, linuxppc-dev
In-Reply-To: <20200821161545.347622-1-sashal@kernel.org>

From: "Desnes A. Nunes do Rosario" <desnesn@linux.ibm.com>

[ Upstream commit 3337bf41e0dd70b4064cdf60acdfcdc2d050066c ]

An extra count on ebb_state.stats.pmc_count[PMC_INDEX(pmc)] is being per-
formed when count_pmc() is used to reset PMCs on a few selftests. This
extra pmc_count can occasionally invalidate results, such as the ones from
cycles_test shown hereafter. The ebb_check_count() failed with an above
the upper limit error due to the extra value on ebb_state.stats.pmc_count.

Furthermore, this extra count is also indicated by extra PMC1 trace_log on
the output of the cycle test (as well as on pmc56_overflow_test):

==========
   ...
   [21]: counter = 8
   [22]: register SPRN_MMCR0 = 0x0000000080000080
   [23]: register SPRN_PMC1  = 0x0000000080000004
   [24]: counter = 9
   [25]: register SPRN_MMCR0 = 0x0000000080000080
   [26]: register SPRN_PMC1  = 0x0000000080000004
   [27]: counter = 10
   [28]: register SPRN_MMCR0 = 0x0000000080000080
   [29]: register SPRN_PMC1  = 0x0000000080000004
>> [30]: register SPRN_PMC1  = 0x000000004000051e
PMC1 count (0x280000546) above upper limit 0x2800003e8 (+0x15e)
[FAIL] Test FAILED on line 52
failure: cycles
==========

Signed-off-by: Desnes A. Nunes do Rosario <desnesn@linux.ibm.com>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200626164737.21943-1-desnesn@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c      | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c    | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/ebb.c              | 2 --
 .../selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c  | 2 --
 .../selftests/powerpc/pmu/ebb/lost_exception_test.c        | 1 -
 .../testing/selftests/powerpc/pmu/ebb/multi_counter_test.c | 7 -------
 .../selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c       | 2 --
 .../testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c | 2 --
 .../selftests/powerpc/pmu/ebb/pmc56_overflow_test.c        | 2 --
 11 files changed, 26 deletions(-)

diff --git a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
index a2d7b0e3dca97..a26ac122c759f 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
@@ -91,8 +91,6 @@ int back_to_back_ebbs(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
index bc893813483ee..bb9f587fa76e8 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
@@ -42,8 +42,6 @@ int cycles(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
index dcd351d203289..9ae795ce314e6 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
@@ -99,8 +99,6 @@ int cycles_with_freeze(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	printf("EBBs while frozen %d\n", ebbs_while_frozen);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
index 94c99c12c0f23..4b45a2e70f62b 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
@@ -71,8 +71,6 @@ int cycles_with_mmcr2(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index dfbc5c3ad52d7..21537d6eb6b7d 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -396,8 +396,6 @@ int ebb_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
index ca2f7d729155b..b208bf6ad58d3 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
@@ -38,8 +38,6 @@ static int victim_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	FAIL_IF(ebb_state.stats.ebb_count == 0);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
index ac3e6e182614a..ba2681a12cc7b 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
@@ -75,7 +75,6 @@ static int test_body(void)
 	ebb_freeze_pmcs();
 	ebb_global_disable();
 
-	count_pmc(4, sample_period);
 	mtspr(SPRN_PMC4, 0xdead);
 
 	dump_summary_ebb_state();
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
index b8242e9d97d2d..791d37ba327b5 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
@@ -70,13 +70,6 @@ int multi_counter(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-	count_pmc(2, sample_period);
-	count_pmc(3, sample_period);
-	count_pmc(4, sample_period);
-	count_pmc(5, sample_period);
-	count_pmc(6, sample_period);
-
 	dump_ebb_state();
 
 	for (i = 0; i < 6; i++)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
index a05c0e18ded63..9b0f70d597020 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
@@ -61,8 +61,6 @@ static int cycles_child(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_summary_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
index 153ebc92234fd..2904c741e04e5 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
@@ -82,8 +82,6 @@ static int test_body(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	if (mmcr0_mismatch)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index eadad75ed7e6f..b29f8ba22d1e6 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -76,8 +76,6 @@ int pmc56_overflow(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(2, sample_period);
-
 	dump_ebb_state();
 
 	printf("PMC5/6 overflow %d\n", pmc56_overflowed);
-- 
2.25.1


^ permalink raw reply related

* [PATCH AUTOSEL 5.4 10/48] powerpc/xive: Ignore kmemleak false positives
From: Sasha Levin @ 2020-08-21 16:16 UTC (permalink / raw)
  To: linux-kernel, stable; +Cc: Alexey Kardashevskiy, linuxppc-dev, Sasha Levin
In-Reply-To: <20200821161704.348164-1-sashal@kernel.org>

From: Alexey Kardashevskiy <aik@ozlabs.ru>

[ Upstream commit f0993c839e95dd6c7f054a1015e693c87e33e4fb ]

xive_native_provision_pages() allocates memory and passes the pointer to
OPAL so kmemleak cannot find the pointer usage in the kernel memory and
produces a false positive report (below) (even if the kernel did scan
OPAL memory, it is unable to deal with __pa() addresses anyway).

This silences the warning.

unreferenced object 0xc000200350c40000 (size 65536):
  comm "qemu-system-ppc", pid 2725, jiffies 4294946414 (age 70776.530s)
  hex dump (first 32 bytes):
    02 00 00 00 50 00 00 00 00 00 00 00 00 00 00 00  ....P...........
    01 00 08 07 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<0000000081ff046c>] xive_native_alloc_vp_block+0x120/0x250
    [<00000000d555d524>] kvmppc_xive_compute_vp_id+0x248/0x350 [kvm]
    [<00000000d69b9c9f>] kvmppc_xive_connect_vcpu+0xc0/0x520 [kvm]
    [<000000006acbc81c>] kvm_arch_vcpu_ioctl+0x308/0x580 [kvm]
    [<0000000089c69580>] kvm_vcpu_ioctl+0x19c/0xae0 [kvm]
    [<00000000902ae91e>] ksys_ioctl+0x184/0x1b0
    [<00000000f3e68bd7>] sys_ioctl+0x48/0xb0
    [<0000000001b2c127>] system_call_exception+0x124/0x1f0
    [<00000000d2b2ee40>] system_call_common+0xe8/0x214

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200612043303.84894-1-aik@ozlabs.ru
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/sysdev/xive/native.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index 50e1a8e02497d..3fd086533dcfc 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -18,6 +18,7 @@
 #include <linux/delay.h>
 #include <linux/cpumask.h>
 #include <linux/mm.h>
+#include <linux/kmemleak.h>
 
 #include <asm/prom.h>
 #include <asm/io.h>
@@ -646,6 +647,7 @@ static bool xive_native_provision_pages(void)
 			pr_err("Failed to allocate provisioning page\n");
 			return false;
 		}
+		kmemleak_ignore(p);
 		opal_xive_donate_page(chip, __pa(p));
 	}
 	return true;
-- 
2.25.1


^ permalink raw reply related

* [PATCH AUTOSEL 5.4 25/48] selftests/powerpc: Purge extra count_pmc() calls of ebb selftests
From: Sasha Levin @ 2020-08-21 16:16 UTC (permalink / raw)
  To: linux-kernel, stable
  Cc: Sachin Sant, Sasha Levin, Desnes A. Nunes do Rosario,
	linux-kselftest, linuxppc-dev
In-Reply-To: <20200821161704.348164-1-sashal@kernel.org>

From: "Desnes A. Nunes do Rosario" <desnesn@linux.ibm.com>

[ Upstream commit 3337bf41e0dd70b4064cdf60acdfcdc2d050066c ]

An extra count on ebb_state.stats.pmc_count[PMC_INDEX(pmc)] is being per-
formed when count_pmc() is used to reset PMCs on a few selftests. This
extra pmc_count can occasionally invalidate results, such as the ones from
cycles_test shown hereafter. The ebb_check_count() failed with an above
the upper limit error due to the extra value on ebb_state.stats.pmc_count.

Furthermore, this extra count is also indicated by extra PMC1 trace_log on
the output of the cycle test (as well as on pmc56_overflow_test):

==========
   ...
   [21]: counter = 8
   [22]: register SPRN_MMCR0 = 0x0000000080000080
   [23]: register SPRN_PMC1  = 0x0000000080000004
   [24]: counter = 9
   [25]: register SPRN_MMCR0 = 0x0000000080000080
   [26]: register SPRN_PMC1  = 0x0000000080000004
   [27]: counter = 10
   [28]: register SPRN_MMCR0 = 0x0000000080000080
   [29]: register SPRN_PMC1  = 0x0000000080000004
>> [30]: register SPRN_PMC1  = 0x000000004000051e
PMC1 count (0x280000546) above upper limit 0x2800003e8 (+0x15e)
[FAIL] Test FAILED on line 52
failure: cycles
==========

Signed-off-by: Desnes A. Nunes do Rosario <desnesn@linux.ibm.com>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200626164737.21943-1-desnesn@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c      | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c    | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/ebb.c              | 2 --
 .../selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c  | 2 --
 .../selftests/powerpc/pmu/ebb/lost_exception_test.c        | 1 -
 .../testing/selftests/powerpc/pmu/ebb/multi_counter_test.c | 7 -------
 .../selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c       | 2 --
 .../testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c | 2 --
 .../selftests/powerpc/pmu/ebb/pmc56_overflow_test.c        | 2 --
 11 files changed, 26 deletions(-)

diff --git a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
index a2d7b0e3dca97..a26ac122c759f 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
@@ -91,8 +91,6 @@ int back_to_back_ebbs(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
index bc893813483ee..bb9f587fa76e8 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
@@ -42,8 +42,6 @@ int cycles(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
index dcd351d203289..9ae795ce314e6 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
@@ -99,8 +99,6 @@ int cycles_with_freeze(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	printf("EBBs while frozen %d\n", ebbs_while_frozen);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
index 94c99c12c0f23..4b45a2e70f62b 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
@@ -71,8 +71,6 @@ int cycles_with_mmcr2(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index dfbc5c3ad52d7..21537d6eb6b7d 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -396,8 +396,6 @@ int ebb_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
index ca2f7d729155b..b208bf6ad58d3 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
@@ -38,8 +38,6 @@ static int victim_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	FAIL_IF(ebb_state.stats.ebb_count == 0);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
index ac3e6e182614a..ba2681a12cc7b 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
@@ -75,7 +75,6 @@ static int test_body(void)
 	ebb_freeze_pmcs();
 	ebb_global_disable();
 
-	count_pmc(4, sample_period);
 	mtspr(SPRN_PMC4, 0xdead);
 
 	dump_summary_ebb_state();
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
index b8242e9d97d2d..791d37ba327b5 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
@@ -70,13 +70,6 @@ int multi_counter(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-	count_pmc(2, sample_period);
-	count_pmc(3, sample_period);
-	count_pmc(4, sample_period);
-	count_pmc(5, sample_period);
-	count_pmc(6, sample_period);
-
 	dump_ebb_state();
 
 	for (i = 0; i < 6; i++)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
index a05c0e18ded63..9b0f70d597020 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
@@ -61,8 +61,6 @@ static int cycles_child(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_summary_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
index 153ebc92234fd..2904c741e04e5 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
@@ -82,8 +82,6 @@ static int test_body(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	if (mmcr0_mismatch)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index eadad75ed7e6f..b29f8ba22d1e6 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -76,8 +76,6 @@ int pmc56_overflow(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(2, sample_period);
-
 	dump_ebb_state();
 
 	printf("PMC5/6 overflow %d\n", pmc56_overflowed);
-- 
2.25.1


^ permalink raw reply related

* [PATCH AUTOSEL 4.19 07/38] powerpc/xive: Ignore kmemleak false positives
From: Sasha Levin @ 2020-08-21 16:17 UTC (permalink / raw)
  To: linux-kernel, stable; +Cc: Alexey Kardashevskiy, linuxppc-dev, Sasha Levin
In-Reply-To: <20200821161807.348600-1-sashal@kernel.org>

From: Alexey Kardashevskiy <aik@ozlabs.ru>

[ Upstream commit f0993c839e95dd6c7f054a1015e693c87e33e4fb ]

xive_native_provision_pages() allocates memory and passes the pointer to
OPAL so kmemleak cannot find the pointer usage in the kernel memory and
produces a false positive report (below) (even if the kernel did scan
OPAL memory, it is unable to deal with __pa() addresses anyway).

This silences the warning.

unreferenced object 0xc000200350c40000 (size 65536):
  comm "qemu-system-ppc", pid 2725, jiffies 4294946414 (age 70776.530s)
  hex dump (first 32 bytes):
    02 00 00 00 50 00 00 00 00 00 00 00 00 00 00 00  ....P...........
    01 00 08 07 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<0000000081ff046c>] xive_native_alloc_vp_block+0x120/0x250
    [<00000000d555d524>] kvmppc_xive_compute_vp_id+0x248/0x350 [kvm]
    [<00000000d69b9c9f>] kvmppc_xive_connect_vcpu+0xc0/0x520 [kvm]
    [<000000006acbc81c>] kvm_arch_vcpu_ioctl+0x308/0x580 [kvm]
    [<0000000089c69580>] kvm_vcpu_ioctl+0x19c/0xae0 [kvm]
    [<00000000902ae91e>] ksys_ioctl+0x184/0x1b0
    [<00000000f3e68bd7>] sys_ioctl+0x48/0xb0
    [<0000000001b2c127>] system_call_exception+0x124/0x1f0
    [<00000000d2b2ee40>] system_call_common+0xe8/0x214

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200612043303.84894-1-aik@ozlabs.ru
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/sysdev/xive/native.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index cb1f51ad48e40..411f785cdfb51 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -22,6 +22,7 @@
 #include <linux/delay.h>
 #include <linux/cpumask.h>
 #include <linux/mm.h>
+#include <linux/kmemleak.h>
 
 #include <asm/prom.h>
 #include <asm/io.h>
@@ -627,6 +628,7 @@ static bool xive_native_provision_pages(void)
 			pr_err("Failed to allocate provisioning page\n");
 			return false;
 		}
+		kmemleak_ignore(p);
 		opal_xive_donate_page(chip, __pa(p));
 	}
 	return true;
-- 
2.25.1


^ permalink raw reply related

* [PATCH AUTOSEL 4.19 20/38] selftests/powerpc: Purge extra count_pmc() calls of ebb selftests
From: Sasha Levin @ 2020-08-21 16:17 UTC (permalink / raw)
  To: linux-kernel, stable
  Cc: Sachin Sant, Sasha Levin, Desnes A. Nunes do Rosario,
	linux-kselftest, linuxppc-dev
In-Reply-To: <20200821161807.348600-1-sashal@kernel.org>

From: "Desnes A. Nunes do Rosario" <desnesn@linux.ibm.com>

[ Upstream commit 3337bf41e0dd70b4064cdf60acdfcdc2d050066c ]

An extra count on ebb_state.stats.pmc_count[PMC_INDEX(pmc)] is being per-
formed when count_pmc() is used to reset PMCs on a few selftests. This
extra pmc_count can occasionally invalidate results, such as the ones from
cycles_test shown hereafter. The ebb_check_count() failed with an above
the upper limit error due to the extra value on ebb_state.stats.pmc_count.

Furthermore, this extra count is also indicated by extra PMC1 trace_log on
the output of the cycle test (as well as on pmc56_overflow_test):

==========
   ...
   [21]: counter = 8
   [22]: register SPRN_MMCR0 = 0x0000000080000080
   [23]: register SPRN_PMC1  = 0x0000000080000004
   [24]: counter = 9
   [25]: register SPRN_MMCR0 = 0x0000000080000080
   [26]: register SPRN_PMC1  = 0x0000000080000004
   [27]: counter = 10
   [28]: register SPRN_MMCR0 = 0x0000000080000080
   [29]: register SPRN_PMC1  = 0x0000000080000004
>> [30]: register SPRN_PMC1  = 0x000000004000051e
PMC1 count (0x280000546) above upper limit 0x2800003e8 (+0x15e)
[FAIL] Test FAILED on line 52
failure: cycles
==========

Signed-off-by: Desnes A. Nunes do Rosario <desnesn@linux.ibm.com>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200626164737.21943-1-desnesn@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c      | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c    | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/ebb.c              | 2 --
 .../selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c  | 2 --
 .../selftests/powerpc/pmu/ebb/lost_exception_test.c        | 1 -
 .../testing/selftests/powerpc/pmu/ebb/multi_counter_test.c | 7 -------
 .../selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c       | 2 --
 .../testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c | 2 --
 .../selftests/powerpc/pmu/ebb/pmc56_overflow_test.c        | 2 --
 11 files changed, 26 deletions(-)

diff --git a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
index 94110b1dcd3d8..031baa43646fb 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
@@ -91,8 +91,6 @@ int back_to_back_ebbs(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
index 7c57a8d79535d..361e0be9df9ae 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
@@ -42,8 +42,6 @@ int cycles(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
index ecf5ee3283a3e..fe7d0dc2a1a26 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
@@ -99,8 +99,6 @@ int cycles_with_freeze(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	printf("EBBs while frozen %d\n", ebbs_while_frozen);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
index c0faba520b35c..b9b30f974b5ea 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
@@ -71,8 +71,6 @@ int cycles_with_mmcr2(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index 46681fec549b8..2694ae161a84a 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -396,8 +396,6 @@ int ebb_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
index a991d2ea8d0a1..174e4f4dae6c0 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
@@ -38,8 +38,6 @@ static int victim_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	FAIL_IF(ebb_state.stats.ebb_count == 0);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
index 2ed7ad33f7a3b..dddb95938304e 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
@@ -75,7 +75,6 @@ static int test_body(void)
 	ebb_freeze_pmcs();
 	ebb_global_disable();
 
-	count_pmc(4, sample_period);
 	mtspr(SPRN_PMC4, 0xdead);
 
 	dump_summary_ebb_state();
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
index 6ff8c8ff27d66..035c02273cd49 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
@@ -70,13 +70,6 @@ int multi_counter(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-	count_pmc(2, sample_period);
-	count_pmc(3, sample_period);
-	count_pmc(4, sample_period);
-	count_pmc(5, sample_period);
-	count_pmc(6, sample_period);
-
 	dump_ebb_state();
 
 	for (i = 0; i < 6; i++)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
index 037cb6154f360..3e9d4ac965c85 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
@@ -61,8 +61,6 @@ static int cycles_child(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_summary_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
index c5fa64790c22e..d90891fe96a32 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
@@ -82,8 +82,6 @@ static int test_body(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	if (mmcr0_mismatch)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index 30e1ac62e8cb4..8ca92b9ee5b01 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -76,8 +76,6 @@ int pmc56_overflow(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(2, sample_period);
-
 	dump_ebb_state();
 
 	printf("PMC5/6 overflow %d\n", pmc56_overflowed);
-- 
2.25.1


^ permalink raw reply related

* [PATCH AUTOSEL 4.14 05/30] powerpc/xive: Ignore kmemleak false positives
From: Sasha Levin @ 2020-08-21 16:18 UTC (permalink / raw)
  To: linux-kernel, stable; +Cc: Alexey Kardashevskiy, linuxppc-dev, Sasha Levin
In-Reply-To: <20200821161857.348955-1-sashal@kernel.org>

From: Alexey Kardashevskiy <aik@ozlabs.ru>

[ Upstream commit f0993c839e95dd6c7f054a1015e693c87e33e4fb ]

xive_native_provision_pages() allocates memory and passes the pointer to
OPAL so kmemleak cannot find the pointer usage in the kernel memory and
produces a false positive report (below) (even if the kernel did scan
OPAL memory, it is unable to deal with __pa() addresses anyway).

This silences the warning.

unreferenced object 0xc000200350c40000 (size 65536):
  comm "qemu-system-ppc", pid 2725, jiffies 4294946414 (age 70776.530s)
  hex dump (first 32 bytes):
    02 00 00 00 50 00 00 00 00 00 00 00 00 00 00 00  ....P...........
    01 00 08 07 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace:
    [<0000000081ff046c>] xive_native_alloc_vp_block+0x120/0x250
    [<00000000d555d524>] kvmppc_xive_compute_vp_id+0x248/0x350 [kvm]
    [<00000000d69b9c9f>] kvmppc_xive_connect_vcpu+0xc0/0x520 [kvm]
    [<000000006acbc81c>] kvm_arch_vcpu_ioctl+0x308/0x580 [kvm]
    [<0000000089c69580>] kvm_vcpu_ioctl+0x19c/0xae0 [kvm]
    [<00000000902ae91e>] ksys_ioctl+0x184/0x1b0
    [<00000000f3e68bd7>] sys_ioctl+0x48/0xb0
    [<0000000001b2c127>] system_call_exception+0x124/0x1f0
    [<00000000d2b2ee40>] system_call_common+0xe8/0x214

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200612043303.84894-1-aik@ozlabs.ru
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/powerpc/sysdev/xive/native.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index 30cdcbfa1c04e..b0e96f4b728c1 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -22,6 +22,7 @@
 #include <linux/delay.h>
 #include <linux/cpumask.h>
 #include <linux/mm.h>
+#include <linux/kmemleak.h>
 
 #include <asm/prom.h>
 #include <asm/io.h>
@@ -630,6 +631,7 @@ static bool xive_native_provision_pages(void)
 			pr_err("Failed to allocate provisioning page\n");
 			return false;
 		}
+		kmemleak_ignore(p);
 		opal_xive_donate_page(chip, __pa(p));
 	}
 	return true;
-- 
2.25.1


^ permalink raw reply related

* [PATCH AUTOSEL 4.14 17/30] selftests/powerpc: Purge extra count_pmc() calls of ebb selftests
From: Sasha Levin @ 2020-08-21 16:18 UTC (permalink / raw)
  To: linux-kernel, stable
  Cc: Sachin Sant, Sasha Levin, Desnes A. Nunes do Rosario,
	linux-kselftest, linuxppc-dev
In-Reply-To: <20200821161857.348955-1-sashal@kernel.org>

From: "Desnes A. Nunes do Rosario" <desnesn@linux.ibm.com>

[ Upstream commit 3337bf41e0dd70b4064cdf60acdfcdc2d050066c ]

An extra count on ebb_state.stats.pmc_count[PMC_INDEX(pmc)] is being per-
formed when count_pmc() is used to reset PMCs on a few selftests. This
extra pmc_count can occasionally invalidate results, such as the ones from
cycles_test shown hereafter. The ebb_check_count() failed with an above
the upper limit error due to the extra value on ebb_state.stats.pmc_count.

Furthermore, this extra count is also indicated by extra PMC1 trace_log on
the output of the cycle test (as well as on pmc56_overflow_test):

==========
   ...
   [21]: counter = 8
   [22]: register SPRN_MMCR0 = 0x0000000080000080
   [23]: register SPRN_PMC1  = 0x0000000080000004
   [24]: counter = 9
   [25]: register SPRN_MMCR0 = 0x0000000080000080
   [26]: register SPRN_PMC1  = 0x0000000080000004
   [27]: counter = 10
   [28]: register SPRN_MMCR0 = 0x0000000080000080
   [29]: register SPRN_PMC1  = 0x0000000080000004
>> [30]: register SPRN_PMC1  = 0x000000004000051e
PMC1 count (0x280000546) above upper limit 0x2800003e8 (+0x15e)
[FAIL] Test FAILED on line 52
failure: cycles
==========

Signed-off-by: Desnes A. Nunes do Rosario <desnesn@linux.ibm.com>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200626164737.21943-1-desnesn@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c      | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c    | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/ebb.c              | 2 --
 .../selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c  | 2 --
 .../selftests/powerpc/pmu/ebb/lost_exception_test.c        | 1 -
 .../testing/selftests/powerpc/pmu/ebb/multi_counter_test.c | 7 -------
 .../selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c       | 2 --
 .../testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c | 2 --
 .../selftests/powerpc/pmu/ebb/pmc56_overflow_test.c        | 2 --
 11 files changed, 26 deletions(-)

diff --git a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
index 94110b1dcd3d8..031baa43646fb 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
@@ -91,8 +91,6 @@ int back_to_back_ebbs(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
index 7c57a8d79535d..361e0be9df9ae 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
@@ -42,8 +42,6 @@ int cycles(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
index ecf5ee3283a3e..fe7d0dc2a1a26 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
@@ -99,8 +99,6 @@ int cycles_with_freeze(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	printf("EBBs while frozen %d\n", ebbs_while_frozen);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
index c0faba520b35c..b9b30f974b5ea 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
@@ -71,8 +71,6 @@ int cycles_with_mmcr2(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index 46681fec549b8..2694ae161a84a 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -396,8 +396,6 @@ int ebb_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
index a991d2ea8d0a1..174e4f4dae6c0 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
@@ -38,8 +38,6 @@ static int victim_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	FAIL_IF(ebb_state.stats.ebb_count == 0);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
index eb8acb78bc6c1..531083accfcad 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
@@ -75,7 +75,6 @@ static int test_body(void)
 	ebb_freeze_pmcs();
 	ebb_global_disable();
 
-	count_pmc(4, sample_period);
 	mtspr(SPRN_PMC4, 0xdead);
 
 	dump_summary_ebb_state();
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
index 6ff8c8ff27d66..035c02273cd49 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
@@ -70,13 +70,6 @@ int multi_counter(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-	count_pmc(2, sample_period);
-	count_pmc(3, sample_period);
-	count_pmc(4, sample_period);
-	count_pmc(5, sample_period);
-	count_pmc(6, sample_period);
-
 	dump_ebb_state();
 
 	for (i = 0; i < 6; i++)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
index 037cb6154f360..3e9d4ac965c85 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
@@ -61,8 +61,6 @@ static int cycles_child(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_summary_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
index c5fa64790c22e..d90891fe96a32 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
@@ -82,8 +82,6 @@ static int test_body(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	if (mmcr0_mismatch)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index 30e1ac62e8cb4..8ca92b9ee5b01 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -76,8 +76,6 @@ int pmc56_overflow(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(2, sample_period);
-
 	dump_ebb_state();
 
 	printf("PMC5/6 overflow %d\n", pmc56_overflowed);
-- 
2.25.1


^ permalink raw reply related

* [PATCH AUTOSEL 4.9 14/26] selftests/powerpc: Purge extra count_pmc() calls of ebb selftests
From: Sasha Levin @ 2020-08-21 16:19 UTC (permalink / raw)
  To: linux-kernel, stable
  Cc: Sachin Sant, Sasha Levin, Desnes A. Nunes do Rosario,
	linux-kselftest, linuxppc-dev
In-Reply-To: <20200821161938.349246-1-sashal@kernel.org>

From: "Desnes A. Nunes do Rosario" <desnesn@linux.ibm.com>

[ Upstream commit 3337bf41e0dd70b4064cdf60acdfcdc2d050066c ]

An extra count on ebb_state.stats.pmc_count[PMC_INDEX(pmc)] is being per-
formed when count_pmc() is used to reset PMCs on a few selftests. This
extra pmc_count can occasionally invalidate results, such as the ones from
cycles_test shown hereafter. The ebb_check_count() failed with an above
the upper limit error due to the extra value on ebb_state.stats.pmc_count.

Furthermore, this extra count is also indicated by extra PMC1 trace_log on
the output of the cycle test (as well as on pmc56_overflow_test):

==========
   ...
   [21]: counter = 8
   [22]: register SPRN_MMCR0 = 0x0000000080000080
   [23]: register SPRN_PMC1  = 0x0000000080000004
   [24]: counter = 9
   [25]: register SPRN_MMCR0 = 0x0000000080000080
   [26]: register SPRN_PMC1  = 0x0000000080000004
   [27]: counter = 10
   [28]: register SPRN_MMCR0 = 0x0000000080000080
   [29]: register SPRN_PMC1  = 0x0000000080000004
>> [30]: register SPRN_PMC1  = 0x000000004000051e
PMC1 count (0x280000546) above upper limit 0x2800003e8 (+0x15e)
[FAIL] Test FAILED on line 52
failure: cycles
==========

Signed-off-by: Desnes A. Nunes do Rosario <desnesn@linux.ibm.com>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200626164737.21943-1-desnesn@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c      | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c    | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/ebb.c              | 2 --
 .../selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c  | 2 --
 .../selftests/powerpc/pmu/ebb/lost_exception_test.c        | 1 -
 .../testing/selftests/powerpc/pmu/ebb/multi_counter_test.c | 7 -------
 .../selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c       | 2 --
 .../testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c | 2 --
 .../selftests/powerpc/pmu/ebb/pmc56_overflow_test.c        | 2 --
 11 files changed, 26 deletions(-)

diff --git a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
index 94110b1dcd3d8..031baa43646fb 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
@@ -91,8 +91,6 @@ int back_to_back_ebbs(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
index 7c57a8d79535d..361e0be9df9ae 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
@@ -42,8 +42,6 @@ int cycles(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
index ecf5ee3283a3e..fe7d0dc2a1a26 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
@@ -99,8 +99,6 @@ int cycles_with_freeze(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	printf("EBBs while frozen %d\n", ebbs_while_frozen);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
index c0faba520b35c..b9b30f974b5ea 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
@@ -71,8 +71,6 @@ int cycles_with_mmcr2(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index 46681fec549b8..2694ae161a84a 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -396,8 +396,6 @@ int ebb_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
index a991d2ea8d0a1..174e4f4dae6c0 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
@@ -38,8 +38,6 @@ static int victim_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	FAIL_IF(ebb_state.stats.ebb_count == 0);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
index eb8acb78bc6c1..531083accfcad 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
@@ -75,7 +75,6 @@ static int test_body(void)
 	ebb_freeze_pmcs();
 	ebb_global_disable();
 
-	count_pmc(4, sample_period);
 	mtspr(SPRN_PMC4, 0xdead);
 
 	dump_summary_ebb_state();
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
index 6ff8c8ff27d66..035c02273cd49 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
@@ -70,13 +70,6 @@ int multi_counter(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-	count_pmc(2, sample_period);
-	count_pmc(3, sample_period);
-	count_pmc(4, sample_period);
-	count_pmc(5, sample_period);
-	count_pmc(6, sample_period);
-
 	dump_ebb_state();
 
 	for (i = 0; i < 6; i++)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
index 037cb6154f360..3e9d4ac965c85 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
@@ -61,8 +61,6 @@ static int cycles_child(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_summary_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
index c5fa64790c22e..d90891fe96a32 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
@@ -82,8 +82,6 @@ static int test_body(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	if (mmcr0_mismatch)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index 30e1ac62e8cb4..8ca92b9ee5b01 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -76,8 +76,6 @@ int pmc56_overflow(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(2, sample_period);
-
 	dump_ebb_state();
 
 	printf("PMC5/6 overflow %d\n", pmc56_overflowed);
-- 
2.25.1


^ permalink raw reply related

* [PATCH AUTOSEL 4.4 12/22] selftests/powerpc: Purge extra count_pmc() calls of ebb selftests
From: Sasha Levin @ 2020-08-21 16:20 UTC (permalink / raw)
  To: linux-kernel, stable
  Cc: Sachin Sant, Sasha Levin, Desnes A. Nunes do Rosario,
	linux-kselftest, linuxppc-dev
In-Reply-To: <20200821162014.349506-1-sashal@kernel.org>

From: "Desnes A. Nunes do Rosario" <desnesn@linux.ibm.com>

[ Upstream commit 3337bf41e0dd70b4064cdf60acdfcdc2d050066c ]

An extra count on ebb_state.stats.pmc_count[PMC_INDEX(pmc)] is being per-
formed when count_pmc() is used to reset PMCs on a few selftests. This
extra pmc_count can occasionally invalidate results, such as the ones from
cycles_test shown hereafter. The ebb_check_count() failed with an above
the upper limit error due to the extra value on ebb_state.stats.pmc_count.

Furthermore, this extra count is also indicated by extra PMC1 trace_log on
the output of the cycle test (as well as on pmc56_overflow_test):

==========
   ...
   [21]: counter = 8
   [22]: register SPRN_MMCR0 = 0x0000000080000080
   [23]: register SPRN_PMC1  = 0x0000000080000004
   [24]: counter = 9
   [25]: register SPRN_MMCR0 = 0x0000000080000080
   [26]: register SPRN_PMC1  = 0x0000000080000004
   [27]: counter = 10
   [28]: register SPRN_MMCR0 = 0x0000000080000080
   [29]: register SPRN_PMC1  = 0x0000000080000004
>> [30]: register SPRN_PMC1  = 0x000000004000051e
PMC1 count (0x280000546) above upper limit 0x2800003e8 (+0x15e)
[FAIL] Test FAILED on line 52
failure: cycles
==========

Signed-off-by: Desnes A. Nunes do Rosario <desnesn@linux.ibm.com>
Tested-by: Sachin Sant <sachinp@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200626164737.21943-1-desnesn@linux.ibm.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c      | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c    | 2 --
 .../selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c     | 2 --
 tools/testing/selftests/powerpc/pmu/ebb/ebb.c              | 2 --
 .../selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c  | 2 --
 .../selftests/powerpc/pmu/ebb/lost_exception_test.c        | 1 -
 .../testing/selftests/powerpc/pmu/ebb/multi_counter_test.c | 7 -------
 .../selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c       | 2 --
 .../testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c | 2 --
 .../selftests/powerpc/pmu/ebb/pmc56_overflow_test.c        | 2 --
 11 files changed, 26 deletions(-)

diff --git a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
index 94110b1dcd3d8..031baa43646fb 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/back_to_back_ebbs_test.c
@@ -91,8 +91,6 @@ int back_to_back_ebbs(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
index 7c57a8d79535d..361e0be9df9ae 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_test.c
@@ -42,8 +42,6 @@ int cycles(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
index ecf5ee3283a3e..fe7d0dc2a1a26 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_freeze_test.c
@@ -99,8 +99,6 @@ int cycles_with_freeze(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	printf("EBBs while frozen %d\n", ebbs_while_frozen);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
index c0faba520b35c..b9b30f974b5ea 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/cycles_with_mmcr2_test.c
@@ -71,8 +71,6 @@ int cycles_with_mmcr2(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
index 9729d9f902187..4154498bc5dc5 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb.c
@@ -398,8 +398,6 @@ int ebb_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
index a991d2ea8d0a1..174e4f4dae6c0 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/ebb_on_willing_child_test.c
@@ -38,8 +38,6 @@ static int victim_child(union pipe read_pipe, union pipe write_pipe)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	FAIL_IF(ebb_state.stats.ebb_count == 0);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
index eb8acb78bc6c1..531083accfcad 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/lost_exception_test.c
@@ -75,7 +75,6 @@ static int test_body(void)
 	ebb_freeze_pmcs();
 	ebb_global_disable();
 
-	count_pmc(4, sample_period);
 	mtspr(SPRN_PMC4, 0xdead);
 
 	dump_summary_ebb_state();
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
index 6ff8c8ff27d66..035c02273cd49 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_counter_test.c
@@ -70,13 +70,6 @@ int multi_counter(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-	count_pmc(2, sample_period);
-	count_pmc(3, sample_period);
-	count_pmc(4, sample_period);
-	count_pmc(5, sample_period);
-	count_pmc(6, sample_period);
-
 	dump_ebb_state();
 
 	for (i = 0; i < 6; i++)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
index 037cb6154f360..3e9d4ac965c85 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/multi_ebb_procs_test.c
@@ -61,8 +61,6 @@ static int cycles_child(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_summary_ebb_state();
 
 	event_close(&event);
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
index c5fa64790c22e..d90891fe96a32 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmae_handling_test.c
@@ -82,8 +82,6 @@ static int test_body(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(1, sample_period);
-
 	dump_ebb_state();
 
 	if (mmcr0_mismatch)
diff --git a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
index 30e1ac62e8cb4..8ca92b9ee5b01 100644
--- a/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
+++ b/tools/testing/selftests/powerpc/pmu/ebb/pmc56_overflow_test.c
@@ -76,8 +76,6 @@ int pmc56_overflow(void)
 	ebb_global_disable();
 	ebb_freeze_pmcs();
 
-	count_pmc(2, sample_period);
-
 	dump_ebb_state();
 
 	printf("PMC5/6 overflow %d\n", pmc56_overflowed);
-- 
2.25.1


^ permalink raw reply related

* Re: [PATCH 2/2] powerpc/64s: Disallow PROT_SAO in LPARs by default
From: Shawn Anastasio @ 2020-08-21 18:55 UTC (permalink / raw)
  To: Nicholas Piggin, linuxppc-dev
In-Reply-To: <1598006106.5gm5wgd52s.astroid@bobo.none>

On 8/21/20 5:37 AM, Nicholas Piggin wrote:> I think this should be okay. 
Could you also update the selftest to skip
> if we have PPC_FEATURE2_ARCH_3_1 set?

Sure. I'll send out a v2 shortly with another patch for this.

> Thanks,
> Nick

Thanks,
Shawn

^ permalink raw reply

* [PATCH v2 0/3] Reintroduce PROT_SAO
From: Shawn Anastasio @ 2020-08-21 18:55 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: npiggin

Changes in v2:
    - Update prot_sao selftest to skip ISA 3.1

This set re-introduces the PROT_SAO prot flag removed in
Commit 5c9fa16e8abd ("powerpc/64s: Remove PROT_SAO support").

To address concerns regarding live migration of guests using SAO
to P10 hosts without SAO support, the flag is disabled by default
in LPARs. A new config option, PPC_PROT_SAO_LPAR was added to
allow users to explicitly enable it if they will not be running
in an environment where this is a conern.

Shawn Anastasio (3):
  Revert "powerpc/64s: Remove PROT_SAO support"
  powerpc/64s: Disallow PROT_SAO in LPARs by default
  selftests/powerpc: Update PROT_SAO test to skip ISA 3.1

 arch/powerpc/Kconfig                          | 12 ++++++
 arch/powerpc/include/asm/book3s/64/pgtable.h  |  8 ++--
 arch/powerpc/include/asm/cputable.h           | 10 ++---
 arch/powerpc/include/asm/mman.h               | 31 +++++++++++--
 arch/powerpc/include/asm/nohash/64/pgtable.h  |  2 +
 arch/powerpc/include/uapi/asm/mman.h          |  2 +-
 arch/powerpc/kernel/dt_cpu_ftrs.c             |  2 +-
 arch/powerpc/mm/book3s64/hash_utils.c         |  2 +
 include/linux/mm.h                            |  2 +
 include/trace/events/mmflags.h                |  2 +
 mm/ksm.c                                      |  4 ++
 tools/testing/selftests/powerpc/mm/.gitignore |  1 +
 tools/testing/selftests/powerpc/mm/Makefile   |  4 +-
 tools/testing/selftests/powerpc/mm/prot_sao.c | 43 +++++++++++++++++++
 14 files changed, 108 insertions(+), 17 deletions(-)
 create mode 100644 tools/testing/selftests/powerpc/mm/prot_sao.c

-- 
2.28.0


^ permalink raw reply

* [PATCH v2 2/3] powerpc/64s: Disallow PROT_SAO in LPARs by default
From: Shawn Anastasio @ 2020-08-21 18:55 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20200821185558.35561-1-shawn@anastas.io>

Since migration of guests using SAO to ISA 3.1 hosts may cause issues,
disable PROT_SAO in LPARs by default and introduce a new Kconfig option
PPC_PROT_SAO_LPAR to allow users to enable it if desired.

Signed-off-by: Shawn Anastasio <shawn@anastas.io>
---
 arch/powerpc/Kconfig            | 12 ++++++++++++
 arch/powerpc/include/asm/mman.h |  9 +++++++--
 2 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 1f48bbfb3ce9..65bed1fdeaad 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -860,6 +860,18 @@ config PPC_SUBPAGE_PROT
 
 	  If unsure, say N here.
 
+config PPC_PROT_SAO_LPAR
+	bool "Support PROT_SAO mappings in LPARs"
+	depends on PPC_BOOK3S_64
+	help
+	  This option adds support for PROT_SAO mappings from userspace
+	  inside LPARs on supported CPUs.
+
+	  This may cause issues when performing guest migration from
+	  a CPU that supports SAO to one that does not.
+
+	  If unsure, say N here.
+
 config PPC_COPRO_BASE
 	bool
 
diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h
index 4ba303ea27f5..7cb6d18f5cd6 100644
--- a/arch/powerpc/include/asm/mman.h
+++ b/arch/powerpc/include/asm/mman.h
@@ -40,8 +40,13 @@ static inline bool arch_validate_prot(unsigned long prot, unsigned long addr)
 {
 	if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO))
 		return false;
-	if ((prot & PROT_SAO) && !cpu_has_feature(CPU_FTR_SAO))
-		return false;
+	if (prot & PROT_SAO) {
+		if (!cpu_has_feature(CPU_FTR_SAO))
+			return false;
+		if (firmware_has_feature(FW_FEATURE_LPAR) &&
+		    !IS_ENABLED(CONFIG_PPC_PROT_SAO_LPAR))
+			return false;
+	}
 	return true;
 }
 #define arch_validate_prot arch_validate_prot
-- 
2.28.0


^ permalink raw reply related

* [PATCH v2 3/3] selftests/powerpc: Update PROT_SAO test to skip ISA 3.1
From: Shawn Anastasio @ 2020-08-21 18:55 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20200821185558.35561-1-shawn@anastas.io>

Since SAO support was removed from ISA 3.1, skip the
prot_sao test if PPC_FEATURE2_ARCH_3_1 is set.

Signed-off-by: Shawn Anastasio <shawn@anastas.io>
---
 tools/testing/selftests/powerpc/mm/prot_sao.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c
index e2eed65b7735..e0cf8ebbf8cd 100644
--- a/tools/testing/selftests/powerpc/mm/prot_sao.c
+++ b/tools/testing/selftests/powerpc/mm/prot_sao.c
@@ -18,8 +18,9 @@ int test_prot_sao(void)
 {
 	char *p;
 
-	/* 2.06 or later should support SAO */
-	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
+	/* SAO was introduced in 2.06 and removed in 3.1 */
+	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06) ||
+		have_hwcap2(PPC_FEATURE2_ARCH_3_1));
 
 	/*
 	 * Ensure we can ask for PROT_SAO.
-- 
2.28.0


^ permalink raw reply related

* [PATCH v2 1/3] Revert "powerpc/64s: Remove PROT_SAO support"
From: Shawn Anastasio @ 2020-08-21 18:55 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: npiggin
In-Reply-To: <20200821185558.35561-1-shawn@anastas.io>

This reverts commit 5c9fa16e8abd342ce04dc830c1ebb2a03abf6c05.

Since PROT_SAO can still be useful for certain classes of software,
reintroduce it. Concerns about guest migration for LPARs using SAO
will be addressed next.

Signed-off-by: Shawn Anastasio <shawn@anastas.io>
---
 arch/powerpc/include/asm/book3s/64/pgtable.h  |  8 ++--
 arch/powerpc/include/asm/cputable.h           | 10 ++---
 arch/powerpc/include/asm/mman.h               | 26 ++++++++++--
 arch/powerpc/include/asm/nohash/64/pgtable.h  |  2 +
 arch/powerpc/include/uapi/asm/mman.h          |  2 +-
 arch/powerpc/kernel/dt_cpu_ftrs.c             |  2 +-
 arch/powerpc/mm/book3s64/hash_utils.c         |  2 +
 include/linux/mm.h                            |  2 +
 include/trace/events/mmflags.h                |  2 +
 mm/ksm.c                                      |  4 ++
 tools/testing/selftests/powerpc/mm/.gitignore |  1 +
 tools/testing/selftests/powerpc/mm/Makefile   |  4 +-
 tools/testing/selftests/powerpc/mm/prot_sao.c | 42 +++++++++++++++++++
 13 files changed, 90 insertions(+), 17 deletions(-)
 create mode 100644 tools/testing/selftests/powerpc/mm/prot_sao.c

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 6de56c3b33c4..495fc0ccb453 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -20,13 +20,9 @@
 #define _PAGE_RW		(_PAGE_READ | _PAGE_WRITE)
 #define _PAGE_RWX		(_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
 #define _PAGE_PRIVILEGED	0x00008 /* kernel access only */
-
-#define _PAGE_CACHE_CTL		0x00030 /* Bits for the folowing cache modes */
-			/*	No bits set is normal cacheable memory */
-			/*	0x00010 unused, is SAO bit on radix POWER9 */
+#define _PAGE_SAO		0x00010 /* Strong access order */
 #define _PAGE_NON_IDEMPOTENT	0x00020 /* non idempotent memory */
 #define _PAGE_TOLERANT		0x00030 /* tolerant memory, cache inhibited */
-
 #define _PAGE_DIRTY		0x00080 /* C: page changed */
 #define _PAGE_ACCESSED		0x00100 /* R: page referenced */
 /*
@@ -828,6 +824,8 @@ static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
 	return hash__set_pte_at(mm, addr, ptep, pte, percpu);
 }
 
+#define _PAGE_CACHE_CTL	(_PAGE_SAO | _PAGE_NON_IDEMPOTENT | _PAGE_TOLERANT)
+
 #define pgprot_noncached pgprot_noncached
 static inline pgprot_t pgprot_noncached(pgprot_t prot)
 {
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index fdddb822d564..f89205eff691 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -191,7 +191,7 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_SPURR			LONG_ASM_CONST(0x0000000001000000)
 #define CPU_FTR_DSCR			LONG_ASM_CONST(0x0000000002000000)
 #define CPU_FTR_VSX			LONG_ASM_CONST(0x0000000004000000)
-// Free					LONG_ASM_CONST(0x0000000008000000)
+#define CPU_FTR_SAO			LONG_ASM_CONST(0x0000000008000000)
 #define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0000000010000000)
 #define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0000000020000000)
 #define CPU_FTR_ASYM_SMT		LONG_ASM_CONST(0x0000000040000000)
@@ -436,7 +436,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | CPU_FTR_ASYM_SMT | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | \
 	    CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX )
@@ -445,7 +445,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
@@ -456,7 +456,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
@@ -474,7 +474,7 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
-	    CPU_FTR_DSCR | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
diff --git a/arch/powerpc/include/asm/mman.h b/arch/powerpc/include/asm/mman.h
index 7c07728af300..4ba303ea27f5 100644
--- a/arch/powerpc/include/asm/mman.h
+++ b/arch/powerpc/include/asm/mman.h
@@ -13,20 +13,38 @@
 #include <linux/pkeys.h>
 #include <asm/cpu_has_feature.h>
 
-#ifdef CONFIG_PPC_MEM_KEYS
 static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot,
 		unsigned long pkey)
 {
-	return pkey_to_vmflag_bits(pkey);
+#ifdef CONFIG_PPC_MEM_KEYS
+	return (((prot & PROT_SAO) ? VM_SAO : 0) | pkey_to_vmflag_bits(pkey));
+#else
+	return ((prot & PROT_SAO) ? VM_SAO : 0);
+#endif
 }
 #define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey)
 
 static inline pgprot_t arch_vm_get_page_prot(unsigned long vm_flags)
 {
-	return __pgprot(vmflag_to_pte_pkey_bits(vm_flags));
+#ifdef CONFIG_PPC_MEM_KEYS
+	return (vm_flags & VM_SAO) ?
+		__pgprot(_PAGE_SAO | vmflag_to_pte_pkey_bits(vm_flags)) :
+		__pgprot(0 | vmflag_to_pte_pkey_bits(vm_flags));
+#else
+	return (vm_flags & VM_SAO) ? __pgprot(_PAGE_SAO) : __pgprot(0);
+#endif
 }
 #define arch_vm_get_page_prot(vm_flags) arch_vm_get_page_prot(vm_flags)
-#endif
+
+static inline bool arch_validate_prot(unsigned long prot, unsigned long addr)
+{
+	if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM | PROT_SAO))
+		return false;
+	if ((prot & PROT_SAO) && !cpu_has_feature(CPU_FTR_SAO))
+		return false;
+	return true;
+}
+#define arch_validate_prot arch_validate_prot
 
 #endif /* CONFIG_PPC64 */
 #endif	/* _ASM_POWERPC_MMAN_H */
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index 59ee9fa4ae09..6cb8aa357191 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -82,6 +82,8 @@
  */
 #include <asm/nohash/pte-book3e.h>
 
+#define _PAGE_SAO	0
+
 #define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
 
 /*
diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h
index 3a700351feca..c0c737215b00 100644
--- a/arch/powerpc/include/uapi/asm/mman.h
+++ b/arch/powerpc/include/uapi/asm/mman.h
@@ -11,7 +11,7 @@
 #include <asm-generic/mman-common.h>
 
 
-#define PROT_SAO	0x10		/* Unsupported since v5.9 */
+#define PROT_SAO	0x10		/* Strong Access Ordering */
 
 #define MAP_RENAME      MAP_ANONYMOUS   /* In SunOS terminology */
 #define MAP_NORESERVE   0x40            /* don't reserve swap pages */
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 6f8c0c6b937a..231f92248140 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -657,7 +657,7 @@ static struct dt_cpu_feature_match __initdata
 	{"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
 	{"processor-utilization-of-resources-register", feat_enable_purr, 0},
 	{"no-execute", feat_enable, 0},
-	/* strong-access-ordering is unused */
+	{"strong-access-ordering", feat_enable, CPU_FTR_SAO},
 	{"cache-inhibited-large-page", feat_enable_large_ci, 0},
 	{"coprocessor-icswx", feat_enable, 0},
 	{"hypervisor-virtualization-interrupt", feat_enable_hvi, 0},
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 1da9dbba9217..c1ea93b368b6 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -232,6 +232,8 @@ unsigned long htab_convert_pte_flags(unsigned long pteflags)
 		rflags |= HPTE_R_I;
 	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_NON_IDEMPOTENT)
 		rflags |= (HPTE_R_I | HPTE_R_G);
+	else if ((pteflags & _PAGE_CACHE_CTL) == _PAGE_SAO)
+		rflags |= (HPTE_R_W | HPTE_R_I | HPTE_R_M);
 	else
 		/*
 		 * Add memory coherence if cache inhibited is not set
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 1983e08f5906..5abe6df4247e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -321,6 +321,8 @@ extern unsigned int kobjsize(const void *objp);
 
 #if defined(CONFIG_X86)
 # define VM_PAT		VM_ARCH_1	/* PAT reserves whole VMA at once (x86) */
+#elif defined(CONFIG_PPC)
+# define VM_SAO		VM_ARCH_1	/* Strong Access Ordering (powerpc) */
 #elif defined(CONFIG_PARISC)
 # define VM_GROWSUP	VM_ARCH_1
 #elif defined(CONFIG_IA64)
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 939092dbcb8b..5fb752034386 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -114,6 +114,8 @@ IF_HAVE_PG_IDLE(PG_idle,		"idle"		)
 
 #if defined(CONFIG_X86)
 #define __VM_ARCH_SPECIFIC_1 {VM_PAT,     "pat"           }
+#elif defined(CONFIG_PPC)
+#define __VM_ARCH_SPECIFIC_1 {VM_SAO,     "sao"           }
 #elif defined(CONFIG_PARISC) || defined(CONFIG_IA64)
 #define __VM_ARCH_SPECIFIC_1 {VM_GROWSUP,	"growsup"	}
 #elif !defined(CONFIG_MMU)
diff --git a/mm/ksm.c b/mm/ksm.c
index 0aa2247bddd7..90a625b02a1d 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2453,6 +2453,10 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		if (vma_is_dax(vma))
 			return 0;
 
+#ifdef VM_SAO
+		if (*vm_flags & VM_SAO)
+			return 0;
+#endif
 #ifdef VM_SPARC_ADI
 		if (*vm_flags & VM_SPARC_ADI)
 			return 0;
diff --git a/tools/testing/selftests/powerpc/mm/.gitignore b/tools/testing/selftests/powerpc/mm/.gitignore
index 91c775c23c66..aac4a59f9e28 100644
--- a/tools/testing/selftests/powerpc/mm/.gitignore
+++ b/tools/testing/selftests/powerpc/mm/.gitignore
@@ -2,6 +2,7 @@
 hugetlb_vs_thp_test
 subpage_prot
 tempfile
+prot_sao
 segv_errors
 wild_bctr
 large_vm_fork_separation
diff --git a/tools/testing/selftests/powerpc/mm/Makefile b/tools/testing/selftests/powerpc/mm/Makefile
index 250ce172e0da..defe488d6bf1 100644
--- a/tools/testing/selftests/powerpc/mm/Makefile
+++ b/tools/testing/selftests/powerpc/mm/Makefile
@@ -2,7 +2,7 @@
 noarg:
 	$(MAKE) -C ../
 
-TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot segv_errors wild_bctr \
+TEST_GEN_PROGS := hugetlb_vs_thp_test subpage_prot prot_sao segv_errors wild_bctr \
 		  large_vm_fork_separation bad_accesses pkey_exec_prot \
 		  pkey_siginfo stack_expansion_signal stack_expansion_ldst
 
@@ -14,6 +14,8 @@ include ../../lib.mk
 
 $(TEST_GEN_PROGS): ../harness.c ../utils.c
 
+$(OUTPUT)/prot_sao: ../utils.c
+
 $(OUTPUT)/wild_bctr: CFLAGS += -m64
 $(OUTPUT)/large_vm_fork_separation: CFLAGS += -m64
 $(OUTPUT)/bad_accesses: CFLAGS += -m64
diff --git a/tools/testing/selftests/powerpc/mm/prot_sao.c b/tools/testing/selftests/powerpc/mm/prot_sao.c
new file mode 100644
index 000000000000..e2eed65b7735
--- /dev/null
+++ b/tools/testing/selftests/powerpc/mm/prot_sao.c
@@ -0,0 +1,42 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2016, Michael Ellerman, IBM Corp.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+
+#include <asm/cputable.h>
+
+#include "utils.h"
+
+#define SIZE (64 * 1024)
+
+int test_prot_sao(void)
+{
+	char *p;
+
+	/* 2.06 or later should support SAO */
+	SKIP_IF(!have_hwcap(PPC_FEATURE_ARCH_2_06));
+
+	/*
+	 * Ensure we can ask for PROT_SAO.
+	 * We can't really verify that it does the right thing, but at least we
+	 * confirm the kernel will accept it.
+	 */
+	p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE | PROT_SAO,
+		 MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+	FAIL_IF(p == MAP_FAILED);
+
+	/* Write to the mapping, to at least cause a fault */
+	memset(p, 0xaa, SIZE);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(test_prot_sao, "prot-sao");
+}
-- 
2.28.0


^ permalink raw reply related

* Re: [PATCH v6 05/12] mm: HUGE_VMAP arch support cleanup
From: Andrew Morton @ 2020-08-21 20:14 UTC (permalink / raw)
  To: Nicholas Piggin
  Cc: linux-arch, H. Peter Anvin, Will Deacon, Catalin Marinas, x86,
	linux-kernel, Christoph Hellwig, linux-mm, Zefan Li,
	Borislav Petkov, Jonathan Cameron, Thomas Gleixner, linuxppc-dev,
	Ingo Molnar, linux-arm-kernel
In-Reply-To: <20200821151216.1005117-6-npiggin@gmail.com>

On Sat, 22 Aug 2020 01:12:09 +1000 Nicholas Piggin <npiggin@gmail.com> wrote:

> This changes the awkward approach where architectures provide init
> functions to determine which levels they can provide large mappings for,
> to one where the arch is queried for each call.
> 
> This removes code and indirection, and allows constant-folding of dead
> code for unsupported levels.
> 
> This also adds a prot argument to the arch query. This is unused
> currently but could help with some architectures (e.g., some powerpc
> processors can't map uncacheable memory with large pages).
> 
> --- a/arch/arm64/include/asm/vmalloc.h
> +++ b/arch/arm64/include/asm/vmalloc.h
> @@ -1,4 +1,12 @@
>  #ifndef _ASM_ARM64_VMALLOC_H
>  #define _ASM_ARM64_VMALLOC_H
>  
> +#include <asm/page.h>
> +
> +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
> +bool arch_vmap_p4d_supported(pgprot_t prot);
> +bool arch_vmap_pud_supported(pgprot_t prot);
> +bool arch_vmap_pmd_supported(pgprot_t prot);
> +#endif

Moving these out of generic code and into multiple arch headers is
unfortunate.  Can we leave them in include/linux/somewhere?  And remove
the ifdefs, if so inclined - they just move the build error from
link-time to compile-time, and such an error shouldn't occur!


^ permalink raw reply

page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox