From a83836dbc53e96f13fec248ecc201d18e1e3111d Mon Sep 17 00:00:00 2001
From: Libor Pechacek
Date: Fri, 31 Jan 2020 14:28:29 +0100
Subject: powerpc/pseries: Avoid NULL pointer dereference when drmem is
 unavailable

In guests without hotplugagble memory drmem structure is only zero
initialized. Trying to manipulate DLPAR parameters results in a crash.

  $ echo "memory add count 1" > /sys/kernel/dlpar
  Oops: Kernel access of bad area, sig: 11 [#1]
  LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
  ...
  NIP:  c0000000000ff294 LR: c0000000000ff248 CTR: 0000000000000000
  REGS: c0000000fb9d3880 TRAP: 0300   Tainted: G            E      (5.5.0-rc6-2-default)
  MSR:  8000000000009033 <SF,EE,ME,IR,DR,RI,LE>  CR: 28242428  XER: 20000000
  CFAR: c0000000009a6c10 DAR: 0000000000000010 DSISR: 40000000 IRQMASK: 0
  ...
  NIP dlpar_memory+0x6e4/0xd00
  LR  dlpar_memory+0x698/0xd00
  Call Trace:
    dlpar_memory+0x698/0xd00 (unreliable)
    handle_dlpar_errorlog+0xc0/0x190
    dlpar_store+0x198/0x4a0
    kobj_attr_store+0x30/0x50
    sysfs_kf_write+0x64/0x90
    kernfs_fop_write+0x1b0/0x290
    __vfs_write+0x3c/0x70
    vfs_write+0xd0/0x260
    ksys_write+0xdc/0x130
    system_call+0x5c/0x68

Taking closer look at the code, I can see that for_each_drmem_lmb is a
macro expanding into `for (lmb = &drmem_info->lmbs[0]; lmb <=
&drmem_info->lmbs[drmem_info->n_lmbs - 1]; lmb++)`. When drmem_info->lmbs
is NULL, the loop would iterate through the whole address range if it
weren't stopped by the NULL pointer dereference on the next line.

This patch aligns for_each_drmem_lmb and for_each_drmem_lmb_in_range
macro behavior with the common C semantics, where the end marker does
not belong to the scanned range, and alters get_lmb_range() semantics.
As a side effect, the wraparound observed in the crash is prevented.

Fixes: 6c6ea53725b3 ("powerpc/mm: Separate ibm, dynamic-memory data from DT format")
Cc: stable@vger.kernel.org # v4.16+
Signed-off-by: Libor Pechacek <lpechacek@suse.cz>
Signed-off-by: Michal Suchanek <msuchanek@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200131132829.10281-1-msuchanek@suse.de
---
 arch/powerpc/include/asm/drmem.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h
index 3d76e1c388c2..28c3d936fdf3 100644
--- a/arch/powerpc/include/asm/drmem.h
+++ b/arch/powerpc/include/asm/drmem.h
@@ -27,12 +27,12 @@ struct drmem_lmb_info {
 extern struct drmem_lmb_info *drmem_info;
 
 #define for_each_drmem_lmb_in_range(lmb, start, end)		\
-	for ((lmb) = (start); (lmb) <= (end); (lmb)++)
+	for ((lmb) = (start); (lmb) < (end); (lmb)++)
 
 #define for_each_drmem_lmb(lmb)					\
 	for_each_drmem_lmb_in_range((lmb),			\
 		&drmem_info->lmbs[0],				\
-		&drmem_info->lmbs[drmem_info->n_lmbs - 1])
+		&drmem_info->lmbs[drmem_info->n_lmbs])
 
 /*
  * The of_drconf_cell_v1 struct defines the layout of the LMB data
-- 
cgit v1.2.3


From 0b1c524caaae2428b20e714297243e5551251eb5 Mon Sep 17 00:00:00 2001
From: Christophe Leroy
Date: Thu, 9 Jan 2020 08:25:25 +0000
Subject: powerpc/32: refactor pmd_offset(pud_offset(pgd_offset...

At several places pmd pointer is retrieved through the same action:

	pmd = pmd_offset(pud_offset(pgd_offset(mm, addr), addr), addr);

or

	pmd = pmd_offset(pud_offset(pgd_offset_k(addr), addr), addr);

Refactor this by implementing two helpers pmd_ptr() and pmd_ptr_k()

This will help when adding the p4d level.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/7b065c5be35726af4066cab238ee35cabceda1fa.1578558199.git.christophe.leroy@c-s.fr
---
 arch/powerpc/include/asm/pgtable.h    | 12 ++++++++++++
 arch/powerpc/mm/book3s32/mmu.c        |  2 +-
 arch/powerpc/mm/book3s32/tlb.c        |  4 ++--
 arch/powerpc/mm/kasan/kasan_init_32.c |  8 ++++----
 arch/powerpc/mm/mem.c                 |  3 +--
 arch/powerpc/mm/nohash/40x.c          |  4 ++--
 arch/powerpc/mm/pgtable_32.c          |  2 +-
 7 files changed, 23 insertions(+), 12 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 8cc543ed114c..22bf7bb666a7 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -41,6 +41,18 @@ struct mm_struct;
 
 #ifndef __ASSEMBLY__
 
+#ifdef CONFIG_PPC32
+static inline pmd_t *pmd_ptr(struct mm_struct *mm, unsigned long va)
+{
+	return pmd_offset(pud_offset(pgd_offset(mm, va), va), va);
+}
+
+static inline pmd_t *pmd_ptr_k(unsigned long va)
+{
+	return pmd_offset(pud_offset(pgd_offset_k(va), va), va);
+}
+#endif
+
 #include <asm/tlbflush.h>
 
 /* Keep these as a macros to avoid include dependency mess */
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index 0a1c65a2c565..c225b0397ffd 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -312,7 +312,7 @@ void hash_preload(struct mm_struct *mm, unsigned long ea)
 
 	if (!Hash)
 		return;
-	pmd = pmd_offset(pud_offset(pgd_offset(mm, ea), ea), ea);
+	pmd = pmd_ptr(mm, ea);
 	if (!pmd_none(*pmd))
 		add_hash_page(mm->context.id, ea, pmd_val(*pmd));
 }
diff --git a/arch/powerpc/mm/book3s32/tlb.c b/arch/powerpc/mm/book3s32/tlb.c
index 724c0490fb17..dc9039a170aa 100644
--- a/arch/powerpc/mm/book3s32/tlb.c
+++ b/arch/powerpc/mm/book3s32/tlb.c
@@ -90,7 +90,7 @@ static void flush_range(struct mm_struct *mm, unsigned long start,
 	if (start >= end)
 		return;
 	end = (end - 1) | ~PAGE_MASK;
-	pmd = pmd_offset(pud_offset(pgd_offset(mm, start), start), start);
+	pmd = pmd_ptr(mm, start);
 	for (;;) {
 		pmd_end = ((start + PGDIR_SIZE) & PGDIR_MASK) - 1;
 		if (pmd_end > end)
@@ -148,7 +148,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 		return;
 	}
 	mm = (vmaddr < TASK_SIZE)? vma->vm_mm: &init_mm;
-	pmd = pmd_offset(pud_offset(pgd_offset(mm, vmaddr), vmaddr), vmaddr);
+	pmd = pmd_ptr(mm, vmaddr);
 	if (!pmd_none(*pmd))
 		flush_hash_pages(mm->context.id, vmaddr, pmd_val(*pmd), 1);
 }
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
index 16dd95bd0749..b195d085970a 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -36,7 +36,7 @@ static int __init kasan_init_shadow_page_tables(unsigned long k_start, unsigned
 	unsigned long k_cur, k_next;
 	pte_t *new = NULL;
 
-	pmd = pmd_offset(pud_offset(pgd_offset_k(k_start), k_start), k_start);
+	pmd = pmd_ptr_k(k_start);
 
 	for (k_cur = k_start; k_cur != k_end; k_cur = k_next, pmd++) {
 		k_next = pgd_addr_end(k_cur, k_end);
@@ -78,7 +78,7 @@ static int __init kasan_init_region(void *start, size_t size)
 	block = memblock_alloc(k_end - k_start, PAGE_SIZE);
 
 	for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
-		pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
+		pmd_t *pmd = pmd_ptr_k(k_cur);
 		void *va = block + k_cur - k_start;
 		pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL);
 
@@ -102,7 +102,7 @@ static void __init kasan_remap_early_shadow_ro(void)
 	kasan_populate_pte(kasan_early_shadow_pte, prot);
 
 	for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
-		pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
+		pmd_t *pmd = pmd_ptr_k(k_cur);
 		pte_t *ptep = pte_offset_kernel(pmd, k_cur);
 
 		if ((pte_val(*ptep) & PTE_RPN_MASK) != pa)
@@ -202,7 +202,7 @@ void __init kasan_early_init(void)
 	unsigned long addr = KASAN_SHADOW_START;
 	unsigned long end = KASAN_SHADOW_END;
 	unsigned long next;
-	pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(addr), addr), addr);
+	pmd_t *pmd = pmd_ptr_k(addr);
 
 	BUILD_BUG_ON(KASAN_SHADOW_START & ~PGDIR_MASK);
 
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index ef7b1119b2e2..b7325bb4c890 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -69,8 +69,7 @@ EXPORT_SYMBOL(kmap_prot);
 
 static inline pte_t *virt_to_kpte(unsigned long vaddr)
 {
-	return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr),
-			vaddr), vaddr), vaddr);
+	return pte_offset_kernel(pmd_ptr_k(vaddr), vaddr);
 }
 #endif
 
diff --git a/arch/powerpc/mm/nohash/40x.c b/arch/powerpc/mm/nohash/40x.c
index f348104eb461..82862723ab42 100644
--- a/arch/powerpc/mm/nohash/40x.c
+++ b/arch/powerpc/mm/nohash/40x.c
@@ -104,7 +104,7 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 		pmd_t *pmdp;
 		unsigned long val = p | _PMD_SIZE_16M | _PAGE_EXEC | _PAGE_HWWRITE;
 
-		pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v);
+		pmdp = pmd_ptr_k(v);
 		*pmdp++ = __pmd(val);
 		*pmdp++ = __pmd(val);
 		*pmdp++ = __pmd(val);
@@ -119,7 +119,7 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
 		pmd_t *pmdp;
 		unsigned long val = p | _PMD_SIZE_4M | _PAGE_EXEC | _PAGE_HWWRITE;
 
-		pmdp = pmd_offset(pud_offset(pgd_offset_k(v), v), v);
+		pmdp = pmd_ptr_k(v);
 		*pmdp = __pmd(val);
 
 		v += LARGE_PAGE_SIZE_4M;
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 5fb90edd865e..d90c166bb6e5 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -63,7 +63,7 @@ int __ref map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot)
 	int err = -ENOMEM;
 
 	/* Use upper 10 bits of VA to index the first level map */
-	pd = pmd_offset(pud_offset(pgd_offset_k(va), va), va);
+	pd = pmd_ptr_k(va);
 	/* Use middle 10 bits of VA to index the second-level map */
 	if (likely(slab_is_available()))
 		pg = pte_alloc_kernel(pd, va);
-- 
cgit v1.2.3


From 2efc7c085f05870eda6f29ac71eeb83f3bd54415 Mon Sep 17 00:00:00 2001
From: Christophe Leroy
Date: Thu, 9 Jan 2020 08:25:26 +0000
Subject: powerpc/32: drop get_pteptr()

Commit 8d30c14cab30 ("powerpc/mm: Rework I$/D$ coherency (v3)") and
commit 90ac19a8b21b ("[POWERPC] Abolish iopa(), mm_ptov(),
io_block_mapping() from arch/powerpc") removed the use of get_pteptr()
outside of mm/pgtable_32.c

In mm/pgtable_32.c, the only user of get_pteptr() is change_page_attr()
which operates on kernel context and on lowmem pages only.

Make virt_to_kpte() available outside of mm/mem.c and use it instead
of get_pteptr(), and drop get_pteptr()

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/788378c6c3ba5c5298caab7c7f95e6c3c88244b8.1578558199.git.christophe.leroy@c-s.fr
---
 arch/powerpc/include/asm/pgtable.h |  5 +++++
 arch/powerpc/mm/mem.c              |  5 -----
 arch/powerpc/mm/pgtable_32.c       | 39 ++------------------------------------
 3 files changed, 7 insertions(+), 42 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index 22bf7bb666a7..b80bfd41828d 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -51,6 +51,11 @@ static inline pmd_t *pmd_ptr_k(unsigned long va)
 {
 	return pmd_offset(pud_offset(pgd_offset_k(va), va), va);
 }
+
+static inline pte_t *virt_to_kpte(unsigned long vaddr)
+{
+	return pte_offset_kernel(pmd_ptr_k(vaddr), vaddr);
+}
 #endif
 
 #include <asm/tlbflush.h>
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index b7325bb4c890..4f852d2a62f5 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -66,11 +66,6 @@ pte_t *kmap_pte;
 EXPORT_SYMBOL(kmap_pte);
 pgprot_t kmap_prot;
 EXPORT_SYMBOL(kmap_prot);
-
-static inline pte_t *virt_to_kpte(unsigned long vaddr)
-{
-	return pte_offset_kernel(pmd_ptr_k(vaddr), vaddr);
-}
 #endif
 
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index d90c166bb6e5..f62de06e3d07 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -121,44 +121,9 @@ void __init mapin_ram(void)
 	}
 }
 
-/* Scan the real Linux page tables and return a PTE pointer for
- * a virtual address in a context.
- * Returns true (1) if PTE was found, zero otherwise.  The pointer to
- * the PTE pointer is unmodified if PTE is not found.
- */
-static int
-get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep, pmd_t **pmdp)
-{
-        pgd_t	*pgd;
-	pud_t	*pud;
-        pmd_t	*pmd;
-        pte_t	*pte;
-        int     retval = 0;
-
-        pgd = pgd_offset(mm, addr & PAGE_MASK);
-        if (pgd) {
-		pud = pud_offset(pgd, addr & PAGE_MASK);
-		if (pud && pud_present(*pud)) {
-			pmd = pmd_offset(pud, addr & PAGE_MASK);
-			if (pmd_present(*pmd)) {
-				pte = pte_offset_map(pmd, addr & PAGE_MASK);
-				if (pte) {
-					retval = 1;
-					*ptep = pte;
-					if (pmdp)
-						*pmdp = pmd;
-					/* XXX caller needs to do pte_unmap, yuck */
-				}
-			}
-		}
-        }
-        return(retval);
-}
-
 static int __change_page_attr_noflush(struct page *page, pgprot_t prot)
 {
 	pte_t *kpte;
-	pmd_t *kpmd;
 	unsigned long address;
 
 	BUG_ON(PageHighMem(page));
@@ -166,10 +131,10 @@ static int __change_page_attr_noflush(struct page *page, pgprot_t prot)
 
 	if (v_block_mapped(address))
 		return 0;
-	if (!get_pteptr(&init_mm, address, &kpte, &kpmd))
+	kpte = virt_to_kpte(address);
+	if (!kpte)
 		return -EINVAL;
 	__set_pte_at(&init_mm, address, kpte, mk_pte(page, prot), 0);
-	pte_unmap(kpte);
 
 	return 0;
 }
-- 
cgit v1.2.3


From c4fd527f52ecb135018655c7f56f87800872c5bc Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman
Date: Sun, 9 Feb 2020 11:58:57 +0100
Subject: powerpc/kvm: no need to check return value of debugfs_create
 functions

When calling debugfs functions, there is no need to ever check the
return value.  The function can work or not, but the code logic should
never do something different based on this.

Because of this cleanup, we get to remove a few fields in struct
kvm_arch that are now unused.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[mpe: Fix build error in kvm/timing.c, adapt kvmppc_remove_cpu_debugfs()]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200209105901.1620958-2-gregkh@linuxfoundation.org
---
 arch/powerpc/include/asm/kvm_host.h    |  3 ---
 arch/powerpc/kvm/book3s_64_mmu_hv.c    |  5 ++---
 arch/powerpc/kvm/book3s_64_mmu_radix.c |  5 ++---
 arch/powerpc/kvm/book3s_hv.c           |  9 ++-------
 arch/powerpc/kvm/timing.c              | 17 ++++-------------
 5 files changed, 10 insertions(+), 29 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 6e8b8ffd06ad..877f8aa2bc1e 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -308,8 +308,6 @@ struct kvm_arch {
 	pgd_t *pgtable;
 	u64 process_table;
 	struct dentry *debugfs_dir;
-	struct dentry *htab_dentry;
-	struct dentry *radix_dentry;
 	struct kvm_resize_hpt *resize_hpt; /* protected by kvm->lock */
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
@@ -830,7 +828,6 @@ struct kvm_vcpu_arch {
 	struct kvmhv_tb_accumulator cede_time;	/* time napping inside guest */
 
 	struct dentry *debugfs_dir;
-	struct dentry *debugfs_timings;
 #endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
 };
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 6c372f5c61b6..8b4eac0c9dcd 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -2138,9 +2138,8 @@ static const struct file_operations debugfs_htab_fops = {
 
 void kvmppc_mmu_debugfs_init(struct kvm *kvm)
 {
-	kvm->arch.htab_dentry = debugfs_create_file("htab", 0400,
-						    kvm->arch.debugfs_dir, kvm,
-						    &debugfs_htab_fops);
+	debugfs_create_file("htab", 0400, kvm->arch.debugfs_dir, kvm,
+			    &debugfs_htab_fops);
 }
 
 void kvmppc_mmu_book3s_hv_init(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 803940d79b73..1d75ed684b53 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -1376,9 +1376,8 @@ static const struct file_operations debugfs_radix_fops = {
 
 void kvmhv_radix_debugfs_init(struct kvm *kvm)
 {
-	kvm->arch.radix_dentry = debugfs_create_file("radix", 0400,
-						     kvm->arch.debugfs_dir, kvm,
-						     &debugfs_radix_fops);
+	debugfs_create_file("radix", 0400, kvm->arch.debugfs_dir, kvm,
+			    &debugfs_radix_fops);
 }
 
 int kvmppc_radix_init(void)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2cefd071b848..33be4d93248a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2258,14 +2258,9 @@ static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
 	struct kvm *kvm = vcpu->kvm;
 
 	snprintf(buf, sizeof(buf), "vcpu%u", id);
-	if (IS_ERR_OR_NULL(kvm->arch.debugfs_dir))
-		return;
 	vcpu->arch.debugfs_dir = debugfs_create_dir(buf, kvm->arch.debugfs_dir);
-	if (IS_ERR_OR_NULL(vcpu->arch.debugfs_dir))
-		return;
-	vcpu->arch.debugfs_timings =
-		debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir,
-				    vcpu, &debugfs_timings_ops);
+	debugfs_create_file("timings", 0444, vcpu->arch.debugfs_dir, vcpu,
+			    &debugfs_timings_ops);
 }
 
 #else /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
diff --git a/arch/powerpc/kvm/timing.c b/arch/powerpc/kvm/timing.c
index bfe4f106cffc..ba56a5cbba97 100644
--- a/arch/powerpc/kvm/timing.c
+++ b/arch/powerpc/kvm/timing.c
@@ -211,23 +211,14 @@ void kvmppc_create_vcpu_debugfs(struct kvm_vcpu *vcpu, unsigned int id)
 
 	snprintf(dbg_fname, sizeof(dbg_fname), "vm%u_vcpu%u_timing",
 		 current->pid, id);
-	debugfs_file = debugfs_create_file(dbg_fname, 0666,
-					kvm_debugfs_dir, vcpu,
-					&kvmppc_exit_timing_fops);
-
-	if (!debugfs_file) {
-		printk(KERN_ERR"%s: error creating debugfs file %s\n",
-			__func__, dbg_fname);
-		return;
-	}
+	debugfs_file = debugfs_create_file(dbg_fname, 0666, kvm_debugfs_dir,
+						vcpu, &kvmppc_exit_timing_fops);
 
 	vcpu->arch.debugfs_exit_timing = debugfs_file;
 }
 
 void kvmppc_remove_vcpu_debugfs(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->arch.debugfs_exit_timing) {
-		debugfs_remove(vcpu->arch.debugfs_exit_timing);
-		vcpu->arch.debugfs_exit_timing = NULL;
-	}
+	debugfs_remove(vcpu->arch.debugfs_exit_timing);
+	vcpu->arch.debugfs_exit_timing = NULL;
 }
-- 
cgit v1.2.3


From 6453f9ed9d4e4b4cdf201bf34bf460c436bf50ea Mon Sep 17 00:00:00 2001
From: Christophe Leroy
Date: Mon, 17 Feb 2020 09:41:35 +0000
Subject: powerpc/mm: Don't kmap_atomic() in pte_offset_map() on PPC32

On PPC32, pte_offset_map() does a kmap_atomic() in order to support
page tables allocated in high memory, just like ARM and x86/32.

But since at least 2008 and commit 8054a3428fbe ("powerpc: Remove dead
CONFIG_HIGHPTE"), page tables are never allocated in high memory.

When the page is in low mem, kmap_atomic() just returns the page
address but still disable preemption and pagefault. And it is
not an inlined function, so we suffer function call for no reason.

Make pte_offset_map() the same as pte_offset_kernel() and make
pte_unmap() void, in the same way as PPC64 which doesn't have HIGHMEM.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/03c97f0f6b3790d164822563be80f2fd4713a955.1581932480.git.christophe.leroy@c-s.fr
---
 arch/powerpc/include/asm/book3s/32/pgtable.h | 6 ++----
 arch/powerpc/include/asm/nohash/32/pgtable.h | 6 ++----
 2 files changed, 4 insertions(+), 8 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 5b39c11e884a..7549393c4c43 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -366,10 +366,8 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
 	(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 #define pte_offset_kernel(dir, addr)	\
 	((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(addr))
-#define pte_offset_map(dir, addr)		\
-	((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \
-		   (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr))
-#define pte_unmap(pte)		kunmap_atomic(pte)
+#define pte_offset_map(dir, addr)	pte_offset_kernel((dir), (addr))
+static inline void pte_unmap(pte_t *pte) { }
 
 /*
  * Encode and decode a swap entry.
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 60c4d829152e..b04ba257fddb 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -372,10 +372,8 @@ static inline int pte_young(pte_t pte)
 #define pte_offset_kernel(dir, addr)	\
 	(pmd_bad(*(dir)) ? NULL : (pte_t *)pmd_page_vaddr(*(dir)) + \
 				  pte_index(addr))
-#define pte_offset_map(dir, addr)		\
-	((pte_t *)(kmap_atomic(pmd_page(*(dir))) + \
-		   (pmd_page_vaddr(*(dir)) & ~PAGE_MASK)) + pte_index(addr))
-#define pte_unmap(pte)		kunmap_atomic(pte)
+#define pte_offset_map(dir, addr)	pte_offset_kernel((dir), (addr))
+static inline void pte_unmap(pte_t *pte) { }
 
 /*
  * Encode and decode a swap entry.
-- 
cgit v1.2.3


From 672e480aa21023fc8e4b6ab8635d8898822b97e7 Mon Sep 17 00:00:00 2001
From: Oliver O'Halloran
Date: Mon, 17 Feb 2020 13:48:33 +1100
Subject: powerpc/powernv: Add explicit fast-reboot support

Add a way to manually invoke a fast-reboot rather than setting the NVRAM
flag. The idea is to allow userspace to invoke a fast-reboot using the
optional string argument to the reboot() system call, or using the xmon
zr command so we don't need to leave around a persistent changes on
a system to use the feature.

Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200217024833.30580-2-oohall@gmail.com
---
 arch/powerpc/include/asm/opal-api.h    | 1 +
 arch/powerpc/platforms/powernv/setup.c | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/opal-api.h b/arch/powerpc/include/asm/opal-api.h
index c1f25a760eb1..1dffa3cb16ba 100644
--- a/arch/powerpc/include/asm/opal-api.h
+++ b/arch/powerpc/include/asm/opal-api.h
@@ -1067,6 +1067,7 @@ enum {
 	OPAL_REBOOT_PLATFORM_ERROR	= 1,
 	OPAL_REBOOT_FULL_IPL		= 2,
 	OPAL_REBOOT_MPIPL		= 3,
+	OPAL_REBOOT_FAST		= 4,
 };
 
 /* Argument to OPAL_PCI_TCE_KILL */
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index a8fe630cf7cc..3bc188da82ba 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -237,6 +237,8 @@ static void  __noreturn pnv_restart(char *cmd)
 			rc = opal_cec_reboot2(OPAL_REBOOT_MPIPL, NULL);
 		else if (strcmp(cmd, "error") == 0)
 			rc = opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR, NULL);
+		else if (strcmp(cmd, "fast") == 0)
+			rc = opal_cec_reboot2(OPAL_REBOOT_FAST, NULL);
 		else
 			rc = OPAL_UNSUPPORTED;
 
-- 
cgit v1.2.3


From 3d13e839e801e081bdece0127c2affa33d0f77cf Mon Sep 17 00:00:00 2001
From: Michael Ellerman
Date: Thu, 20 Feb 2020 22:51:37 +1100
Subject: powerpc: Rename current_stack_pointer() to current_stack_frame()

current_stack_pointer(), which was called __get_SP(), used to just
return the value in r1.

But that caused problems in some cases, so it was turned into a
function in commit bfe9a2cfe91a ("powerpc: Reimplement __get_SP() as a
function not a define").

Because it's a function in a separate compilation unit to all its
callers, it has the effect of causing a stack frame to be created, and
then returns the address of that frame. This is good in some cases
like those described in the above commit, but in other cases it's
overkill, we just need to know what stack page we're on.

On some other arches current_stack_pointer is just a register global
giving the stack pointer, and we'd like to do that too. So rename our
current_stack_pointer() to current_stack_frame() to make that
possible.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr>
Link: https://lore.kernel.org/r/20200220115141.2707-1-mpe@ellerman.id.au
---
 arch/powerpc/include/asm/perf_event.h | 2 +-
 arch/powerpc/include/asm/reg.h        | 2 +-
 arch/powerpc/kernel/irq.c             | 4 ++--
 arch/powerpc/kernel/misc.S            | 4 ++--
 arch/powerpc/kernel/process.c         | 2 +-
 arch/powerpc/kernel/stacktrace.c      | 6 +++---
 6 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/perf_event.h b/arch/powerpc/include/asm/perf_event.h
index 7426d7a90e1e..eed3954082fa 100644
--- a/arch/powerpc/include/asm/perf_event.h
+++ b/arch/powerpc/include/asm/perf_event.h
@@ -32,7 +32,7 @@
 	do {							\
 		(regs)->result = 0;				\
 		(regs)->nip = __ip;				\
-		(regs)->gpr[1] = current_stack_pointer();	\
+		(regs)->gpr[1] = current_stack_frame();		\
 		asm volatile("mfmsr %0" : "=r" ((regs)->msr));	\
 	} while (0)
 
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 1aa46dff0957..1b1ffdba6097 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1448,7 +1448,7 @@ static inline void mtsrin(u32 val, u32 idx)
 
 #define proc_trap()	asm volatile("trap")
 
-extern unsigned long current_stack_pointer(void);
+extern unsigned long current_stack_frame(void);
 
 extern unsigned long scom970_read(unsigned int address);
 extern void scom970_write(unsigned int address, unsigned long value);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 5c9b11878555..02118c18434d 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -602,7 +602,7 @@ static inline void check_stack_overflow(void)
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
 	long sp;
 
-	sp = current_stack_pointer() & (THREAD_SIZE-1);
+	sp = current_stack_frame() & (THREAD_SIZE-1);
 
 	/* check for stack overflow: is there less than 2KB free? */
 	if (unlikely(sp < 2048)) {
@@ -647,7 +647,7 @@ void do_IRQ(struct pt_regs *regs)
 	void *cursp, *irqsp, *sirqsp;
 
 	/* Switch to the irq stack to handle this */
-	cursp = (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
+	cursp = (void *)(current_stack_frame() & ~(THREAD_SIZE - 1));
 	irqsp = hardirq_ctx[raw_smp_processor_id()];
 	sirqsp = softirq_ctx[raw_smp_processor_id()];
 
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 974f65f79a8e..65f9f731c229 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -110,7 +110,7 @@ _GLOBAL(longjmp)
 	li	r3, 1
 	blr
 
-_GLOBAL(current_stack_pointer)
+_GLOBAL(current_stack_frame)
 	PPC_LL	r3,0(r1)
 	blr
-EXPORT_SYMBOL(current_stack_pointer)
+EXPORT_SYMBOL(current_stack_frame)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index e730b8e522b0..110db94cdf3c 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -2051,7 +2051,7 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
 	sp = (unsigned long) stack;
 	if (sp == 0) {
 		if (tsk == current)
-			sp = current_stack_pointer();
+			sp = current_stack_frame();
 		else
 			sp = tsk->thread.ksp;
 	}
diff --git a/arch/powerpc/kernel/stacktrace.c b/arch/powerpc/kernel/stacktrace.c
index e2a46cfed5fd..c477b8585a29 100644
--- a/arch/powerpc/kernel/stacktrace.c
+++ b/arch/powerpc/kernel/stacktrace.c
@@ -57,7 +57,7 @@ void save_stack_trace(struct stack_trace *trace)
 {
 	unsigned long sp;
 
-	sp = current_stack_pointer();
+	sp = current_stack_frame();
 
 	save_context_stack(trace, sp, current, 1);
 }
@@ -71,7 +71,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 		return;
 
 	if (tsk == current)
-		sp = current_stack_pointer();
+		sp = current_stack_frame();
 	else
 		sp = tsk->thread.ksp;
 
@@ -131,7 +131,7 @@ static int __save_stack_trace_tsk_reliable(struct task_struct *tsk,
 	}
 
 	if (tsk == current)
-		sp = current_stack_pointer();
+		sp = current_stack_frame();
 	else
 		sp = tsk->thread.ksp;
 
-- 
cgit v1.2.3


From 0e63f0151719ee4cb90d85e60c98045099c995e2 Mon Sep 17 00:00:00 2001
From: Christophe Leroy
Date: Thu, 20 Feb 2020 22:51:38 +1100
Subject: powerpc: Add current_stack_pointer as a register global

current_stack_frame() doesn't return the stack pointer, but the
caller's stack frame. See commit bfe9a2cfe91a ("powerpc: Reimplement
__get_SP() as a function not a define") and commit
acf620ecf56c ("powerpc: Rename __get_SP() to current_stack_pointer()")
for details.

In some cases this is overkill or incorrect, as it doesn't return the
current value of r1.

So add a current_stack_pointer register global to get the value of r1
directly.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
[mpe: Split out of other patch, tweak change log]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200220115141.2707-2-mpe@ellerman.id.au
---
 arch/powerpc/include/asm/reg.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 1b1ffdba6097..da5cab038e25 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -1450,6 +1450,8 @@ static inline void mtsrin(u32 val, u32 idx)
 
 extern unsigned long current_stack_frame(void);
 
+register unsigned long current_stack_pointer asm("r1");
+
 extern unsigned long scom970_read(unsigned int address);
 extern void scom970_write(unsigned int address, unsigned long value);
 
-- 
cgit v1.2.3


From a05f0e5be4e81e4977d3f92aaf7688ee0cb7d5db Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju
Date: Wed, 29 Jan 2020 19:21:21 +0530
Subject: powerpc/smp: Use nid as fallback for package_id

package_id is to match cores that are part of the same chip. On
PowerNV machines, package_id defaults to chip_id. However ibm,chip_id
property is not present in device-tree of PowerVM LPARs. Hence lscpu
output shows one core per socket and multiple cores.

To overcome this, use nid as the package_id on PowerVM LPARs.

Before the patch:

  Architecture:        ppc64le
  Byte Order:          Little Endian
  CPU(s):              128
  On-line CPU(s) list: 0-127
  Thread(s) per core:  8
  Core(s) per socket:  1                     <----------------------
  Socket(s):           16                    <----------------------
  NUMA node(s):        2
  Model:               2.2 (pvr 004e 0202)
  Model name:          POWER9 (architected), altivec supported
  Hypervisor vendor:   pHyp
  Virtualization type: para
  L1d cache:           32K
  L1i cache:           32K
  L2 cache:            512K
  L3 cache:            10240K
  NUMA node0 CPU(s):   0-63
  NUMA node1 CPU(s):   64-127
  #
  # cat /sys/devices/system/cpu/cpu0/topology/physical_package_id
  -1

After the patch:

  Architecture:        ppc64le
  Byte Order:          Little Endian
  CPU(s):              128
  On-line CPU(s) list: 0-127
  Thread(s) per core:  8                     <---------------------
  Core(s) per socket:  8                     <---------------------
  Socket(s):           2
  NUMA node(s):        2
  Model:               2.2 (pvr 004e 0202)
  Model name:          POWER9 (architected), altivec supported
  Hypervisor vendor:   pHyp
  Virtualization type: para
  L1d cache:           32K
  L1i cache:           32K
  L2 cache:            512K
  L3 cache:            10240K
  NUMA node0 CPU(s):   0-63
  NUMA node1 CPU(s):   64-127
  #
  # cat /sys/devices/system/cpu/cpu0/topology/physical_package_id
  0

Now lscpu output is more in line with the system configuration.

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
[mpe: Use pkg_id instead of ppid, tweak change log and comment]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200129135121.24617-1-srikar@linux.vnet.ibm.com
---
 arch/powerpc/include/asm/topology.h |  6 ++++++
 arch/powerpc/kernel/smp.c           | 30 +++++++++++++++++++++++++++---
 2 files changed, 33 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 2f7e1ea5089e..e2e1ccd4a18d 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -134,7 +134,13 @@ static inline void shared_proc_topology_init(void) {}
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
 
+#ifdef CONFIG_PPC_SPLPAR
+int get_physical_package_id(int cpu);
+#define topology_physical_package_id(cpu)	(get_physical_package_id(cpu))
+#else
 #define topology_physical_package_id(cpu)	(cpu_to_chip_id(cpu))
+#endif
+
 #define topology_sibling_cpumask(cpu)	(per_cpu(cpu_sibling_map, cpu))
 #define topology_core_cpumask(cpu)	(per_cpu(cpu_core_map, cpu))
 #define topology_core_id(cpu)		(cpu_to_core_id(cpu))
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ea6adbf6a221..f68cde82bdf3 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1185,10 +1185,34 @@ static inline void add_cpu_to_smallcore_masks(int cpu)
 	}
 }
 
+int get_physical_package_id(int cpu)
+{
+	int pkg_id = cpu_to_chip_id(cpu);
+
+#ifdef CONFIG_PPC_SPLPAR
+	/*
+	 * If the platform is PowerNV or Guest on KVM, ibm,chip-id is
+	 * defined. Hence we would return the chip-id as the result of
+	 * get_physical_package_id.
+	 */
+	if (pkg_id == -1 && firmware_has_feature(FW_FEATURE_LPAR)) {
+		struct device_node *np = of_get_cpu_node(cpu, NULL);
+
+		if (np) {
+			pkg_id = of_node_to_nid(np);
+			of_node_put(np);
+		}
+	}
+#endif /* CONFIG_PPC_SPLPAR */
+
+	return pkg_id;
+}
+EXPORT_SYMBOL_GPL(get_physical_package_id);
+
 static void add_cpu_to_masks(int cpu)
 {
 	int first_thread = cpu_first_thread_sibling(cpu);
-	int chipid = cpu_to_chip_id(cpu);
+	int pkg_id = get_physical_package_id(cpu);
 	int i;
 
 	/*
@@ -1217,11 +1241,11 @@ static void add_cpu_to_masks(int cpu)
 	for_each_cpu(i, cpu_l2_cache_mask(cpu))
 		set_cpus_related(cpu, i, cpu_core_mask);
 
-	if (chipid == -1)
+	if (pkg_id == -1)
 		return;
 
 	for_each_cpu(i, cpu_online_mask)
-		if (cpu_to_chip_id(i) == chipid)
+		if (get_physical_package_id(i) == pkg_id)
 			set_cpus_related(cpu, i, cpu_core_mask);
 }
 
-- 
cgit v1.2.3


From 247257b03b04398ca07da4bce3d17bee25d623cb Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju
Date: Wed, 29 Jan 2020 19:23:01 +0530
Subject: powerpc/numa: Remove late request for home node associativity

With commit ("powerpc/numa: Early request for home node associativity"),
commit 2ea626306810 ("powerpc/topology: Get topology for shared
processors at boot") which was requesting home node associativity
becomes redundant.

Hence remove the late request for home node associativity.

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Reported-by: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Reviewed-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200129135301.24739-6-srikar@linux.vnet.ibm.com
---
 arch/powerpc/include/asm/topology.h | 4 ----
 arch/powerpc/kernel/smp.c           | 5 -----
 arch/powerpc/mm/numa.c              | 9 ---------
 3 files changed, 18 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index e2e1ccd4a18d..2db7ba789720 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -98,7 +98,6 @@ extern int stop_topology_update(void);
 extern int prrn_is_enabled(void);
 extern int find_and_online_cpu_nid(int cpu);
 extern int timed_topology_update(int nsecs);
-extern void __init shared_proc_topology_init(void);
 #else
 static inline int start_topology_update(void)
 {
@@ -121,9 +120,6 @@ static inline int timed_topology_update(int nsecs)
 	return 0;
 }
 
-#ifdef CONFIG_SMP
-static inline void shared_proc_topology_init(void) {}
-#endif
 #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
 
 #include <asm-generic/topology.h>
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index f68cde82bdf3..37c12e3bab9e 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1383,11 +1383,6 @@ void __init smp_cpus_done(unsigned int max_cpus)
 	if (smp_ops && smp_ops->bringup_done)
 		smp_ops->bringup_done();
 
-	/*
-	 * On a shared LPAR, associativity needs to be requested.
-	 * Hence, get numa topology before dumping cpu topology
-	 */
-	shared_proc_topology_init();
 	dump_numa_cpu_topology();
 
 #ifdef CONFIG_SCHED_SMT
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 5a8abf0165d7..9fcf2d195830 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1632,15 +1632,6 @@ int prrn_is_enabled(void)
 	return prrn_enabled;
 }
 
-void __init shared_proc_topology_init(void)
-{
-	if (lppaca_shared_proc(get_lppaca())) {
-		bitmap_fill(cpumask_bits(&cpu_associativity_changes_mask),
-			    nr_cpumask_bits);
-		numa_update_cpu_topology(false);
-	}
-}
-
 static int topology_read(struct seq_file *file, void *v)
 {
 	if (vphn_enabled || prrn_enabled)
-- 
cgit v1.2.3


From cc6f0e39000900e5dd1448103a9571f0eccd7d4e Mon Sep 17 00:00:00 2001
From: Christophe Leroy
Date: Sat, 7 Mar 2020 10:09:15 +0000
Subject: powerpc/32: Fix missing NULL pmd check in virt_to_kpte()

Commit 2efc7c085f05 ("powerpc/32: drop get_pteptr()"),
replaced get_pteptr() by virt_to_kpte(). But virt_to_kpte() lacks a
NULL pmd check and returns an invalid non NULL pointer when there
is no page table.

Reported-by: Nick Desaulniers <ndesaulniers@google.com>
Fixes: 2efc7c085f05 ("powerpc/32: drop get_pteptr()")
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/b1177cdfc6af74a3e277bba5d9e708c4b3315ebe.1583575707.git.christophe.leroy@c-s.fr
---
 arch/powerpc/include/asm/pgtable.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index b80bfd41828d..b1f1d5339735 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -54,7 +54,9 @@ static inline pmd_t *pmd_ptr_k(unsigned long va)
 
 static inline pte_t *virt_to_kpte(unsigned long vaddr)
 {
-	return pte_offset_kernel(pmd_ptr_k(vaddr), vaddr);
+	pmd_t *pmd = pmd_ptr_k(vaddr);
+
+	return pmd_none(*pmd) ? NULL : pte_offset_kernel(pmd, vaddr);
 }
 #endif
 
-- 
cgit v1.2.3


From ffd3eaf178b0f616a071e510e289d937330b0b35 Mon Sep 17 00:00:00 2001
From: Joe Lawrence
Date: Mon, 24 Feb 2020 16:18:48 -0500
Subject: powerpc/vdso: remove deprecated VDS64_HAS_DESCRIPTORS references

The original 2005 patch that introduced the powerpc vdso, pre-git
("ppc64: Implement a vDSO and use it for signal trampoline") notes that:

  ... symbols exposed by the vDSO aren't "normal" function symbols, apps
  can't be expected to link against them directly, the vDSO's are both
  seen as if they were linked at 0 and the symbols just contain offsets
  to the various functions.  This is done on purpose to avoid a
  relocation step (ppc64 functions normally have descriptors with abs
  addresses in them).  When glibc uses those functions, it's expected to
  use it's own trampolines that know how to reach them.

Despite that explanation, there remains dead #ifdef
VDS64_HAS_DESCRIPTORS code-blocks that provide alternate function
definitions that setup function descriptors.

Since VDS64_HAS_DESCRIPTORS has been unused for all these years, we
might as well finally remove it from the codebase.

Signed-off-by: Joe Lawrence <joe.lawrence@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200224211848.26087-1-joe.lawrence@redhat.com
---
 arch/powerpc/include/asm/vdso.h | 24 ------------------------
 arch/powerpc/kernel/vdso.c      |  5 -----
 2 files changed, 29 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h
index b5e1f8f8a05c..2ff884853f97 100644
--- a/arch/powerpc/include/asm/vdso.h
+++ b/arch/powerpc/include/asm/vdso.h
@@ -13,9 +13,6 @@
 
 #define VDSO_VERSION_STRING	LINUX_2.6.15
 
-/* Define if 64 bits VDSO has procedure descriptors */
-#undef VDS64_HAS_DESCRIPTORS
-
 #ifndef __ASSEMBLY__
 
 /* Offsets relative to thread->vdso_base */
@@ -28,25 +25,6 @@ int vdso_getcpu_init(void);
 #else /* __ASSEMBLY__ */
 
 #ifdef __VDSO64__
-#ifdef VDS64_HAS_DESCRIPTORS
-#define V_FUNCTION_BEGIN(name)		\
-	.globl name;			\
-        .section ".opd","a";		\
-        .align 3;			\
-	name:				\
-	.quad .name,.TOC.@tocbase,0;	\
-	.previous;			\
-	.globl .name;			\
-	.type .name,@function; 		\
-	.name:				\
-
-#define V_FUNCTION_END(name)		\
-	.size .name,.-.name;
-
-#define V_LOCAL_FUNC(name) (.name)
-
-#else /* VDS64_HAS_DESCRIPTORS */
-
 #define V_FUNCTION_BEGIN(name)		\
 	.globl name;			\
 	name:				\
@@ -55,8 +33,6 @@ int vdso_getcpu_init(void);
 	.size name,.-name;
 
 #define V_LOCAL_FUNC(name) (name)
-
-#endif /* VDS64_HAS_DESCRIPTORS */
 #endif /* __VDSO64__ */
 
 #ifdef __VDSO32__
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index b9a108411c0d..d3b77c15f9ce 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -391,12 +391,7 @@ static unsigned long __init find_function64(struct lib64_elfinfo *lib,
 		       symname);
 		return 0;
 	}
-#ifdef VDS64_HAS_DESCRIPTORS
-	return *((u64 *)(vdso64_kbase + sym->st_value - VDSO64_LBASE)) -
-		VDSO64_LBASE;
-#else
 	return sym->st_value - VDSO64_LBASE;
-#endif
 }
 
 static int __init vdso_do_func_patch64(struct lib32_elfinfo *v32,
-- 
cgit v1.2.3


From 697ece78f8f749aeea40f2711389901f0974017a Mon Sep 17 00:00:00 2001
From: Christophe Leroy
Date: Tue, 10 Mar 2020 17:29:12 +0000
Subject: powerpc/32s: reorder Linux PTE bits to better match Hash PTE bits.

Reorder Linux PTE bits to (almost) match Hash PTE bits.

RW Kernel : PP = 00
RO Kernel : PP = 00
RW User   : PP = 01
RO User   : PP = 11

So naturally, we should have
_PAGE_USER = 0x001
_PAGE_RW   = 0x002

Today 0x001 and 0x002 and _PAGE_PRESENT and _PAGE_HASHPTE which
both are software only bits.

Switch _PAGE_USER and _PAGE_PRESET
Switch _PAGE_RW and _PAGE_HASHPTE

This allows to remove a few insns.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/c4d6c18a7f8d9d3b899bc492f55fbc40ef38896a.1583861325.git.christophe.leroy@c-s.fr
---
 arch/powerpc/include/asm/book3s/32/hash.h |  8 ++++----
 arch/powerpc/kernel/head_32.S             |  9 +++------
 arch/powerpc/mm/book3s32/hash_low.S       | 14 ++++++--------
 3 files changed, 13 insertions(+), 18 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/book3s/32/hash.h b/arch/powerpc/include/asm/book3s/32/hash.h
index 2a0a467d2985..34a7215ae81e 100644
--- a/arch/powerpc/include/asm/book3s/32/hash.h
+++ b/arch/powerpc/include/asm/book3s/32/hash.h
@@ -17,9 +17,9 @@
  * updating the accessed and modified bits in the page table tree.
  */
 
-#define _PAGE_PRESENT	0x001	/* software: pte contains a translation */
-#define _PAGE_HASHPTE	0x002	/* hash_page has made an HPTE for this pte */
-#define _PAGE_USER	0x004	/* usermode access allowed */
+#define _PAGE_USER	0x001	/* usermode access allowed */
+#define _PAGE_RW	0x002	/* software: user write access allowed */
+#define _PAGE_PRESENT	0x004	/* software: pte contains a translation */
 #define _PAGE_GUARDED	0x008	/* G: prohibit speculative access */
 #define _PAGE_COHERENT	0x010	/* M: enforce memory coherence (SMP systems) */
 #define _PAGE_NO_CACHE	0x020	/* I: cache inhibit */
@@ -27,7 +27,7 @@
 #define _PAGE_DIRTY	0x080	/* C: page changed */
 #define _PAGE_ACCESSED	0x100	/* R: page referenced */
 #define _PAGE_EXEC	0x200	/* software: exec allowed */
-#define _PAGE_RW	0x400	/* software: user write access allowed */
+#define _PAGE_HASHPTE	0x400	/* hash_page has made an HPTE for this pte */
 #define _PAGE_SPECIAL	0x800	/* software: Special page */
 
 #ifdef CONFIG_PTE_64BIT
diff --git a/arch/powerpc/kernel/head_32.S b/arch/powerpc/kernel/head_32.S
index 97c887950c3c..daaa153950c2 100644
--- a/arch/powerpc/kernel/head_32.S
+++ b/arch/powerpc/kernel/head_32.S
@@ -348,7 +348,7 @@ BEGIN_MMU_FTR_SECTION
 	andis.	r0, r5, (DSISR_BAD_FAULT_32S | DSISR_DABRMATCH)@h
 #endif
 	bne	handle_page_fault_tramp_2	/* if not, try to put a PTE */
-	rlwinm	r3, r5, 32 - 15, 21, 21		/* DSISR_STORE -> _PAGE_RW */
+	rlwinm	r3, r5, 32 - 24, 30, 30		/* DSISR_STORE -> _PAGE_RW */
 	bl	hash_page
 	b	handle_page_fault_tramp_1
 FTR_SECTION_ELSE
@@ -497,7 +497,6 @@ InstructionTLBMiss:
 	andc.	r1,r1,r0		/* check access & ~permission */
 	bne-	InstructionAddressInvalid /* return if access not permitted */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
-	rlwimi	r0,r0,32-2,31,31	/* _PAGE_USER -> PP lsb */
 	ori	r1, r1, 0xe06		/* clear out reserved bits */
 	andc	r1, r0, r1		/* PP = user? 1 : 0 */
 BEGIN_FTR_SECTION
@@ -565,9 +564,8 @@ DataLoadTLBMiss:
 	 * we would need to update the pte atomically with lwarx/stwcx.
 	 */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
-	rlwinm	r1,r0,32-9,30,30	/* _PAGE_RW -> PP msb */
-	rlwimi	r0,r0,32-1,30,30	/* _PAGE_USER -> PP msb */
-	rlwimi	r0,r0,32-1,31,31	/* _PAGE_USER -> PP lsb */
+	rlwinm	r1,r0,0,30,30		/* _PAGE_RW -> PP msb */
+	rlwimi	r0,r0,1,30,30		/* _PAGE_USER -> PP msb */
 	ori	r1,r1,0xe04		/* clear out reserved bits */
 	andc	r1,r0,r1		/* PP = user? rw? 1: 3: 0 */
 BEGIN_FTR_SECTION
@@ -645,7 +643,6 @@ DataStoreTLBMiss:
 	 * we would need to update the pte atomically with lwarx/stwcx.
 	 */
 	/* Convert linux-style PTE to low word of PPC-style PTE */
-	rlwimi	r0,r0,32-2,31,31	/* _PAGE_USER -> PP lsb */
 	li	r1,0xe06		/* clear out reserved bits & PP msb */
 	andc	r1,r0,r1		/* PP = user? 1: 0 */
 BEGIN_FTR_SECTION
diff --git a/arch/powerpc/mm/book3s32/hash_low.S b/arch/powerpc/mm/book3s32/hash_low.S
index 877d880890fe..6d236080cb1a 100644
--- a/arch/powerpc/mm/book3s32/hash_low.S
+++ b/arch/powerpc/mm/book3s32/hash_low.S
@@ -35,7 +35,7 @@ mmu_hash_lock:
 /*
  * Load a PTE into the hash table, if possible.
  * The address is in r4, and r3 contains an access flag:
- * _PAGE_RW (0x400) if a write.
+ * _PAGE_RW (0x002) if a write.
  * r9 contains the SRR1 value, from which we use the MSR_PR bit.
  * SPRG_THREAD contains the physical address of the current task's thread.
  *
@@ -69,7 +69,7 @@ _GLOBAL(hash_page)
 	blt+	112f			/* assume user more likely */
 	lis	r5, (swapper_pg_dir - PAGE_OFFSET)@ha	/* if kernel address, use */
 	addi	r5 ,r5 ,(swapper_pg_dir - PAGE_OFFSET)@l	/* kernel page table */
-	rlwimi	r3,r9,32-12,29,29	/* MSR_PR -> _PAGE_USER */
+	rlwimi	r3,r9,32-14,31,31	/* MSR_PR -> _PAGE_USER */
 112:
 #ifndef CONFIG_PTE_64BIT
 	rlwimi	r5,r4,12,20,29		/* insert top 10 bits of address */
@@ -94,7 +94,7 @@ _GLOBAL(hash_page)
 #else
 	rlwimi	r8,r4,23,20,28		/* compute pte address */
 #endif
-	rlwinm	r0,r3,32-3,24,24	/* _PAGE_RW access -> _PAGE_DIRTY */
+	rlwinm	r0,r3,6,24,24		/* _PAGE_RW access -> _PAGE_DIRTY */
 	ori	r0,r0,_PAGE_ACCESSED|_PAGE_HASHPTE
 
 	/*
@@ -310,11 +310,9 @@ Hash_msk = (((1 << Hash_bits) - 1) * 64)
 
 _GLOBAL(create_hpte)
 	/* Convert linux-style PTE (r5) to low word of PPC-style PTE (r8) */
-	rlwinm	r8,r5,32-9,30,30	/* _PAGE_RW -> PP msb */
 	rlwinm	r0,r5,32-6,30,30	/* _PAGE_DIRTY -> PP msb */
-	and	r8,r8,r0		/* writable if _RW & _DIRTY */
-	rlwimi	r5,r5,32-1,30,30	/* _PAGE_USER -> PP msb */
-	rlwimi	r5,r5,32-2,31,31	/* _PAGE_USER -> PP lsb */
+	and	r8,r5,r0		/* writable if _RW & _DIRTY */
+	rlwimi	r5,r5,1,30,30		/* _PAGE_USER -> PP msb */
 	ori	r8,r8,0xe04		/* clear out reserved bits */
 	andc	r8,r5,r8		/* PP = user? (rw&dirty? 1: 3): 0 */
 BEGIN_FTR_SECTION
@@ -566,7 +564,7 @@ _GLOBAL(flush_hash_pages)
 33:	lwarx	r8,0,r5			/* fetch the pte flags word */
 	andi.	r0,r8,_PAGE_HASHPTE
 	beq	8f			/* done if HASHPTE is already clear */
-	rlwinm	r8,r8,0,31,29		/* clear HASHPTE bit */
+	rlwinm	r8,r8,0,~_PAGE_HASHPTE	/* clear HASHPTE bit */
 	stwcx.	r8,0,r5			/* update the pte */
 	bne-	33b
 
-- 
cgit v1.2.3


From 36b78402d97a3b9aeab136feb9b00d8647ec2c20 Mon Sep 17 00:00:00 2001
From: Aneesh Kumar K.V
Date: Fri, 13 Mar 2020 15:18:42 +0530
Subject: powerpc/hash64/devmap: Use H_PAGE_THP_HUGE when setting up huge
 devmap PTE entries

H_PAGE_THP_HUGE is used to differentiate between a THP hugepage and
hugetlb hugepage entries. The difference is WRT how we handle hash
fault on these address. THP address enables MPSS in segments. We want
to manage devmap hugepage entries similar to THP pt entries. Hence use
H_PAGE_THP_HUGE for devmap huge PTE entries.

With current code while handling hash PTE fault, we do set is_thp =
true when finding devmap PTE huge PTE entries.

Current code also does the below sequence we setting up huge devmap
entries.

	entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
	if (pfn_t_devmap(pfn))
		entry = pmd_mkdevmap(entry);

In that case we would find both H_PAGE_THP_HUGE and PAGE_DEVMAP set
for huge devmap PTE entries. This results in false positive error like
below.

  kernel BUG at /home/kvaneesh/src/linux/mm/memory.c:4321!
  Oops: Exception in kernel mode, sig: 5 [#1]
  LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
  Modules linked in:
  CPU: 56 PID: 67996 Comm: t_mmap_dio Not tainted 5.6.0-rc4-59640-g371c804dedbc #128
  ....
  NIP [c00000000044c9e4] __follow_pte_pmd+0x264/0x900
  LR [c0000000005d45f8] dax_writeback_one+0x1a8/0x740
  Call Trace:
    str_spec.74809+0x22ffb4/0x2d116c (unreliable)
    dax_writeback_one+0x1a8/0x740
    dax_writeback_mapping_range+0x26c/0x700
    ext4_dax_writepages+0x150/0x5a0
    do_writepages+0x68/0x180
    __filemap_fdatawrite_range+0x138/0x180
    file_write_and_wait_range+0xa4/0x110
    ext4_sync_file+0x370/0x6e0
    vfs_fsync_range+0x70/0xf0
    sys_msync+0x220/0x2e0
    system_call+0x5c/0x68

This is because our pmd_trans_huge check doesn't exclude _PAGE_DEVMAP.

To make this all consistent, update pmd_mkdevmap to set
H_PAGE_THP_HUGE and pmd_trans_huge check now excludes _PAGE_DEVMAP
correctly.

Fixes: ebd31197931d ("powerpc/mm: Add devmap support for ppc64")
Cc: stable@vger.kernel.org # v4.13+
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200313094842.351830-1-aneesh.kumar@linux.ibm.com
---
 arch/powerpc/include/asm/book3s/64/hash-4k.h  | 6 ++++++
 arch/powerpc/include/asm/book3s/64/hash-64k.h | 8 +++++++-
 arch/powerpc/include/asm/book3s/64/pgtable.h  | 4 +++-
 arch/powerpc/include/asm/book3s/64/radix.h    | 5 +++++
 4 files changed, 21 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 8fd8599c9395..3f9ae3585ab9 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -156,6 +156,12 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
 extern int hash__has_transparent_hugepage(void);
 #endif
 
+static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd)
+{
+	BUG();
+	return pmd;
+}
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index d1d9177d9ebd..0729c034e56f 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -246,7 +246,7 @@ static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
  */
 static inline int hash__pmd_trans_huge(pmd_t pmd)
 {
-	return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE)) ==
+	return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)) ==
 		  (_PAGE_PTE | H_PAGE_THP_HUGE));
 }
 
@@ -272,6 +272,12 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
 				       unsigned long addr, pmd_t *pmdp);
 extern int hash__has_transparent_hugepage(void);
 #endif /*  CONFIG_TRANSPARENT_HUGEPAGE */
+
+static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP));
+}
+
 #endif	/* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 201a69e6a355..368b136517e0 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -1303,7 +1303,9 @@ extern void serialize_against_pte_lookup(struct mm_struct *mm);
 
 static inline pmd_t pmd_mkdevmap(pmd_t pmd)
 {
-	return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
+	if (radix_enabled())
+		return radix__pmd_mkdevmap(pmd);
+	return hash__pmd_mkdevmap(pmd);
 }
 
 static inline int pmd_devmap(pmd_t pmd)
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index d97db3ad9aae..a1c60d5b50af 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -263,6 +263,11 @@ static inline int radix__has_transparent_hugepage(void)
 }
 #endif
 
+static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
+}
+
 extern int __meminit radix__vmemmap_create_mapping(unsigned long start,
 					     unsigned long page_size,
 					     unsigned long phys);
-- 
cgit v1.2.3


From 8645aaa87963439007773ed8862ae6a29ea15eae Mon Sep 17 00:00:00 2001
From: Oliver O'Halloran
Date: Fri, 6 Mar 2020 18:38:59 +1100
Subject: powerpc/eeh: Add sysfs files in late probe

Move creating the EEH specific sysfs files into eeh_add_device_late()
rather than being open-coded all over the place. Calling the function is
generally done immediately after calling eeh_add_device_late() anyway. This
is also a correctness fix since currently the sysfs files will be added
even if the EEH probe happens to fail.

Similarly, on pseries we currently add the sysfs files before calling
eeh_add_device_late(). This is flat-out broken since the sysfs files
require the pci_dev->dev.archdata.edev pointer to be set, and that is done
in eeh_add_device_late().

Reviewed-by: Sam Bobroff <sbobroff@linux.ibm.com>
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200306073904.4737-1-oohall@gmail.com
---
 arch/powerpc/include/asm/eeh.h               |  3 ---
 arch/powerpc/kernel/eeh.c                    | 24 +-----------------------
 arch/powerpc/kernel/of_platform.c            |  3 ---
 arch/powerpc/kernel/pci-common.c             |  3 ---
 arch/powerpc/platforms/powernv/eeh-powernv.c |  1 -
 arch/powerpc/platforms/pseries/eeh_pseries.c |  3 +--
 6 files changed, 2 insertions(+), 35 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 6f9b2a12540a..5a349079057d 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -305,7 +305,6 @@ void eeh_add_device_early(struct pci_dn *);
 void eeh_add_device_tree_early(struct pci_dn *);
 void eeh_add_device_late(struct pci_dev *);
 void eeh_add_device_tree_late(struct pci_bus *);
-void eeh_add_sysfs_files(struct pci_bus *);
 void eeh_remove_device(struct pci_dev *);
 int eeh_unfreeze_pe(struct eeh_pe *pe);
 int eeh_pe_reset_and_recover(struct eeh_pe *pe);
@@ -368,8 +367,6 @@ static inline void eeh_add_device_late(struct pci_dev *dev) { }
 
 static inline void eeh_add_device_tree_late(struct pci_bus *bus) { }
 
-static inline void eeh_add_sysfs_files(struct pci_bus *bus) { }
-
 static inline void eeh_remove_device(struct pci_dev *dev) { }
 
 #define EEH_POSSIBLE_ERROR(val, type) (0)
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 17cb3e9b5697..087891214739 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1210,6 +1210,7 @@ void eeh_add_device_late(struct pci_dev *dev)
 	dev->dev.archdata.edev = edev;
 
 	eeh_addr_cache_insert_dev(dev);
+	eeh_sysfs_add_device(dev);
 }
 
 /**
@@ -1237,29 +1238,6 @@ void eeh_add_device_tree_late(struct pci_bus *bus)
 }
 EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
 
-/**
- * eeh_add_sysfs_files - Add EEH sysfs files for the indicated PCI bus
- * @bus: PCI bus
- *
- * This routine must be used to add EEH sysfs files for PCI
- * devices which are attached to the indicated PCI bus. The PCI bus
- * is added after system boot through hotplug or dlpar.
- */
-void eeh_add_sysfs_files(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		eeh_sysfs_add_device(dev);
-		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-			struct pci_bus *subbus = dev->subordinate;
-			if (subbus)
-				eeh_add_sysfs_files(subbus);
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(eeh_add_sysfs_files);
-
 /**
  * eeh_remove_device - Undo EEH setup for the indicated pci device
  * @dev: pci device to be removed
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index 427fc22f72b6..cb6880092dd7 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -86,9 +86,6 @@ static int of_pci_phb_probe(struct platform_device *dev)
 	/* Add probed PCI devices to the device model */
 	pci_bus_add_devices(phb->bus);
 
-	/* sysfs files should only be added after devices are added */
-	eeh_add_sysfs_files(phb->bus);
-
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index c6c03416a151..3d2b1cf30b80 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1404,9 +1404,6 @@ void pcibios_finish_adding_to_bus(struct pci_bus *bus)
 
 	/* Add new devices to global lists.  Register in proc, sysfs. */
 	pci_bus_add_devices(bus);
-
-	/* sysfs files should only be added after devices are added */
-	eeh_add_sysfs_files(bus);
 }
 EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus);
 
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 6f300ab7f0e9..ef727ecd99cd 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -48,7 +48,6 @@ void pnv_pcibios_bus_add_device(struct pci_dev *pdev)
 	dev_dbg(&pdev->dev, "EEH: Setting up device\n");
 	eeh_add_device_early(pdn);
 	eeh_add_device_late(pdev);
-	eeh_sysfs_add_device(pdev);
 }
 
 static int pnv_eeh_init(void)
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 893ba3f562c4..95bbf9102584 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -68,7 +68,6 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev)
 	}
 #endif
 	eeh_add_device_early(pdn);
-	eeh_add_device_late(pdev);
 #ifdef CONFIG_PCI_IOV
 	if (pdev->is_virtfn) {
 		struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
@@ -78,7 +77,7 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev)
 		eeh_add_to_parent_pe(edev);   /* Add as VF PE type */
 	}
 #endif
-	eeh_sysfs_add_device(pdev);
+	eeh_add_device_late(pdev);
 }
 
 /*
-- 
cgit v1.2.3


From 2d0953f7d5acc53a97d0dbfab8b1827e9897a7e6 Mon Sep 17 00:00:00 2001
From: Oliver O'Halloran
Date: Fri, 6 Mar 2020 18:39:00 +1100
Subject: powerpc/eeh: Remove eeh_add_device_tree_late()

On pseries and PowerNV pcibios_bus_add_device() calls eeh_add_device_late()
so there's no need to do a separate tree traversal to bind the eeh_dev and
pci_dev together setting up the PHB at boot. As a result we can remove
eeh_add_device_tree_late().

Reviewed-by: Sam Bobroff <sbobroff@linux.ibm.com>
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200306073904.4737-2-oohall@gmail.com
---
 arch/powerpc/include/asm/eeh.h    |  3 ---
 arch/powerpc/kernel/eeh.c         | 25 -------------------------
 arch/powerpc/kernel/of_platform.c |  3 ---
 arch/powerpc/kernel/pci-common.c  |  3 ---
 4 files changed, 34 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 5a349079057d..5d1078166417 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -304,7 +304,6 @@ void eeh_addr_cache_init(void);
 void eeh_add_device_early(struct pci_dn *);
 void eeh_add_device_tree_early(struct pci_dn *);
 void eeh_add_device_late(struct pci_dev *);
-void eeh_add_device_tree_late(struct pci_bus *);
 void eeh_remove_device(struct pci_dev *);
 int eeh_unfreeze_pe(struct eeh_pe *pe);
 int eeh_pe_reset_and_recover(struct eeh_pe *pe);
@@ -365,8 +364,6 @@ static inline void eeh_add_device_tree_early(struct pci_dn *pdn) { }
 
 static inline void eeh_add_device_late(struct pci_dev *dev) { }
 
-static inline void eeh_add_device_tree_late(struct pci_bus *bus) { }
-
 static inline void eeh_remove_device(struct pci_dev *dev) { }
 
 #define EEH_POSSIBLE_ERROR(val, type) (0)
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 087891214739..9cb33706ef80 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1213,31 +1213,6 @@ void eeh_add_device_late(struct pci_dev *dev)
 	eeh_sysfs_add_device(dev);
 }
 
-/**
- * eeh_add_device_tree_late - Perform EEH initialization for the indicated PCI bus
- * @bus: PCI bus
- *
- * This routine must be used to perform EEH initialization for PCI
- * devices which are attached to the indicated PCI bus. The PCI bus
- * is added after system boot through hotplug or dlpar.
- */
-void eeh_add_device_tree_late(struct pci_bus *bus)
-{
-	struct pci_dev *dev;
-
-	if (eeh_has_flag(EEH_FORCE_DISABLED))
-		return;
-	list_for_each_entry(dev, &bus->devices, bus_list) {
-		eeh_add_device_late(dev);
-		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-			struct pci_bus *subbus = dev->subordinate;
-			if (subbus)
-				eeh_add_device_tree_late(subbus);
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
-
 /**
  * eeh_remove_device - Undo EEH setup for the indicated pci device
  * @dev: pci device to be removed
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index cb6880092dd7..64edac81c633 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -80,9 +80,6 @@ static int of_pci_phb_probe(struct platform_device *dev)
 	 */
 	pcibios_claim_one_bus(phb->bus);
 
-	/* Finish EEH setup */
-	eeh_add_device_tree_late(phb->bus);
-
 	/* Add probed PCI devices to the device model */
 	pci_bus_add_devices(phb->bus);
 
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 3d2b1cf30b80..8983afa6d62a 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1399,9 +1399,6 @@ void pcibios_finish_adding_to_bus(struct pci_bus *bus)
 			pci_assign_unassigned_bus_resources(bus);
 	}
 
-	/* Fixup EEH */
-	eeh_add_device_tree_late(bus);
-
 	/* Add new devices to global lists.  Register in proc, sysfs. */
 	pci_bus_add_devices(bus);
 }
-- 
cgit v1.2.3


From b6eebb093cad0feb56c717611ee0d2d7c66b4ec7 Mon Sep 17 00:00:00 2001
From: Oliver O'Halloran
Date: Fri, 6 Mar 2020 18:39:03 +1100
Subject: powerpc/eeh: Make early EEH init pseries specific

The eeh_ops->probe() function is called from two different contexts:

1. On pseries, where we set EEH_PROBE_MODE_DEVTREE, it's called in
   eeh_add_device_early() which is supposed to run before we create
   a pci_dev.

2. On PowerNV, where we set EEH_PROBE_MODE_DEV, it's called in
   eeh_device_add_late() which is supposed to run *after* the
   pci_dev is created.

The "early" probe is required because PAPR requires that we perform an RTAS
call to enable EEH support on a device before we start interacting with it
via config space or MMIO. This requirement doesn't exist on PowerNV and
shoehorning two completely separate initialisation paths into a common
interface just results in a convoluted code everywhere.

Additionally the early probe requires the probe function to take an pci_dn
rather than a pci_dev argument. We'd like to make pci_dn a pseries specific
data structure since there's no real requirement for them on PowerNV. To
help both goals move the early probe into the pseries containment zone
so the platform depedence is more explicit.

Reviewed-by: Sam Bobroff <sbobroff@linux.ibm.com>
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200306073904.4737-5-oohall@gmail.com
---
 arch/powerpc/include/asm/eeh.h               | 14 +++---
 arch/powerpc/kernel/eeh.c                    | 46 --------------------
 arch/powerpc/kernel/of_platform.c            |  6 +--
 arch/powerpc/platforms/powernv/eeh-powernv.c |  6 ---
 arch/powerpc/platforms/pseries/eeh_pseries.c | 65 ++++++++++++++++++++++------
 arch/powerpc/platforms/pseries/pci_dlpar.c   |  2 +-
 drivers/pci/hotplug/rpadlpar_core.c          |  2 +-
 drivers/pci/hotplug/rpaphp_core.c            |  2 +-
 drivers/pci/hotplug/rpaphp_pci.c             |  2 +-
 9 files changed, 64 insertions(+), 81 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 5d1078166417..8580238e4852 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -301,8 +301,6 @@ int __exit eeh_ops_unregister(const char *name);
 int eeh_check_failure(const volatile void __iomem *token);
 int eeh_dev_check_failure(struct eeh_dev *edev);
 void eeh_addr_cache_init(void);
-void eeh_add_device_early(struct pci_dn *);
-void eeh_add_device_tree_early(struct pci_dn *);
 void eeh_add_device_late(struct pci_dev *);
 void eeh_remove_device(struct pci_dev *);
 int eeh_unfreeze_pe(struct eeh_pe *pe);
@@ -358,10 +356,6 @@ static inline int eeh_check_failure(const volatile void __iomem *token)
 
 static inline void eeh_addr_cache_init(void) { }
 
-static inline void eeh_add_device_early(struct pci_dn *pdn) { }
-
-static inline void eeh_add_device_tree_early(struct pci_dn *pdn) { }
-
 static inline void eeh_add_device_late(struct pci_dev *dev) { }
 
 static inline void eeh_remove_device(struct pci_dev *dev) { }
@@ -370,6 +364,14 @@ static inline void eeh_remove_device(struct pci_dev *dev) { }
 #define EEH_IO_ERROR_VALUE(size) (-1UL)
 #endif /* CONFIG_EEH */
 
+#if defined(CONFIG_PPC_PSERIES) && defined(CONFIG_EEH)
+void pseries_eeh_init_edev(struct pci_dn *pdn);
+void pseries_eeh_init_edev_recursive(struct pci_dn *pdn);
+#else
+static inline void pseries_eeh_add_device_early(struct pci_dn *pdn) { }
+static inline void pseries_eeh_add_device_tree_early(struct pci_dn *pdn) { }
+#endif
+
 #ifdef CONFIG_PPC64
 /*
  * MMIO read/write operations with EEH support.
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index a9e4ca7b5e09..55d3ef6e5b9c 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1106,52 +1106,6 @@ static int eeh_init(void)
 
 core_initcall_sync(eeh_init);
 
-/**
- * eeh_add_device_early - Enable EEH for the indicated device node
- * @pdn: PCI device node for which to set up EEH
- *
- * This routine must be used to perform EEH initialization for PCI
- * devices that were added after system boot (e.g. hotplug, dlpar).
- * This routine must be called before any i/o is performed to the
- * adapter (inluding any config-space i/o).
- * Whether this actually enables EEH or not for this device depends
- * on the CEC architecture, type of the device, on earlier boot
- * command-line arguments & etc.
- */
-void eeh_add_device_early(struct pci_dn *pdn)
-{
-	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
-
-	if (!edev)
-		return;
-
-	if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE))
-		return;
-
-	eeh_ops->probe(pdn, NULL);
-}
-
-/**
- * eeh_add_device_tree_early - Enable EEH for the indicated device
- * @pdn: PCI device node
- *
- * This routine must be used to perform EEH initialization for the
- * indicated PCI device that was added after system boot (e.g.
- * hotplug, dlpar).
- */
-void eeh_add_device_tree_early(struct pci_dn *pdn)
-{
-	struct pci_dn *n;
-
-	if (!pdn)
-		return;
-
-	list_for_each_entry(n, &pdn->child_list, list)
-		eeh_add_device_tree_early(n);
-	eeh_add_device_early(pdn);
-}
-EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
-
 /**
  * eeh_add_device_late - Perform EEH initialization for the indicated pci device
  * @dev: pci device for which to set up EEH
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index 64edac81c633..71a3f97dc988 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -62,13 +62,9 @@ static int of_pci_phb_probe(struct platform_device *dev)
 	/* Init pci_dn data structures */
 	pci_devs_phb_init_dynamic(phb);
 
-	/* Create EEH devices for the PHB */
+	/* Create EEH PEs for the PHB */
 	eeh_dev_phb_init_dynamic(phb);
 
-	/* Register devices with EEH */
-	if (dev->dev.of_node->child)
-		eeh_add_device_tree_early(PCI_DN(dev->dev.of_node));
-
 	/* Scan the bus */
 	pcibios_scan_phb(phb);
 	if (phb->bus == NULL)
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index ef727ecd99cd..eaa8dfefa124 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -40,13 +40,7 @@ static int eeh_event_irq = -EINVAL;
 
 void pnv_pcibios_bus_add_device(struct pci_dev *pdev)
 {
-	struct pci_dn *pdn = pci_get_pdn(pdev);
-
-	if (!pdn || eeh_has_flag(EEH_FORCE_DISABLED))
-		return;
-
 	dev_dbg(&pdev->dev, "EEH: Setting up device\n");
-	eeh_add_device_early(pdn);
 	eeh_add_device_late(pdev);
 }
 
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 95bbf9102584..1ca7cf0fc0d8 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -67,7 +67,7 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev)
 		pdn->pe_number  =  physfn_pdn->pe_num_map[pdn->vf_index];
 	}
 #endif
-	eeh_add_device_early(pdn);
+	pseries_eeh_init_edev(pdn);
 #ifdef CONFIG_PCI_IOV
 	if (pdev->is_virtfn) {
 		struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
@@ -221,15 +221,16 @@ static int pseries_eeh_find_ecap(struct pci_dn *pdn, int cap)
 }
 
 /**
- * pseries_eeh_probe - EEH probe on the given device
+ * pseries_eeh_init_edev - initialise the eeh_dev and eeh_pe for a pci_dn
+ *
  * @pdn: PCI device node
- * @data: Unused
  *
- * When EEH module is installed during system boot, all PCI devices
- * are checked one by one to see if it supports EEH. The function
- * is introduced for the purpose.
+ * When we discover a new PCI device via the device-tree we create a
+ * corresponding pci_dn and we allocate, but don't initialise, an eeh_dev.
+ * This function takes care of the initialisation and inserts the eeh_dev
+ * into the correct eeh_pe. If no eeh_pe exists we'll allocate one.
  */
-static void *pseries_eeh_probe(struct pci_dn *pdn, void *data)
+void pseries_eeh_init_edev(struct pci_dn *pdn)
 {
 	struct eeh_dev *edev;
 	struct eeh_pe pe;
@@ -237,18 +238,35 @@ static void *pseries_eeh_probe(struct pci_dn *pdn, void *data)
 	int enable = 0;
 	int ret;
 
-	/* Retrieve OF node and eeh device */
+	if (WARN_ON_ONCE(!eeh_has_flag(EEH_PROBE_MODE_DEVTREE)))
+		return;
+
+	/*
+	 * Find the eeh_dev for this pdn. The storage for the eeh_dev was
+	 * allocated at the same time as the pci_dn.
+	 *
+	 * XXX: We should probably re-visit that.
+	 */
 	edev = pdn_to_eeh_dev(pdn);
-	if (!edev || edev->pe)
-		return NULL;
+	if (!edev)
+		return;
+
+	/*
+	 * If ->pe is set then we've already probed this device. We hit
+	 * this path when a pci_dev is removed and rescanned while recovering
+	 * a PE (i.e. for devices where the driver doesn't support error
+	 * recovery).
+	 */
+	if (edev->pe)
+		return;
 
 	/* Check class/vendor/device IDs */
 	if (!pdn->vendor_id || !pdn->device_id || !pdn->class_code)
-		return NULL;
+		return;
 
 	/* Skip for PCI-ISA bridge */
         if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA)
-		return NULL;
+		return;
 
 	eeh_edev_dbg(edev, "Probing device\n");
 
@@ -315,9 +333,29 @@ static void *pseries_eeh_probe(struct pci_dn *pdn, void *data)
 
 	/* Save memory bars */
 	eeh_save_bars(edev);
+}
+
+/**
+ * pseries_eeh_init_edev_recursive - Enable EEH for the indicated device
+ * @pdn: PCI device node
+ *
+ * This routine must be used to perform EEH initialization for the
+ * indicated PCI device that was added after system boot (e.g.
+ * hotplug, dlpar).
+ */
+void pseries_eeh_init_edev_recursive(struct pci_dn *pdn)
+{
+	struct pci_dn *n;
+
+	if (!pdn)
+		return;
+
+	list_for_each_entry(n, &pdn->child_list, list)
+		pseries_eeh_init_edev_recursive(n);
 
-	return NULL;
+	pseries_eeh_init_edev(pdn);
 }
+EXPORT_SYMBOL_GPL(pseries_eeh_init_edev_recursive);
 
 /**
  * pseries_eeh_set_option - Initialize EEH or MMIO/DMA reenable
@@ -775,7 +813,6 @@ static int pseries_notify_resume(struct pci_dn *pdn)
 static struct eeh_ops pseries_eeh_ops = {
 	.name			= "pseries",
 	.init			= pseries_eeh_init,
-	.probe			= pseries_eeh_probe,
 	.set_option		= pseries_eeh_set_option,
 	.get_pe_addr		= pseries_eeh_get_pe_addr,
 	.get_state		= pseries_eeh_get_state,
diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 361986e4354e..b3a38f5a6b68 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -37,7 +37,7 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn)
 	eeh_dev_phb_init_dynamic(phb);
 
 	if (dn->child)
-		eeh_add_device_tree_early(PCI_DN(dn));
+		pseries_eeh_init_edev_recursive(PCI_DN(dn));
 
 	pcibios_scan_phb(phb);
 	pcibios_finish_adding_to_bus(phb->bus);
diff --git a/drivers/pci/hotplug/rpadlpar_core.c b/drivers/pci/hotplug/rpadlpar_core.c
index 977946e4e613..c5eb509c72f0 100644
--- a/drivers/pci/hotplug/rpadlpar_core.c
+++ b/drivers/pci/hotplug/rpadlpar_core.c
@@ -140,7 +140,7 @@ static void dlpar_pci_add_bus(struct device_node *dn)
 	struct pci_controller *phb = pdn->phb;
 	struct pci_dev *dev = NULL;
 
-	eeh_add_device_tree_early(pdn);
+	pseries_eeh_init_edev_recursive(pdn);
 
 	/* Add EADS device to PHB bus, adding new entry to bus->devices */
 	dev = of_create_pci_dev(dn, phb->bus, pdn->devfn);
diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c
index 392a936c17de..6504869efabc 100644
--- a/drivers/pci/hotplug/rpaphp_core.c
+++ b/drivers/pci/hotplug/rpaphp_core.c
@@ -493,7 +493,7 @@ static int enable_slot(struct hotplug_slot *hotplug_slot)
 		return retval;
 
 	if (state == PRESENT) {
-		eeh_add_device_tree_early(PCI_DN(slot->dn));
+		pseries_eeh_init_edev_recursive(PCI_DN(slot->dn));
 
 		pci_lock_rescan_remove();
 		pci_hp_add_devices(slot->bus);
diff --git a/drivers/pci/hotplug/rpaphp_pci.c b/drivers/pci/hotplug/rpaphp_pci.c
index 61ebbd832afb..c380bdacd146 100644
--- a/drivers/pci/hotplug/rpaphp_pci.c
+++ b/drivers/pci/hotplug/rpaphp_pci.c
@@ -96,7 +96,7 @@ int rpaphp_enable_slot(struct slot *slot)
 		}
 
 		if (list_empty(&bus->devices)) {
-			eeh_add_device_tree_early(PCI_DN(slot->dn));
+			pseries_eeh_init_edev_recursive(PCI_DN(slot->dn));
 			pci_hp_add_devices(bus);
 		}
 
-- 
cgit v1.2.3


From e86350f70a02e5b4e26b0eccedb575a7490bc834 Mon Sep 17 00:00:00 2001
From: Oliver O'Halloran
Date: Fri, 6 Mar 2020 18:39:04 +1100
Subject: powerpc/eeh: Rework eeh_ops->probe()

With the EEH early probe now being pseries specific there's no need for
eeh_ops->probe() to take a pci_dn. Instead, we can make it take a pci_dev
and use the probe function to map a pci_dev to an eeh_dev. This allows
the platform to implement it's own method for finding (or creating) an
eeh_dev for a given pci_dev which also removes a use of pci_dn in
generic EEH code.

This patch also renames eeh_device_add_late() to eeh_device_probe(). This
better reflects what it does does and removes the last vestiges of the
early/late EEH probe split.

Reviewed-by: Sam Bobroff <sbobroff@linux.ibm.com>
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200306073904.4737-6-oohall@gmail.com
---
 arch/powerpc/include/asm/eeh.h               |  6 ++--
 arch/powerpc/kernel/eeh.c                    | 44 +++++++++++++++-------------
 arch/powerpc/platforms/powernv/eeh-powernv.c | 30 +++++++++----------
 arch/powerpc/platforms/pseries/eeh_pseries.c | 23 ++++++++++++++-
 4 files changed, 62 insertions(+), 41 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 8580238e4852..964a54292b36 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -215,7 +215,7 @@ enum {
 struct eeh_ops {
 	char *name;
 	int (*init)(void);
-	void* (*probe)(struct pci_dn *pdn, void *data);
+	struct eeh_dev *(*probe)(struct pci_dev *pdev);
 	int (*set_option)(struct eeh_pe *pe, int option);
 	int (*get_pe_addr)(struct eeh_pe *pe);
 	int (*get_state)(struct eeh_pe *pe, int *delay);
@@ -301,7 +301,7 @@ int __exit eeh_ops_unregister(const char *name);
 int eeh_check_failure(const volatile void __iomem *token);
 int eeh_dev_check_failure(struct eeh_dev *edev);
 void eeh_addr_cache_init(void);
-void eeh_add_device_late(struct pci_dev *);
+void eeh_probe_device(struct pci_dev *pdev);
 void eeh_remove_device(struct pci_dev *);
 int eeh_unfreeze_pe(struct eeh_pe *pe);
 int eeh_pe_reset_and_recover(struct eeh_pe *pe);
@@ -356,7 +356,7 @@ static inline int eeh_check_failure(const volatile void __iomem *token)
 
 static inline void eeh_addr_cache_init(void) { }
 
-static inline void eeh_add_device_late(struct pci_dev *dev) { }
+static inline void eeh_probe_device(struct pci_dev *dev) { }
 
 static inline void eeh_remove_device(struct pci_dev *dev) { }
 
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 55d3ef6e5b9c..7cdcb413bb44 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -1107,35 +1107,43 @@ static int eeh_init(void)
 core_initcall_sync(eeh_init);
 
 /**
- * eeh_add_device_late - Perform EEH initialization for the indicated pci device
+ * eeh_probe_device() - Perform EEH initialization for the indicated pci device
  * @dev: pci device for which to set up EEH
  *
  * This routine must be used to complete EEH initialization for PCI
  * devices that were added after system boot (e.g. hotplug, dlpar).
  */
-void eeh_add_device_late(struct pci_dev *dev)
+void eeh_probe_device(struct pci_dev *dev)
 {
-	struct pci_dn *pdn;
 	struct eeh_dev *edev;
 
-	if (!dev)
+	pr_debug("EEH: Adding device %s\n", pci_name(dev));
+
+	/*
+	 * pci_dev_to_eeh_dev() can only work if eeh_probe_dev() was
+	 * already called for this device.
+	 */
+	if (WARN_ON_ONCE(pci_dev_to_eeh_dev(dev))) {
+		pci_dbg(dev, "Already bound to an eeh_dev!\n");
 		return;
+	}
 
-	pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
-	edev = pdn_to_eeh_dev(pdn);
-	eeh_edev_dbg(edev, "Adding device\n");
-	if (edev->pdev == dev) {
-		eeh_edev_dbg(edev, "Device already referenced!\n");
+	edev = eeh_ops->probe(dev);
+	if (!edev) {
+		pr_debug("EEH: Adding device failed\n");
 		return;
 	}
 
 	/*
-	 * The EEH cache might not be removed correctly because of
-	 * unbalanced kref to the device during unplug time, which
-	 * relies on pcibios_release_device(). So we have to remove
-	 * that here explicitly.
+	 * FIXME: We rely on pcibios_release_device() to remove the
+	 * existing EEH state. The release function is only called if
+	 * the pci_dev's refcount drops to zero so if something is
+	 * keeping a ref to a device (e.g. a filesystem) we need to
+	 * remove the old EEH state.
+	 *
+	 * FIXME: HEY MA, LOOK AT ME, NO LOCKING!
 	 */
-	if (edev->pdev) {
+	if (edev->pdev && edev->pdev != dev) {
 		eeh_rmv_from_parent_pe(edev);
 		eeh_addr_cache_rmv_dev(edev->pdev);
 		eeh_sysfs_remove_device(edev->pdev);
@@ -1146,17 +1154,11 @@ void eeh_add_device_late(struct pci_dev *dev)
 		 * into error handler afterwards.
 		 */
 		edev->mode |= EEH_DEV_NO_HANDLER;
-
-		edev->pdev = NULL;
-		dev->dev.archdata.edev = NULL;
 	}
 
-	if (eeh_has_flag(EEH_PROBE_MODE_DEV))
-		eeh_ops->probe(pdn, NULL);
-
+	/* bind the pdev and the edev together */
 	edev->pdev = dev;
 	dev->dev.archdata.edev = edev;
-
 	eeh_addr_cache_insert_dev(dev);
 	eeh_sysfs_add_device(dev);
 }
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index eaa8dfefa124..79409e005fcd 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -41,7 +41,7 @@ static int eeh_event_irq = -EINVAL;
 void pnv_pcibios_bus_add_device(struct pci_dev *pdev)
 {
 	dev_dbg(&pdev->dev, "EEH: Setting up device\n");
-	eeh_add_device_late(pdev);
+	eeh_probe_device(pdev);
 }
 
 static int pnv_eeh_init(void)
@@ -340,23 +340,13 @@ static int pnv_eeh_find_ecap(struct pci_dn *pdn, int cap)
 
 /**
  * pnv_eeh_probe - Do probe on PCI device
- * @pdn: PCI device node
- * @data: unused
+ * @pdev: pci_dev to probe
  *
- * When EEH module is installed during system boot, all PCI devices
- * are checked one by one to see if it supports EEH. The function
- * is introduced for the purpose. By default, EEH has been enabled
- * on all PCI devices. That's to say, we only need do necessary
- * initialization on the corresponding eeh device and create PE
- * accordingly.
- *
- * It's notable that's unsafe to retrieve the EEH device through
- * the corresponding PCI device. During the PCI device hotplug, which
- * was possiblly triggered by EEH core, the binding between EEH device
- * and the PCI device isn't built yet.
+ * Create, or find the existing, eeh_dev for this pci_dev.
  */
-static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
+static struct eeh_dev *pnv_eeh_probe(struct pci_dev *pdev)
 {
+	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct pci_controller *hose = pdn->phb;
 	struct pnv_phb *phb = hose->private_data;
 	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
@@ -373,6 +363,14 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
 	if (!edev || edev->pe)
 		return NULL;
 
+	/* already configured? */
+	if (edev->pdev) {
+		pr_debug("%s: found existing edev for %04x:%02x:%02x.%01x\n",
+			__func__, hose->global_number, config_addr >> 8,
+			PCI_SLOT(config_addr), PCI_FUNC(config_addr));
+		return edev;
+	}
+
 	/* Skip for PCI-ISA bridge */
 	if ((pdn->class_code >> 8) == PCI_CLASS_BRIDGE_ISA)
 		return NULL;
@@ -464,7 +462,7 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
 
 	eeh_edev_dbg(edev, "EEH enabled on device\n");
 
-	return NULL;
+	return edev;
 }
 
 /**
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 1ca7cf0fc0d8..845342814edc 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -77,7 +77,7 @@ void pseries_pcibios_bus_add_device(struct pci_dev *pdev)
 		eeh_add_to_parent_pe(edev);   /* Add as VF PE type */
 	}
 #endif
-	eeh_add_device_late(pdev);
+	eeh_probe_device(pdev);
 }
 
 /*
@@ -335,6 +335,26 @@ void pseries_eeh_init_edev(struct pci_dn *pdn)
 	eeh_save_bars(edev);
 }
 
+static struct eeh_dev *pseries_eeh_probe(struct pci_dev *pdev)
+{
+	struct eeh_dev *edev;
+	struct pci_dn *pdn;
+
+	pdn = pci_get_pdn_by_devfn(pdev->bus, pdev->devfn);
+	if (!pdn)
+		return NULL;
+
+	/*
+	 * If the system supports EEH on this device then the eeh_dev was
+	 * configured and inserted into a PE in pseries_eeh_init_edev()
+	 */
+	edev = pdn_to_eeh_dev(pdn);
+	if (!edev || !edev->pe)
+		return NULL;
+
+	return edev;
+}
+
 /**
  * pseries_eeh_init_edev_recursive - Enable EEH for the indicated device
  * @pdn: PCI device node
@@ -813,6 +833,7 @@ static int pseries_notify_resume(struct pci_dn *pdn)
 static struct eeh_ops pseries_eeh_ops = {
 	.name			= "pseries",
 	.init			= pseries_eeh_init,
+	.probe			= pseries_eeh_probe,
 	.set_option		= pseries_eeh_set_option,
 	.get_pe_addr		= pseries_eeh_get_pe_addr,
 	.get_state		= pseries_eeh_get_state,
-- 
cgit v1.2.3


From a7032637b54186e5649917679727d7feaec932b1 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers
Date: Mon, 12 Aug 2019 14:50:43 -0700
Subject: powerpc: Prefer __section and __printf from compiler_attributes.h

Reported-by: Sedat Dilek <sedat.dilek@gmail.com>
Suggested-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
[mpe: Drop changes to a/p/boot which doesn't use linux headers]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20190812215052.71840-10-ndesaulniers@google.com
---
 arch/powerpc/include/asm/cache.h | 2 +-
 arch/powerpc/kernel/btext.c      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/cache.h b/arch/powerpc/include/asm/cache.h
index 72b81015cebe..609cab1d58f2 100644
--- a/arch/powerpc/include/asm/cache.h
+++ b/arch/powerpc/include/asm/cache.h
@@ -97,7 +97,7 @@ static inline u32 l1_icache_bytes(void)
 
 #endif
 
-#define __read_mostly __attribute__((__section__(".data..read_mostly")))
+#define __read_mostly __section(.data..read_mostly)
 
 #ifdef CONFIG_PPC_BOOK3S_32
 extern long _get_L2CR(void);
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index 6dfceaa820e4..f57712a55815 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -26,7 +26,7 @@
 static void scrollscreen(void);
 #endif
 
-#define __force_data __attribute__((__section__(".data")))
+#define __force_data __section(.data)
 
 static int g_loc_X __force_data;
 static int g_loc_Y __force_data;
-- 
cgit v1.2.3


From efbc4303b255bb80ab1283794b36dd5fe1fb0ec3 Mon Sep 17 00:00:00 2001
From: Ganesh Goudar
Date: Fri, 27 Mar 2020 00:19:16 +0530
Subject: powerpc/pseries: Handle UE event for memcpy_mcsafe

memcpy_mcsafe has been implemented for power machines which is used
by pmem infrastructure, so that an UE encountered during memcpy from
pmem devices would not result in panic instead a right error code
is returned. The implementation expects machine check handler to ignore
the event and set nip to continue the execution from fixup code.

Appropriate changes are already made to powernv machine check handler,
make similar changes to pseries machine check handler to ignore the
the event and set nip to continue execution at the fixup entry if we
hit UE at an instruction with a fixup entry.

while we are at it, have a common function which searches the exception
table entry and updates nip with fixup address, and any future common
changes can be made in this function that are valid for both architectures.

powernv changes are made by
commit 895e3dceeb97 ("powerpc/mce: Handle UE event for memcpy_mcsafe")

Reviewed-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Reviewed-by: Santosh S <santosh@fossix.org>
Signed-off-by: Ganesh Goudar <ganeshgr@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200326184916.31172-1-ganeshgr@linux.ibm.com
---
 arch/powerpc/include/asm/mce.h       |  2 ++
 arch/powerpc/kernel/mce.c            | 14 ++++++++++++++
 arch/powerpc/kernel/mce_power.c      |  8 ++------
 arch/powerpc/platforms/pseries/ras.c |  3 +++
 4 files changed, 21 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index 6a6ddaabdb34..376a395daf32 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -218,6 +218,8 @@ extern void machine_check_queue_event(void);
 extern void machine_check_print_event_info(struct machine_check_event *evt,
 					   bool user_mode, bool in_guest);
 unsigned long addr_to_pfn(struct pt_regs *regs, unsigned long addr);
+extern void mce_common_process_ue(struct pt_regs *regs,
+				  struct mce_error_info *mce_err);
 #ifdef CONFIG_PPC_BOOK3S_64
 void flush_and_reload_slb(void);
 #endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index 34c1001e9e8b..8077b5fb18a7 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -15,6 +15,7 @@
 #include <linux/percpu.h>
 #include <linux/export.h>
 #include <linux/irq_work.h>
+#include <linux/extable.h>
 
 #include <asm/machdep.h>
 #include <asm/mce.h>
@@ -251,6 +252,19 @@ void machine_check_queue_event(void)
 	/* Queue irq work to process this event later. */
 	irq_work_queue(&mce_event_process_work);
 }
+
+void mce_common_process_ue(struct pt_regs *regs,
+			   struct mce_error_info *mce_err)
+{
+	const struct exception_table_entry *entry;
+
+	entry = search_kernel_exception_table(regs->nip);
+	if (entry) {
+		mce_err->ignore_event = true;
+		regs->nip = extable_fixup(entry);
+	}
+}
+
 /*
  * process pending MCE event from the mce event queue. This function will be
  * called during syscall exit.
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index 1cbf7f1a4e3d..067b094bfeff 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -579,14 +579,10 @@ static long mce_handle_ue_error(struct pt_regs *regs,
 				struct mce_error_info *mce_err)
 {
 	long handled = 0;
-	const struct exception_table_entry *entry;
 
-	entry = search_kernel_exception_table(regs->nip);
-	if (entry) {
-		mce_err->ignore_event = true;
-		regs->nip = extable_fixup(entry);
+	mce_common_process_ue(regs, mce_err);
+	if (mce_err->ignore_event)
 		return 1;
-	}
 
 	/*
 	 * On specific SCOM read via MMIO we may get a machine check
diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c
index 1d7f973c647b..aa6208c8d4f0 100644
--- a/arch/powerpc/platforms/pseries/ras.c
+++ b/arch/powerpc/platforms/pseries/ras.c
@@ -558,6 +558,9 @@ static int mce_handle_error(struct pt_regs *regs, struct rtas_error_log *errp)
 	switch (mce_log->error_type) {
 	case MC_ERROR_TYPE_UE:
 		mce_err.error_type = MCE_ERROR_TYPE_UE;
+		mce_common_process_ue(regs, &mce_err);
+		if (mce_err.ignore_event)
+			disposition = RTAS_DISP_FULLY_RECOVERED;
 		switch (err_sub_type) {
 		case MC_ERROR_UE_IFETCH:
 			mce_err.u.ue_error_type = MCE_UE_ERROR_IFETCH;
-- 
cgit v1.2.3


From 233ba5461838a56c19600216f0919e7cd3aec40e Mon Sep 17 00:00:00 2001
From: Aneesh Kumar K.V
Date: Fri, 20 Mar 2020 16:02:42 +0530
Subject: powerpc/64: Avoid isync in flush_dcache_range()

As per ISA an isync is only needed on instruction cache block
invalidate. Remove the same from dcache invalidate.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200320103242.229223-1-aneesh.kumar@linux.ibm.com
---
 arch/powerpc/include/asm/cacheflush.h | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index 4a1c9f0200e1..e92191b390f3 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -65,17 +65,13 @@ static inline void flush_dcache_range(unsigned long start, unsigned long stop)
 	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
 	unsigned long i;
 
-	if (IS_ENABLED(CONFIG_PPC64)) {
+	if (IS_ENABLED(CONFIG_PPC64))
 		mb();	/* sync */
-		isync();
-	}
 
 	for (i = 0; i < size >> shift; i++, addr += bytes)
 		dcbf(addr);
 	mb();	/* sync */
 
-	if (IS_ENABLED(CONFIG_PPC64))
-		isync();
 }
 
 /*
-- 
cgit v1.2.3


From 8729c26e675c356de4179d587af6cd1f16147a39 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin
Date: Wed, 26 Feb 2020 03:35:19 +1000
Subject: powerpc/64s/exception: Move real to virt switch into the common
 handler

The real mode interrupt entry points currently use rfid to branch to
the common handler in virtual mode. This is a significant amount of
code, and forces other code (notably the KVM test) to live in the
real mode handler.

In the interest of minimising the amount of code that runs unrelocated
move the switch to virt mode into the common code, and do it with
mtmsrd, which avoids clobbering SRRs (although the post-KVMTEST
performance of real-mode interrupt handlers is not a big concern these
days).

This requires CTR to always be saved (real-mode needs to reach 0xc...)
but that's not a huge impact these days. It could be optimized away in
future.

mpe: Incorporate fix from Nick:

It's possible for interrupts to be replayed when TM is enabled and
suspended, for example rt_sigreturn, where the mtmsrd MSR_KERNEL in
the real-mode entry point to the common handler causes a TM Bad Thing
exception (due to attempting to clear suspended).

The fix for this is to have replay interrupts go to the _virt entry
point and skip the mtmsrd, which matches what happens before this
patch.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200225173541.1549955-11-npiggin@gmail.com
---
 arch/powerpc/include/asm/exception-64s.h |   4 -
 arch/powerpc/kernel/exceptions-64s.S     | 265 ++++++++++++++-----------------
 2 files changed, 116 insertions(+), 153 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 33f4f72eb035..47bd4ea0837d 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -33,11 +33,7 @@
 #include <asm/feature-fixups.h>
 
 /* PACA save area size in u64 units (exgen, exmc, etc) */
-#if defined(CONFIG_RELOCATABLE)
 #define EX_SIZE		10
-#else
-#define EX_SIZE		9
-#endif
 
 /*
  * maximum recursive depth of MCE exceptions
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4eb099046f9d..42fced32c8af 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -32,16 +32,10 @@
 #define EX_CCR		52
 #define EX_CFAR		56
 #define EX_PPR		64
-#if defined(CONFIG_RELOCATABLE)
 #define EX_CTR		72
 .if EX_SIZE != 10
 	.error "EX_SIZE is wrong"
 .endif
-#else
-.if EX_SIZE != 9
-	.error "EX_SIZE is wrong"
-.endif
-#endif
 
 /*
  * Following are fixed section helper macros.
@@ -124,22 +118,6 @@ name:
 #define EXC_HV		1
 #define EXC_STD		0
 
-#if defined(CONFIG_RELOCATABLE)
-/*
- * If we support interrupts with relocation on AND we're a relocatable kernel,
- * we need to use CTR to get to the 2nd level handler.  So, save/restore it
- * when required.
- */
-#define SAVE_CTR(reg, area)	mfctr	reg ; 	std	reg,area+EX_CTR(r13)
-#define GET_CTR(reg, area) 			ld	reg,area+EX_CTR(r13)
-#define RESTORE_CTR(reg, area)	ld	reg,area+EX_CTR(r13) ; mtctr reg
-#else
-/* ...else CTR is unused and in register. */
-#define SAVE_CTR(reg, area)
-#define GET_CTR(reg, area) 	mfctr	reg
-#define RESTORE_CTR(reg, area)
-#endif
-
 /*
  * PPR save/restore macros used in exceptions-64s.S
  * Used for P7 or later processors
@@ -199,6 +177,7 @@ END_FTR_SECTION_NESTED(ftr,ftr,943)
 #define IVEC		.L_IVEC_\name\()
 #define IHSRR		.L_IHSRR_\name\()
 #define IAREA		.L_IAREA_\name\()
+#define IVIRT		.L_IVIRT_\name\()
 #define IISIDE		.L_IISIDE_\name\()
 #define IDAR		.L_IDAR_\name\()
 #define IDSISR		.L_IDSISR_\name\()
@@ -232,6 +211,9 @@ do_define_int n
 	.ifndef IAREA
 		IAREA=PACA_EXGEN
 	.endif
+	.ifndef IVIRT
+		IVIRT=1
+	.endif
 	.ifndef IISIDE
 		IISIDE=0
 	.endif
@@ -325,7 +307,7 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948)
 	 * outside the head section. CONFIG_RELOCATABLE KVM expects CTR
 	 * to be saved in HSTATE_SCRATCH1.
 	 */
-	mfctr	r9
+	ld	r9,IAREA+EX_CTR(r13)
 	std	r9,HSTATE_SCRATCH1(r13)
 	__LOAD_FAR_HANDLER(r9, kvmppc_interrupt)
 	mtctr	r9
@@ -362,101 +344,6 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948)
 .endm
 #endif
 
-.macro INT_SAVE_SRR_AND_JUMP label, hsrr, set_ri
-	ld	r10,PACAKMSR(r13)	/* get MSR value for kernel */
-	.if ! \set_ri
-	xori	r10,r10,MSR_RI		/* Clear MSR_RI */
-	.endif
-	.if \hsrr == EXC_HV_OR_STD
-	BEGIN_FTR_SECTION
-	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
-	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
-	mtspr	SPRN_HSRR1,r10
-	FTR_SECTION_ELSE
-	mfspr	r11,SPRN_SRR0		/* save SRR0 */
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-	mtspr	SPRN_SRR1,r10
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-	.elseif \hsrr
-	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
-	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
-	mtspr	SPRN_HSRR1,r10
-	.else
-	mfspr	r11,SPRN_SRR0		/* save SRR0 */
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-	mtspr	SPRN_SRR1,r10
-	.endif
-	LOAD_HANDLER(r10, \label\())
-	.if \hsrr == EXC_HV_OR_STD
-	BEGIN_FTR_SECTION
-	mtspr	SPRN_HSRR0,r10
-	HRFI_TO_KERNEL
-	FTR_SECTION_ELSE
-	mtspr	SPRN_SRR0,r10
-	RFI_TO_KERNEL
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-	.elseif \hsrr
-	mtspr	SPRN_HSRR0,r10
-	HRFI_TO_KERNEL
-	.else
-	mtspr	SPRN_SRR0,r10
-	RFI_TO_KERNEL
-	.endif
-	b	.	/* prevent speculative execution */
-.endm
-
-/* INT_SAVE_SRR_AND_JUMP works for real or virt, this is faster but virt only */
-.macro INT_VIRT_SAVE_SRR_AND_JUMP label, hsrr
-#ifdef CONFIG_RELOCATABLE
-	.if \hsrr == EXC_HV_OR_STD
-	BEGIN_FTR_SECTION
-	mfspr	r11,SPRN_HSRR0	/* save HSRR0 */
-	FTR_SECTION_ELSE
-	mfspr	r11,SPRN_SRR0	/* save SRR0 */
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-	.elseif \hsrr
-	mfspr	r11,SPRN_HSRR0	/* save HSRR0 */
-	.else
-	mfspr	r11,SPRN_SRR0	/* save SRR0 */
-	.endif
-	LOAD_HANDLER(r12, \label\())
-	mtctr	r12
-	.if \hsrr == EXC_HV_OR_STD
-	BEGIN_FTR_SECTION
-	mfspr	r12,SPRN_HSRR1	/* and HSRR1 */
-	FTR_SECTION_ELSE
-	mfspr	r12,SPRN_SRR1	/* and HSRR1 */
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-	.elseif \hsrr
-	mfspr	r12,SPRN_HSRR1	/* and HSRR1 */
-	.else
-	mfspr	r12,SPRN_SRR1	/* and HSRR1 */
-	.endif
-	li	r10,MSR_RI
-	mtmsrd 	r10,1		/* Set RI (EE=0) */
-	bctr
-#else
-	.if \hsrr == EXC_HV_OR_STD
-	BEGIN_FTR_SECTION
-	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
-	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
-	FTR_SECTION_ELSE
-	mfspr	r11,SPRN_SRR0		/* save SRR0 */
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
-	.elseif \hsrr
-	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
-	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
-	.else
-	mfspr	r11,SPRN_SRR0		/* save SRR0 */
-	mfspr	r12,SPRN_SRR1		/* and SRR1 */
-	.endif
-	li	r10,MSR_RI
-	mtmsrd 	r10,1			/* Set RI (EE=0) */
-	b	\label
-#endif
-.endm
-
 /*
  * This is the BOOK3S interrupt entry code macro.
  *
@@ -477,6 +364,23 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948)
  * - Fall through and continue executing in real, unrelocated mode.
  *   This is done if early=2.
  */
+
+.macro GEN_BRANCH_TO_COMMON name, virt
+	.if \virt
+#ifndef CONFIG_RELOCATABLE
+	b	\name\()_common_virt
+#else
+	LOAD_HANDLER(r10, \name\()_common_virt)
+	mtctr	r10
+	bctr
+#endif
+	.else
+	LOAD_HANDLER(r10, \name\()_common_real)
+	mtctr	r10
+	bctr
+	.endif
+.endm
+
 .macro GEN_INT_ENTRY name, virt, ool=0
 	SET_SCRATCH0(r13)			/* save r13 */
 	GET_PACA(r13)
@@ -500,8 +404,10 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948)
 	OPT_SAVE_REG_TO_PACA(IAREA+EX_PPR, r9, CPU_FTR_HAS_PPR)
 	OPT_SAVE_REG_TO_PACA(IAREA+EX_CFAR, r10, CPU_FTR_CFAR)
 	INTERRUPT_TO_KERNEL
-	SAVE_CTR(r10, IAREA)
+	mfctr	r10
+	std	r10,IAREA+EX_CTR(r13)
 	mfcr	r9
+
 	.if (!\virt && IKVM_REAL) || (\virt && IKVM_VIRT)
 		KVMTEST \name IHSRR IVEC
 	.endif
@@ -566,27 +472,58 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948)
 	.if IEARLY == 2
 	/* nothing more */
 	.elseif IEARLY
-	mfctr	r10			/* save ctr, even for !RELOCATABLE */
 	BRANCH_TO_C000(r11, \name\()_common)
-	.elseif !\virt
-	INT_SAVE_SRR_AND_JUMP \name\()_common, IHSRR, ISET_RI
 	.else
-	INT_VIRT_SAVE_SRR_AND_JUMP \name\()_common, IHSRR
+	.if IHSRR == EXC_HV_OR_STD
+	BEGIN_FTR_SECTION
+	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
+	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
+	FTR_SECTION_ELSE
+	mfspr	r11,SPRN_SRR0		/* save SRR0 */
+	mfspr	r12,SPRN_SRR1		/* and SRR1 */
+	ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+	.elseif IHSRR
+	mfspr	r11,SPRN_HSRR0		/* save HSRR0 */
+	mfspr	r12,SPRN_HSRR1		/* and HSRR1 */
+	.else
+	mfspr	r11,SPRN_SRR0		/* save SRR0 */
+	mfspr	r12,SPRN_SRR1		/* and SRR1 */
 	.endif
+	GEN_BRANCH_TO_COMMON \name \virt
+	.endif
+
 	.if \ool
 	.popsection
 	.endif
 .endm
 
 /*
- * On entry r13 points to the paca, r9-r13 are saved in the paca,
- * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and
- * SRR1, and relocation is on.
- *
- * If stack=0, then the stack is already set in r1, and r1 is saved in r10.
- * PPR save and CPU accounting is not done for the !stack case (XXX why not?)
+ * __GEN_COMMON_ENTRY is required to receive the branch from interrupt
+ * entry, except in the case of the IEARLY handlers.
+ * This switches to virtual mode and sets MSR[RI].
  */
-.macro GEN_COMMON name
+.macro __GEN_COMMON_ENTRY name
+DEFINE_FIXED_SYMBOL(\name\()_common_real)
+\name\()_common_real:
+	ld	r10,PACAKMSR(r13)	/* get MSR value for kernel */
+	/* MSR[RI] is clear iff using SRR regs */
+	.if IHSRR == EXC_HV_OR_STD
+	BEGIN_FTR_SECTION
+	xori	r10,r10,MSR_RI
+	END_FTR_SECTION_IFCLR(CPU_FTR_HVMODE)
+	.elseif ! IHSRR
+	xori	r10,r10,MSR_RI
+	.endif
+	mtmsrd	r10
+
+	.if IVIRT
+	.balign IFETCH_ALIGN_BYTES
+DEFINE_FIXED_SYMBOL(\name\()_common_virt)
+\name\()_common_virt:
+	.endif /* IVIRT */
+.endm
+
+.macro __GEN_COMMON_BODY name
 	.if ISTACK
 	andi.	r10,r12,MSR_PR		/* See if coming from user	*/
 	mr	r10,r1			/* Save r1			*/
@@ -604,6 +541,11 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,948)
 	std	r0,GPR0(r1)		/* save r0 in stackframe	*/
 	std	r10,GPR1(r1)		/* save r1 in stackframe	*/
 
+	.if ISET_RI
+	li	r10,MSR_RI
+	mtmsrd	r10,1			/* Set MSR_RI */
+	.endif
+
 	.if ISTACK
 	.if IKUAP
 	kuap_save_amr_and_lock r9, r10, cr1, cr0
@@ -654,7 +596,7 @@ BEGIN_FTR_SECTION_NESTED(66)
 	ld	r10,IAREA+EX_CFAR(r13)
 	std	r10,ORIG_GPR3(r1)
 END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66)
-	GET_CTR(r10, IAREA)
+	ld	r10,IAREA+EX_CTR(r13)
 	std	r10,_CTR(r1)
 	std	r2,GPR2(r1)		/* save r2 in stackframe	*/
 	SAVE_4GPRS(3, r1)		/* save r3 - r6 in stackframe   */
@@ -682,6 +624,19 @@ END_FTR_SECTION_NESTED(CPU_FTR_CFAR, CPU_FTR_CFAR, 66)
 	.endif
 .endm
 
+/*
+ * On entry r13 points to the paca, r9-r13 are saved in the paca,
+ * r9 contains the saved CR, r11 and r12 contain the saved SRR0 and
+ * SRR1, and relocation is on.
+ *
+ * If stack=0, then the stack is already set in r1, and r1 is saved in r10.
+ * PPR save and CPU accounting is not done for the !stack case (XXX why not?)
+ */
+.macro GEN_COMMON name
+	__GEN_COMMON_ENTRY \name
+	__GEN_COMMON_BODY \name
+.endm
+
 /*
  * Restore all registers including H/SRR0/1 saved in a stack frame of a
  * standard exception.
@@ -834,6 +789,7 @@ EXC_VIRT_NONE(0x4000, 0x100)
 INT_DEFINE_BEGIN(system_reset)
 	IVEC=0x100
 	IAREA=PACA_EXNMI
+	IVIRT=0 /* no virt entry point */
 	/*
 	 * MSR_RI is not enabled, because PACA_EXNMI and nmi stack is
 	 * being used, so a nested NMI exception would corrupt it.
@@ -913,6 +869,7 @@ TRAMP_REAL_BEGIN(system_reset_fwnmi)
 #endif /* CONFIG_PPC_PSERIES */
 
 EXC_COMMON_BEGIN(system_reset_common)
+	__GEN_COMMON_ENTRY system_reset
 	/*
 	 * Increment paca->in_nmi then enable MSR_RI. SLB or MCE will be able
 	 * to recover, but nested NMI will notice in_nmi and not recover
@@ -928,7 +885,7 @@ EXC_COMMON_BEGIN(system_reset_common)
 	mr	r10,r1
 	ld	r1,PACA_NMI_EMERG_SP(r13)
 	subi	r1,r1,INT_FRAME_SIZE
-	GEN_COMMON system_reset
+	__GEN_COMMON_BODY system_reset
 	bl	save_nvgprs
 	/*
 	 * Set IRQS_ALL_DISABLED unconditionally so arch_irqs_disabled does
@@ -973,6 +930,7 @@ EXC_COMMON_BEGIN(system_reset_common)
 INT_DEFINE_BEGIN(machine_check_early)
 	IVEC=0x200
 	IAREA=PACA_EXMC
+	IVIRT=0 /* no virt entry point */
 	/*
 	 * MSR_RI is not enabled, because PACA_EXMC is being used, so a
 	 * nested machine check corrupts it. machine_check_common enables
@@ -990,6 +948,7 @@ INT_DEFINE_END(machine_check_early)
 INT_DEFINE_BEGIN(machine_check)
 	IVEC=0x200
 	IAREA=PACA_EXMC
+	IVIRT=0 /* no virt entry point */
 	ISET_RI=0
 	IDAR=1
 	IDSISR=1
@@ -1022,7 +981,6 @@ TRAMP_KVM_BEGIN(machine_check_kvm)
 	EXCEPTION_RESTORE_REGS EXC_STD
 
 EXC_COMMON_BEGIN(machine_check_early_common)
-	mtctr	r10			/* Restore ctr */
 	mfspr	r11,SPRN_SRR0
 	mfspr	r12,SPRN_SRR1
 
@@ -1061,7 +1019,7 @@ EXC_COMMON_BEGIN(machine_check_early_common)
 	bgt	cr1,unrecoverable_mce	/* Check if we hit limit of 4 */
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame */
 
-	GEN_COMMON machine_check_early
+	__GEN_COMMON_BODY machine_check_early
 
 BEGIN_FTR_SECTION
 	bl	enable_machine_check
@@ -1448,6 +1406,8 @@ EXC_VIRT_END(program_check, 0x4700, 0x100)
 TRAMP_KVM_BEGIN(program_check_kvm)
 	GEN_KVM program_check
 EXC_COMMON_BEGIN(program_check_common)
+	__GEN_COMMON_ENTRY program_check
+
 	/*
 	 * It's possible to receive a TM Bad Thing type program check with
 	 * userspace register values (in particular r1), but with SRR1 reporting
@@ -1473,11 +1433,11 @@ EXC_COMMON_BEGIN(program_check_common)
 	ld	r1,PACAEMERGSP(r13)	/* Use emergency stack		*/
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame		*/
 	__ISTACK(program_check)=0
-	GEN_COMMON program_check
+	__GEN_COMMON_BODY program_check
 	b 3f
 2:
 	__ISTACK(program_check)=1
-	GEN_COMMON program_check
+	__GEN_COMMON_BODY program_check
 3:
 	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
@@ -1861,14 +1821,13 @@ TRAMP_KVM_BEGIN(hmi_exception_kvm)
 	GEN_KVM hmi_exception
 
 EXC_COMMON_BEGIN(hmi_exception_early_common)
-	mtctr	r10			/* Restore ctr */
 	mfspr	r11,SPRN_HSRR0		/* Save HSRR0 */
 	mfspr	r12,SPRN_HSRR1		/* Save HSRR1 */
 	mr	r10,r1			/* Save r1 */
 	ld	r1,PACAEMERGSP(r13)	/* Use emergency stack for realmode */
 	subi	r1,r1,INT_FRAME_SIZE	/* alloc stack frame		*/
 
-	GEN_COMMON hmi_exception_early
+	__GEN_COMMON_BODY hmi_exception_early
 
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	hmi_exception_realmode
@@ -2195,7 +2154,9 @@ EXC_REAL_BEGIN(denorm_exception, 0x1500, 0x100)
 	bne+	denorm_assist
 #endif
 	KVMTEST denorm_exception, EXC_HV, 0x1500
-	INT_SAVE_SRR_AND_JUMP denorm_exception_common, EXC_HV, 1
+	mfspr	r11,SPRN_HSRR0
+	mfspr	r12,SPRN_HSRR1
+	GEN_BRANCH_TO_COMMON denorm_exception, virt=0
 EXC_REAL_END(denorm_exception, 0x1500, 0x100)
 #ifdef CONFIG_PPC_DENORMALISATION
 EXC_VIRT_BEGIN(denorm_exception, 0x5500, 0x100)
@@ -2203,7 +2164,9 @@ EXC_VIRT_BEGIN(denorm_exception, 0x5500, 0x100)
 	mfspr	r10,SPRN_HSRR1
 	andis.	r10,r10,(HSRR1_DENORM)@h /* denorm? */
 	bne+	denorm_assist
-	INT_VIRT_SAVE_SRR_AND_JUMP denorm_exception_common, EXC_HV
+	mfspr	r11,SPRN_HSRR0
+	mfspr	r12,SPRN_HSRR1
+	GEN_BRANCH_TO_COMMON denorm_exception, virt=1
 EXC_VIRT_END(denorm_exception, 0x5500, 0x100)
 #else
 EXC_VIRT_NONE(0x5500, 0x100)
@@ -2374,7 +2337,11 @@ EXC_VIRT_NONE(0x5800, 0x100)
 	std	r12,PACA_EXGEN+EX_R12(r13);		\
 	GET_SCRATCH0(r10);				\
 	std	r10,PACA_EXGEN+EX_R13(r13);		\
-	INT_SAVE_SRR_AND_JUMP soft_nmi_common, _H, 1
+	mfspr	r11,SPRN_SRR0;		/* save SRR0 */	\
+	mfspr	r12,SPRN_SRR1;		/* and SRR1 */	\
+	LOAD_HANDLER(r10, soft_nmi_common);		\
+	mtctr	r10;					\
+	bctr
 
 /*
  * Branch to soft_nmi_interrupt using the emergency stack. The emergency
@@ -2390,7 +2357,7 @@ EXC_COMMON_BEGIN(soft_nmi_common)
 	ld	r1,PACAEMERGSP(r13)
 	subi	r1,r1,INT_FRAME_SIZE
 	__ISTACK(decrementer)=0
-	GEN_COMMON decrementer
+	__GEN_COMMON_BODY decrementer
 	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	soft_nmi_interrupt
@@ -2790,12 +2757,12 @@ handle_dabr_fault:
 h_doorbell_common_msgclr:
 	LOAD_REG_IMMEDIATE(r3, PPC_DBELL_MSGTYPE << (63-36))
 	PPC_MSGCLR(3)
-	b 	h_doorbell_common
+	b 	h_doorbell_common_virt
 
 doorbell_super_common_msgclr:
 	LOAD_REG_IMMEDIATE(r3, PPC_DBELL_MSGTYPE << (63-36))
 	PPC_MSGCLRP(3)
-	b 	doorbell_super_common
+	b 	doorbell_super_common_virt
 
 /*
  * Called from arch_local_irq_enable when an interrupt needs
@@ -2821,20 +2788,20 @@ _GLOBAL(__replay_interrupt)
 	mfcr	r9
 	ori	r12,r12,MSR_EE
 	cmpwi	r3,0x900
-	beq	decrementer_common
+	beq	decrementer_common_virt
 	cmpwi	r3,0x500
 BEGIN_FTR_SECTION
-	beq	h_virt_irq_common
+	beq	h_virt_irq_common_virt
 FTR_SECTION_ELSE
-	beq	hardware_interrupt_common
+	beq	hardware_interrupt_common_virt
 ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_300)
 	cmpwi	r3,0xf00
-	beq	performance_monitor_common
+	beq	performance_monitor_common_virt
 BEGIN_FTR_SECTION
 	cmpwi	r3,0xa00
 	beq	h_doorbell_common_msgclr
 	cmpwi	r3,0xe60
-	beq	hmi_exception_common
+	beq	hmi_exception_common_virt
 FTR_SECTION_ELSE
 	cmpwi	r3,0xa00
 	beq	doorbell_super_common_msgclr
-- 
cgit v1.2.3


From 2babd6ea43edacfc1577432baa187a7d212f3f4f Mon Sep 17 00:00:00 2001
From: Nicholas Piggin
Date: Wed, 26 Feb 2020 03:35:25 +1000
Subject: powerpc/64s/exception: Avoid touching the stack in hdecrementer

The hdec interrupt handler is reported to sometimes fire in Linux if
KVM leaves it pending after a guest exists. This is harmless, so there
is a no-op handler for it.

The interrupt handler currently uses the regular kernel stack. Change
this to avoid touching the stack entirely.

This should be the last place where the regular Linux stack can be
accessed with asynchronous interrupts (including PMI) soft-masked.
It might be possible to take advantage of this invariant, e.g., to
context switch the kernel stack SLB entry without clearing MSR[EE].

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200225173541.1549955-17-npiggin@gmail.com
---
 arch/powerpc/include/asm/time.h      |  1 -
 arch/powerpc/kernel/exceptions-64s.S | 25 ++++++++++++++++++++-----
 arch/powerpc/kernel/time.c           |  9 ---------
 3 files changed, 20 insertions(+), 15 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 08dbe3e6831c..e0107495c4de 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -24,7 +24,6 @@ extern struct clock_event_device decrementer_clockevent;
 
 
 extern void generic_calibrate_decr(void);
-extern void hdec_interrupt(struct pt_regs *regs);
 
 /* Some sane defaults: 125 MHz timebase, 1GHz processor */
 extern unsigned long ppc_proc_freq;
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index da15ec4fc8cb..146afa0922fb 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1507,6 +1507,8 @@ EXC_COMMON_BEGIN(decrementer_common)
 INT_DEFINE_BEGIN(hdecrementer)
 	IVEC=0x980
 	IHSRR=EXC_HV
+	ISTACK=0
+	IRECONCILE=0
 	IKVM_REAL=1
 	IKVM_VIRT=1
 INT_DEFINE_END(hdecrementer)
@@ -1518,11 +1520,24 @@ EXC_VIRT_BEGIN(hdecrementer, 0x4980, 0x80)
 	GEN_INT_ENTRY hdecrementer, virt=1
 EXC_VIRT_END(hdecrementer, 0x4980, 0x80)
 EXC_COMMON_BEGIN(hdecrementer_common)
-	GEN_COMMON hdecrementer
-	bl	save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	hdec_interrupt
-	b	ret_from_except
+	__GEN_COMMON_ENTRY hdecrementer
+	/*
+	 * Hypervisor decrementer interrupts not caught by the KVM test
+	 * shouldn't occur but are sometimes left pending on exit from a KVM
+	 * guest.  We don't need to do anything to clear them, as they are
+	 * edge-triggered.
+	 *
+	 * Be careful to avoid touching the kernel stack.
+	 */
+	ld	r10,PACA_EXGEN+EX_CTR(r13)
+	mtctr	r10
+	mtcrf	0x80,r9
+	ld	r9,PACA_EXGEN+EX_R9(r13)
+	ld	r10,PACA_EXGEN+EX_R10(r13)
+	ld	r11,PACA_EXGEN+EX_R11(r13)
+	ld	r12,PACA_EXGEN+EX_R12(r13)
+	ld	r13,PACA_EXGEN+EX_R13(r13)
+	HRFI_TO_KERNEL
 
 	GEN_KVM hdecrementer
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 1168e8b37e30..bda9cb4a0a5f 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -663,15 +663,6 @@ void timer_broadcast_interrupt(void)
 }
 #endif
 
-/*
- * Hypervisor decrementer interrupts shouldn't occur but are sometimes
- * left pending on exit from a KVM guest.  We don't need to do anything
- * to clear them, as they are edge-triggered.
- */
-void hdec_interrupt(struct pt_regs *regs)
-{
-}
-
 #ifdef CONFIG_SUSPEND
 static void generic_suspend_disable_irqs(void)
 {
-- 
cgit v1.2.3


From 68b34588e2027f699a3c034235f21cd19356b2e6 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin
Date: Wed, 26 Feb 2020 03:35:34 +1000
Subject: powerpc/64/sycall: Implement syscall entry/exit logic in C

System call entry and particularly exit code is beyond the limit of
what is reasonable to implement in asm.

This conversion moves all conditional branches out of the asm code,
except for the case that all GPRs should be restored at exit.

Null syscall test is about 5% faster after this patch, because the
exit work is handled under local_irq_disable, and the hard mask and
pending interrupt replay is handled after that, which avoids games
with MSR.

mpe: Includes subsequent fixes from Nick:

This fixes 4 issues caught by TM selftests. First was a tm-syscall bug
that hit due to tabort_syscall being called after interrupts were
reconciled (in a subsequent patch), which led to interrupts being
enabled before tabort_syscall was called. Rather than going through an
un-reconciling interrupts for the return, I just go back to putting
the test early in asm, the C-ification of that wasn't a big win
anyway.

Second is the syscall return _TIF_USER_WORK_MASK check would go into
an infinite loop if _TIF_RESTORE_TM became set. The asm code uses
_TIF_USER_WORK_MASK to brach to slowpath which includes
restore_tm_state.

Third is system call return was not calling restore_tm_state, I missed
this completely (alhtough it's in the return from interrupt C
conversion because when the asm syscall code encountered problems it
would branch to the interrupt return code.

Fourth is MSR_VEC missing from restore_math, which was caught by
tm-unavailable selftest taking an unexpected facility unavailable
interrupt when testing VSX unavailble exception with MSR.FP=1
MSR.VEC=1. Fourth case also has a fixup in a subsequent patch.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michal Suchanek <msuchanek@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200225173541.1549955-26-npiggin@gmail.com
---
 arch/powerpc/include/asm/asm-prototypes.h      |  13 +-
 arch/powerpc/include/asm/book3s/64/kup-radix.h |  14 +-
 arch/powerpc/include/asm/cputime.h             |  33 +++
 arch/powerpc/include/asm/hw_irq.h              |   4 +
 arch/powerpc/include/asm/ptrace.h              |   3 +
 arch/powerpc/include/asm/signal.h              |   3 +
 arch/powerpc/include/asm/switch_to.h           |   5 +
 arch/powerpc/include/asm/time.h                |   3 +
 arch/powerpc/kernel/Makefile                   |   3 +-
 arch/powerpc/kernel/entry_64.S                 | 326 ++++---------------------
 arch/powerpc/kernel/signal.h                   |   2 -
 arch/powerpc/kernel/syscall_64.c               | 214 ++++++++++++++++
 arch/powerpc/kernel/systbl.S                   |   9 +-
 13 files changed, 326 insertions(+), 306 deletions(-)
 create mode 100644 arch/powerpc/kernel/syscall_64.c

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index 983c0084fb3f..ab59a4904254 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -97,6 +97,8 @@ ppc_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp,
 unsigned long __init early_init(unsigned long dt_ptr);
 void __init machine_init(u64 dt_ptr);
 #endif
+long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8, unsigned long r0, struct pt_regs *regs);
+notrace unsigned long syscall_exit_prepare(unsigned long r3, struct pt_regs *regs);
 
 long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low,
 		      u32 len_high, u32 len_low);
@@ -104,14 +106,6 @@ long sys_switch_endian(void);
 notrace unsigned int __check_irq_replay(void);
 void notrace restore_interrupts(void);
 
-/* ptrace */
-long do_syscall_trace_enter(struct pt_regs *regs);
-void do_syscall_trace_leave(struct pt_regs *regs);
-
-/* process */
-void restore_math(struct pt_regs *regs);
-void restore_tm_state(struct pt_regs *regs);
-
 /* prom_init (OpenFirmware) */
 unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 			       unsigned long pp,
@@ -122,9 +116,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 void __init early_setup(unsigned long dt_ptr);
 void early_setup_secondary(void);
 
-/* time */
-void accumulate_stolen_time(void);
-
 /* misc runtime */
 extern u64 __bswapdi2(u64);
 extern s64 __lshrdi3(s64, int);
diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h
index 90dd3a3fc8c7..71081d90f999 100644
--- a/arch/powerpc/include/asm/book3s/64/kup-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h
@@ -3,6 +3,7 @@
 #define _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H
 
 #include <linux/const.h>
+#include <asm/reg.h>
 
 #define AMR_KUAP_BLOCK_READ	UL(0x4000000000000000)
 #define AMR_KUAP_BLOCK_WRITE	UL(0x8000000000000000)
@@ -56,7 +57,14 @@
 
 #ifdef CONFIG_PPC_KUAP
 
-#include <asm/reg.h>
+#include <asm/mmu.h>
+#include <asm/ptrace.h>
+
+static inline void kuap_check_amr(void)
+{
+	if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG) && mmu_has_feature(MMU_FTR_RADIX_KUAP))
+		WARN_ON_ONCE(mfspr(SPRN_AMR) != AMR_KUAP_BLOCKED);
+}
 
 /*
  * We support individually allowing read or write, but we don't support nesting
@@ -127,6 +135,10 @@ bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 		    (regs->kuap & (is_write ? AMR_KUAP_BLOCK_WRITE : AMR_KUAP_BLOCK_READ)),
 		    "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read");
 }
+#else /* CONFIG_PPC_KUAP */
+static inline void kuap_check_amr(void)
+{
+}
 #endif /* CONFIG_PPC_KUAP */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h
index 2431b4ada2fa..0fccd5ea1e9a 100644
--- a/arch/powerpc/include/asm/cputime.h
+++ b/arch/powerpc/include/asm/cputime.h
@@ -43,9 +43,12 @@ static inline unsigned long cputime_to_usecs(const cputime_t ct)
  */
 #ifdef CONFIG_PPC64
 #define get_accounting(tsk)	(&get_paca()->accounting)
+#define raw_get_accounting(tsk)	(&local_paca->accounting)
 static inline void arch_vtime_task_switch(struct task_struct *tsk) { }
+
 #else
 #define get_accounting(tsk)	(&task_thread_info(tsk)->accounting)
+#define raw_get_accounting(tsk)	get_accounting(tsk)
 /*
  * Called from the context switch with interrupts disabled, to charge all
  * accumulated times to the current process, and to prepare accounting on
@@ -60,6 +63,36 @@ static inline void arch_vtime_task_switch(struct task_struct *prev)
 }
 #endif
 
+/*
+ * account_cpu_user_entry/exit runs "unreconciled", so can't trace,
+ * can't use use get_paca()
+ */
+static notrace inline void account_cpu_user_entry(void)
+{
+	unsigned long tb = mftb();
+	struct cpu_accounting_data *acct = raw_get_accounting(current);
+
+	acct->utime += (tb - acct->starttime_user);
+	acct->starttime = tb;
+}
+
+static notrace inline void account_cpu_user_exit(void)
+{
+	unsigned long tb = mftb();
+	struct cpu_accounting_data *acct = raw_get_accounting(current);
+
+	acct->stime += (tb - acct->starttime);
+	acct->starttime_user = tb;
+}
+
+
 #endif /* __KERNEL__ */
+#else /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+static inline void account_cpu_user_entry(void)
+{
+}
+static inline void account_cpu_user_exit(void)
+{
+}
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 #endif /* __POWERPC_CPUTIME_H */
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index e3a905e3d573..310583e62bd9 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -228,9 +228,13 @@ static inline bool arch_irqs_disabled(void)
 #ifdef CONFIG_PPC_BOOK3E
 #define __hard_irq_enable()	wrtee(MSR_EE)
 #define __hard_irq_disable()	wrtee(0)
+#define __hard_EE_RI_disable()	wrtee(0)
+#define __hard_RI_enable()	do { } while (0)
 #else
 #define __hard_irq_enable()	__mtmsrd(MSR_EE|MSR_RI, 1)
 #define __hard_irq_disable()	__mtmsrd(MSR_RI, 1)
+#define __hard_EE_RI_disable()	__mtmsrd(0, 1)
+#define __hard_RI_enable()	__mtmsrd(MSR_RI, 1)
 #endif
 
 #define hard_irq_disable()	do {					\
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index ee3ada66deb5..082a40153b94 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -138,6 +138,9 @@ extern unsigned long profile_pc(struct pt_regs *regs);
 #define profile_pc(regs) instruction_pointer(regs)
 #endif
 
+long do_syscall_trace_enter(struct pt_regs *regs);
+void do_syscall_trace_leave(struct pt_regs *regs);
+
 #define kernel_stack_pointer(regs) ((regs)->gpr[1])
 static inline int is_syscall_success(struct pt_regs *regs)
 {
diff --git a/arch/powerpc/include/asm/signal.h b/arch/powerpc/include/asm/signal.h
index 0803ca8b9149..99e1c6de27bc 100644
--- a/arch/powerpc/include/asm/signal.h
+++ b/arch/powerpc/include/asm/signal.h
@@ -6,4 +6,7 @@
 #include <uapi/asm/signal.h>
 #include <uapi/asm/ptrace.h>
 
+struct pt_regs;
+void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags);
+
 #endif /* _ASM_POWERPC_SIGNAL_H */
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 5b03d8a82409..476008bc3d08 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -5,6 +5,7 @@
 #ifndef _ASM_POWERPC_SWITCH_TO_H
 #define _ASM_POWERPC_SWITCH_TO_H
 
+#include <linux/sched.h>
 #include <asm/reg.h>
 
 struct thread_struct;
@@ -22,6 +23,10 @@ extern void switch_booke_debug_regs(struct debug_reg *new_debug);
 
 extern int emulate_altivec(struct pt_regs *);
 
+void restore_math(struct pt_regs *regs);
+
+void restore_tm_state(struct pt_regs *regs);
+
 extern void flush_all_to_thread(struct task_struct *);
 extern void giveup_all(struct task_struct *);
 
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index e0107495c4de..39ce95016a3a 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -194,5 +194,8 @@ DECLARE_PER_CPU(u64, decrementers_next_tb);
 /* Convert timebase ticks to nanoseconds */
 unsigned long long tb_to_ns(unsigned long long tb_ticks);
 
+/* SPLPAR */
+void accumulate_stolen_time(void);
+
 #endif /* __KERNEL__ */
 #endif /* __POWERPC_TIME_H */
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 78a1b22d4fd8..5700231a8988 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -50,7 +50,8 @@ obj-y				:= cputable.o ptrace.o syscalls.o \
 				   of_platform.o prom_parse.o
 obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
-				   paca.o nvram_64.o firmware.o note.o
+				   paca.o nvram_64.o firmware.o note.o \
+				   syscall_64.o
 obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_PPC_WATCHDOG)	+= watchdog.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 14afe12eae8c..5f70830b5ae4 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -69,6 +69,7 @@ BEGIN_FTR_SECTION
 	bne	.Ltabort_syscall
 END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
+_ASM_NOKPROBE_SYMBOL(system_call_common)
 	mr	r10,r1
 	ld	r1,PACAKSAVE(r13)
 	std	r10,0(r1)
@@ -76,341 +77,98 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 	std	r12,_MSR(r1)
 	std	r0,GPR0(r1)
 	std	r10,GPR1(r1)
+	std	r2,GPR2(r1)
 #ifdef CONFIG_PPC_FSL_BOOK3E
 START_BTB_FLUSH_SECTION
 	BTB_FLUSH(r10)
 END_BTB_FLUSH_SECTION
 #endif
-	ACCOUNT_CPU_USER_ENTRY(r13, r10, r11)
-	std	r2,GPR2(r1)
+	ld	r2,PACATOC(r13)
+	mfcr	r12
+	li	r11,0
+	/* Can we avoid saving r3-r8 in common case? */
 	std	r3,GPR3(r1)
-	mfcr	r2
 	std	r4,GPR4(r1)
 	std	r5,GPR5(r1)
 	std	r6,GPR6(r1)
 	std	r7,GPR7(r1)
 	std	r8,GPR8(r1)
-	li	r11,0
+	/* Zero r9-r12, this should only be required when restoring all GPRs */
 	std	r11,GPR9(r1)
 	std	r11,GPR10(r1)
 	std	r11,GPR11(r1)
 	std	r11,GPR12(r1)
-	std	r11,_XER(r1)
-	std	r11,_CTR(r1)
 	std	r9,GPR13(r1)
 	SAVE_NVGPRS(r1)
+	std	r11,_XER(r1)
+	std	r11,_CTR(r1)
 	mflr	r10
+
 	/*
 	 * This clears CR0.SO (bit 28), which is the error indication on
 	 * return from this system call.
 	 */
-	rldimi	r2,r11,28,(63-28)
+	rldimi	r12,r11,28,(63-28)
 	li	r11,0xc00
 	std	r10,_LINK(r1)
 	std	r11,_TRAP(r1)
+	std	r12,_CCR(r1)
 	std	r3,ORIG_GPR3(r1)
-	std	r2,_CCR(r1)
-	ld	r2,PACATOC(r13)
-	addi	r9,r1,STACK_FRAME_OVERHEAD
+	addi	r10,r1,STACK_FRAME_OVERHEAD
 	ld	r11,exception_marker@toc(r2)
-	std	r11,-16(r9)		/* "regshere" marker */
-
-	kuap_check_amr r10, r11
-
-#if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) && defined(CONFIG_PPC_SPLPAR)
-BEGIN_FW_FTR_SECTION
-	/* see if there are any DTL entries to process */
-	ld	r10,PACALPPACAPTR(r13)	/* get ptr to VPA */
-	ld	r11,PACA_DTL_RIDX(r13)	/* get log read index */
-	addi	r10,r10,LPPACA_DTLIDX
-	LDX_BE	r10,0,r10		/* get log write index */
-	cmpd	r11,r10
-	beq+	33f
-	bl	accumulate_stolen_time
-	REST_GPR(0,r1)
-	REST_4GPRS(3,r1)
-	REST_2GPRS(7,r1)
-	addi	r9,r1,STACK_FRAME_OVERHEAD
-33:
-END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
-#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE && CONFIG_PPC_SPLPAR */
-
-	/*
-	 * A syscall should always be called with interrupts enabled
-	 * so we just unconditionally hard-enable here. When some kind
-	 * of irq tracing is used, we additionally check that condition
-	 * is correct
-	 */
-#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
-	lbz	r10,PACAIRQSOFTMASK(r13)
-1:	tdnei	r10,IRQS_ENABLED
-	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
-#endif
-
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	1
-#else
-	li	r11,MSR_RI
-	ori	r11,r11,MSR_EE
-	mtmsrd	r11,1
-#endif /* CONFIG_PPC_BOOK3E */
-
-system_call:			/* label this so stack traces look sane */
-	/* We do need to set SOFTE in the stack frame or the return
-	 * from interrupt will be painful
-	 */
-	li	r10,IRQS_ENABLED
-	std	r10,SOFTE(r1)
-
-	ld	r11, PACA_THREAD_INFO(r13)
-	ld	r10,TI_FLAGS(r11)
-	andi.	r11,r10,_TIF_SYSCALL_DOTRACE
-	bne	.Lsyscall_dotrace		/* does not return */
-	cmpldi	0,r0,NR_syscalls
-	bge-	.Lsyscall_enosys
+	std	r11,-16(r10)		/* "regshere" marker */
 
-.Lsyscall:
-/*
- * Need to vector to 32 Bit or default sys_call_table here,
- * based on caller's run-mode / personality.
- */
-	ld	r11,SYS_CALL_TABLE@toc(2)
-	andis.	r10,r10,_TIF_32BIT@h
-	beq	15f
-	ld	r11,COMPAT_SYS_CALL_TABLE@toc(2)
-	clrldi	r3,r3,32
-	clrldi	r4,r4,32
-	clrldi	r5,r5,32
-	clrldi	r6,r6,32
-	clrldi	r7,r7,32
-	clrldi	r8,r8,32
-15:
-	slwi	r0,r0,3
-
-	barrier_nospec_asm
-	/*
-	 * Prevent the load of the handler below (based on the user-passed
-	 * system call number) being speculatively executed until the test
-	 * against NR_syscalls and branch to .Lsyscall_enosys above has
-	 * committed.
-	 */
-
-	ldx	r12,r11,r0	/* Fetch system call handler [ptr] */
-	mtctr   r12
-	bctrl			/* Call handler */
+	/* Calling convention has r9 = orig r0, r10 = regs */
+	mr	r9,r0
+	bl	system_call_exception
 
-	/* syscall_exit can exit to kernel mode, via ret_from_kernel_thread */
 .Lsyscall_exit:
-	std	r3,RESULT(r1)
-
-#ifdef CONFIG_DEBUG_RSEQ
-	/* Check whether the syscall is issued inside a restartable sequence */
-	addi    r3,r1,STACK_FRAME_OVERHEAD
-	bl      rseq_syscall
-	ld	r3,RESULT(r1)
-#endif
-
-	ld	r12, PACA_THREAD_INFO(r13)
-
-	ld	r8,_MSR(r1)
-
-/*
- * This is a few instructions into the actual syscall exit path (which actually
- * starts at .Lsyscall_exit) to cater to kprobe blacklisting and to reduce the
- * number of visible symbols for profiling purposes.
- *
- * We can probe from system_call until this point as MSR_RI is set. But once it
- * is cleared below, we won't be able to take a trap.
- *
- * This is blacklisted from kprobes further below with _ASM_NOKPROBE_SYMBOL().
- */
-system_call_exit:
-	/*
-	 * Disable interrupts so current_thread_info()->flags can't change,
-	 * and so that we don't get interrupted after loading SRR0/1.
-	 *
-	 * Leave MSR_RI enabled for now, because with THREAD_INFO_IN_TASK we
-	 * could fault on the load of the TI_FLAGS below.
-	 */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	0
-#else
-	li	r11,MSR_RI
-	mtmsrd	r11,1
-#endif /* CONFIG_PPC_BOOK3E */
+	addi    r4,r1,STACK_FRAME_OVERHEAD
+	bl	syscall_exit_prepare
 
-	ld	r9,TI_FLAGS(r12)
-	li	r11,-MAX_ERRNO
-	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
-	bne-	.Lsyscall_exit_work
+	ld	r2,_CCR(r1)
+	ld	r4,_NIP(r1)
+	ld	r5,_MSR(r1)
+	ld	r6,_LINK(r1)
 
-	andi.	r0,r8,MSR_FP
-	beq 2f
-#ifdef CONFIG_ALTIVEC
-	andis.	r0,r8,MSR_VEC@h
-	bne	3f
-#endif
-2:	addi    r3,r1,STACK_FRAME_OVERHEAD
-	bl	restore_math
-	ld	r8,_MSR(r1)
-	ld	r3,RESULT(r1)
-	li	r11,-MAX_ERRNO
-
-3:	cmpld	r3,r11
-	ld	r5,_CCR(r1)
-	bge-	.Lsyscall_error
-.Lsyscall_error_cont:
-	ld	r7,_NIP(r1)
 BEGIN_FTR_SECTION
 	stdcx.	r0,0,r1			/* to clear the reservation */
 END_FTR_SECTION_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
-	andi.	r6,r8,MSR_PR
-	ld	r4,_LINK(r1)
 
-	kuap_check_amr r10, r11
+	mtspr	SPRN_SRR0,r4
+	mtspr	SPRN_SRR1,r5
+	mtlr	r6
 
-#ifdef CONFIG_PPC_BOOK3S
-	/*
-	 * Clear MSR_RI, MSR_EE is already and remains disabled. We could do
-	 * this later, but testing shows that doing it here causes less slow
-	 * down than doing it closer to the rfid.
-	 */
-	li	r11,0
-	mtmsrd	r11,1
-#endif
-
-	beq-	1f
-	ACCOUNT_CPU_USER_EXIT(r13, r11, r12)
+	cmpdi	r3,0
+	bne	.Lsyscall_restore_regs
+.Lsyscall_restore_regs_cont:
 
 BEGIN_FTR_SECTION
 	HMT_MEDIUM_LOW
 END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	std	r8, PACATMSCRATCH(r13)
-#endif
-
 	/*
 	 * We don't need to restore AMR on the way back to userspace for KUAP.
 	 * The value of AMR only matters while we're in the kernel.
 	 */
-	ld	r13,GPR13(r1)	/* only restore r13 if returning to usermode */
+	mtcr	r2
 	ld	r2,GPR2(r1)
+	ld	r3,GPR3(r1)
+	ld	r13,GPR13(r1)
 	ld	r1,GPR1(r1)
-	mtlr	r4
-	mtcr	r5
-	mtspr	SPRN_SRR0,r7
-	mtspr	SPRN_SRR1,r8
 	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 
-1:	/* exit to kernel */
-	kuap_restore_amr r2
-
-	ld	r2,GPR2(r1)
-	ld	r1,GPR1(r1)
-	mtlr	r4
-	mtcr	r5
-	mtspr	SPRN_SRR0,r7
-	mtspr	SPRN_SRR1,r8
-	RFI_TO_KERNEL
-	b	.	/* prevent speculative execution */
-
-.Lsyscall_error:
-	oris	r5,r5,0x1000	/* Set SO bit in CR */
-	neg	r3,r3
-	std	r5,_CCR(r1)
-	b	.Lsyscall_error_cont
-
-/* Traced system call support */
-.Lsyscall_dotrace:
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	do_syscall_trace_enter
-
-	/*
-	 * We use the return value of do_syscall_trace_enter() as the syscall
-	 * number. If the syscall was rejected for any reason do_syscall_trace_enter()
-	 * returns an invalid syscall number and the test below against
-	 * NR_syscalls will fail.
-	 */
-	mr	r0,r3
-
-	/* Restore argument registers just clobbered and/or possibly changed. */
-	ld	r3,GPR3(r1)
-	ld	r4,GPR4(r1)
-	ld	r5,GPR5(r1)
-	ld	r6,GPR6(r1)
-	ld	r7,GPR7(r1)
-	ld	r8,GPR8(r1)
-
-	/* Repopulate r9 and r10 for the syscall path */
-	addi	r9,r1,STACK_FRAME_OVERHEAD
-	ld	r10, PACA_THREAD_INFO(r13)
-	ld	r10,TI_FLAGS(r10)
-
-	cmpldi	r0,NR_syscalls
-	blt+	.Lsyscall
-
-	/* Return code is already in r3 thanks to do_syscall_trace_enter() */
-	b	.Lsyscall_exit
-
-
-.Lsyscall_enosys:
-	li	r3,-ENOSYS
-	b	.Lsyscall_exit
-	
-.Lsyscall_exit_work:
-	/* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr.
-	 If TIF_NOERROR is set, just save r3 as it is. */
-
-	andi.	r0,r9,_TIF_RESTOREALL
-	beq+	0f
+.Lsyscall_restore_regs:
+	ld	r3,_CTR(r1)
+	ld	r4,_XER(r1)
 	REST_NVGPRS(r1)
-	b	2f
-0:	cmpld	r3,r11		/* r11 is -MAX_ERRNO */
-	blt+	1f
-	andi.	r0,r9,_TIF_NOERROR
-	bne-	1f
-	ld	r5,_CCR(r1)
-	neg	r3,r3
-	oris	r5,r5,0x1000	/* Set SO bit in CR */
-	std	r5,_CCR(r1)
-1:	std	r3,GPR3(r1)
-2:	andi.	r0,r9,(_TIF_PERSYSCALL_MASK)
-	beq	4f
-
-	/* Clear per-syscall TIF flags if any are set.  */
-
-	li	r11,_TIF_PERSYSCALL_MASK
-	addi	r12,r12,TI_FLAGS
-3:	ldarx	r10,0,r12
-	andc	r10,r10,r11
-	stdcx.	r10,0,r12
-	bne-	3b
-	subi	r12,r12,TI_FLAGS
-
-4:	/* Anything else left to do? */
-BEGIN_FTR_SECTION
-	lis	r3,DEFAULT_PPR@highest	/* Set default PPR */
-	sldi	r3,r3,32	/* bits 11-13 are used for ppr */
-	std	r3,_PPR(r1)
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-
-	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP)
-	beq	ret_from_except_lite
-
-	/* Re-enable interrupts */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	1
-#else
-	li	r10,MSR_RI
-	ori	r10,r10,MSR_EE
-	mtmsrd	r10,1
-#endif /* CONFIG_PPC_BOOK3E */
-
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	do_syscall_trace_leave
-	b	ret_from_except
+	mtctr	r3
+	mtspr	SPRN_XER,r4
+	ld	r0,GPR0(r1)
+	REST_8GPRS(4, r1)
+	ld	r12,GPR12(r1)
+	b	.Lsyscall_restore_regs_cont
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 .Ltabort_syscall:
@@ -438,8 +196,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	RFI_TO_USER
 	b	.	/* prevent speculative execution */
 #endif
-_ASM_NOKPROBE_SYMBOL(system_call_common);
-_ASM_NOKPROBE_SYMBOL(system_call_exit);
 
 _GLOBAL(ret_from_fork)
 	bl	schedule_tail
diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h
index 800433685888..d396efca4068 100644
--- a/arch/powerpc/kernel/signal.h
+++ b/arch/powerpc/kernel/signal.h
@@ -10,8 +10,6 @@
 #ifndef _POWERPC_ARCH_SIGNAL_H
 #define _POWERPC_ARCH_SIGNAL_H
 
-extern void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags);
-
 extern void __user *get_sigframe(struct ksignal *ksig, unsigned long sp,
 				  size_t frame_size, int is_32);
 
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
new file mode 100644
index 000000000000..75be20fdb270
--- /dev/null
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/err.h>
+#include <asm/asm-prototypes.h>
+#include <asm/book3s/64/kup-radix.h>
+#include <asm/cputime.h>
+#include <asm/hw_irq.h>
+#include <asm/kprobes.h>
+#include <asm/paca.h>
+#include <asm/ptrace.h>
+#include <asm/reg.h>
+#include <asm/signal.h>
+#include <asm/switch_to.h>
+#include <asm/syscall.h>
+#include <asm/time.h>
+#include <asm/unistd.h>
+
+typedef long (*syscall_fn)(long, long, long, long, long, long);
+
+/* Has to run notrace because it is entered "unreconciled" */
+notrace long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8,
+			   unsigned long r0, struct pt_regs *regs)
+{
+	unsigned long ti_flags;
+	syscall_fn f;
+
+	BUG_ON(!(regs->msr & MSR_PR));
+
+	account_cpu_user_entry();
+
+#ifdef CONFIG_PPC_SPLPAR
+	if (IS_ENABLED(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) &&
+	    firmware_has_feature(FW_FEATURE_SPLPAR)) {
+		struct lppaca *lp = local_paca->lppaca_ptr;
+
+		if (unlikely(local_paca->dtl_ridx != be64_to_cpu(lp->dtl_idx)))
+			accumulate_stolen_time();
+	}
+#endif
+
+	kuap_check_amr();
+
+	/*
+	 * A syscall should always be called with interrupts enabled
+	 * so we just unconditionally hard-enable here. When some kind
+	 * of irq tracing is used, we additionally check that condition
+	 * is correct
+	 */
+	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+		WARN_ON(irq_soft_mask_return() != IRQS_ENABLED);
+		WARN_ON(local_paca->irq_happened);
+	}
+	/*
+	 * This is not required for the syscall exit path, but makes the
+	 * stack frame look nicer. If this was initialised in the first stack
+	 * frame, or if the unwinder was taught the first stack frame always
+	 * returns to user with IRQS_ENABLED, this store could be avoided!
+	 */
+	regs->softe = IRQS_ENABLED;
+
+	__hard_irq_enable();
+
+	ti_flags = current_thread_info()->flags;
+	if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE)) {
+		/*
+		 * We use the return value of do_syscall_trace_enter() as the
+		 * syscall number. If the syscall was rejected for any reason
+		 * do_syscall_trace_enter() returns an invalid syscall number
+		 * and the test against NR_syscalls will fail and the return
+		 * value to be used is in regs->gpr[3].
+		 */
+		r0 = do_syscall_trace_enter(regs);
+		if (unlikely(r0 >= NR_syscalls))
+			return regs->gpr[3];
+		r3 = regs->gpr[3];
+		r4 = regs->gpr[4];
+		r5 = regs->gpr[5];
+		r6 = regs->gpr[6];
+		r7 = regs->gpr[7];
+		r8 = regs->gpr[8];
+
+	} else if (unlikely(r0 >= NR_syscalls)) {
+		return -ENOSYS;
+	}
+
+	/* May be faster to do array_index_nospec? */
+	barrier_nospec();
+
+	if (unlikely(ti_flags & _TIF_32BIT)) {
+		f = (void *)compat_sys_call_table[r0];
+
+		r3 &= 0x00000000ffffffffULL;
+		r4 &= 0x00000000ffffffffULL;
+		r5 &= 0x00000000ffffffffULL;
+		r6 &= 0x00000000ffffffffULL;
+		r7 &= 0x00000000ffffffffULL;
+		r8 &= 0x00000000ffffffffULL;
+
+	} else {
+		f = (void *)sys_call_table[r0];
+	}
+
+	return f(r3, r4, r5, r6, r7, r8);
+}
+
+/*
+ * This should be called after a syscall returns, with r3 the return value
+ * from the syscall. If this function returns non-zero, the system call
+ * exit assembly should additionally load all GPR registers and CTR and XER
+ * from the interrupt frame.
+ *
+ * The function graph tracer can not trace the return side of this function,
+ * because RI=0 and soft mask state is "unreconciled", so it is marked notrace.
+ */
+notrace unsigned long syscall_exit_prepare(unsigned long r3,
+					   struct pt_regs *regs)
+{
+	unsigned long *ti_flagsp = &current_thread_info()->flags;
+	unsigned long ti_flags;
+	unsigned long ret = 0;
+
+	regs->result = r3;
+
+	/* Check whether the syscall is issued inside a restartable sequence */
+	rseq_syscall(regs);
+
+	ti_flags = *ti_flagsp;
+
+	if (unlikely(r3 >= (unsigned long)-MAX_ERRNO)) {
+		if (likely(!(ti_flags & (_TIF_NOERROR | _TIF_RESTOREALL)))) {
+			r3 = -r3;
+			regs->ccr |= 0x10000000; /* Set SO bit in CR */
+		}
+	}
+
+	if (unlikely(ti_flags & _TIF_PERSYSCALL_MASK)) {
+		if (ti_flags & _TIF_RESTOREALL)
+			ret = _TIF_RESTOREALL;
+		else
+			regs->gpr[3] = r3;
+		clear_bits(_TIF_PERSYSCALL_MASK, ti_flagsp);
+	} else {
+		regs->gpr[3] = r3;
+	}
+
+	if (unlikely(ti_flags & _TIF_SYSCALL_DOTRACE)) {
+		do_syscall_trace_leave(regs);
+		ret |= _TIF_RESTOREALL;
+	}
+
+again:
+	local_irq_disable();
+	ti_flags = READ_ONCE(*ti_flagsp);
+	while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
+		local_irq_enable();
+		if (ti_flags & _TIF_NEED_RESCHED) {
+			schedule();
+		} else {
+			/*
+			 * SIGPENDING must restore signal handler function
+			 * argument GPRs, and some non-volatiles (e.g., r1).
+			 * Restore all for now. This could be made lighter.
+			 */
+			if (ti_flags & _TIF_SIGPENDING)
+				ret |= _TIF_RESTOREALL;
+			do_notify_resume(regs, ti_flags);
+		}
+		local_irq_disable();
+		ti_flags = READ_ONCE(*ti_flagsp);
+	}
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && IS_ENABLED(CONFIG_PPC_FPU)) {
+		if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+				unlikely((ti_flags & _TIF_RESTORE_TM))) {
+			restore_tm_state(regs);
+		} else {
+			unsigned long mathflags = MSR_FP;
+
+			if (cpu_has_feature(CPU_FTR_VSX))
+				mathflags |= MSR_VEC | MSR_VSX;
+			else if (cpu_has_feature(CPU_FTR_ALTIVEC))
+				mathflags |= MSR_VEC;
+
+			if ((regs->msr & mathflags) != mathflags)
+				restore_math(regs);
+		}
+	}
+
+	/* This must be done with RI=1 because tracing may touch vmaps */
+	trace_hardirqs_on();
+
+	/* This pattern matches prep_irq_for_idle */
+	__hard_EE_RI_disable();
+	if (unlikely(lazy_irq_pending())) {
+		__hard_RI_enable();
+		trace_hardirqs_off();
+		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+		local_irq_enable();
+		/* Took an interrupt which may have more exit work to do. */
+		goto again;
+	}
+	local_paca->irq_happened = 0;
+	irq_soft_mask_set(IRQS_ENABLED);
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	local_paca->tm_scratch = regs->msr;
+#endif
+
+	kuap_check_amr();
+
+	account_cpu_user_exit();
+
+	return ret;
+}
diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S
index 5b905a2f4e4d..d34276f3c495 100644
--- a/arch/powerpc/kernel/systbl.S
+++ b/arch/powerpc/kernel/systbl.S
@@ -16,25 +16,22 @@
 
 #ifdef CONFIG_PPC64
 	.p2align	3
+#define __SYSCALL(nr, entry)	.8byte entry
+#else
+#define __SYSCALL(nr, entry)	.long entry
 #endif
 
 .globl sys_call_table
 sys_call_table:
 #ifdef CONFIG_PPC64
-#define __SYSCALL(nr, entry)	.8byte DOTSYM(entry)
 #include <asm/syscall_table_64.h>
-#undef __SYSCALL
 #else
-#define __SYSCALL(nr, entry)	.long entry
 #include <asm/syscall_table_32.h>
-#undef __SYSCALL
 #endif
 
 #ifdef CONFIG_COMPAT
 .globl compat_sys_call_table
 compat_sys_call_table:
 #define compat_sys_sigsuspend	sys_sigsuspend
-#define __SYSCALL(nr, entry)	.8byte DOTSYM(entry)
 #include <asm/syscall_table_c32.h>
-#undef __SYSCALL
 #endif
-- 
cgit v1.2.3


From 3282a3da25bd63fdb7240bc35dbdefa4b1947005 Mon Sep 17 00:00:00 2001
From: Nicholas Piggin
Date: Wed, 26 Feb 2020 03:35:36 +1000
Subject: powerpc/64: Implement soft interrupt replay in C

When local_irq_enable() finds a pending soft-masked interrupt, it
"replays" it by setting up registers like the initial interrupt entry,
then calls into the low level handler to set up an interrupt stack
frame and process the interrupt.

This is not necessary, and uses more stack than needed. The high level
interrupt handler can be called directly from C, with just pt_regs set
up on stack. This should be faster and use less stack.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200225173541.1549955-28-npiggin@gmail.com
---
 arch/powerpc/include/asm/hw_irq.h    |   1 -
 arch/powerpc/kernel/exceptions-64e.S |  32 -------
 arch/powerpc/kernel/exceptions-64s.S |  47 ----------
 arch/powerpc/kernel/irq.c            | 165 +++++++++++++++++++++++++++--------
 4 files changed, 130 insertions(+), 115 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 310583e62bd9..0e9a9598f91f 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -52,7 +52,6 @@
 #ifndef __ASSEMBLY__
 
 extern void replay_system_reset(void);
-extern void __replay_interrupt(unsigned int vector);
 
 extern void timer_interrupt(struct pt_regs *);
 extern void timer_broadcast_interrupt(void);
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index e4076e3c072d..4efac5490216 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -1002,38 +1002,6 @@ masked_interrupt_book3e_0x280:
 masked_interrupt_book3e_0x2c0:
 	masked_interrupt_book3e PACA_IRQ_DBELL 0
 
-/*
- * Called from arch_local_irq_enable when an interrupt needs
- * to be resent. r3 contains either 0x500,0x900,0x260 or 0x280
- * to indicate the kind of interrupt. MSR:EE is already off.
- * We generate a stackframe like if a real interrupt had happened.
- *
- * Note: While MSR:EE is off, we need to make sure that _MSR
- * in the generated frame has EE set to 1 or the exception
- * handler will not properly re-enable them.
- */
-_GLOBAL(__replay_interrupt)
-	/* We are going to jump to the exception common code which
-	 * will retrieve various register values from the PACA which
-	 * we don't give a damn about.
-	 */
-	mflr	r10
-	mfmsr	r11
-	mfcr	r4
-	mtspr	SPRN_SPRG_GEN_SCRATCH,r13;
-	std	r1,PACA_EXGEN+EX_R1(r13);
-	stw	r4,PACA_EXGEN+EX_CR(r13);
-	ori	r11,r11,MSR_EE
-	subi	r1,r1,INT_FRAME_SIZE;
-	cmpwi	cr0,r3,0x500
-	beq	exc_0x500_common
-	cmpwi	cr0,r3,0x900
-	beq	exc_0x900_common
-	cmpwi	cr0,r3,0x280
-	beq	exc_0x280_common
-	blr
-
-
 /*
  * This is called from 0x300 and 0x400 handlers after the prologs with
  * r14 and r15 containing the fault address and error code, with the
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index d75df223da7c..d6536a7c2a01 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -3165,50 +3165,3 @@ doorbell_super_common_msgclr:
 	LOAD_REG_IMMEDIATE(r3, PPC_DBELL_MSGTYPE << (63-36))
 	PPC_MSGCLRP(3)
 	b 	doorbell_super_common_virt
-
-/*
- * Called from arch_local_irq_enable when an interrupt needs
- * to be resent. r3 contains 0x500, 0x900, 0xa00 or 0xe80 to indicate
- * which kind of interrupt. MSR:EE is already off. We generate a
- * stackframe like if a real interrupt had happened.
- *
- * Note: While MSR:EE is off, we need to make sure that _MSR
- * in the generated frame has EE set to 1 or the exception
- * handler will not properly re-enable them.
- *
- * Note that we don't specify LR as the NIP (return address) for
- * the interrupt because that would unbalance the return branch
- * predictor.
- */
-_GLOBAL(__replay_interrupt)
-	/* We are going to jump to the exception common code which
-	 * will retrieve various register values from the PACA which
-	 * we don't give a damn about, so we don't bother storing them.
-	 */
-	mfmsr	r12
-	LOAD_REG_ADDR(r11, replay_interrupt_return)
-	mfcr	r9
-	ori	r12,r12,MSR_EE
-	cmpwi	r3,0x900
-	beq	decrementer_common_virt
-	cmpwi	r3,0x500
-BEGIN_FTR_SECTION
-	beq	h_virt_irq_common_virt
-FTR_SECTION_ELSE
-	beq	hardware_interrupt_common_virt
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_300)
-	cmpwi	r3,0xf00
-	beq	performance_monitor_common_virt
-BEGIN_FTR_SECTION
-	cmpwi	r3,0xa00
-	beq	h_doorbell_common_msgclr
-	cmpwi	r3,0xe60
-	beq	hmi_exception_common_virt
-FTR_SECTION_ELSE
-	cmpwi	r3,0xa00
-	beq	doorbell_super_common_msgclr
-ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
-replay_interrupt_return:
-	blr
-
-_ASM_NOKPROBE_SYMBOL(__replay_interrupt)
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 1bed18b7229e..2e5dca87b936 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -70,6 +70,7 @@
 #include <asm/paca.h>
 #include <asm/firmware.h>
 #include <asm/lv1call.h>
+#include <asm/dbell.h>
 #endif
 #define CREATE_TRACE_POINTS
 #include <asm/trace.h>
@@ -230,10 +231,121 @@ notrace unsigned int __check_irq_replay(void)
 	return 0;
 }
 
+static void replay_soft_interrupts(void)
+{
+	/*
+	 * We use local_paca rather than get_paca() to avoid all
+	 * the debug_smp_processor_id() business in this low level
+	 * function
+	 */
+	unsigned char happened = local_paca->irq_happened;
+	struct pt_regs regs;
+
+	ppc_save_regs(&regs);
+	regs.softe = IRQS_ALL_DISABLED;
+
+again:
+	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+		WARN_ON_ONCE(mfmsr() & MSR_EE);
+
+	if (happened & PACA_IRQ_HARD_DIS) {
+		/*
+		 * We may have missed a decrementer interrupt if hard disabled.
+		 * Check the decrementer register in case we had a rollover
+		 * while hard disabled.
+		 */
+		if (!(happened & PACA_IRQ_DEC)) {
+			if (decrementer_check_overflow())
+				happened |= PACA_IRQ_DEC;
+		}
+	}
+
+	/*
+	 * Force the delivery of pending soft-disabled interrupts on PS3.
+	 * Any HV call will have this side effect.
+	 */
+	if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
+		u64 tmp, tmp2;
+		lv1_get_version_info(&tmp, &tmp2);
+	}
+
+	/*
+	 * Check if an hypervisor Maintenance interrupt happened.
+	 * This is a higher priority interrupt than the others, so
+	 * replay it first.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_HMI)) {
+		local_paca->irq_happened &= ~PACA_IRQ_HMI;
+		regs.trap = 0xe60;
+		handle_hmi_exception(&regs);
+		if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+			hard_irq_disable();
+	}
+
+	if (happened & PACA_IRQ_DEC) {
+		local_paca->irq_happened &= ~PACA_IRQ_DEC;
+		regs.trap = 0x900;
+		timer_interrupt(&regs);
+		if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+			hard_irq_disable();
+	}
+
+	if (happened & PACA_IRQ_EE) {
+		local_paca->irq_happened &= ~PACA_IRQ_EE;
+		regs.trap = 0x500;
+		do_IRQ(&regs);
+		if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+			hard_irq_disable();
+	}
+
+	/*
+	 * Check if an EPR external interrupt happened this bit is typically
+	 * set if we need to handle another "edge" interrupt from within the
+	 * MPIC "EPR" handler.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_BOOK3E) && (happened & PACA_IRQ_EE_EDGE)) {
+		local_paca->irq_happened &= ~PACA_IRQ_EE_EDGE;
+		regs.trap = 0x500;
+		do_IRQ(&regs);
+		if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+			hard_irq_disable();
+	}
+
+	if (IS_ENABLED(CONFIG_PPC_DOORBELL) && (happened & PACA_IRQ_DBELL)) {
+		local_paca->irq_happened &= ~PACA_IRQ_DBELL;
+		if (IS_ENABLED(CONFIG_PPC_BOOK3E))
+			regs.trap = 0x280;
+		else
+			regs.trap = 0xa00;
+		doorbell_exception(&regs);
+		if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+			hard_irq_disable();
+	}
+
+	/* Book3E does not support soft-masking PMI interrupts */
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && (happened & PACA_IRQ_PMI)) {
+		local_paca->irq_happened &= ~PACA_IRQ_PMI;
+		regs.trap = 0xf00;
+		performance_monitor_exception(&regs);
+		if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS))
+			hard_irq_disable();
+	}
+
+	happened = local_paca->irq_happened;
+	if (happened & ~PACA_IRQ_HARD_DIS) {
+		/*
+		 * We are responding to the next interrupt, so interrupt-off
+		 * latencies should be reset here.
+		 */
+		trace_hardirqs_on();
+		trace_hardirqs_off();
+		goto again;
+	}
+}
+
 notrace void arch_local_irq_restore(unsigned long mask)
 {
 	unsigned char irq_happened;
-	unsigned int replay;
 
 	/* Write the new soft-enabled value */
 	irq_soft_mask_set(mask);
@@ -255,24 +367,16 @@ notrace void arch_local_irq_restore(unsigned long mask)
 	 */
 	irq_happened = get_irq_happened();
 	if (!irq_happened) {
-#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
-		WARN_ON_ONCE(!(mfmsr() & MSR_EE));
-#endif
+		if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+			WARN_ON_ONCE(!(mfmsr() & MSR_EE));
 		return;
 	}
 
-	/*
-	 * We need to hard disable to get a trusted value from
-	 * __check_irq_replay(). We also need to soft-disable
-	 * again to avoid warnings in there due to the use of
-	 * per-cpu variables.
-	 */
+	/* We need to hard disable to replay. */
 	if (!(irq_happened & PACA_IRQ_HARD_DIS)) {
-#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
-		WARN_ON_ONCE(!(mfmsr() & MSR_EE));
-#endif
+		if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+			WARN_ON_ONCE(!(mfmsr() & MSR_EE));
 		__hard_irq_disable();
-#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
 	} else {
 		/*
 		 * We should already be hard disabled here. We had bugs
@@ -280,35 +384,26 @@ notrace void arch_local_irq_restore(unsigned long mask)
 		 * warn if we are wrong. Only do that when IRQ tracing
 		 * is enabled as mfmsr() can be costly.
 		 */
-		if (WARN_ON_ONCE(mfmsr() & MSR_EE))
-			__hard_irq_disable();
-#endif
+		if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG)) {
+			if (WARN_ON_ONCE(mfmsr() & MSR_EE))
+				__hard_irq_disable();
+		}
+
+		if (irq_happened == PACA_IRQ_HARD_DIS) {
+			local_paca->irq_happened = 0;
+			__hard_irq_enable();
+			return;
+		}
 	}
 
 	irq_soft_mask_set(IRQS_ALL_DISABLED);
 	trace_hardirqs_off();
 
-	/*
-	 * Check if anything needs to be re-emitted. We haven't
-	 * soft-enabled yet to avoid warnings in decrementer_check_overflow
-	 * accessing per-cpu variables
-	 */
-	replay = __check_irq_replay();
+	replay_soft_interrupts();
+	local_paca->irq_happened = 0;
 
-	/* We can soft-enable now */
 	trace_hardirqs_on();
 	irq_soft_mask_set(IRQS_ENABLED);
-
-	/*
-	 * And replay if we have to. This will return with interrupts
-	 * hard-enabled.
-	 */
-	if (replay) {
-		__replay_interrupt(replay);
-		return;
-	}
-
-	/* Finally, let's ensure we are hard enabled */
 	__hard_irq_enable();
 }
 EXPORT_SYMBOL(arch_local_irq_restore);
-- 
cgit v1.2.3


From 6cc0c16d82f889f0083f3608237189afb55b67be Mon Sep 17 00:00:00 2001
From: Nicholas Piggin
Date: Wed, 26 Feb 2020 03:35:37 +1000
Subject: powerpc/64s: Implement interrupt exit logic in C

Implement the bulk of interrupt return logic in C. The asm return code
must handle a few cases: restoring full GPRs, and emulating stack
store.

The stack store emulation is significantly simplfied, rather than
creating a new return frame and switching to that before performing
the store, it uses the PACA to keep a scratch register around to
perform the store.

The asm return code is moved into 64e for now. The new logic has made
allowance for 64e, but I don't have a full environment that works well
to test it, and even booting in emulated qemu is not great for stress
testing. 64e shouldn't be too far off working with this, given a bit
more testing and auditing of the logic.

This is slightly faster on a POWER9 (page fault speed increases about
1.1%), probably due to reduced mtmsrd.

mpe: Includes fixes from Nick for _TIF_EMULATE_STACK_STORE
handling (including the fast_interrupt_return path), to remove
trace_hardirqs_on(), and fixes the interrupt-return part of the
MSR_VSX restore bug caught by tm-unavailable selftest.

mpe: Incorporate fix from Nick:

The return-to-kernel path has to replay any soft-pending interrupts if
it is returning to a context that had interrupts soft-enabled. It has
to do this carefully and avoid plain enabling interrupts if this is an
irq context, which can cause multiple nesting of interrupts on the
stack, and other unexpected issues.

The code which avoided this case got the soft-mask state wrong, and
marked interrupts as enabled before going around again to retry. This
seems to be mostly harmless except when PREEMPT=y, this calls
preempt_schedule_irq with irqs apparently enabled and runs into a BUG
in kernel/sched/core.c

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michal Suchanek <msuchanek@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200225173541.1549955-29-npiggin@gmail.com
---
 arch/powerpc/include/asm/asm-prototypes.h      |   2 +
 arch/powerpc/include/asm/book3s/64/kup-radix.h |  10 +
 arch/powerpc/include/asm/hw_irq.h              |   1 +
 arch/powerpc/include/asm/switch_to.h           |   6 +
 arch/powerpc/kernel/entry_64.S                 | 487 ++++++-------------------
 arch/powerpc/kernel/exceptions-64e.S           | 255 ++++++++++++-
 arch/powerpc/kernel/exceptions-64s.S           | 119 +++---
 arch/powerpc/kernel/irq.c                      |  36 +-
 arch/powerpc/kernel/process.c                  |  89 ++---
 arch/powerpc/kernel/syscall_64.c               | 171 ++++++++-
 arch/powerpc/kernel/vector.S                   |   2 +-
 11 files changed, 652 insertions(+), 526 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/asm-prototypes.h b/arch/powerpc/include/asm/asm-prototypes.h
index ab59a4904254..7d81e86a1e5d 100644
--- a/arch/powerpc/include/asm/asm-prototypes.h
+++ b/arch/powerpc/include/asm/asm-prototypes.h
@@ -99,6 +99,8 @@ void __init machine_init(u64 dt_ptr);
 #endif
 long system_call_exception(long r3, long r4, long r5, long r6, long r7, long r8, unsigned long r0, struct pt_regs *regs);
 notrace unsigned long syscall_exit_prepare(unsigned long r3, struct pt_regs *regs);
+notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr);
+notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsigned long msr);
 
 long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low,
 		      u32 len_high, u32 len_low);
diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h
index 71081d90f999..3bcef989a35d 100644
--- a/arch/powerpc/include/asm/book3s/64/kup-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h
@@ -60,6 +60,12 @@
 #include <asm/mmu.h>
 #include <asm/ptrace.h>
 
+static inline void kuap_restore_amr(struct pt_regs *regs)
+{
+	if (mmu_has_feature(MMU_FTR_RADIX_KUAP))
+		mtspr(SPRN_AMR, regs->kuap);
+}
+
 static inline void kuap_check_amr(void)
 {
 	if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG) && mmu_has_feature(MMU_FTR_RADIX_KUAP))
@@ -136,6 +142,10 @@ bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
 		    "Bug: %s fault blocked by AMR!", is_write ? "Write" : "Read");
 }
 #else /* CONFIG_PPC_KUAP */
+static inline void kuap_restore_amr(struct pt_regs *regs)
+{
+}
+
 static inline void kuap_check_amr(void)
 {
 }
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index 0e9a9598f91f..e0e71777961f 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -52,6 +52,7 @@
 #ifndef __ASSEMBLY__
 
 extern void replay_system_reset(void);
+extern void replay_soft_interrupts(void);
 
 extern void timer_interrupt(struct pt_regs *);
 extern void timer_broadcast_interrupt(void);
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 476008bc3d08..b867b58b1093 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -23,7 +23,13 @@ extern void switch_booke_debug_regs(struct debug_reg *new_debug);
 
 extern int emulate_altivec(struct pt_regs *);
 
+#ifdef CONFIG_PPC_BOOK3S_64
 void restore_math(struct pt_regs *regs);
+#else
+static inline void restore_math(struct pt_regs *regs)
+{
+}
+#endif
 
 void restore_tm_state(struct pt_regs *regs);
 
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 29949bbe857b..5d782acb86d4 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -16,6 +16,7 @@
 
 #include <linux/errno.h>
 #include <linux/err.h>
+#include <asm/cache.h>
 #include <asm/unistd.h>
 #include <asm/processor.h>
 #include <asm/page.h>
@@ -228,6 +229,7 @@ _GLOBAL(ret_from_kernel_thread)
 	li	r3,0
 	b	.Lsyscall_exit
 
+#ifdef CONFIG_PPC_BOOK3E
 /* Save non-volatile GPRs, if not already saved. */
 _GLOBAL(save_nvgprs)
 	ld	r11,_TRAP(r1)
@@ -238,6 +240,7 @@ _GLOBAL(save_nvgprs)
 	std	r0,_TRAP(r1)
 	blr
 _ASM_NOKPROBE_SYMBOL(save_nvgprs);
+#endif
 
 #ifdef CONFIG_PPC_BOOK3S_64
 
@@ -301,7 +304,7 @@ flush_count_cache:
  * state of one is saved on its kernel stack.  Then the state
  * of the other is restored from its kernel stack.  The memory
  * management hardware is updated to the second process's state.
- * Finally, we can return to the second process, via ret_from_except.
+ * Finally, we can return to the second process, via interrupt_return.
  * On entry, r3 points to the THREAD for the current task, r4
  * points to the THREAD for the new task.
  *
@@ -453,408 +456,152 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
 	addi	r1,r1,SWITCH_FRAME_SIZE
 	blr
 
-	.align	7
-_GLOBAL(ret_from_except)
-	ld	r11,_TRAP(r1)
-	andi.	r0,r11,1
-	bne	ret_from_except_lite
-	REST_NVGPRS(r1)
-
-_GLOBAL(ret_from_except_lite)
+#ifdef CONFIG_PPC_BOOK3S
 	/*
-	 * Disable interrupts so that current_thread_info()->flags
-	 * can't change between when we test it and when we return
-	 * from the interrupt.
-	 */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	0
-#else
-	li	r10,MSR_RI
-	mtmsrd	r10,1		  /* Update machine state */
-#endif /* CONFIG_PPC_BOOK3E */
+	 * If MSR EE/RI was never enabled, IRQs not reconciled, NVGPRs not
+	 * touched, AMR not set, no exit work created, then this can be used.
+	 */
+	.balign IFETCH_ALIGN_BYTES
+	.globl fast_interrupt_return
+fast_interrupt_return:
+_ASM_NOKPROBE_SYMBOL(fast_interrupt_return)
+	ld	r4,_MSR(r1)
+	andi.	r0,r4,MSR_PR
+	bne	.Lfast_user_interrupt_return
+	andi.	r0,r4,MSR_RI
+	li	r3,0 /* 0 return value, no EMULATE_STACK_STORE */
+	bne+	.Lfast_kernel_interrupt_return
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	unrecoverable_exception
+	b	. /* should not get here */
 
-	ld	r9, PACA_THREAD_INFO(r13)
-	ld	r3,_MSR(r1)
-#ifdef CONFIG_PPC_BOOK3E
-	ld	r10,PACACURRENT(r13)
-#endif /* CONFIG_PPC_BOOK3E */
-	ld	r4,TI_FLAGS(r9)
-	andi.	r3,r3,MSR_PR
-	beq	resume_kernel
-#ifdef CONFIG_PPC_BOOK3E
-	lwz	r3,(THREAD+THREAD_DBCR0)(r10)
-#endif /* CONFIG_PPC_BOOK3E */
+	.balign IFETCH_ALIGN_BYTES
+	.globl interrupt_return
+interrupt_return:
+_ASM_NOKPROBE_SYMBOL(interrupt_return)
+	REST_NVGPRS(r1)
 
-	/* Check current_thread_info()->flags */
-	andi.	r0,r4,_TIF_USER_WORK_MASK
-	bne	1f
-#ifdef CONFIG_PPC_BOOK3E
-	/*
-	 * Check to see if the dbcr0 register is set up to debug.
-	 * Use the internal debug mode bit to do this.
-	 */
-	andis.	r0,r3,DBCR0_IDM@h
-	beq	restore
-	mfmsr	r0
-	rlwinm	r0,r0,0,~MSR_DE	/* Clear MSR.DE */
-	mtmsr	r0
-	mtspr	SPRN_DBCR0,r3
-	li	r10, -1
-	mtspr	SPRN_DBSR,r10
-	b	restore
-#else
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	restore_math
-	b	restore
-#endif
-1:	andi.	r0,r4,_TIF_NEED_RESCHED
-	beq	2f
-	bl	restore_interrupts
-	SCHEDULE_USER
-	b	ret_from_except_lite
-2:
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	andi.	r0,r4,_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM
-	bne	3f		/* only restore TM if nothing else to do */
+	.balign IFETCH_ALIGN_BYTES
+	.globl interrupt_return_lite
+interrupt_return_lite:
+_ASM_NOKPROBE_SYMBOL(interrupt_return_lite)
+	ld	r4,_MSR(r1)
+	andi.	r0,r4,MSR_PR
+	beq	.Lkernel_interrupt_return
 	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	restore_tm_state
-	b	restore
-3:
-#endif
-	bl	save_nvgprs
-	/*
-	 * Use a non volatile GPR to save and restore our thread_info flags
-	 * across the call to restore_interrupts.
-	 */
-	mr	r30,r4
-	bl	restore_interrupts
-	mr	r4,r30
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	do_notify_resume
-	b	ret_from_except
-
-resume_kernel:
-	/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
-	andis.	r8,r4,_TIF_EMULATE_STACK_STORE@h
-	beq+	1f
+	bl	interrupt_exit_user_prepare
+	cmpdi	r3,0
+	bne-	.Lrestore_nvgprs
 
-	addi	r8,r1,INT_FRAME_SIZE	/* Get the kprobed function entry */
+.Lfast_user_interrupt_return:
+	ld	r11,_NIP(r1)
+	ld	r12,_MSR(r1)
+BEGIN_FTR_SECTION
+	ld	r10,_PPR(r1)
+	mtspr	SPRN_PPR,r10
+END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
+	mtspr	SPRN_SRR0,r11
+	mtspr	SPRN_SRR1,r12
 
-	ld	r3,GPR1(r1)
-	subi	r3,r3,INT_FRAME_SIZE	/* dst: Allocate a trampoline exception frame */
-	mr	r4,r1			/* src:  current exception frame */
-	mr	r1,r3			/* Reroute the trampoline frame to r1 */
+BEGIN_FTR_SECTION
+	stdcx.	r0,0,r1		/* to clear the reservation */
+FTR_SECTION_ELSE
+	ldarx	r0,0,r1
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
-	/* Copy from the original to the trampoline. */
-	li	r5,INT_FRAME_SIZE/8	/* size: INT_FRAME_SIZE */
-	li	r6,0			/* start offset: 0 */
-	mtctr	r5
-2:	ldx	r0,r6,r4
-	stdx	r0,r6,r3
-	addi	r6,r6,8
-	bdnz	2b
-
-	/* Do real store operation to complete stdu */
-	ld	r5,GPR1(r1)
-	std	r8,0(r5)
-
-	/* Clear _TIF_EMULATE_STACK_STORE flag */
-	lis	r11,_TIF_EMULATE_STACK_STORE@h
-	addi	r5,r9,TI_FLAGS
-0:	ldarx	r4,0,r5
-	andc	r4,r4,r11
-	stdcx.	r4,0,r5
-	bne-	0b
-1:
-
-#ifdef CONFIG_PREEMPTION
-	/* Check if we need to preempt */
-	andi.	r0,r4,_TIF_NEED_RESCHED
-	beq+	restore
-	/* Check that preempt_count() == 0 and interrupts are enabled */
-	lwz	r8,TI_PREEMPT(r9)
-	cmpwi	cr0,r8,0
-	bne	restore
-	ld	r0,SOFTE(r1)
-	andi.	r0,r0,IRQS_DISABLED
-	bne	restore
+	ld	r3,_CCR(r1)
+	ld	r4,_LINK(r1)
+	ld	r5,_CTR(r1)
+	ld	r6,_XER(r1)
+	li	r0,0
 
-	/*
-	 * Here we are preempting the current task. We want to make
-	 * sure we are soft-disabled first and reconcile irq state.
-	 */
-	RECONCILE_IRQ_STATE(r3,r4)
-	bl	preempt_schedule_irq
+	REST_4GPRS(7, r1)
+	REST_2GPRS(11, r1)
+	REST_GPR(13, r1)
 
-	/*
-	 * arch_local_irq_restore() from preempt_schedule_irq above may
-	 * enable hard interrupt but we really should disable interrupts
-	 * when we return from the interrupt, and so that we don't get
-	 * interrupted after loading SRR0/1.
-	 */
-#ifdef CONFIG_PPC_BOOK3E
-	wrteei	0
-#else
-	li	r10,MSR_RI
-	mtmsrd	r10,1		  /* Update machine state */
-#endif /* CONFIG_PPC_BOOK3E */
-#endif /* CONFIG_PREEMPTION */
+	mtcr	r3
+	mtlr	r4
+	mtctr	r5
+	mtspr	SPRN_XER,r6
 
-	.globl	fast_exc_return_irq
-fast_exc_return_irq:
-restore:
-	/*
-	 * This is the main kernel exit path. First we check if we
-	 * are about to re-enable interrupts
-	 */
-	ld	r5,SOFTE(r1)
-	lbz	r6,PACAIRQSOFTMASK(r13)
-	andi.	r5,r5,IRQS_DISABLED
-	bne	.Lrestore_irq_off
+	REST_4GPRS(2, r1)
+	REST_GPR(6, r1)
+	REST_GPR(0, r1)
+	REST_GPR(1, r1)
+	RFI_TO_USER
+	b	.	/* prevent speculative execution */
 
-	/* We are enabling, were we already enabled ? Yes, just return */
-	andi.	r6,r6,IRQS_DISABLED
-	beq	cr0,.Ldo_restore
+.Lrestore_nvgprs:
+	REST_NVGPRS(r1)
+	b	.Lfast_user_interrupt_return
 
-	/*
-	 * We are about to soft-enable interrupts (we are hard disabled
-	 * at this point). We check if there's anything that needs to
-	 * be replayed first.
-	 */
-	lbz	r0,PACAIRQHAPPENED(r13)
-	cmpwi	cr0,r0,0
-	bne-	.Lrestore_check_irq_replay
+	.balign IFETCH_ALIGN_BYTES
+.Lkernel_interrupt_return:
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	interrupt_exit_kernel_prepare
 
-	/*
-	 * Get here when nothing happened while soft-disabled, just
-	 * soft-enable and move-on. We will hard-enable as a side
-	 * effect of rfi
-	 */
-.Lrestore_no_replay:
-	TRACE_ENABLE_INTS
-	li	r0,IRQS_ENABLED
-	stb	r0,PACAIRQSOFTMASK(r13);
+.Lfast_kernel_interrupt_return:
+	cmpdi	cr1,r3,0
+	ld	r11,_NIP(r1)
+	ld	r12,_MSR(r1)
+	mtspr	SPRN_SRR0,r11
+	mtspr	SPRN_SRR1,r12
 
-	/*
-	 * Final return path. BookE is handled in a different file
-	 */
-.Ldo_restore:
-#ifdef CONFIG_PPC_BOOK3E
-	b	exception_return_book3e
-#else
-	/*
-	 * Clear the reservation. If we know the CPU tracks the address of
-	 * the reservation then we can potentially save some cycles and use
-	 * a larx. On POWER6 and POWER7 this is significantly faster.
-	 */
 BEGIN_FTR_SECTION
 	stdcx.	r0,0,r1		/* to clear the reservation */
 FTR_SECTION_ELSE
-	ldarx	r4,0,r1
+	ldarx	r0,0,r1
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_STCX_CHECKS_ADDRESS)
 
-	/*
-	 * Some code path such as load_up_fpu or altivec return directly
-	 * here. They run entirely hard disabled and do not alter the
-	 * interrupt state. They also don't use lwarx/stwcx. and thus
-	 * are known not to leave dangling reservations.
-	 */
-	.globl	fast_exception_return
-fast_exception_return:
-	ld	r3,_MSR(r1)
+	ld	r3,_LINK(r1)
 	ld	r4,_CTR(r1)
-	ld	r0,_LINK(r1)
-	mtctr	r4
-	mtlr	r0
-	ld	r4,_XER(r1)
-	mtspr	SPRN_XER,r4
-
-	kuap_check_amr r5, r6
-
-	REST_8GPRS(5, r1)
-
-	andi.	r0,r3,MSR_RI
-	beq-	.Lunrecov_restore
-
-	/*
-	 * Clear RI before restoring r13.  If we are returning to
-	 * userspace and we take an exception after restoring r13,
-	 * we end up corrupting the userspace r13 value.
-	 */
-	li	r4,0
-	mtmsrd	r4,1
-
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	/* TM debug */
-	std	r3, PACATMSCRATCH(r13) /* Stash returned-to MSR */
-#endif
-	/*
-	 * r13 is our per cpu area, only restore it if we are returning to
-	 * userspace the value stored in the stack frame may belong to
-	 * another CPU.
-	 */
-	andi.	r0,r3,MSR_PR
-	beq	1f
-BEGIN_FTR_SECTION
-	/* Restore PPR */
-	ld	r2,_PPR(r1)
-	mtspr	SPRN_PPR,r2
-END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
-	ACCOUNT_CPU_USER_EXIT(r13, r2, r4)
-	REST_GPR(13, r1)
-
-	/*
-	 * We don't need to restore AMR on the way back to userspace for KUAP.
-	 * The value of AMR only matters while we're in the kernel.
-	 */
-	mtspr	SPRN_SRR1,r3
-
-	ld	r2,_CCR(r1)
-	mtcrf	0xFF,r2
-	ld	r2,_NIP(r1)
-	mtspr	SPRN_SRR0,r2
-
-	ld	r0,GPR0(r1)
-	ld	r2,GPR2(r1)
-	ld	r3,GPR3(r1)
-	ld	r4,GPR4(r1)
-	ld	r1,GPR1(r1)
-	RFI_TO_USER
-	b	.	/* prevent speculative execution */
+	ld	r5,_XER(r1)
+	ld	r6,_CCR(r1)
+	li	r0,0
 
-1:	mtspr	SPRN_SRR1,r3
+	REST_4GPRS(7, r1)
+	REST_2GPRS(11, r1)
 
-	ld	r2,_CCR(r1)
-	mtcrf	0xFF,r2
-	ld	r2,_NIP(r1)
-	mtspr	SPRN_SRR0,r2
+	mtlr	r3
+	mtctr	r4
+	mtspr	SPRN_XER,r5
 
 	/*
 	 * Leaving a stale exception_marker on the stack can confuse
 	 * the reliable stack unwinder later on. Clear it.
 	 */
-	li	r2,0
-	std	r2,STACK_FRAME_OVERHEAD-16(r1)
+	std	r0,STACK_FRAME_OVERHEAD-16(r1)
 
-	ld	r0,GPR0(r1)
-	ld	r2,GPR2(r1)
-	ld	r3,GPR3(r1)
+	REST_4GPRS(2, r1)
 
-	kuap_restore_amr r4
-
-	ld	r4,GPR4(r1)
-	ld	r1,GPR1(r1)
+	bne-	cr1,1f /* emulate stack store */
+	mtcr	r6
+	REST_GPR(6, r1)
+	REST_GPR(0, r1)
+	REST_GPR(1, r1)
 	RFI_TO_KERNEL
 	b	.	/* prevent speculative execution */
 
-#endif /* CONFIG_PPC_BOOK3E */
-
-	/*
-	 * We are returning to a context with interrupts soft disabled.
-	 *
-	 * However, we may also about to hard enable, so we need to
-	 * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
-	 * or that bit can get out of sync and bad things will happen
-	 */
-.Lrestore_irq_off:
-	ld	r3,_MSR(r1)
-	lbz	r7,PACAIRQHAPPENED(r13)
-	andi.	r0,r3,MSR_EE
-	beq	1f
-	rlwinm	r7,r7,0,~PACA_IRQ_HARD_DIS
-	stb	r7,PACAIRQHAPPENED(r13)
-1:
-#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
-	/* The interrupt should not have soft enabled. */
-	lbz	r7,PACAIRQSOFTMASK(r13)
-1:	tdeqi	r7,IRQS_ENABLED
-	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
-#endif
-	b	.Ldo_restore
-
-	/*
-	 * Something did happen, check if a re-emit is needed
-	 * (this also clears paca->irq_happened)
-	 */
-.Lrestore_check_irq_replay:
-	/* XXX: We could implement a fast path here where we check
-	 * for irq_happened being just 0x01, in which case we can
-	 * clear it and return. That means that we would potentially
-	 * miss a decrementer having wrapped all the way around.
-	 *
-	 * Still, this might be useful for things like hash_page
-	 */
-	bl	__check_irq_replay
-	cmpwi	cr0,r3,0
-	beq	.Lrestore_no_replay
- 
-	/*
-	 * We need to re-emit an interrupt. We do so by re-using our
-	 * existing exception frame. We first change the trap value,
-	 * but we need to ensure we preserve the low nibble of it
-	 */
-	ld	r4,_TRAP(r1)
-	clrldi	r4,r4,60
-	or	r4,r4,r3
-	std	r4,_TRAP(r1)
-
-	/*
-	 * PACA_IRQ_HARD_DIS won't always be set here, so set it now
-	 * to reconcile the IRQ state. Tracing is already accounted for.
-	 */
-	lbz	r4,PACAIRQHAPPENED(r13)
-	ori	r4,r4,PACA_IRQ_HARD_DIS
-	stb	r4,PACAIRQHAPPENED(r13)
-
-	/*
-	 * Then find the right handler and call it. Interrupts are
-	 * still soft-disabled and we keep them that way.
-	*/
-	cmpwi	cr0,r3,0x500
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
- 	bl	do_IRQ
-	b	ret_from_except
-1:	cmpwi	cr0,r3,0xf00
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	performance_monitor_exception
-	b	ret_from_except
-1:	cmpwi	cr0,r3,0xe60
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	handle_hmi_exception
-	b	ret_from_except
-1:	cmpwi	cr0,r3,0x900
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	timer_interrupt
-	b	ret_from_except
-#ifdef CONFIG_PPC_DOORBELL
-1:
-#ifdef CONFIG_PPC_BOOK3E
-	cmpwi	cr0,r3,0x280
-#else
-	cmpwi	cr0,r3,0xa00
-#endif /* CONFIG_PPC_BOOK3E */
-	bne	1f
-	addi	r3,r1,STACK_FRAME_OVERHEAD;
-	bl	doorbell_exception
-#endif /* CONFIG_PPC_DOORBELL */
-1:	b	ret_from_except /* What else to do here ? */
- 
-.Lunrecov_restore:
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	unrecoverable_exception
-	b	.Lunrecov_restore
-
-_ASM_NOKPROBE_SYMBOL(ret_from_except);
-_ASM_NOKPROBE_SYMBOL(ret_from_except_lite);
-_ASM_NOKPROBE_SYMBOL(resume_kernel);
-_ASM_NOKPROBE_SYMBOL(fast_exc_return_irq);
-_ASM_NOKPROBE_SYMBOL(restore);
-_ASM_NOKPROBE_SYMBOL(fast_exception_return);
+1:	/*
+	 * Emulate stack store with update. New r1 value was already calculated
+	 * and updated in our interrupt regs by emulate_loadstore, but we can't
+	 * store the previous value of r1 to the stack before re-loading our
+	 * registers from it, otherwise they could be clobbered.  Use
+	 * PACA_EXGEN as temporary storage to hold the store data, as
+	 * interrupts are disabled here so it won't be clobbered.
+	 */
+	mtcr	r6
+	std	r9,PACA_EXGEN+0(r13)
+	addi	r9,r1,INT_FRAME_SIZE /* get original r1 */
+	REST_GPR(6, r1)
+	REST_GPR(0, r1)
+	REST_GPR(1, r1)
+	std	r9,0(r1) /* perform store component of stdu */
+	ld	r9,PACA_EXGEN+0(r13)
 
+	RFI_TO_KERNEL
+	b	.	/* prevent speculative execution */
+#endif /* CONFIG_PPC_BOOK3S */
 
 #ifdef CONFIG_PPC_RTAS
 /*
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 4efac5490216..d9ed79415100 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -24,6 +24,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_booke_hv_asm.h>
 #include <asm/feature-fixups.h>
+#include <asm/context_tracking.h>
 
 /* XXX This will ultimately add space for a special exception save
  *     structure used to save things like SRR0/SRR1, SPRGs, MAS, etc...
@@ -1041,17 +1042,161 @@ alignment_more:
 	bl	alignment_exception
 	b	ret_from_except
 
-/*
- * We branch here from entry_64.S for the last stage of the exception
- * return code path. MSR:EE is expected to be off at that point
- */
-_GLOBAL(exception_return_book3e)
-	b	1f
+	.align	7
+_GLOBAL(ret_from_except)
+	ld	r11,_TRAP(r1)
+	andi.	r0,r11,1
+	bne	ret_from_except_lite
+	REST_NVGPRS(r1)
+
+_GLOBAL(ret_from_except_lite)
+	/*
+	 * Disable interrupts so that current_thread_info()->flags
+	 * can't change between when we test it and when we return
+	 * from the interrupt.
+	 */
+	wrteei	0
+
+	ld	r9, PACA_THREAD_INFO(r13)
+	ld	r3,_MSR(r1)
+	ld	r10,PACACURRENT(r13)
+	ld	r4,TI_FLAGS(r9)
+	andi.	r3,r3,MSR_PR
+	beq	resume_kernel
+	lwz	r3,(THREAD+THREAD_DBCR0)(r10)
+
+	/* Check current_thread_info()->flags */
+	andi.	r0,r4,_TIF_USER_WORK_MASK
+	bne	1f
+	/*
+	 * Check to see if the dbcr0 register is set up to debug.
+	 * Use the internal debug mode bit to do this.
+	 */
+	andis.	r0,r3,DBCR0_IDM@h
+	beq	restore
+	mfmsr	r0
+	rlwinm	r0,r0,0,~MSR_DE	/* Clear MSR.DE */
+	mtmsr	r0
+	mtspr	SPRN_DBCR0,r3
+	li	r10, -1
+	mtspr	SPRN_DBSR,r10
+	b	restore
+1:	andi.	r0,r4,_TIF_NEED_RESCHED
+	beq	2f
+	bl	restore_interrupts
+	SCHEDULE_USER
+	b	ret_from_except_lite
+2:
+	bl	save_nvgprs
+	/*
+	 * Use a non volatile GPR to save and restore our thread_info flags
+	 * across the call to restore_interrupts.
+	 */
+	mr	r30,r4
+	bl	restore_interrupts
+	mr	r4,r30
+	addi	r3,r1,STACK_FRAME_OVERHEAD
+	bl	do_notify_resume
+	b	ret_from_except
+
+resume_kernel:
+	/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
+	andis.	r8,r4,_TIF_EMULATE_STACK_STORE@h
+	beq+	1f
+
+	addi	r8,r1,INT_FRAME_SIZE	/* Get the kprobed function entry */
+
+	ld	r3,GPR1(r1)
+	subi	r3,r3,INT_FRAME_SIZE	/* dst: Allocate a trampoline exception frame */
+	mr	r4,r1			/* src:  current exception frame */
+	mr	r1,r3			/* Reroute the trampoline frame to r1 */
+
+	/* Copy from the original to the trampoline. */
+	li	r5,INT_FRAME_SIZE/8	/* size: INT_FRAME_SIZE */
+	li	r6,0			/* start offset: 0 */
+	mtctr	r5
+2:	ldx	r0,r6,r4
+	stdx	r0,r6,r3
+	addi	r6,r6,8
+	bdnz	2b
+
+	/* Do real store operation to complete stdu */
+	ld	r5,GPR1(r1)
+	std	r8,0(r5)
+
+	/* Clear _TIF_EMULATE_STACK_STORE flag */
+	lis	r11,_TIF_EMULATE_STACK_STORE@h
+	addi	r5,r9,TI_FLAGS
+0:	ldarx	r4,0,r5
+	andc	r4,r4,r11
+	stdcx.	r4,0,r5
+	bne-	0b
+1:
+
+#ifdef CONFIG_PREEMPT
+	/* Check if we need to preempt */
+	andi.	r0,r4,_TIF_NEED_RESCHED
+	beq+	restore
+	/* Check that preempt_count() == 0 and interrupts are enabled */
+	lwz	r8,TI_PREEMPT(r9)
+	cmpwi	cr0,r8,0
+	bne	restore
+	ld	r0,SOFTE(r1)
+	andi.	r0,r0,IRQS_DISABLED
+	bne	restore
+
+	/*
+	 * Here we are preempting the current task. We want to make
+	 * sure we are soft-disabled first and reconcile irq state.
+	 */
+	RECONCILE_IRQ_STATE(r3,r4)
+	bl	preempt_schedule_irq
+
+	/*
+	 * arch_local_irq_restore() from preempt_schedule_irq above may
+	 * enable hard interrupt but we really should disable interrupts
+	 * when we return from the interrupt, and so that we don't get
+	 * interrupted after loading SRR0/1.
+	 */
+	wrteei	0
+#endif /* CONFIG_PREEMPT */
+
+restore:
+	/*
+	 * This is the main kernel exit path. First we check if we
+	 * are about to re-enable interrupts
+	 */
+	ld	r5,SOFTE(r1)
+	lbz	r6,PACAIRQSOFTMASK(r13)
+	andi.	r5,r5,IRQS_DISABLED
+	bne	.Lrestore_irq_off
+
+	/* We are enabling, were we already enabled ? Yes, just return */
+	andi.	r6,r6,IRQS_DISABLED
+	beq	cr0,fast_exception_return
+
+	/*
+	 * We are about to soft-enable interrupts (we are hard disabled
+	 * at this point). We check if there's anything that needs to
+	 * be replayed first.
+	 */
+	lbz	r0,PACAIRQHAPPENED(r13)
+	cmpwi	cr0,r0,0
+	bne-	.Lrestore_check_irq_replay
+
+	/*
+	 * Get here when nothing happened while soft-disabled, just
+	 * soft-enable and move-on. We will hard-enable as a side
+	 * effect of rfi
+	 */
+.Lrestore_no_replay:
+	TRACE_ENABLE_INTS
+	li	r0,IRQS_ENABLED
+	stb	r0,PACAIRQSOFTMASK(r13);
 
 /* This is the return from load_up_fpu fast path which could do with
  * less GPR restores in fact, but for now we have a single return path
  */
-	.globl fast_exception_return
 fast_exception_return:
 	wrteei	0
 1:	mr	r0,r13
@@ -1092,6 +1237,102 @@ fast_exception_return:
 	mfspr	r13,SPRN_SPRG_GEN_SCRATCH
 	rfi
 
+	/*
+	 * We are returning to a context with interrupts soft disabled.
+	 *
+	 * However, we may also about to hard enable, so we need to
+	 * make sure that in this case, we also clear PACA_IRQ_HARD_DIS
+	 * or that bit can get out of sync and bad things will happen
+	 */
+.Lrestore_irq_off:
+	ld	r3,_MSR(r1)
+	lbz	r7,PACAIRQHAPPENED(r13)
+	andi.	r0,r3,MSR_EE
+	beq	1f
+	rlwinm	r7,r7,0,~PACA_IRQ_HARD_DIS
+	stb	r7,PACAIRQHAPPENED(r13)
+1:
+#if defined(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG) && defined(CONFIG_BUG)
+	/* The interrupt should not have soft enabled. */
+	lbz	r7,PACAIRQSOFTMASK(r13)
+1:	tdeqi	r7,IRQS_ENABLED
+	EMIT_BUG_ENTRY 1b,__FILE__,__LINE__,BUGFLAG_WARNING
+#endif
+	b	fast_exception_return
+
+	/*
+	 * Something did happen, check if a re-emit is needed
+	 * (this also clears paca->irq_happened)
+	 */
+.Lrestore_check_irq_replay:
+	/* XXX: We could implement a fast path here where we check
+	 * for irq_happened being just 0x01, in which case we can
+	 * clear it and return. That means that we would potentially
+	 * miss a decrementer having wrapped all the way around.
+	 *
+	 * Still, this might be useful for things like hash_page
+	 */
+	bl	__check_irq_replay
+	cmpwi	cr0,r3,0
+	beq	.Lrestore_no_replay
+
+	/*
+	 * We need to re-emit an interrupt. We do so by re-using our
+	 * existing exception frame. We first change the trap value,
+	 * but we need to ensure we preserve the low nibble of it
+	 */
+	ld	r4,_TRAP(r1)
+	clrldi	r4,r4,60
+	or	r4,r4,r3
+	std	r4,_TRAP(r1)
+
+	/*
+	 * PACA_IRQ_HARD_DIS won't always be set here, so set it now
+	 * to reconcile the IRQ state. Tracing is already accounted for.
+	 */
+	lbz	r4,PACAIRQHAPPENED(r13)
+	ori	r4,r4,PACA_IRQ_HARD_DIS
+	stb	r4,PACAIRQHAPPENED(r13)
+
+	/*
+	 * Then find the right handler and call it. Interrupts are
+	 * still soft-disabled and we keep them that way.
+	*/
+	cmpwi	cr0,r3,0x500
+	bne	1f
+	addi	r3,r1,STACK_FRAME_OVERHEAD;
+	bl	do_IRQ
+	b	ret_from_except
+1:	cmpwi	cr0,r3,0xf00
+	bne	1f
+	addi	r3,r1,STACK_FRAME_OVERHEAD;
+	bl	performance_monitor_exception
+	b	ret_from_except
+1:	cmpwi	cr0,r3,0xe60
+	bne	1f
+	addi	r3,r1,STACK_FRAME_OVERHEAD;
+	bl	handle_hmi_exception
+	b	ret_from_except
+1:	cmpwi	cr0,r3,0x900
+	bne	1f
+	addi	r3,r1,STACK_FRAME_OVERHEAD;
+	bl	timer_interrupt
+	b	ret_from_except
+#ifdef CONFIG_PPC_DOORBELL
+1:
+	cmpwi	cr0,r3,0x280
+	bne	1f
+	addi	r3,r1,STACK_FRAME_OVERHEAD;
+	bl	doorbell_exception
+#endif /* CONFIG_PPC_DOORBELL */
+1:	b	ret_from_except /* What else to do here ? */
+
+_ASM_NOKPROBE_SYMBOL(ret_from_except);
+_ASM_NOKPROBE_SYMBOL(ret_from_except_lite);
+_ASM_NOKPROBE_SYMBOL(resume_kernel);
+_ASM_NOKPROBE_SYMBOL(restore);
+_ASM_NOKPROBE_SYMBOL(fast_exception_return);
+
 /*
  * Trampolines used when spotting a bad kernel stack pointer in
  * the exception entry code.
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index d6536a7c2a01..11244031adc5 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -589,6 +589,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	std	r10,GPR12(r1)
 	std	r11,GPR13(r1)
 
+	SAVE_NVGPRS(r1)
+
 	.if IDAR
 	.if IISIDE
 	ld	r10,_NIP(r1)
@@ -625,7 +627,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	mfspr	r11,SPRN_XER		/* save XER in stackframe	*/
 	std	r10,SOFTE(r1)
 	std	r11,_XER(r1)
-	li	r9,(IVEC)+1
+	li	r9,IVEC
 	std	r9,_TRAP(r1)		/* set trap number		*/
 	li	r10,0
 	ld	r11,exception_marker@toc(r2)
@@ -932,7 +934,6 @@ EXC_COMMON_BEGIN(system_reset_common)
 	ld	r1,PACA_NMI_EMERG_SP(r13)
 	subi	r1,r1,INT_FRAME_SIZE
 	__GEN_COMMON_BODY system_reset
-	bl	save_nvgprs
 	/*
 	 * Set IRQS_ALL_DISABLED unconditionally so irqs_disabled() does
 	 * the right thing. We do not want to reconcile because that goes
@@ -1115,7 +1116,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_HVMODE)
 	li	r10,MSR_RI
 	mtmsrd	r10,1
 
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	machine_check_early
 	std	r3,RESULT(r1)	/* Save result */
@@ -1208,10 +1208,9 @@ EXC_COMMON_BEGIN(machine_check_common)
 	/* Enable MSR_RI when finished with PACA_EXMC */
 	li	r10,MSR_RI
 	mtmsrd 	r10,1
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	machine_check_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM machine_check
 
@@ -1378,20 +1377,19 @@ BEGIN_MMU_FTR_SECTION
 	bl	do_slb_fault
 	cmpdi	r3,0
 	bne-	1f
-	b	fast_exception_return
+	b	fast_interrupt_return
 1:	/* Error case */
 MMU_FTR_SECTION_ELSE
 	/* Radix case, access is outside page table range */
 	li	r3,-EFAULT
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	std	r3,RESULT(r1)
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	ld	r4,_DAR(r1)
 	ld	r5,RESULT(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_bad_slb_fault
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM data_access_slb
 
@@ -1471,20 +1469,19 @@ BEGIN_MMU_FTR_SECTION
 	bl	do_slb_fault
 	cmpdi	r3,0
 	bne-	1f
-	b	fast_exception_return
+	b	fast_interrupt_return
 1:	/* Error case */
 MMU_FTR_SECTION_ELSE
 	/* Radix case, access is outside page table range */
 	li	r3,-EFAULT
 ALT_MMU_FTR_SECTION_END_IFCLR(MMU_FTR_TYPE_RADIX)
 	std	r3,RESULT(r1)
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	ld	r4,_DAR(r1)
 	ld	r5,RESULT(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_bad_slb_fault
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM instruction_access_slb
 
@@ -1532,7 +1529,7 @@ EXC_COMMON_BEGIN(hardware_interrupt_common)
 	RUNLATCH_ON
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_IRQ
-	b	ret_from_except_lite
+	b	interrupt_return_lite
 
 	GEN_KVM hardware_interrupt
 
@@ -1558,10 +1555,9 @@ EXC_VIRT_BEGIN(alignment, 0x4600, 0x100)
 EXC_VIRT_END(alignment, 0x4600, 0x100)
 EXC_COMMON_BEGIN(alignment_common)
 	GEN_COMMON alignment
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	alignment_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM alignment
 
@@ -1622,10 +1618,9 @@ EXC_COMMON_BEGIN(program_check_common)
 	__ISTACK(program_check)=1
 	__GEN_COMMON_BODY program_check
 3:
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	program_check_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM program_check
 
@@ -1656,7 +1651,6 @@ EXC_VIRT_END(fp_unavailable, 0x4800, 0x100)
 EXC_COMMON_BEGIN(fp_unavailable_common)
 	GEN_COMMON fp_unavailable
 	bne	1f			/* if from user, just load it up */
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	kernel_fp_unavailable_exception
@@ -1673,14 +1667,13 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_TM)
 #endif
 	bl	load_up_fpu
-	b	fast_exception_return
+	b	fast_interrupt_return
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	fp_unavailable_tm
-	b	ret_from_except
+	b	interrupt_return
 #endif
 
 	GEN_KVM fp_unavailable
@@ -1723,7 +1716,7 @@ EXC_COMMON_BEGIN(decrementer_common)
 	RUNLATCH_ON
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	timer_interrupt
-	b	ret_from_except_lite
+	b	interrupt_return_lite
 
 	GEN_KVM decrementer
 
@@ -1814,7 +1807,7 @@ EXC_COMMON_BEGIN(doorbell_super_common)
 #else
 	bl	unknown_exception
 #endif
-	b	ret_from_except_lite
+	b	interrupt_return_lite
 
 	GEN_KVM doorbell_super
 
@@ -1986,10 +1979,9 @@ EXC_VIRT_BEGIN(single_step, 0x4d00, 0x100)
 EXC_VIRT_END(single_step, 0x4d00, 0x100)
 EXC_COMMON_BEGIN(single_step_common)
 	GEN_COMMON single_step
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	single_step_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM single_step
 
@@ -2024,7 +2016,6 @@ EXC_VIRT_BEGIN(h_data_storage, 0x4e00, 0x20)
 EXC_VIRT_END(h_data_storage, 0x4e00, 0x20)
 EXC_COMMON_BEGIN(h_data_storage_common)
 	GEN_COMMON h_data_storage
-	bl      save_nvgprs
 	addi    r3,r1,STACK_FRAME_OVERHEAD
 BEGIN_MMU_FTR_SECTION
 	ld	r4,_DAR(r1)
@@ -2033,7 +2024,7 @@ BEGIN_MMU_FTR_SECTION
 MMU_FTR_SECTION_ELSE
 	bl      unknown_exception
 ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
-	b       ret_from_except
+	b       interrupt_return
 
 	GEN_KVM h_data_storage
 
@@ -2058,10 +2049,9 @@ EXC_VIRT_BEGIN(h_instr_storage, 0x4e20, 0x20)
 EXC_VIRT_END(h_instr_storage, 0x4e20, 0x20)
 EXC_COMMON_BEGIN(h_instr_storage_common)
 	GEN_COMMON h_instr_storage
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	unknown_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM h_instr_storage
 
@@ -2084,10 +2074,9 @@ EXC_VIRT_BEGIN(emulation_assist, 0x4e40, 0x20)
 EXC_VIRT_END(emulation_assist, 0x4e40, 0x20)
 EXC_COMMON_BEGIN(emulation_assist_common)
 	GEN_COMMON emulation_assist
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	emulation_assist_interrupt
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM emulation_assist
 
@@ -2169,10 +2158,9 @@ EXC_COMMON_BEGIN(hmi_exception_common)
 	GEN_COMMON hmi_exception
 	FINISH_NAP
 	RUNLATCH_ON
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	handle_hmi_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM hmi_exception
 
@@ -2206,7 +2194,7 @@ EXC_COMMON_BEGIN(h_doorbell_common)
 #else
 	bl	unknown_exception
 #endif
-	b	ret_from_except_lite
+	b	interrupt_return_lite
 
 	GEN_KVM h_doorbell
 
@@ -2236,7 +2224,7 @@ EXC_COMMON_BEGIN(h_virt_irq_common)
 	RUNLATCH_ON
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_IRQ
-	b	ret_from_except_lite
+	b	interrupt_return_lite
 
 	GEN_KVM h_virt_irq
 
@@ -2283,7 +2271,7 @@ EXC_COMMON_BEGIN(performance_monitor_common)
 	RUNLATCH_ON
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	performance_monitor_exception
-	b	ret_from_except_lite
+	b	interrupt_return_lite
 
 	GEN_KVM performance_monitor
 
@@ -2323,23 +2311,21 @@ BEGIN_FTR_SECTION
   END_FTR_SECTION_NESTED(CPU_FTR_TM, CPU_FTR_TM, 69)
 #endif
 	bl	load_up_altivec
-	b	fast_exception_return
+	b	fast_interrupt_return
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	altivec_unavailable_tm
-	b	ret_from_except
+	b	interrupt_return
 #endif
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	altivec_unavailable_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM altivec_unavailable
 
@@ -2381,20 +2367,18 @@ BEGIN_FTR_SECTION
 	b	load_up_vsx
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 2:	/* User process was in a transaction */
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	vsx_unavailable_tm
-	b	ret_from_except
+	b	interrupt_return
 #endif
 1:
 END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 #endif
-	bl	save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	vsx_unavailable_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM vsx_unavailable
 
@@ -2421,10 +2405,9 @@ EXC_VIRT_BEGIN(facility_unavailable, 0x4f60, 0x20)
 EXC_VIRT_END(facility_unavailable, 0x4f60, 0x20)
 EXC_COMMON_BEGIN(facility_unavailable_common)
 	GEN_COMMON facility_unavailable
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	facility_unavailable_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM facility_unavailable
 
@@ -2451,10 +2434,9 @@ EXC_VIRT_BEGIN(h_facility_unavailable, 0x4f80, 0x20)
 EXC_VIRT_END(h_facility_unavailable, 0x4f80, 0x20)
 EXC_COMMON_BEGIN(h_facility_unavailable_common)
 	GEN_COMMON h_facility_unavailable
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	facility_unavailable_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM h_facility_unavailable
 
@@ -2485,10 +2467,9 @@ EXC_REAL_END(cbe_system_error, 0x1200, 0x100)
 EXC_VIRT_NONE(0x5200, 0x100)
 EXC_COMMON_BEGIN(cbe_system_error_common)
 	GEN_COMMON cbe_system_error
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	cbe_system_error_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM cbe_system_error
 
@@ -2514,10 +2495,9 @@ EXC_VIRT_BEGIN(instruction_breakpoint, 0x5300, 0x100)
 EXC_VIRT_END(instruction_breakpoint, 0x5300, 0x100)
 EXC_COMMON_BEGIN(instruction_breakpoint_common)
 	GEN_COMMON instruction_breakpoint
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	instruction_breakpoint_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM instruction_breakpoint
 
@@ -2637,10 +2617,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 
 EXC_COMMON_BEGIN(denorm_exception_common)
 	GEN_COMMON denorm_exception
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	unknown_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM denorm_exception
 
@@ -2659,10 +2638,9 @@ EXC_REAL_END(cbe_maintenance, 0x1600, 0x100)
 EXC_VIRT_NONE(0x5600, 0x100)
 EXC_COMMON_BEGIN(cbe_maintenance_common)
 	GEN_COMMON cbe_maintenance
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	cbe_maintenance_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM cbe_maintenance
 
@@ -2687,14 +2665,13 @@ EXC_VIRT_BEGIN(altivec_assist, 0x5700, 0x100)
 EXC_VIRT_END(altivec_assist, 0x5700, 0x100)
 EXC_COMMON_BEGIN(altivec_assist_common)
 	GEN_COMMON altivec_assist
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 #ifdef CONFIG_ALTIVEC
 	bl	altivec_assist_exception
 #else
 	bl	unknown_exception
 #endif
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM altivec_assist
 
@@ -2713,10 +2690,9 @@ EXC_REAL_END(cbe_thermal, 0x1800, 0x100)
 EXC_VIRT_NONE(0x5800, 0x100)
 EXC_COMMON_BEGIN(cbe_thermal_common)
 	GEN_COMMON cbe_thermal
-	bl	save_nvgprs
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	cbe_thermal_exception
-	b	ret_from_except
+	b	interrupt_return
 
 	GEN_KVM cbe_thermal
 
@@ -2749,7 +2725,6 @@ EXC_COMMON_BEGIN(soft_nmi_common)
 	ld	r1,PACAEMERGSP(r13)
 	subi	r1,r1,INT_FRAME_SIZE
 	__GEN_COMMON_BODY soft_nmi
-	bl	save_nvgprs
 
 	/*
 	 * Set IRQS_ALL_DISABLED and save PACAIRQHAPPENED (see
@@ -3082,7 +3057,7 @@ do_hash_page:
         cmpdi	r3,0			/* see if __hash_page succeeded */
 
 	/* Success */
-	beq	fast_exc_return_irq	/* Return from exception on success */
+	beq	interrupt_return_lite	/* Return from exception on success */
 
 	/* Error */
 	blt-	13f
@@ -3099,17 +3074,15 @@ handle_page_fault:
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_page_fault
 	cmpdi	r3,0
-	beq+	ret_from_except_lite
-	bl	save_nvgprs
+	beq+	interrupt_return_lite
 	mr	r5,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r4,_DAR(r1)
 	bl	bad_page_fault
-	b	ret_from_except
+	b	interrupt_return
 
 /* We have a data breakpoint exception - handle it */
 handle_dabr_fault:
-	bl	save_nvgprs
 	ld      r4,_DAR(r1)
 	ld      r5,_DSISR(r1)
 	addi    r3,r1,STACK_FRAME_OVERHEAD
@@ -3117,21 +3090,20 @@ handle_dabr_fault:
 	/*
 	 * do_break() may have changed the NV GPRS while handling a breakpoint.
 	 * If so, we need to restore them with their updated values. Don't use
-	 * ret_from_except_lite here.
+	 * interrupt_return_lite here.
 	 */
-	b       ret_from_except
+	b       interrupt_return
 
 
 #ifdef CONFIG_PPC_BOOK3S_64
 /* We have a page fault that hash_page could handle but HV refused
  * the PTE insertion
  */
-13:	bl	save_nvgprs
-	mr	r5,r3
+13:	mr	r5,r3
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	ld	r4,_DAR(r1)
 	bl	low_hash_fault
-	b	ret_from_except
+	b	interrupt_return
 #endif
 
 /*
@@ -3141,11 +3113,10 @@ handle_dabr_fault:
  * were soft-disabled.  We want to invoke the exception handler for
  * the access, or panic if there isn't a handler.
  */
-77:	bl	save_nvgprs
-	addi	r3,r1,STACK_FRAME_OVERHEAD
+77:	addi	r3,r1,STACK_FRAME_OVERHEAD
 	li	r5,SIGSEGV
 	bl	bad_page_fault
-	b	ret_from_except
+	b	interrupt_return
 
 /*
  * When doorbell is triggered from system reset wakeup, the message is
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 2e5dca87b936..a25ed47087ee 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -110,6 +110,8 @@ static inline notrace int decrementer_check_overflow(void)
 	return now >= *next_tb;
 }
 
+#ifdef CONFIG_PPC_BOOK3E
+
 /* This is called whenever we are re-enabling interrupts
  * and returns either 0 (nothing to do) or 500/900/280/a00/e80 if
  * there's an EE, DEC or DBELL to generate.
@@ -169,41 +171,16 @@ notrace unsigned int __check_irq_replay(void)
 		}
 	}
 
-	/*
-	 * Force the delivery of pending soft-disabled interrupts on PS3.
-	 * Any HV call will have this side effect.
-	 */
-	if (firmware_has_feature(FW_FEATURE_PS3_LV1)) {
-		u64 tmp, tmp2;
-		lv1_get_version_info(&tmp, &tmp2);
-	}
-
-	/*
-	 * Check if an hypervisor Maintenance interrupt happened.
-	 * This is a higher priority interrupt than the others, so
-	 * replay it first.
-	 */
-	if (happened & PACA_IRQ_HMI) {
-		local_paca->irq_happened &= ~PACA_IRQ_HMI;
-		return 0xe60;
-	}
-
 	if (happened & PACA_IRQ_DEC) {
 		local_paca->irq_happened &= ~PACA_IRQ_DEC;
 		return 0x900;
 	}
 
-	if (happened & PACA_IRQ_PMI) {
-		local_paca->irq_happened &= ~PACA_IRQ_PMI;
-		return 0xf00;
-	}
-
 	if (happened & PACA_IRQ_EE) {
 		local_paca->irq_happened &= ~PACA_IRQ_EE;
 		return 0x500;
 	}
 
-#ifdef CONFIG_PPC_BOOK3E
 	/*
 	 * Check if an EPR external interrupt happened this bit is typically
 	 * set if we need to handle another "edge" interrupt from within the
@@ -218,20 +195,15 @@ notrace unsigned int __check_irq_replay(void)
 		local_paca->irq_happened &= ~PACA_IRQ_DBELL;
 		return 0x280;
 	}
-#else
-	if (happened & PACA_IRQ_DBELL) {
-		local_paca->irq_happened &= ~PACA_IRQ_DBELL;
-		return 0xa00;
-	}
-#endif /* CONFIG_PPC_BOOK3E */
 
 	/* There should be nothing left ! */
 	BUG_ON(local_paca->irq_happened != 0);
 
 	return 0;
 }
+#endif /* CONFIG_PPC_BOOK3E */
 
-static void replay_soft_interrupts(void)
+void replay_soft_interrupts(void)
 {
 	/*
 	 * We use local_paca rather than get_paca() to avoid all
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 009833f928bf..9c21288f8645 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -236,23 +236,9 @@ void enable_kernel_fp(void)
 	}
 }
 EXPORT_SYMBOL(enable_kernel_fp);
-
-static int restore_fp(struct task_struct *tsk)
-{
-	if (tsk->thread.load_fp) {
-		load_fp_state(&current->thread.fp_state);
-		current->thread.load_fp++;
-		return 1;
-	}
-	return 0;
-}
-#else
-static int restore_fp(struct task_struct *tsk) { return 0; }
 #endif /* CONFIG_PPC_FPU */
 
 #ifdef CONFIG_ALTIVEC
-#define loadvec(thr) ((thr).load_vec)
-
 static void __giveup_altivec(struct task_struct *tsk)
 {
 	unsigned long msr;
@@ -318,21 +304,6 @@ void flush_altivec_to_thread(struct task_struct *tsk)
 	}
 }
 EXPORT_SYMBOL_GPL(flush_altivec_to_thread);
-
-static int restore_altivec(struct task_struct *tsk)
-{
-	if (cpu_has_feature(CPU_FTR_ALTIVEC) && (tsk->thread.load_vec)) {
-		load_vr_state(&tsk->thread.vr_state);
-		tsk->thread.used_vr = 1;
-		tsk->thread.load_vec++;
-
-		return 1;
-	}
-	return 0;
-}
-#else
-#define loadvec(thr) 0
-static inline int restore_altivec(struct task_struct *tsk) { return 0; }
 #endif /* CONFIG_ALTIVEC */
 
 #ifdef CONFIG_VSX
@@ -400,18 +371,6 @@ void flush_vsx_to_thread(struct task_struct *tsk)
 	}
 }
 EXPORT_SYMBOL_GPL(flush_vsx_to_thread);
-
-static int restore_vsx(struct task_struct *tsk)
-{
-	if (cpu_has_feature(CPU_FTR_VSX)) {
-		tsk->thread.used_vsr = 1;
-		return 1;
-	}
-
-	return 0;
-}
-#else
-static inline int restore_vsx(struct task_struct *tsk) { return 0; }
 #endif /* CONFIG_VSX */
 
 #ifdef CONFIG_SPE
@@ -511,6 +470,53 @@ void giveup_all(struct task_struct *tsk)
 }
 EXPORT_SYMBOL(giveup_all);
 
+#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_PPC_FPU
+static int restore_fp(struct task_struct *tsk)
+{
+	if (tsk->thread.load_fp) {
+		load_fp_state(&current->thread.fp_state);
+		current->thread.load_fp++;
+		return 1;
+	}
+	return 0;
+}
+#else
+static int restore_fp(struct task_struct *tsk) { return 0; }
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_ALTIVEC
+#define loadvec(thr) ((thr).load_vec)
+static int restore_altivec(struct task_struct *tsk)
+{
+	if (cpu_has_feature(CPU_FTR_ALTIVEC) && (tsk->thread.load_vec)) {
+		load_vr_state(&tsk->thread.vr_state);
+		tsk->thread.used_vr = 1;
+		tsk->thread.load_vec++;
+
+		return 1;
+	}
+	return 0;
+}
+#else
+#define loadvec(thr) 0
+static inline int restore_altivec(struct task_struct *tsk) { return 0; }
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_VSX
+static int restore_vsx(struct task_struct *tsk)
+{
+	if (cpu_has_feature(CPU_FTR_VSX)) {
+		tsk->thread.used_vsr = 1;
+		return 1;
+	}
+
+	return 0;
+}
+#else
+static inline int restore_vsx(struct task_struct *tsk) { return 0; }
+#endif /* CONFIG_VSX */
+
 /*
  * The exception exit path calls restore_math() with interrupts hard disabled
  * but the soft irq state not "reconciled". ftrace code that calls
@@ -551,6 +557,7 @@ void notrace restore_math(struct pt_regs *regs)
 
 	regs->msr = msr;
 }
+#endif
 
 static void save_all(struct task_struct *tsk)
 {
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 75be20fdb270..a986effee1e0 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -24,7 +24,11 @@ notrace long system_call_exception(long r3, long r4, long r5, long r6, long r7,
 	unsigned long ti_flags;
 	syscall_fn f;
 
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S))
+		BUG_ON(!(regs->msr & MSR_RI));
 	BUG_ON(!(regs->msr & MSR_PR));
+	BUG_ON(!FULL_REGS(regs));
+	BUG_ON(regs->softe != IRQS_ENABLED);
 
 	account_cpu_user_entry();
 
@@ -196,7 +200,7 @@ again:
 		trace_hardirqs_off();
 		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
 		local_irq_enable();
-		/* Took an interrupt which may have more exit work to do. */
+		/* Took an interrupt, may have more exit work to do. */
 		goto again;
 	}
 	local_paca->irq_happened = 0;
@@ -212,3 +216,168 @@ again:
 
 	return ret;
 }
+
+#ifdef CONFIG_PPC_BOOK3S /* BOOK3E not yet using this */
+notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned long msr)
+{
+#ifdef CONFIG_PPC_BOOK3E
+	struct thread_struct *ts = &current->thread;
+#endif
+	unsigned long *ti_flagsp = &current_thread_info()->flags;
+	unsigned long ti_flags;
+	unsigned long flags;
+	unsigned long ret = 0;
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S))
+		BUG_ON(!(regs->msr & MSR_RI));
+	BUG_ON(!(regs->msr & MSR_PR));
+	BUG_ON(!FULL_REGS(regs));
+	BUG_ON(regs->softe != IRQS_ENABLED);
+
+	local_irq_save(flags);
+
+again:
+	ti_flags = READ_ONCE(*ti_flagsp);
+	while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
+		local_irq_enable(); /* returning to user: may enable */
+		if (ti_flags & _TIF_NEED_RESCHED) {
+			schedule();
+		} else {
+			if (ti_flags & _TIF_SIGPENDING)
+				ret |= _TIF_RESTOREALL;
+			do_notify_resume(regs, ti_flags);
+		}
+		local_irq_disable();
+		ti_flags = READ_ONCE(*ti_flagsp);
+	}
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && IS_ENABLED(CONFIG_PPC_FPU)) {
+		if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+				unlikely((ti_flags & _TIF_RESTORE_TM))) {
+			restore_tm_state(regs);
+		} else {
+			unsigned long mathflags = MSR_FP;
+
+			if (cpu_has_feature(CPU_FTR_VSX))
+				mathflags |= MSR_VEC | MSR_VSX;
+			else if (cpu_has_feature(CPU_FTR_ALTIVEC))
+				mathflags |= MSR_VEC;
+
+			if ((regs->msr & mathflags) != mathflags)
+				restore_math(regs);
+		}
+	}
+
+	trace_hardirqs_on();
+	__hard_EE_RI_disable();
+	if (unlikely(lazy_irq_pending())) {
+		__hard_RI_enable();
+		trace_hardirqs_off();
+		local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+		local_irq_enable();
+		local_irq_disable();
+		/* Took an interrupt, may have more exit work to do. */
+		goto again;
+	}
+	local_paca->irq_happened = 0;
+	irq_soft_mask_set(IRQS_ENABLED);
+
+#ifdef CONFIG_PPC_BOOK3E
+	if (unlikely(ts->debug.dbcr0 & DBCR0_IDM)) {
+		/*
+		 * Check to see if the dbcr0 register is set up to debug.
+		 * Use the internal debug mode bit to do this.
+		 */
+		mtmsr(mfmsr() & ~MSR_DE);
+		mtspr(SPRN_DBCR0, ts->debug.dbcr0);
+		mtspr(SPRN_DBSR, -1);
+	}
+#endif
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	local_paca->tm_scratch = regs->msr;
+#endif
+
+	kuap_check_amr();
+
+	account_cpu_user_exit();
+
+	return ret;
+}
+
+void unrecoverable_exception(struct pt_regs *regs);
+void preempt_schedule_irq(void);
+
+notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsigned long msr)
+{
+	unsigned long *ti_flagsp = &current_thread_info()->flags;
+	unsigned long flags;
+	unsigned long ret = 0;
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S) && unlikely(!(regs->msr & MSR_RI)))
+		unrecoverable_exception(regs);
+	BUG_ON(regs->msr & MSR_PR);
+	BUG_ON(!FULL_REGS(regs));
+
+	if (unlikely(*ti_flagsp & _TIF_EMULATE_STACK_STORE)) {
+		clear_bits(_TIF_EMULATE_STACK_STORE, ti_flagsp);
+		ret = 1;
+	}
+
+	local_irq_save(flags);
+
+	if (regs->softe == IRQS_ENABLED) {
+		/* Returning to a kernel context with local irqs enabled. */
+		WARN_ON_ONCE(!(regs->msr & MSR_EE));
+again:
+		if (IS_ENABLED(CONFIG_PREEMPT)) {
+			/* Return to preemptible kernel context */
+			if (unlikely(*ti_flagsp & _TIF_NEED_RESCHED)) {
+				if (preempt_count() == 0)
+					preempt_schedule_irq();
+			}
+		}
+
+		trace_hardirqs_on();
+		__hard_EE_RI_disable();
+		if (unlikely(lazy_irq_pending())) {
+			__hard_RI_enable();
+			irq_soft_mask_set(IRQS_ALL_DISABLED);
+			trace_hardirqs_off();
+			local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+			/*
+			 * Can't local_irq_restore to replay if we were in
+			 * interrupt context. Must replay directly.
+			 */
+			if (irqs_disabled_flags(flags)) {
+				replay_soft_interrupts();
+			} else {
+				local_irq_restore(flags);
+				local_irq_save(flags);
+			}
+			/* Took an interrupt, may have more exit work to do. */
+			goto again;
+		}
+		local_paca->irq_happened = 0;
+		irq_soft_mask_set(IRQS_ENABLED);
+	} else {
+		/* Returning to a kernel context with local irqs disabled. */
+		__hard_EE_RI_disable();
+		if (regs->msr & MSR_EE)
+			local_paca->irq_happened &= ~PACA_IRQ_HARD_DIS;
+	}
+
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	local_paca->tm_scratch = regs->msr;
+#endif
+
+	/*
+	 * We don't need to restore AMR on the way back to userspace for KUAP.
+	 * The value of AMR only matters while we're in the kernel.
+	 */
+	kuap_restore_amr(regs);
+
+	return ret;
+}
+#endif
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 25c14a0981bf..d20c5e79e03c 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -134,7 +134,7 @@ _GLOBAL(load_up_vsx)
 	/* enable use of VSX after return */
 	oris	r12,r12,MSR_VSX@h
 	std	r12,_MSR(r1)
-	b	fast_exception_return
+	b	fast_interrupt_return
 
 #endif /* CONFIG_VSX */
 
-- 
cgit v1.2.3


From f1763e623c69bcec2c1e739e990058de41d45030 Mon Sep 17 00:00:00 2001
From: Christophe Leroy
Date: Fri, 28 Feb 2020 00:14:39 +0000
Subject: powerpc/ptrace: drop unnecessary #ifdefs CONFIG_PPC64

Drop a bunch of #ifdefs CONFIG_PPC64 that are not vital.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/af38b87a7e1e3efe4f9b664eaeb029e6e7d69fdb.1582848567.git.christophe.leroy@c-s.fr
---
 arch/powerpc/include/asm/ptrace.h   |  2 ++
 arch/powerpc/kernel/ptrace/ptrace.c | 18 +++---------------
 2 files changed, 5 insertions(+), 15 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index 082a40153b94..e0195e6b892b 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -279,6 +279,8 @@ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs,
 #endif /* __ASSEMBLY__ */
 
 #ifndef __powerpc64__
+/* We need PT_SOFTE defined at all time to avoid #ifdefs */
+#define PT_SOFTE PT_MQ
 #else /* __powerpc64__ */
 #define PT_FPSCR32 (PT_FPR0 + 2*32 + 1)	/* each FP reg occupies 2 32-bit userspace slots */
 #define PT_VR0_32 164	/* each Vector reg occupies 4 slots in 32-bit */
diff --git a/arch/powerpc/kernel/ptrace/ptrace.c b/arch/powerpc/kernel/ptrace/ptrace.c
index 7ed54dbb2d7e..3dd94c296ac7 100644
--- a/arch/powerpc/kernel/ptrace/ptrace.c
+++ b/arch/powerpc/kernel/ptrace/ptrace.c
@@ -274,17 +274,15 @@ int ptrace_get_reg(struct task_struct *task, int regno, unsigned long *data)
 	if (regno == PT_DSCR)
 		return get_user_dscr(task, data);
 
-#ifdef CONFIG_PPC64
 	/*
 	 * softe copies paca->irq_soft_mask variable state. Since irq_soft_mask is
 	 * no more used as a flag, lets force usr to alway see the softe value as 1
 	 * which means interrupts are not soft disabled.
 	 */
-	if (regno == PT_SOFTE) {
+	if (IS_ENABLED(CONFIG_PPC64) && regno == PT_SOFTE) {
 		*data = 1;
 		return  0;
 	}
-#endif
 
 	regs_max = sizeof(struct user_pt_regs) / sizeof(unsigned long);
 	if (regno < regs_max) {
@@ -1998,7 +1996,6 @@ static const struct user_regset_view user_ppc_native_view = {
 	.regsets = native_regsets, .n = ARRAY_SIZE(native_regsets)
 };
 
-#ifdef CONFIG_PPC64
 #include <linux/compat.h>
 
 static int gpr32_get_common(struct task_struct *target,
@@ -2272,14 +2269,11 @@ static const struct user_regset_view user_ppc_compat_view = {
 	.name = "ppc", .e_machine = EM_PPC, .ei_osabi = ELF_OSABI,
 	.regsets = compat_regsets, .n = ARRAY_SIZE(compat_regsets)
 };
-#endif	/* CONFIG_PPC64 */
 
 const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 {
-#ifdef CONFIG_PPC64
-	if (test_tsk_thread_flag(task, TIF_32BIT))
+	if (IS_ENABLED(CONFIG_PPC64) && test_tsk_thread_flag(task, TIF_32BIT))
 		return &user_ppc_compat_view;
-#endif
 	return &user_ppc_native_view;
 }
 
@@ -3063,11 +3057,7 @@ long arch_ptrace(struct task_struct *child, long request,
 		else
 			dbginfo.num_data_bps = 0;
 		dbginfo.num_condition_regs = 0;
-#ifdef CONFIG_PPC64
-		dbginfo.data_bp_alignment = 8;
-#else
-		dbginfo.data_bp_alignment = 4;
-#endif
+		dbginfo.data_bp_alignment = sizeof(long);
 		dbginfo.sizeof_condition = 0;
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 		dbginfo.features = PPC_DEBUG_FEATURE_DATA_BP_RANGE;
@@ -3304,12 +3294,10 @@ long do_syscall_trace_enter(struct pt_regs *regs)
 	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
 		trace_sys_enter(regs, regs->gpr[0]);
 
-#ifdef CONFIG_PPC64
 	if (!is_32bit_task())
 		audit_syscall_entry(regs->gpr[0], regs->gpr[3], regs->gpr[4],
 				    regs->gpr[5], regs->gpr[6]);
 	else
-#endif
 		audit_syscall_entry(regs->gpr[0],
 				    regs->gpr[3] & 0xffffffff,
 				    regs->gpr[4] & 0xffffffff,
-- 
cgit v1.2.3


From b77afad84e1eedca03658ae1478ce5b8ed5aa18c Mon Sep 17 00:00:00 2001
From: Mike Rapoport
Date: Mon, 25 Nov 2019 11:20:33 +0200
Subject: powerpc/32: drop unused ISA_DMA_THRESHOLD

The ISA_DMA_THRESHOLD variable is set by several platforms but never
referenced.
Remove it.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20191125092033.20014-1-rppt@kernel.org
---
 arch/powerpc/include/asm/dma.h          | 3 +--
 arch/powerpc/kernel/setup_32.c          | 1 -
 arch/powerpc/platforms/44x/warp.c       | 3 ---
 arch/powerpc/platforms/52xx/efika.c     | 1 -
 arch/powerpc/platforms/amigaone/setup.c | 1 -
 arch/powerpc/platforms/chrp/setup.c     | 1 -
 arch/powerpc/platforms/powermac/setup.c | 1 -
 7 files changed, 1 insertion(+), 10 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/dma.h b/arch/powerpc/include/asm/dma.h
index 1b4f0254868f..6161a9596196 100644
--- a/arch/powerpc/include/asm/dma.h
+++ b/arch/powerpc/include/asm/dma.h
@@ -151,10 +151,9 @@
 #define DMA2_EXT_REG		0x4D6
 
 #ifndef __powerpc64__
-    /* in arch/ppc/kernel/setup.c -- Cort */
+    /* in arch/powerpc/kernel/setup_32.c -- Cort */
     extern unsigned int DMA_MODE_WRITE;
     extern unsigned int DMA_MODE_READ;
-    extern unsigned long ISA_DMA_THRESHOLD;
 #else
     #define DMA_MODE_READ	0x44	/* I/O to memory, no autoinit, increment, single mode */
     #define DMA_MODE_WRITE	0x48	/* memory to I/O, no autoinit, increment, single mode */
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 5b49b26eb154..305ca89d856f 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -58,7 +58,6 @@ EXPORT_SYMBOL_GPL(boot_cpuid_phys);
 int smp_hw_index[NR_CPUS];
 EXPORT_SYMBOL(smp_hw_index);
 
-unsigned long ISA_DMA_THRESHOLD;
 unsigned int DMA_MODE_READ;
 unsigned int DMA_MODE_WRITE;
 
diff --git a/arch/powerpc/platforms/44x/warp.c b/arch/powerpc/platforms/44x/warp.c
index 6620b64e4963..665f18e37efb 100644
--- a/arch/powerpc/platforms/44x/warp.c
+++ b/arch/powerpc/platforms/44x/warp.c
@@ -43,9 +43,6 @@ static int __init warp_probe(void)
 	if (!of_machine_is_compatible("pika,warp"))
 		return 0;
 
-	/* For arch_dma_alloc */
-	ISA_DMA_THRESHOLD = ~0L;
-
 	return 1;
 }
 
diff --git a/arch/powerpc/platforms/52xx/efika.c b/arch/powerpc/platforms/52xx/efika.c
index 61538869e88a..4514a6f7458a 100644
--- a/arch/powerpc/platforms/52xx/efika.c
+++ b/arch/powerpc/platforms/52xx/efika.c
@@ -205,7 +205,6 @@ static int __init efika_probe(void)
 	if (strcmp(model, "EFIKA5K2"))
 		return 0;
 
-	ISA_DMA_THRESHOLD = ~0L;
 	DMA_MODE_READ = 0x44;
 	DMA_MODE_WRITE = 0x48;
 
diff --git a/arch/powerpc/platforms/amigaone/setup.c b/arch/powerpc/platforms/amigaone/setup.c
index ea5e45e32683..f5d0bf999759 100644
--- a/arch/powerpc/platforms/amigaone/setup.c
+++ b/arch/powerpc/platforms/amigaone/setup.c
@@ -146,7 +146,6 @@ static int __init amigaone_probe(void)
 		 */
 		cur_cpu_spec->cpu_features &= ~CPU_FTR_NEED_COHERENT;
 
-		ISA_DMA_THRESHOLD = 0x00ffffff;
 		DMA_MODE_READ = 0x44;
 		DMA_MODE_WRITE = 0x48;
 
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index 8328cd5817b0..65a7e01a8f7d 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -569,7 +569,6 @@ static int __init chrp_probe(void)
  	if (strcmp(dtype, "chrp"))
 		return 0;
 
-	ISA_DMA_THRESHOLD = ~0L;
 	DMA_MODE_READ = 0x44;
 	DMA_MODE_WRITE = 0x48;
 
diff --git a/arch/powerpc/platforms/powermac/setup.c b/arch/powerpc/platforms/powermac/setup.c
index c6d5333729ed..95fb4feb6ccc 100644
--- a/arch/powerpc/platforms/powermac/setup.c
+++ b/arch/powerpc/platforms/powermac/setup.c
@@ -586,7 +586,6 @@ static int __init pmac_probe(void)
 
 #ifdef CONFIG_PPC32
 	/* isa_io_base gets set in pmac_pci_init */
-	ISA_DMA_THRESHOLD = ~0L;
 	DMA_MODE_READ = 1;
 	DMA_MODE_WRITE = 2;
 #endif /* CONFIG_PPC32 */
-- 
cgit v1.2.3


From c17eb4dca5a353a9dbbb8ad6934fe57af7165e91 Mon Sep 17 00:00:00 2001
From: Clement Courbet
Date: Mon, 30 Mar 2020 10:03:56 +0200
Subject: powerpc: Make setjmp/longjmp signature standard

Declaring setjmp()/longjmp() as taking longs makes the signature
non-standard, and makes clang complain. In the past, this has been
worked around by adding -ffreestanding to the compile flags.

The implementation looks like it only ever propagates the value
(in longjmp) or sets it to 1 (in setjmp), and we only call longjmp
with integer parameters.

This allows removing -ffreestanding from the compilation flags.

Fixes: c9029ef9c957 ("powerpc: Avoid clang warnings around setjmp and longjmp")
Cc: stable@vger.kernel.org # v4.14+
Signed-off-by: Clement Courbet <courbet@google.com>
Reviewed-by: Nathan Chancellor <natechancellor@gmail.com>
Tested-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200330080400.124803-1-courbet@google.com
---
 arch/powerpc/include/asm/setjmp.h | 6 ++++--
 arch/powerpc/kexec/Makefile       | 3 ---
 arch/powerpc/xmon/Makefile        | 3 ---
 3 files changed, 4 insertions(+), 8 deletions(-)

(limited to 'arch/powerpc/include/asm')

diff --git a/arch/powerpc/include/asm/setjmp.h b/arch/powerpc/include/asm/setjmp.h
index e9f81bb3f83b..f798e80e4106 100644
--- a/arch/powerpc/include/asm/setjmp.h
+++ b/arch/powerpc/include/asm/setjmp.h
@@ -7,7 +7,9 @@
 
 #define JMP_BUF_LEN    23
 
-extern long setjmp(long *) __attribute__((returns_twice));
-extern void longjmp(long *, long) __attribute__((noreturn));
+typedef long jmp_buf[JMP_BUF_LEN];
+
+extern int setjmp(jmp_buf env) __attribute__((returns_twice));
+extern void longjmp(jmp_buf env, int val) __attribute__((noreturn));
 
 #endif /* _ASM_POWERPC_SETJMP_H */
diff --git a/arch/powerpc/kexec/Makefile b/arch/powerpc/kexec/Makefile
index 378f6108a414..86380c69f5ce 100644
--- a/arch/powerpc/kexec/Makefile
+++ b/arch/powerpc/kexec/Makefile
@@ -3,9 +3,6 @@
 # Makefile for the linux kernel.
 #
 
-# Avoid clang warnings around longjmp/setjmp declarations
-CFLAGS_crash.o += -ffreestanding
-
 obj-y				+= core.o crash.o core_$(BITS).o
 
 obj-$(CONFIG_PPC32)		+= relocate_32.o
diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
index c3842dbeb1b7..6f9cccea54f3 100644
--- a/arch/powerpc/xmon/Makefile
+++ b/arch/powerpc/xmon/Makefile
@@ -1,9 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for xmon
 
-# Avoid clang warnings around longjmp/setjmp declarations
-subdir-ccflags-y := -ffreestanding
-
 GCOV_PROFILE := n
 KCOV_INSTRUMENT := n
 UBSAN_SANITIZE := n
-- 
cgit v1.2.3