From 1a18a66446f3f289b05b634f18012424d82aa63a Mon Sep 17 00:00:00 2001
From: Kevin Hao <haokexin@gmail.com>
Date: Fri, 17 Jan 2014 12:25:28 +0800
Subject: powerpc: Set the correct ksp_limit on ppc32 when switching to irq
stack
Guenter Roeck has got the following call trace on a p2020 board:
Kernel stack overflow in process eb3e5a00, r1=eb79df90
CPU: 0 PID: 2838 Comm: ssh Not tainted 3.13.0-rc8-juniper-00146-g19eca00 #4
task: eb3e5a00 ti: c0616000 task.ti: ef440000
NIP: c003a420 LR: c003a410 CTR: c0017518
REGS: eb79dee0 TRAP: 0901 Not tainted (3.13.0-rc8-juniper-00146-g19eca00)
MSR: 00029000 <CE,EE,ME> CR: 24008444 XER: 00000000
GPR00: c003a410 eb79df90 eb3e5a00 00000000 eb05d900 00000001 65d87646 00000000
GPR08: 00000000 020b8000 00000000 00000000 44008442
NIP [c003a420] __do_softirq+0x94/0x1ec
LR [c003a410] __do_softirq+0x84/0x1ec
Call Trace:
[eb79df90] [c003a410] __do_softirq+0x84/0x1ec (unreliable)
[eb79dfe0] [c003a970] irq_exit+0xbc/0xc8
[eb79dff0] [c000cc1c] call_do_irq+0x24/0x3c
[ef441f20] [c00046a8] do_IRQ+0x8c/0xf8
[ef441f40] [c000e7f4] ret_from_except+0x0/0x18
--- Exception: 501 at 0xfcda524
LR = 0x10024900
Instruction dump:
7c781b78 3b40000a 3a73b040 543c0024 3a800000 3b3913a0 7ef5bb78 48201bf9
5463103a 7d3b182e 7e89b92e 7c008146 <3ba00000> 7e7e9b78 48000014 57fff87f
Kernel panic - not syncing: kernel stack overflow
CPU: 0 PID: 2838 Comm: ssh Not tainted 3.13.0-rc8-juniper-00146-g19eca00 #4
Call Trace:
The reason is that we have used the wrong register to calculate the
ksp_limit in commit cbc9565ee826 (powerpc: Remove ksp_limit on ppc64).
Just fix it.
As suggested by Benjamin Herrenschmidt, also add the C prototype of the
function in the comment in order to avoid such kind of errors in the
future.
Cc: stable@vger.kernel.org # 3.12
Reported-by: Guenter Roeck <linux@roeck-us.net>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/kernel/misc_32.S | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 879f09620f83..7c6bb4b17b49 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -57,11 +57,14 @@ _GLOBAL(call_do_softirq)
mtlr r0
blr
+/*
+ * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
+ */
_GLOBAL(call_do_irq)
mflr r0
stw r0,4(r1)
lwz r10,THREAD+KSP_LIMIT(r2)
- addi r11,r3,THREAD_INFO_GAP
+ addi r11,r4,THREAD_INFO_GAP
stwu r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
mr r1,r4
stw r10,8(r1)
--
cgit
From b020cc6c03a37c3526fcb1dff274f649257949e0 Mon Sep 17 00:00:00 2001
From: Kleber Sacilotto de Souza <klebers@linux.vnet.ibm.com>
Date: Fri, 17 Jan 2014 11:56:51 -0200
Subject: powerpc/pseries: Fix regression on PCI link speed
Commit 5091f0c (powerpc/pseries: Fix PCIE link speed endian issue)
introduced a regression on the PCI link speed detection using the
device-tree property. The ibm,pcie-link-speed-stats property is composed
of two 32-bit integers, the first one being the maxinum link speed and
the second the current link speed. The changes introduced by the
aforementioned commit are considering just the first integer.
Fix this issue by changing how the property is accessed, using the
helper functions to properly access the array of values. The explicit
byte swapping is not needed anymore here, since it's done by the helper
functions.
Signed-off-by: Kleber Sacilotto de Souza <klebers@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/platforms/pseries/pci.c | 16 +++++++++-------
1 file changed, 9 insertions(+), 7 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 70670a2d9cf2..a6f7a1460e2f 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -113,7 +113,8 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
{
struct device_node *dn, *pdn;
struct pci_bus *bus;
- const __be32 *pcie_link_speed_stats;
+ u32 pcie_link_speed_stats[2];
+ int rc;
bus = bridge->bus;
@@ -122,20 +123,21 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
return 0;
for (pdn = dn; pdn != NULL; pdn = of_get_next_parent(pdn)) {
- pcie_link_speed_stats = of_get_property(pdn,
- "ibm,pcie-link-speed-stats", NULL);
- if (pcie_link_speed_stats)
+ rc = of_property_read_u32_array(pdn,
+ "ibm,pcie-link-speed-stats",
+ &pcie_link_speed_stats[0], 2);
+ if (!rc)
break;
}
of_node_put(pdn);
- if (!pcie_link_speed_stats) {
+ if (rc) {
pr_err("no ibm,pcie-link-speed-stats property\n");
return 0;
}
- switch (be32_to_cpup(pcie_link_speed_stats)) {
+ switch (pcie_link_speed_stats[0]) {
case 0x01:
bus->max_bus_speed = PCIE_SPEED_2_5GT;
break;
@@ -147,7 +149,7 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
break;
}
- switch (be32_to_cpup(pcie_link_speed_stats)) {
+ switch (pcie_link_speed_stats[1]) {
case 0x01:
bus->cur_bus_speed = PCIE_SPEED_2_5GT;
break;
--
cgit
From 49d9684a54d21930372b7fb0d3d7b5617f621706 Mon Sep 17 00:00:00 2001
From: Kleber Sacilotto de Souza <klebers@linux.vnet.ibm.com>
Date: Fri, 17 Jan 2014 11:56:52 -0200
Subject: powerpc/pseries: Add Gen3 definitions for PCIE link speed
Rev3 of the PCI Express Base Specification defines a Supported Link
Speeds Vector where the bit definitions within this field are:
Bit 0 - 2.5 GT/s
Bit 1 - 5.0 GT/s
Bit 2 - 8.0 GT/s
This vector definition is used by the platform firmware to export the
maximum and current link speeds of the PCI bus via the
"ibm,pcie-link-speed-stats" device-tree property.
This patch updates pseries_root_bridge_prepare() to detect Gen3
speed buses (defined by 0x04).
Signed-off-by: Kleber Sacilotto de Souza <klebers@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/platforms/pseries/pci.c | 6 ++++++
1 file changed, 6 insertions(+)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index a6f7a1460e2f..c413ec158ff5 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -144,6 +144,9 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
case 0x02:
bus->max_bus_speed = PCIE_SPEED_5_0GT;
break;
+ case 0x04:
+ bus->max_bus_speed = PCIE_SPEED_8_0GT;
+ break;
default:
bus->max_bus_speed = PCI_SPEED_UNKNOWN;
break;
@@ -156,6 +159,9 @@ int pseries_root_bridge_prepare(struct pci_host_bridge *bridge)
case 0x02:
bus->cur_bus_speed = PCIE_SPEED_5_0GT;
break;
+ case 0x04:
+ bus->cur_bus_speed = PCIE_SPEED_8_0GT;
+ break;
default:
bus->cur_bus_speed = PCI_SPEED_UNKNOWN;
break;
--
cgit
From 88247e8d7ba6639f2c199e147ebbc91f7673150c Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Wed, 12 Feb 2014 09:13:36 +0530
Subject: powerpc/mm: Add new "set" flag argument to pte/pmd update function
pte_update() is a powerpc-ism used to change the bits of a PTE
when the access permission is being restricted (a flush is
potentially needed).
It uses atomic operations on when needed and handles the hash
synchronization on hash based processors.
It is currently only used to clear PTE bits and so the current
implementation doesn't provide a way to also set PTE bits.
The new _PAGE_NUMA bit, when set, is actually restricting access
so it must use that function too, so this change adds the ability
for pte_update() to also set bits.
We will use this later to set the _PAGE_NUMA bit.
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/include/asm/hugetlb.h | 2 +-
arch/powerpc/include/asm/pgtable-ppc64.h | 26 +++++++++++++++-----------
arch/powerpc/mm/pgtable_64.c | 12 +++++++-----
arch/powerpc/mm/subpage-prot.c | 2 +-
4 files changed, 24 insertions(+), 18 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index d750336b171d..623f2971ce0e 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -127,7 +127,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
#ifdef CONFIG_PPC64
- return __pte(pte_update(mm, addr, ptep, ~0UL, 1));
+ return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
#else
return __pte(pte_update(ptep, ~0UL, 0));
#endif
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index bc141c950b1e..eb9261024f51 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -195,6 +195,7 @@ extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
static inline unsigned long pte_update(struct mm_struct *mm,
unsigned long addr,
pte_t *ptep, unsigned long clr,
+ unsigned long set,
int huge)
{
#ifdef PTE_ATOMIC_UPDATES
@@ -205,14 +206,15 @@ static inline unsigned long pte_update(struct mm_struct *mm,
andi. %1,%0,%6\n\
bne- 1b \n\
andc %1,%0,%4 \n\
+ or %1,%1,%7\n\
stdcx. %1,0,%3 \n\
bne- 1b"
: "=&r" (old), "=&r" (tmp), "=m" (*ptep)
- : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY)
+ : "r" (ptep), "r" (clr), "m" (*ptep), "i" (_PAGE_BUSY), "r" (set)
: "cc" );
#else
unsigned long old = pte_val(*ptep);
- *ptep = __pte(old & ~clr);
+ *ptep = __pte((old & ~clr) | set);
#endif
/* huge pages use the old page table lock */
if (!huge)
@@ -231,9 +233,9 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
{
unsigned long old;
- if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
+ if ((pte_val(*ptep) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
return 0;
- old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0);
+ old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
return (old & _PAGE_ACCESSED) != 0;
}
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
@@ -252,7 +254,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
if ((pte_val(*ptep) & _PAGE_RW) == 0)
return;
- pte_update(mm, addr, ptep, _PAGE_RW, 0);
+ pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
}
static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
@@ -261,7 +263,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
if ((pte_val(*ptep) & _PAGE_RW) == 0)
return;
- pte_update(mm, addr, ptep, _PAGE_RW, 1);
+ pte_update(mm, addr, ptep, _PAGE_RW, 0, 1);
}
/*
@@ -284,14 +286,14 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
unsigned long addr, pte_t *ptep)
{
- unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0);
+ unsigned long old = pte_update(mm, addr, ptep, ~0UL, 0, 0);
return __pte(old);
}
static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t * ptep)
{
- pte_update(mm, addr, ptep, ~0UL, 0);
+ pte_update(mm, addr, ptep, ~0UL, 0, 0);
}
@@ -506,7 +508,9 @@ extern int pmdp_set_access_flags(struct vm_area_struct *vma,
extern unsigned long pmd_hugepage_update(struct mm_struct *mm,
unsigned long addr,
- pmd_t *pmdp, unsigned long clr);
+ pmd_t *pmdp,
+ unsigned long clr,
+ unsigned long set);
static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
unsigned long addr, pmd_t *pmdp)
@@ -515,7 +519,7 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
if ((pmd_val(*pmdp) & (_PAGE_ACCESSED | _PAGE_HASHPTE)) == 0)
return 0;
- old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED);
+ old = pmd_hugepage_update(mm, addr, pmdp, _PAGE_ACCESSED, 0);
return ((old & _PAGE_ACCESSED) != 0);
}
@@ -542,7 +546,7 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
if ((pmd_val(*pmdp) & _PAGE_RW) == 0)
return;
- pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW);
+ pmd_hugepage_update(mm, addr, pmdp, _PAGE_RW, 0);
}
#define __HAVE_ARCH_PMDP_SPLITTING_FLUSH
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 65b7b65e8708..62bf5e8e78da 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -510,7 +510,8 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address,
}
unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
- pmd_t *pmdp, unsigned long clr)
+ pmd_t *pmdp, unsigned long clr,
+ unsigned long set)
{
unsigned long old, tmp;
@@ -526,14 +527,15 @@ unsigned long pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
andi. %1,%0,%6\n\
bne- 1b \n\
andc %1,%0,%4 \n\
+ or %1,%1,%7\n\
stdcx. %1,0,%3 \n\
bne- 1b"
: "=&r" (old), "=&r" (tmp), "=m" (*pmdp)
- : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY)
+ : "r" (pmdp), "r" (clr), "m" (*pmdp), "i" (_PAGE_BUSY), "r" (set)
: "cc" );
#else
old = pmd_val(*pmdp);
- *pmdp = __pmd(old & ~clr);
+ *pmdp = __pmd((old & ~clr) | set);
#endif
if (old & _PAGE_HASHPTE)
hpte_do_hugepage_flush(mm, addr, pmdp);
@@ -708,7 +710,7 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
- pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT);
+ pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0);
}
/*
@@ -835,7 +837,7 @@ pmd_t pmdp_get_and_clear(struct mm_struct *mm,
unsigned long old;
pgtable_t *pgtable_slot;
- old = pmd_hugepage_update(mm, addr, pmdp, ~0UL);
+ old = pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0);
old_pmd = __pmd(old);
/*
* We have pmd == none and we are holding page_table_lock.
diff --git a/arch/powerpc/mm/subpage-prot.c b/arch/powerpc/mm/subpage-prot.c
index a770df2dae70..6c0b1f5f8d2c 100644
--- a/arch/powerpc/mm/subpage-prot.c
+++ b/arch/powerpc/mm/subpage-prot.c
@@ -78,7 +78,7 @@ static void hpte_flush_range(struct mm_struct *mm, unsigned long addr,
pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
arch_enter_lazy_mmu_mode();
for (; npages > 0; --npages) {
- pte_update(mm, addr, pte, 0, 0);
+ pte_update(mm, addr, pte, 0, 0, 0);
addr += PAGE_SIZE;
++pte;
}
--
cgit
From 56eecdb912b536a4fa97fb5bfe5a940a54d79be6 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Wed, 12 Feb 2014 09:13:38 +0530
Subject: mm: Use ptep/pmdp_set_numa() for updating _PAGE_NUMA bit
Archs like ppc64 doesn't do tlb flush in set_pte/pmd functions when using
a hash table MMU for various reasons (the flush is handled as part of
the PTE modification when necessary).
ppc64 thus doesn't implement flush_tlb_range for hash based MMUs.
Additionally ppc64 require the tlb flushing to be batched within ptl locks.
The reason to do that is to ensure that the hash page table is in sync with
linux page table.
We track the hpte index in linux pte and if we clear them without flushing
hash and drop the ptl lock, we can have another cpu update the pte and can
end up with duplicate entry in the hash table, which is fatal.
We also want to keep set_pte_at simpler by not requiring them to do hash
flush for performance reason. We do that by assuming that set_pte_at() is
never *ever* called on a PTE that is already valid.
This was the case until the NUMA code went in which broke that assumption.
Fix that by introducing a new pair of helpers to set _PAGE_NUMA in a
way similar to ptep/pmdp_set_wrprotect(), with a generic implementation
using set_pte_at() and a powerpc specific one using the appropriate
mechanism needed to keep the hash table in sync.
Acked-by: Mel Gorman <mgorman@suse.de>
Reviewed-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/include/asm/pgtable.h | 22 +++++++++++++++++++++
include/asm-generic/pgtable.h | 39 ++++++++++++++++++++++++++++++++++++++
mm/huge_memory.c | 9 ++-------
mm/mprotect.c | 4 +---
4 files changed, 64 insertions(+), 10 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index f83b6f3e1b39..3ebb188c3ff5 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -75,12 +75,34 @@ static inline pte_t pte_mknuma(pte_t pte)
return pte;
}
+#define ptep_set_numa ptep_set_numa
+static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep)
+{
+ if ((pte_val(*ptep) & _PAGE_PRESENT) == 0)
+ VM_BUG_ON(1);
+
+ pte_update(mm, addr, ptep, _PAGE_PRESENT, _PAGE_NUMA, 0);
+ return;
+}
+
#define pmd_numa pmd_numa
static inline int pmd_numa(pmd_t pmd)
{
return pte_numa(pmd_pte(pmd));
}
+#define pmdp_set_numa pmdp_set_numa
+static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp)
+{
+ if ((pmd_val(*pmdp) & _PAGE_PRESENT) == 0)
+ VM_BUG_ON(1);
+
+ pmd_hugepage_update(mm, addr, pmdp, _PAGE_PRESENT, _PAGE_NUMA);
+ return;
+}
+
#define pmd_mknonnuma pmd_mknonnuma
static inline pmd_t pmd_mknonnuma(pmd_t pmd)
{
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 8e4f41d9af4d..34c7bdc06014 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -701,6 +701,18 @@ static inline pte_t pte_mknuma(pte_t pte)
}
#endif
+#ifndef ptep_set_numa
+static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep)
+{
+ pte_t ptent = *ptep;
+
+ ptent = pte_mknuma(ptent);
+ set_pte_at(mm, addr, ptep, ptent);
+ return;
+}
+#endif
+
#ifndef pmd_mknuma
static inline pmd_t pmd_mknuma(pmd_t pmd)
{
@@ -708,6 +720,18 @@ static inline pmd_t pmd_mknuma(pmd_t pmd)
return pmd_clear_flags(pmd, _PAGE_PRESENT);
}
#endif
+
+#ifndef pmdp_set_numa
+static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp)
+{
+ pmd_t pmd = *pmdp;
+
+ pmd = pmd_mknuma(pmd);
+ set_pmd_at(mm, addr, pmdp, pmd);
+ return;
+}
+#endif
#else
extern int pte_numa(pte_t pte);
extern int pmd_numa(pmd_t pmd);
@@ -715,6 +739,8 @@ extern pte_t pte_mknonnuma(pte_t pte);
extern pmd_t pmd_mknonnuma(pmd_t pmd);
extern pte_t pte_mknuma(pte_t pte);
extern pmd_t pmd_mknuma(pmd_t pmd);
+extern void ptep_set_numa(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+extern void pmdp_set_numa(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp);
#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
#else
static inline int pmd_numa(pmd_t pmd)
@@ -742,10 +768,23 @@ static inline pte_t pte_mknuma(pte_t pte)
return pte;
}
+static inline void ptep_set_numa(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep)
+{
+ return;
+}
+
+
static inline pmd_t pmd_mknuma(pmd_t pmd)
{
return pmd;
}
+
+static inline void pmdp_set_numa(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp)
+{
+ return ;
+}
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_MMU */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 82166bf974e1..da23eb96779f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1545,6 +1545,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
entry = pmd_mknonnuma(entry);
entry = pmd_modify(entry, newprot);
ret = HPAGE_PMD_NR;
+ set_pmd_at(mm, addr, pmd, entry);
BUG_ON(pmd_write(entry));
} else {
struct page *page = pmd_page(*pmd);
@@ -1557,16 +1558,10 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
*/
if (!is_huge_zero_page(page) &&
!pmd_numa(*pmd)) {
- entry = *pmd;
- entry = pmd_mknuma(entry);
+ pmdp_set_numa(mm, addr, pmd);
ret = HPAGE_PMD_NR;
}
}
-
- /* Set PMD if cleared earlier */
- if (ret == HPAGE_PMD_NR)
- set_pmd_at(mm, addr, pmd, entry);
-
spin_unlock(ptl);
}
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 33eab902f10e..769a67a15803 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -69,12 +69,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
} else {
struct page *page;
- ptent = *pte;
page = vm_normal_page(vma, addr, oldpte);
if (page && !PageKsm(page)) {
if (!pte_numa(oldpte)) {
- ptent = pte_mknuma(ptent);
- set_pte_at(mm, addr, pte, ptent);
+ ptep_set_numa(mm, addr, pte);
updated = true;
}
}
--
cgit
From a0a4419e302fedb548d56129e02130347810f892 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@au1.ibm.com>
Date: Wed, 12 Feb 2014 17:17:05 +1100
Subject: powerpc: Link VDSOs at 0x0
perf is failing to resolve symbols in the VDSO. A while (1)
gettimeofday() loop shows:
93.99% [vdso] [.] 0x00000000000005e0
3.12% test [.] 00000037.plt_call.gettimeofday@@GLIBC_2.18
2.81% test [.] main
The reason for this is that we are linking our VDSO shared libraries
at 1MB, which is a little weird. Even though this is uncommon, Alan
points out that it is valid and we should probably fix perf userspace.
Regardless, I can't see a reason why we are doing this. The code
is all position independent and we never rely on the VDSO ending
up at 1M (and we never place it there on 64bit tasks).
Changing our link address to 0x0 fixes perf VDSO symbol resolution:
73.18% [vdso] [.] 0x000000000000060c
12.39% [vdso] [.] __kernel_gettimeofday
3.58% test [.] 00000037.plt_call.gettimeofday@@GLIBC_2.18
2.94% [vdso] [.] __kernel_datapage_offset
2.90% test [.] main
We still have some local symbol resolution issues that will be
fixed in a subsequent patch.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/include/asm/vdso.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/include/asm/vdso.h b/arch/powerpc/include/asm/vdso.h
index 0d9cecddf8a4..c53f5f6d1761 100644
--- a/arch/powerpc/include/asm/vdso.h
+++ b/arch/powerpc/include/asm/vdso.h
@@ -4,11 +4,11 @@
#ifdef __KERNEL__
/* Default link addresses for the vDSOs */
-#define VDSO32_LBASE 0x100000
-#define VDSO64_LBASE 0x100000
+#define VDSO32_LBASE 0x0
+#define VDSO64_LBASE 0x0
/* Default map addresses for 32bit vDSO */
-#define VDSO32_MBASE VDSO32_LBASE
+#define VDSO32_MBASE 0x100000
#define VDSO_VERSION_STRING LINUX_2.6.15
--
cgit
From 24b659a13866b935eca72748ce725279bd3c4466 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@au1.ibm.com>
Date: Wed, 12 Feb 2014 17:18:50 +1100
Subject: powerpc: Use unstripped VDSO image for more accurate profiling data
We are seeing a lot of hits in the VDSO that are not resolved by perf.
A while(1) gettimeofday() loop shows the issue:
27.64% [vdso] [.] 0x000000000000060c
22.57% [vdso] [.] 0x0000000000000628
16.88% [vdso] [.] 0x0000000000000610
12.39% [vdso] [.] __kernel_gettimeofday
6.09% [vdso] [.] 0x00000000000005f8
3.58% test [.] 00000037.plt_call.gettimeofday@@GLIBC_2.18
2.94% [vdso] [.] __kernel_datapage_offset
2.90% test [.] main
We are using a stripped VDSO image which means only symbols with
relocation info can be resolved. There isn't a lot of point to
stripping the VDSO, the debug info is only about 1kB:
4680 arch/powerpc/kernel/vdso64/vdso64.so
5815 arch/powerpc/kernel/vdso64/vdso64.so.dbg
By using the unstripped image, we can resolve all the symbols in the
VDSO and the perf profile data looks much better:
76.53% [vdso] [.] __do_get_tspec
12.20% [vdso] [.] __kernel_gettimeofday
5.05% [vdso] [.] __get_datapage
3.20% test [.] main
2.92% test [.] 00000037.plt_call.gettimeofday@@GLIBC_2.18
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/kernel/vdso32/vdso32_wrapper.S | 2 +-
arch/powerpc/kernel/vdso64/vdso64_wrapper.S | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S
index 79683d0393f5..6ac107ac402a 100644
--- a/arch/powerpc/kernel/vdso32/vdso32_wrapper.S
+++ b/arch/powerpc/kernel/vdso32/vdso32_wrapper.S
@@ -6,7 +6,7 @@
.globl vdso32_start, vdso32_end
.balign PAGE_SIZE
vdso32_start:
- .incbin "arch/powerpc/kernel/vdso32/vdso32.so"
+ .incbin "arch/powerpc/kernel/vdso32/vdso32.so.dbg"
.balign PAGE_SIZE
vdso32_end:
diff --git a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S
index 8df9e2463007..df60fca6a13d 100644
--- a/arch/powerpc/kernel/vdso64/vdso64_wrapper.S
+++ b/arch/powerpc/kernel/vdso64/vdso64_wrapper.S
@@ -6,7 +6,7 @@
.globl vdso64_start, vdso64_end
.balign PAGE_SIZE
vdso64_start:
- .incbin "arch/powerpc/kernel/vdso64/vdso64.so"
+ .incbin "arch/powerpc/kernel/vdso64/vdso64.so.dbg"
.balign PAGE_SIZE
vdso64_end:
--
cgit
From 5b2e198e50f6ba57081586b853163ea1bb95f1a8 Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Wed, 12 Feb 2014 15:24:54 +0800
Subject: powerpc/powernv: Rework EEH reset
When doing reset in order to recover the affected PE, we issue
hot reset on PE primary bus if it's not root bus. Otherwise, we
issue hot or fundamental reset on root port or PHB accordingly.
For the later case, we didn't cover the situation where PE only
includes root port and it potentially causes kernel crash upon
EEH error to the PE.
The patch reworks the logic of EEH reset to improve the code
readability and also avoid the kernel crash.
Cc: stable@vger.kernel.org
Reported-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/platforms/powernv/eeh-ioda.c | 29 ++++-------------------------
1 file changed, 4 insertions(+), 25 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index e1e71618b70c..fcb79cffdb66 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -489,8 +489,7 @@ static int ioda_eeh_bridge_reset(struct pci_controller *hose,
static int ioda_eeh_reset(struct eeh_pe *pe, int option)
{
struct pci_controller *hose = pe->phb;
- struct eeh_dev *edev;
- struct pci_dev *dev;
+ struct pci_bus *bus;
int ret;
/*
@@ -519,31 +518,11 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
if (pe->type & EEH_PE_PHB) {
ret = ioda_eeh_phb_reset(hose, option);
} else {
- if (pe->type & EEH_PE_DEVICE) {
- /*
- * If it's device PE, we didn't refer to the parent
- * PCI bus yet. So we have to figure it out indirectly.
- */
- edev = list_first_entry(&pe->edevs,
- struct eeh_dev, list);
- dev = eeh_dev_to_pci_dev(edev);
- dev = dev->bus->self;
- } else {
- /*
- * If it's bus PE, the parent PCI bus is already there
- * and just pick it up.
- */
- dev = pe->bus->self;
- }
-
- /*
- * Do reset based on the fact that the direct upstream bridge
- * is root bridge (port) or not.
- */
- if (dev->bus->number == 0)
+ bus = eeh_pe_bus_get(pe);
+ if (pci_is_root_bus(bus))
ret = ioda_eeh_root_reset(hose, option);
else
- ret = ioda_eeh_bridge_reset(hose, dev, option);
+ ret = ioda_eeh_bridge_reset(hose, bus->self, option);
}
return ret;
--
cgit
From 2ec5a0adf60c23bb6b0a95d3b96a8c1ff1e1aa5a Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Wed, 12 Feb 2014 15:24:55 +0800
Subject: powerpc/eeh: Cleanup on eeh_subsystem_enabled
The patch cleans up variable eeh_subsystem_enabled so that we needn't
refer the variable directly from external. Instead, we will use
function eeh_enabled() and eeh_set_enable() to operate the variable.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/include/asm/eeh.h | 21 +++++++++++++++++++--
arch/powerpc/kernel/eeh.c | 12 ++++++------
arch/powerpc/platforms/powernv/eeh-powernv.c | 2 +-
arch/powerpc/platforms/pseries/eeh_pseries.c | 2 +-
4 files changed, 27 insertions(+), 10 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 9e39ceb1d19f..d4dd41fb951b 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -172,10 +172,20 @@ struct eeh_ops {
};
extern struct eeh_ops *eeh_ops;
-extern int eeh_subsystem_enabled;
+extern bool eeh_subsystem_enabled;
extern raw_spinlock_t confirm_error_lock;
extern int eeh_probe_mode;
+static inline bool eeh_enabled(void)
+{
+ return eeh_subsystem_enabled;
+}
+
+static inline void eeh_set_enable(bool mode)
+{
+ eeh_subsystem_enabled = mode;
+}
+
#define EEH_PROBE_MODE_DEV (1<<0) /* From PCI device */
#define EEH_PROBE_MODE_DEVTREE (1<<1) /* From device tree */
@@ -246,7 +256,7 @@ void eeh_remove_device(struct pci_dev *);
* If this macro yields TRUE, the caller relays to eeh_check_failure()
* which does further tests out of line.
*/
-#define EEH_POSSIBLE_ERROR(val, type) ((val) == (type)~0 && eeh_subsystem_enabled)
+#define EEH_POSSIBLE_ERROR(val, type) ((val) == (type)~0 && eeh_enabled())
/*
* Reads from a device which has been isolated by EEH will return
@@ -257,6 +267,13 @@ void eeh_remove_device(struct pci_dev *);
#else /* !CONFIG_EEH */
+static inline bool eeh_enabled(void)
+{
+ return false;
+}
+
+static inline void eeh_set_enable(bool mode) { }
+
static inline int eeh_init(void)
{
return 0;
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 148db72a8c43..f22f7b6f6b01 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -89,7 +89,7 @@
/* Platform dependent EEH operations */
struct eeh_ops *eeh_ops = NULL;
-int eeh_subsystem_enabled;
+bool eeh_subsystem_enabled = false;
EXPORT_SYMBOL(eeh_subsystem_enabled);
/*
@@ -364,7 +364,7 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
eeh_stats.total_mmio_ffs++;
- if (!eeh_subsystem_enabled)
+ if (!eeh_enabled())
return 0;
if (!edev) {
@@ -822,7 +822,7 @@ int eeh_init(void)
return ret;
}
- if (eeh_subsystem_enabled)
+ if (eeh_enabled())
pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n");
else
pr_warning("EEH: No capable adapters found\n");
@@ -897,7 +897,7 @@ void eeh_add_device_late(struct pci_dev *dev)
struct device_node *dn;
struct eeh_dev *edev;
- if (!dev || !eeh_subsystem_enabled)
+ if (!dev || !eeh_enabled())
return;
pr_debug("EEH: Adding device %s\n", pci_name(dev));
@@ -1005,7 +1005,7 @@ void eeh_remove_device(struct pci_dev *dev)
{
struct eeh_dev *edev;
- if (!dev || !eeh_subsystem_enabled)
+ if (!dev || !eeh_enabled())
return;
edev = pci_dev_to_eeh_dev(dev);
@@ -1045,7 +1045,7 @@ void eeh_remove_device(struct pci_dev *dev)
static int proc_eeh_show(struct seq_file *m, void *v)
{
- if (0 == eeh_subsystem_enabled) {
+ if (!eeh_enabled()) {
seq_printf(m, "EEH Subsystem is globally disabled\n");
seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs);
} else {
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index a79fddc5e74e..a59788e83b8b 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -145,7 +145,7 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
* Enable EEH explicitly so that we will do EEH check
* while accessing I/O stuff
*/
- eeh_subsystem_enabled = 1;
+ eeh_set_enable(true);
/* Save memory bars */
eeh_save_bars(edev);
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 9ef3cc8ebc11..8a8f0472d98f 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -265,7 +265,7 @@ static void *pseries_eeh_of_probe(struct device_node *dn, void *flag)
enable = 1;
if (enable) {
- eeh_subsystem_enabled = 1;
+ eeh_set_enable(true);
eeh_add_to_parent_pe(edev);
pr_debug("%s: EEH enabled on %s PHB#%d-PE#%x, config addr#%x\n",
--
cgit
From 66f9af83e56bfa12964d251df9d60fb571579913 Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Wed, 12 Feb 2014 15:24:56 +0800
Subject: powerpc/eeh: Disable EEH on reboot
We possiblly detect EEH errors during reboot, particularly in kexec
path, but it's impossible for device drivers and EEH core to handle
or recover them properly.
The patch registers one reboot notifier for EEH and disable EEH
subsystem during reboot. That means the EEH errors is going to be
cleared by hardware reset or second kernel during early stage of
PCI probe.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/kernel/eeh.c | 20 ++++++++++++++++++++
arch/powerpc/platforms/powernv/eeh-ioda.c | 3 ++-
2 files changed, 22 insertions(+), 1 deletion(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index f22f7b6f6b01..e7b76a6bf150 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -28,6 +28,7 @@
#include <linux/pci.h>
#include <linux/proc_fs.h>
#include <linux/rbtree.h>
+#include <linux/reboot.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
#include <linux/export.h>
@@ -747,6 +748,17 @@ int __exit eeh_ops_unregister(const char *name)
return -EEXIST;
}
+static int eeh_reboot_notifier(struct notifier_block *nb,
+ unsigned long action, void *unused)
+{
+ eeh_set_enable(false);
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block eeh_reboot_nb = {
+ .notifier_call = eeh_reboot_notifier,
+};
+
/**
* eeh_init - EEH initialization
*
@@ -778,6 +790,14 @@ int eeh_init(void)
if (machine_is(powernv) && cnt++ <= 0)
return ret;
+ /* Register reboot notifier */
+ ret = register_reboot_notifier(&eeh_reboot_nb);
+ if (ret) {
+ pr_warn("%s: Failed to register notifier (%d)\n",
+ __func__, ret);
+ return ret;
+ }
+
/* call platform initialization function */
if (!eeh_ops) {
pr_warning("%s: Platform EEH operation not found\n",
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index fcb79cffdb66..f51474336460 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -44,7 +44,8 @@ static int ioda_eeh_event(struct notifier_block *nb,
/* We simply send special EEH event */
if ((changed_evts & OPAL_EVENT_PCI_ERROR) &&
- (events & OPAL_EVENT_PCI_ERROR))
+ (events & OPAL_EVENT_PCI_ERROR) &&
+ eeh_enabled())
eeh_send_failure_event(NULL);
return 0;
--
cgit
From 41dd03a94c7d408d2ef32530545097f7d1befe5c Mon Sep 17 00:00:00 2001
From: Tony Breeds <tony@bakeyournoodle.com>
Date: Thu, 20 Feb 2014 21:13:52 +1100
Subject: powerpc/le: Ensure that the 'stop-self' RTAS token is handled
correctly
Currently we're storing a host endian RTAS token in
rtas_stop_self_args.token. We then pass that directly to rtas. This is
fine on big endian however on little endian the token is not what we
expect.
This will typically result in hitting:
panic("Alas, I survived.\n");
To fix this we always use the stop-self token in host order and always
convert it to be32 before passing this to rtas.
Signed-off-by: Tony Breeds <tony@bakeyournoodle.com>
Cc: stable@vger.kernel.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/platforms/pseries/hotplug-cpu.c | 22 +++++++++++-----------
1 file changed, 11 insertions(+), 11 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 82789e79e539..0ea99e3d4815 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -35,12 +35,7 @@
#include "offline_states.h"
/* This version can't take the spinlock, because it never returns */
-static struct rtas_args rtas_stop_self_args = {
- .token = RTAS_UNKNOWN_SERVICE,
- .nargs = 0,
- .nret = 1,
- .rets = &rtas_stop_self_args.args[0],
-};
+static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE;
static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) =
CPU_STATE_OFFLINE;
@@ -93,15 +88,20 @@ void set_default_offline_state(int cpu)
static void rtas_stop_self(void)
{
- struct rtas_args *args = &rtas_stop_self_args;
+ struct rtas_args args = {
+ .token = cpu_to_be32(rtas_stop_self_token),
+ .nargs = 0,
+ .nret = 1,
+ .rets = &args.args[0],
+ };
local_irq_disable();
- BUG_ON(args->token == RTAS_UNKNOWN_SERVICE);
+ BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE);
printk("cpu %u (hwid %u) Ready to die...\n",
smp_processor_id(), hard_smp_processor_id());
- enter_rtas(__pa(args));
+ enter_rtas(__pa(&args));
panic("Alas, I survived.\n");
}
@@ -392,10 +392,10 @@ static int __init pseries_cpu_hotplug_init(void)
}
}
- rtas_stop_self_args.token = rtas_token("stop-self");
+ rtas_stop_self_token = rtas_token("stop-self");
qcss_tok = rtas_token("query-cpu-stopped-state");
- if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE ||
+ if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE ||
qcss_tok == RTAS_UNKNOWN_SERVICE) {
printk(KERN_INFO "CPU Hotplug not supported by firmware "
"- disabling.\n");
--
cgit
From f5295bd8ea8a65dc5eac608b151386314cb978f1 Mon Sep 17 00:00:00 2001
From: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Date: Mon, 24 Feb 2014 17:30:55 +0100
Subject: powerpc/crashdump : Fix page frame number check in copy_oldmem_page
In copy_oldmem_page, the current check using max_pfn and min_low_pfn to
decide if the page is backed or not, is not valid when the memory layout is
not continuous.
This happens when running as a QEMU/KVM guest, where RTAS is mapped higher
in the memory. In that case max_pfn points to the end of RTAS, and a hole
between the end of the kdump kernel and RTAS is not backed by PTEs. As a
consequence, the kdump kernel is crashing in copy_oldmem_page when accessing
in a direct way the pages in that hole.
This fix relies on the memblock's service memblock_is_region_memory to
check if the read page is part or not of the directly accessible memory.
Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Tested-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
CC: <stable@vger.kernel.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/kernel/crash_dump.c | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 11c1d069d920..7a13f378ca2c 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -98,17 +98,19 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
size_t csize, unsigned long offset, int userbuf)
{
void *vaddr;
+ phys_addr_t paddr;
if (!csize)
return 0;
csize = min_t(size_t, csize, PAGE_SIZE);
+ paddr = pfn << PAGE_SHIFT;
- if ((min_low_pfn < pfn) && (pfn < max_pfn)) {
- vaddr = __va(pfn << PAGE_SHIFT);
+ if (memblock_is_region_memory(paddr, csize)) {
+ vaddr = __va(paddr);
csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
} else {
- vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0);
+ vaddr = __ioremap(paddr, PAGE_SIZE, 0);
csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
iounmap(vaddr);
}
--
cgit
From a95fc58549e8f462e560868a16b1fa97b12d5db6 Mon Sep 17 00:00:00 2001
From: Liu Ping Fan <kernelfans@gmail.com>
Date: Wed, 26 Feb 2014 10:23:01 +0800
Subject: powerpc/ftrace: bugfix for test_24bit_addr
The branch target should be the func addr, not the addr of func_descr_t.
So using ppc_function_entry() to generate the right target addr.
Signed-off-by: Liu Ping Fan <pingfank@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/kernel/ftrace.c | 1 +
1 file changed, 1 insertion(+)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 9b27b293a922..b0ded97ee4e1 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -74,6 +74,7 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
*/
static int test_24bit_addr(unsigned long ip, unsigned long addr)
{
+ addr = ppc_function_entry((void *)addr);
/* use the create_branch to verify that this offset can be branched */
return create_branch((unsigned int *)ip, addr, 0);
--
cgit
From 573ebfa6601fa58b439e7f15828762839ccd306a Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Wed, 26 Feb 2014 17:07:38 +1100
Subject: powerpc: Increase stack redzone for 64-bit userspace to 512 bytes
The new ELFv2 little-endian ABI increases the stack redzone -- the
area below the stack pointer that can be used for storing data --
from 288 bytes to 512 bytes. This means that we need to allow more
space on the user stack when delivering a signal to a 64-bit process.
To make the code a bit clearer, we define new USER_REDZONE_SIZE and
KERNEL_REDZONE_SIZE symbols in ptrace.h. For now, we leave the
kernel redzone size at 288 bytes, since increasing it to 512 bytes
would increase the size of interrupt stack frames correspondingly.
Gcc currently only makes use of 288 bytes of redzone even when
compiling for the new little-endian ABI, and the kernel cannot
currently be compiled with the new ABI anyway.
In the future, hopefully gcc will provide an option to control the
amount of redzone used, and then we could reduce it even more.
This also changes the code in arch_compat_alloc_user_space() to
preserve the expanded redzone. It is not clear why this function would
ever be used on a 64-bit process, though.
Signed-off-by: Paul Mackerras <paulus@samba.org>
CC: <stable@vger.kernel.org> [v3.13]
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/include/asm/compat.h | 5 +++--
arch/powerpc/include/asm/ptrace.h | 16 +++++++++++++++-
arch/powerpc/kernel/signal_64.c | 4 ++--
3 files changed, 20 insertions(+), 5 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 84fdf6857c31..a613d2c82fd9 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -200,10 +200,11 @@ static inline void __user *arch_compat_alloc_user_space(long len)
/*
* We can't access below the stack pointer in the 32bit ABI and
- * can access 288 bytes in the 64bit ABI
+ * can access 288 bytes in the 64bit big-endian ABI,
+ * or 512 bytes with the new ELFv2 little-endian ABI.
*/
if (!is_32bit_task())
- usp -= 288;
+ usp -= USER_REDZONE_SIZE;
return (void __user *) (usp - len);
}
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index becc08e6a65c..279b80f3bb29 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -28,11 +28,23 @@
#ifdef __powerpc64__
+/*
+ * Size of redzone that userspace is allowed to use below the stack
+ * pointer. This is 288 in the 64-bit big-endian ELF ABI, and 512 in
+ * the new ELFv2 little-endian ABI, so we allow the larger amount.
+ *
+ * For kernel code we allow a 288-byte redzone, in order to conserve
+ * kernel stack space; gcc currently only uses 288 bytes, and will
+ * hopefully allow explicit control of the redzone size in future.
+ */
+#define USER_REDZONE_SIZE 512
+#define KERNEL_REDZONE_SIZE 288
+
#define STACK_FRAME_OVERHEAD 112 /* size of minimum stack frame */
#define STACK_FRAME_LR_SAVE 2 /* Location of LR in stack frame */
#define STACK_FRAME_REGS_MARKER ASM_CONST(0x7265677368657265)
#define STACK_INT_FRAME_SIZE (sizeof(struct pt_regs) + \
- STACK_FRAME_OVERHEAD + 288)
+ STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE)
#define STACK_FRAME_MARKER 12
/* Size of dummy stack frame allocated when calling signal handler. */
@@ -41,6 +53,8 @@
#else /* __powerpc64__ */
+#define USER_REDZONE_SIZE 0
+#define KERNEL_REDZONE_SIZE 0
#define STACK_FRAME_OVERHEAD 16 /* size of minimum stack frame */
#define STACK_FRAME_LR_SAVE 1 /* Location of LR in stack frame */
#define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773)
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index e35bf773df7a..8d253c29649b 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -65,8 +65,8 @@ struct rt_sigframe {
struct siginfo __user *pinfo;
void __user *puc;
struct siginfo info;
- /* 64 bit ABI allows for 288 bytes below sp before decrementing it. */
- char abigap[288];
+ /* New 64 bit little-endian ABI allows redzone of 512 bytes below sp */
+ char abigap[USER_REDZONE_SIZE];
} __attribute__ ((aligned (16)));
static const char fmt32[] = KERN_INFO \
--
cgit
From 947166043732b69878123bf31f51933ad0316080 Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Tue, 25 Feb 2014 15:28:37 +0800
Subject: powerpc/powernv: Dump PHB diag-data immediately
The PHB diag-data is important to help locating the root cause for
EEH errors such as frozen PE or fenced PHB. However, the EEH core
enables IO path by clearing part of HW registers before collecting
this data causing it to be corrupted.
This patch fixes this by dumping the PHB diag-data immediately when
frozen/fenced state on PE or PHB is detected for the first time in
eeh_ops::get_state() or next_error() backend.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
CC: <stable@vger.kernel.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/platforms/powernv/eeh-ioda.c | 96 ++++++++++++++-----------------
1 file changed, 43 insertions(+), 53 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index f51474336460..253fefe3d1a0 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -114,6 +114,7 @@ DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbB_dbgfs_ops, ioda_eeh_inbB_dbgfs_get,
ioda_eeh_inbB_dbgfs_set, "0x%llx\n");
#endif /* CONFIG_DEBUG_FS */
+
/**
* ioda_eeh_post_init - Chip dependent post initialization
* @hose: PCI controller
@@ -221,6 +222,22 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
return ret;
}
+static void ioda_eeh_phb_diag(struct pci_controller *hose)
+{
+ struct pnv_phb *phb = hose->private_data;
+ long rc;
+
+ rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+ PNV_PCI_DIAG_BUF_SIZE);
+ if (rc != OPAL_SUCCESS) {
+ pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
+ __func__, hose->global_number, rc);
+ return;
+ }
+
+ pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
+}
+
/**
* ioda_eeh_get_state - Retrieve the state of PE
* @pe: EEH PE
@@ -272,6 +289,9 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
result |= EEH_STATE_DMA_ACTIVE;
result |= EEH_STATE_MMIO_ENABLED;
result |= EEH_STATE_DMA_ENABLED;
+ } else if (!(pe->state & EEH_PE_ISOLATED)) {
+ eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+ ioda_eeh_phb_diag(hose);
}
return result;
@@ -315,6 +335,15 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
__func__, fstate, hose->global_number, pe_no);
}
+ /* Dump PHB diag-data for frozen PE */
+ if (result != EEH_STATE_NOT_SUPPORT &&
+ (result & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) !=
+ (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE) &&
+ !(pe->state & EEH_PE_ISOLATED)) {
+ eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+ ioda_eeh_phb_diag(hose);
+ }
+
return result;
}
@@ -529,42 +558,6 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
return ret;
}
-/**
- * ioda_eeh_get_log - Retrieve error log
- * @pe: EEH PE
- * @severity: Severity level of the log
- * @drv_log: buffer to store the log
- * @len: space of the log buffer
- *
- * The function is used to retrieve error log from P7IOC.
- */
-static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
- char *drv_log, unsigned long len)
-{
- s64 ret;
- unsigned long flags;
- struct pci_controller *hose = pe->phb;
- struct pnv_phb *phb = hose->private_data;
-
- spin_lock_irqsave(&phb->lock, flags);
-
- ret = opal_pci_get_phb_diag_data2(phb->opal_id,
- phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
- if (ret) {
- spin_unlock_irqrestore(&phb->lock, flags);
- pr_warning("%s: Can't get log for PHB#%x-PE#%x (%lld)\n",
- __func__, hose->global_number, pe->addr, ret);
- return -EIO;
- }
-
- /* The PHB diag-data is always indicative */
- pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-
- spin_unlock_irqrestore(&phb->lock, flags);
-
- return 0;
-}
-
/**
* ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE
* @pe: EEH PE
@@ -646,22 +639,6 @@ static void ioda_eeh_hub_diag(struct pci_controller *hose)
}
}
-static void ioda_eeh_phb_diag(struct pci_controller *hose)
-{
- struct pnv_phb *phb = hose->private_data;
- long rc;
-
- rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
- PNV_PCI_DIAG_BUF_SIZE);
- if (rc != OPAL_SUCCESS) {
- pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
- __func__, hose->global_number, rc);
- return;
- }
-
- pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-}
-
static int ioda_eeh_get_phb_pe(struct pci_controller *hose,
struct eeh_pe **pe)
{
@@ -834,6 +811,20 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
__func__, err_type);
}
+ /*
+ * EEH core will try recover from fenced PHB or
+ * frozen PE. In the time for frozen PE, EEH core
+ * enable IO path for that before collecting logs,
+ * but it ruins the site. So we have to dump the
+ * log in advance here.
+ */
+ if ((ret == EEH_NEXT_ERR_FROZEN_PE ||
+ ret == EEH_NEXT_ERR_FENCED_PHB) &&
+ !((*pe)->state & EEH_PE_ISOLATED)) {
+ eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
+ ioda_eeh_phb_diag(hose);
+ }
+
/*
* If we have no errors on the specific PHB or only
* informative error there, we continue poking it.
@@ -852,7 +843,6 @@ struct pnv_eeh_ops ioda_eeh_ops = {
.set_option = ioda_eeh_set_option,
.get_state = ioda_eeh_get_state,
.reset = ioda_eeh_reset,
- .get_log = ioda_eeh_get_log,
.configure_bridge = ioda_eeh_configure_bridge,
.next_error = ioda_eeh_next_error
};
--
cgit
From af87d2fe95444d107e0c0cf0ba7e20e6716a7bfd Mon Sep 17 00:00:00 2001
From: Gavin Shan <shangw@linux.vnet.ibm.com>
Date: Tue, 25 Feb 2014 15:28:38 +0800
Subject: powerpc/powernv: Refactor PHB diag-data dump
As Ben suggested, the patch prints PHB diag-data with multiple
fields in one line and omits the line if the fields of that
line are all zero.
With the patch applied, the PHB3 diag-data dump looks like:
PHB3 PHB#3 Diag-data (Version: 1)
brdgCtl: 00000002
RootSts: 0000000f 00400000 b0830008 00100147 00002000
nFir: 0000000000000000 0030006e00000000 0000000000000000
PhbSts: 0000001c00000000 0000000000000000
Lem: 0000000000100000 42498e327f502eae 0000000000000000
InAErr: 8000000000000000 8000000000000000 0402030000000000 0000000000000000
PE[ 8] A/B: 8480002b00000000 8000000000000000
[ The current diag data is so big that it overflows the printk
buffer pretty quickly in cases when we get a handful of errors
at once which can happen. --BenH
]
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
CC: <stable@vger.kernel.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/platforms/powernv/pci.c | 220 ++++++++++++++++++++---------------
1 file changed, 125 insertions(+), 95 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 95633d79ef5d..8518817dcdfd 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -134,57 +134,72 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose,
pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n",
hose->global_number, common->version);
- pr_info(" brdgCtl: %08x\n", data->brdgCtl);
-
- pr_info(" portStatusReg: %08x\n", data->portStatusReg);
- pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus);
- pr_info(" busAgentStatus: %08x\n", data->busAgentStatus);
-
- pr_info(" deviceStatus: %08x\n", data->deviceStatus);
- pr_info(" slotStatus: %08x\n", data->slotStatus);
- pr_info(" linkStatus: %08x\n", data->linkStatus);
- pr_info(" devCmdStatus: %08x\n", data->devCmdStatus);
- pr_info(" devSecStatus: %08x\n", data->devSecStatus);
-
- pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus);
- pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus);
- pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus);
- pr_info(" tlpHdr1: %08x\n", data->tlpHdr1);
- pr_info(" tlpHdr2: %08x\n", data->tlpHdr2);
- pr_info(" tlpHdr3: %08x\n", data->tlpHdr3);
- pr_info(" tlpHdr4: %08x\n", data->tlpHdr4);
- pr_info(" sourceId: %08x\n", data->sourceId);
- pr_info(" errorClass: %016llx\n", data->errorClass);
- pr_info(" correlator: %016llx\n", data->correlator);
- pr_info(" p7iocPlssr: %016llx\n", data->p7iocPlssr);
- pr_info(" p7iocCsr: %016llx\n", data->p7iocCsr);
- pr_info(" lemFir: %016llx\n", data->lemFir);
- pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask);
- pr_info(" lemWOF: %016llx\n", data->lemWOF);
- pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus);
- pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus);
- pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0);
- pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1);
- pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus);
- pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
- pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0);
- pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1);
- pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus);
- pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
- pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0);
- pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1);
- pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus);
- pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
- pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0);
- pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1);
+ if (data->brdgCtl)
+ pr_info(" brdgCtl: %08x\n",
+ data->brdgCtl);
+ if (data->portStatusReg || data->rootCmplxStatus ||
+ data->busAgentStatus)
+ pr_info(" UtlSts: %08x %08x %08x\n",
+ data->portStatusReg, data->rootCmplxStatus,
+ data->busAgentStatus);
+ if (data->deviceStatus || data->slotStatus ||
+ data->linkStatus || data->devCmdStatus ||
+ data->devSecStatus)
+ pr_info(" RootSts: %08x %08x %08x %08x %08x\n",
+ data->deviceStatus, data->slotStatus,
+ data->linkStatus, data->devCmdStatus,
+ data->devSecStatus);
+ if (data->rootErrorStatus || data->uncorrErrorStatus ||
+ data->corrErrorStatus)
+ pr_info(" RootErrSts: %08x %08x %08x\n",
+ data->rootErrorStatus, data->uncorrErrorStatus,
+ data->corrErrorStatus);
+ if (data->tlpHdr1 || data->tlpHdr2 ||
+ data->tlpHdr3 || data->tlpHdr4)
+ pr_info(" RootErrLog: %08x %08x %08x %08x\n",
+ data->tlpHdr1, data->tlpHdr2,
+ data->tlpHdr3, data->tlpHdr4);
+ if (data->sourceId || data->errorClass ||
+ data->correlator)
+ pr_info(" RootErrLog1: %08x %016llx %016llx\n",
+ data->sourceId, data->errorClass,
+ data->correlator);
+ if (data->p7iocPlssr || data->p7iocCsr)
+ pr_info(" PhbSts: %016llx %016llx\n",
+ data->p7iocPlssr, data->p7iocCsr);
+ if (data->lemFir || data->lemErrorMask ||
+ data->lemWOF)
+ pr_info(" Lem: %016llx %016llx %016llx\n",
+ data->lemFir, data->lemErrorMask,
+ data->lemWOF);
+ if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+ data->phbErrorLog0 || data->phbErrorLog1)
+ pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n",
+ data->phbErrorStatus, data->phbFirstErrorStatus,
+ data->phbErrorLog0, data->phbErrorLog1);
+ if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+ data->mmioErrorLog0 || data->mmioErrorLog1)
+ pr_info(" OutErr: %016llx %016llx %016llx %016llx\n",
+ data->mmioErrorStatus, data->mmioFirstErrorStatus,
+ data->mmioErrorLog0, data->mmioErrorLog1);
+ if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+ data->dma0ErrorLog0 || data->dma0ErrorLog1)
+ pr_info(" InAErr: %016llx %016llx %016llx %016llx\n",
+ data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+ data->dma0ErrorLog0, data->dma0ErrorLog1);
+ if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+ data->dma1ErrorLog0 || data->dma1ErrorLog1)
+ pr_info(" InBErr: %016llx %016llx %016llx %016llx\n",
+ data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+ data->dma1ErrorLog0, data->dma1ErrorLog1);
for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
if ((data->pestA[i] >> 63) == 0 &&
(data->pestB[i] >> 63) == 0)
continue;
- pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]);
- pr_info(" PESTB: %016llx\n", data->pestB[i]);
+ pr_info(" PE[%3d] A/B: %016llx %016llx\n",
+ i, data->pestA[i], data->pestB[i]);
}
}
@@ -197,62 +212,77 @@ static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose,
data = (struct OpalIoPhb3ErrorData*)common;
pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n",
hose->global_number, common->version);
-
- pr_info(" brdgCtl: %08x\n", data->brdgCtl);
-
- pr_info(" portStatusReg: %08x\n", data->portStatusReg);
- pr_info(" rootCmplxStatus: %08x\n", data->rootCmplxStatus);
- pr_info(" busAgentStatus: %08x\n", data->busAgentStatus);
-
- pr_info(" deviceStatus: %08x\n", data->deviceStatus);
- pr_info(" slotStatus: %08x\n", data->slotStatus);
- pr_info(" linkStatus: %08x\n", data->linkStatus);
- pr_info(" devCmdStatus: %08x\n", data->devCmdStatus);
- pr_info(" devSecStatus: %08x\n", data->devSecStatus);
-
- pr_info(" rootErrorStatus: %08x\n", data->rootErrorStatus);
- pr_info(" uncorrErrorStatus: %08x\n", data->uncorrErrorStatus);
- pr_info(" corrErrorStatus: %08x\n", data->corrErrorStatus);
- pr_info(" tlpHdr1: %08x\n", data->tlpHdr1);
- pr_info(" tlpHdr2: %08x\n", data->tlpHdr2);
- pr_info(" tlpHdr3: %08x\n", data->tlpHdr3);
- pr_info(" tlpHdr4: %08x\n", data->tlpHdr4);
- pr_info(" sourceId: %08x\n", data->sourceId);
- pr_info(" errorClass: %016llx\n", data->errorClass);
- pr_info(" correlator: %016llx\n", data->correlator);
-
- pr_info(" nFir: %016llx\n", data->nFir);
- pr_info(" nFirMask: %016llx\n", data->nFirMask);
- pr_info(" nFirWOF: %016llx\n", data->nFirWOF);
- pr_info(" PhbPlssr: %016llx\n", data->phbPlssr);
- pr_info(" PhbCsr: %016llx\n", data->phbCsr);
- pr_info(" lemFir: %016llx\n", data->lemFir);
- pr_info(" lemErrorMask: %016llx\n", data->lemErrorMask);
- pr_info(" lemWOF: %016llx\n", data->lemWOF);
- pr_info(" phbErrorStatus: %016llx\n", data->phbErrorStatus);
- pr_info(" phbFirstErrorStatus: %016llx\n", data->phbFirstErrorStatus);
- pr_info(" phbErrorLog0: %016llx\n", data->phbErrorLog0);
- pr_info(" phbErrorLog1: %016llx\n", data->phbErrorLog1);
- pr_info(" mmioErrorStatus: %016llx\n", data->mmioErrorStatus);
- pr_info(" mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
- pr_info(" mmioErrorLog0: %016llx\n", data->mmioErrorLog0);
- pr_info(" mmioErrorLog1: %016llx\n", data->mmioErrorLog1);
- pr_info(" dma0ErrorStatus: %016llx\n", data->dma0ErrorStatus);
- pr_info(" dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
- pr_info(" dma0ErrorLog0: %016llx\n", data->dma0ErrorLog0);
- pr_info(" dma0ErrorLog1: %016llx\n", data->dma0ErrorLog1);
- pr_info(" dma1ErrorStatus: %016llx\n", data->dma1ErrorStatus);
- pr_info(" dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
- pr_info(" dma1ErrorLog0: %016llx\n", data->dma1ErrorLog0);
- pr_info(" dma1ErrorLog1: %016llx\n", data->dma1ErrorLog1);
+ if (data->brdgCtl)
+ pr_info(" brdgCtl: %08x\n",
+ data->brdgCtl);
+ if (data->portStatusReg || data->rootCmplxStatus ||
+ data->busAgentStatus)
+ pr_info(" UtlSts: %08x %08x %08x\n",
+ data->portStatusReg, data->rootCmplxStatus,
+ data->busAgentStatus);
+ if (data->deviceStatus || data->slotStatus ||
+ data->linkStatus || data->devCmdStatus ||
+ data->devSecStatus)
+ pr_info(" RootSts: %08x %08x %08x %08x %08x\n",
+ data->deviceStatus, data->slotStatus,
+ data->linkStatus, data->devCmdStatus,
+ data->devSecStatus);
+ if (data->rootErrorStatus || data->uncorrErrorStatus ||
+ data->corrErrorStatus)
+ pr_info(" RootErrSts: %08x %08x %08x\n",
+ data->rootErrorStatus, data->uncorrErrorStatus,
+ data->corrErrorStatus);
+ if (data->tlpHdr1 || data->tlpHdr2 ||
+ data->tlpHdr3 || data->tlpHdr4)
+ pr_info(" RootErrLog: %08x %08x %08x %08x\n",
+ data->tlpHdr1, data->tlpHdr2,
+ data->tlpHdr3, data->tlpHdr4);
+ if (data->sourceId || data->errorClass ||
+ data->correlator)
+ pr_info(" RootErrLog1: %08x %016llx %016llx\n",
+ data->sourceId, data->errorClass,
+ data->correlator);
+ if (data->nFir || data->nFirMask ||
+ data->nFirWOF)
+ pr_info(" nFir: %016llx %016llx %016llx\n",
+ data->nFir, data->nFirMask,
+ data->nFirWOF);
+ if (data->phbPlssr || data->phbCsr)
+ pr_info(" PhbSts: %016llx %016llx\n",
+ data->phbPlssr, data->phbCsr);
+ if (data->lemFir || data->lemErrorMask ||
+ data->lemWOF)
+ pr_info(" Lem: %016llx %016llx %016llx\n",
+ data->lemFir, data->lemErrorMask,
+ data->lemWOF);
+ if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+ data->phbErrorLog0 || data->phbErrorLog1)
+ pr_info(" PhbErr: %016llx %016llx %016llx %016llx\n",
+ data->phbErrorStatus, data->phbFirstErrorStatus,
+ data->phbErrorLog0, data->phbErrorLog1);
+ if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+ data->mmioErrorLog0 || data->mmioErrorLog1)
+ pr_info(" OutErr: %016llx %016llx %016llx %016llx\n",
+ data->mmioErrorStatus, data->mmioFirstErrorStatus,
+ data->mmioErrorLog0, data->mmioErrorLog1);
+ if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+ data->dma0ErrorLog0 || data->dma0ErrorLog1)
+ pr_info(" InAErr: %016llx %016llx %016llx %016llx\n",
+ data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+ data->dma0ErrorLog0, data->dma0ErrorLog1);
+ if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+ data->dma1ErrorLog0 || data->dma1ErrorLog1)
+ pr_info(" InBErr: %016llx %016llx %016llx %016llx\n",
+ data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+ data->dma1ErrorLog0, data->dma1ErrorLog1);
for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) {
if ((data->pestA[i] >> 63) == 0 &&
(data->pestB[i] >> 63) == 0)
continue;
- pr_info(" PE[%3d] PESTA: %016llx\n", i, data->pestA[i]);
- pr_info(" PESTB: %016llx\n", data->pestB[i]);
+ pr_info(" PE[%3d] A/B: %016llx %016llx\n",
+ i, data->pestA[i], data->pestB[i]);
}
}
--
cgit
From 2f3f38e4d3d03dd4125cc9a1f49ab3cc91d8d670 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Fri, 28 Feb 2014 16:20:29 +1100
Subject: powerpc/powernv: Fix opal_xscom_{read,write} prototype
The OPAL firmware functions opal_xscom_read and opal_xscom_write
take a 64-bit argument for the XSCOM (PCB) address in order to
support the indirect mode on P8.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@vger.kernel.org> [v3.13]
---
arch/powerpc/include/asm/opal.h | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 40157e2ca691..ed82142a3251 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -816,8 +816,8 @@ int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe,
int64_t opal_pci_poll(uint64_t phb_id);
int64_t opal_return_cpu(void);
-int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val);
-int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val);
+int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val);
+int64_t opal_xscom_write(uint32_t gcid, uint64_t pcb_addr, uint64_t val);
int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
uint32_t addr, uint32_t data, uint32_t sz);
--
cgit
From e0cf957614976896111e676e5134ac98ee227d3d Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Fri, 28 Feb 2014 16:20:38 +1100
Subject: powerpc/powernv: Fix indirect XSCOM unmangling
We need to unmangle the full address, not just the register
number, and we also need to support the real indirect bit
being set for in-kernel uses.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@vger.kernel.org> [v3.13]
---
arch/powerpc/platforms/powernv/opal-xscom.c | 21 ++++++++++++---------
1 file changed, 12 insertions(+), 9 deletions(-)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 4fbf276ac99e..4cd2ea6c0dbe 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -71,11 +71,11 @@ static int opal_xscom_err_xlate(int64_t rc)
}
}
-static u64 opal_scom_unmangle(u64 reg)
+static u64 opal_scom_unmangle(u64 addr)
{
/*
* XSCOM indirect addresses have the top bit set. Additionally
- * the reset of the top 3 nibbles is always 0.
+ * the rest of the top 3 nibbles is always 0.
*
* Because the debugfs interface uses signed offsets and shifts
* the address left by 3, we basically cannot use the top 4 bits
@@ -86,10 +86,13 @@ static u64 opal_scom_unmangle(u64 reg)
* conversion here. To leave room for further xscom address
* expansion, we only clear out the top byte
*
+ * For in-kernel use, we also support the real indirect bit, so
+ * we test for any of the top 5 bits
+ *
*/
- if (reg & (1ull << 59))
- reg = (reg & ~(0xffull << 56)) | (1ull << 63);
- return reg;
+ if (addr & (0x1full << 59))
+ addr = (addr & ~(0xffull << 56)) | (1ull << 63);
+ return addr;
}
static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
@@ -98,8 +101,8 @@ static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
int64_t rc;
__be64 v;
- reg = opal_scom_unmangle(reg);
- rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v));
+ reg = opal_scom_unmangle(m->addr + reg);
+ rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v));
*value = be64_to_cpu(v);
return opal_xscom_err_xlate(rc);
}
@@ -109,8 +112,8 @@ static int opal_scom_write(scom_map_t map, u64 reg, u64 value)
struct opal_scom_map *m = map;
int64_t rc;
- reg = opal_scom_unmangle(reg);
- rc = opal_xscom_write(m->chip, m->addr + reg, value);
+ reg = opal_scom_unmangle(m->addr + reg);
+ rc = opal_xscom_write(m->chip, reg, value);
return opal_xscom_err_xlate(rc);
}
--
cgit
From 621b5060e823301d0cba4cb52a7ee3491922d291 Mon Sep 17 00:00:00 2001
From: Michael Neuling <mikey@neuling.org>
Date: Mon, 3 Mar 2014 14:21:40 +1100
Subject: powerpc/tm: Fix crash when forking inside a transaction
When we fork/clone we currently don't copy any of the TM state to the new
thread. This results in a TM bad thing (program check) when the new process is
switched in as the kernel does a tmrechkpt with TEXASR FS not set. Also, since
R1 is from userspace, we trigger the bad kernel stack pointer detection. So we
end up with something like this:
Bad kernel stack pointer 0 at c0000000000404fc
cpu 0x2: Vector: 700 (Program Check) at [c00000003ffefd40]
pc: c0000000000404fc: restore_gprs+0xc0/0x148
lr: 0000000000000000
sp: 0
msr: 9000000100201030
current = 0xc000001dd1417c30
paca = 0xc00000000fe00800 softe: 0 irq_happened: 0x01
pid = 0, comm = swapper/2
WARNING: exception is not recoverable, can't continue
The below fixes this by flushing the TM state before we copy the task_struct to
the clone. To do this we go through the tmreclaim patch, which removes the
checkpointed registers from the CPU and transitions the CPU out of TM suspend
mode. Hence we need to call tmrechkpt after to restore the checkpointed state
and the TM mode for the current task.
To make this fail from userspace is simply:
tbegin
li r0, 2
sc
<boom>
Kudos to Adhemerval Zanella Neto for finding this.
Signed-off-by: Michael Neuling <mikey@neuling.org>
cc: Adhemerval Zanella Neto <azanella@br.ibm.com>
cc: stable@vger.kernel.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/kernel/process.c | 9 +++++++++
1 file changed, 9 insertions(+)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8d4c247f1738..af064d28b365 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1048,6 +1048,15 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
flush_altivec_to_thread(src);
flush_vsx_to_thread(src);
flush_spe_to_thread(src);
+ /*
+ * Flush TM state out so we can copy it. __switch_to_tm() does this
+ * flush but it removes the checkpointed state from the current CPU and
+ * transitions the CPU out of TM mode. Hence we need to call
+ * tm_recheckpoint_new_task() (on the same task) to restore the
+ * checkpointed state back and the TM mode.
+ */
+ __switch_to_tm(src);
+ tm_recheckpoint_new_task(src);
*dst = *src;
--
cgit
From a5b2cf5b1af424ee3dd9e3ce6d5cea18cb927e67 Mon Sep 17 00:00:00 2001
From: Anton Blanchard <anton@samba.org>
Date: Tue, 4 Mar 2014 08:31:24 +1100
Subject: powerpc: Align p_dyn, p_rela and p_st symbols
The 64bit relocation code places a few symbols in the text segment.
These symbols are only 4 byte aligned where they need to be 8 byte
aligned. Add an explicit alignment.
Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: stable@vger.kernel.org
Tested-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
arch/powerpc/kernel/reloc_64.S | 1 +
1 file changed, 1 insertion(+)
(limited to 'arch/powerpc')
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
index 1482327cfeba..d88736fbece6 100644
--- a/arch/powerpc/kernel/reloc_64.S
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -81,6 +81,7 @@ _GLOBAL(relocate)
6: blr
+.balign 8
p_dyn: .llong __dynamic_start - 0b
p_rela: .llong __rela_dyn_start - 0b
p_st: .llong _stext - 0b
--
cgit