* [PATCH] cxl: Add new kernel traces
From: Christophe Lombard @ 2018-03-13 9:30 UTC (permalink / raw)
To: linuxppc-dev, fbarrat, vaibhav, andrew.donnellan
This patch adds new kernel traces in the current in-kernel 'library'
which can be called by other drivers to help interacting with an
IBM XSL on a POWER9 system.
If some kernel traces exist in the 'normal path' to handle a page or a
segment fault, some others are missing when a page fault is handle
through cxllib.
Signed-off-by: Christophe Lombard <clombard@linux.vnet.ibm.com>
---
drivers/misc/cxl/cxllib.c | 3 ++
drivers/misc/cxl/fault.c | 2 +
drivers/misc/cxl/irq.c | 2 +-
drivers/misc/cxl/trace.h | 115 ++++++++++++++++++++++++++--------------------
4 files changed, 72 insertions(+), 50 deletions(-)
diff --git a/drivers/misc/cxl/cxllib.c b/drivers/misc/cxl/cxllib.c
index 30ccba4..91cfb69 100644
--- a/drivers/misc/cxl/cxllib.c
+++ b/drivers/misc/cxl/cxllib.c
@@ -13,6 +13,7 @@
#include <misc/cxllib.h>
#include "cxl.h"
+#include "trace.h"
#define CXL_INVALID_DRA ~0ull
#define CXL_DUMMY_READ_SIZE 128
@@ -218,6 +219,8 @@ int cxllib_handle_fault(struct mm_struct *mm, u64 addr, u64 size, u64 flags)
if (mm == NULL)
return -EFAULT;
+ trace_cxl_lib_handle_fault(addr, size, flags);
+
down_read(&mm->mmap_sem);
vma = find_vma(mm, addr);
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index 70dbb6d..1c4fd74 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -138,6 +138,8 @@ int cxl_handle_mm_fault(struct mm_struct *mm, u64 dsisr, u64 dar)
int result;
unsigned long access, flags, inv_flags = 0;
+ trace_cxl_handle_mm_fault(dsisr, dar);
+
/*
* Add the fault handling cpu to task mm cpumask so that we
* can do a safe lockless page table walk when inserting the
diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c
index ce08a9f..79b8b49 100644
--- a/drivers/misc/cxl/irq.c
+++ b/drivers/misc/cxl/irq.c
@@ -41,7 +41,7 @@ irqreturn_t cxl_irq_psl9(int irq, struct cxl_context *ctx, struct cxl_irq_info *
dsisr = irq_info->dsisr;
dar = irq_info->dar;
- trace_cxl_psl9_irq(ctx, irq, dsisr, dar);
+ trace_cxl_psl_irq(ctx, irq, dsisr, dar);
pr_devel("CXL interrupt %i for afu pe: %i DSISR: %#llx DAR: %#llx\n", irq, ctx->pe, dsisr, dar);
diff --git a/drivers/misc/cxl/trace.h b/drivers/misc/cxl/trace.h
index b8e300a..8eb2607 100644
--- a/drivers/misc/cxl/trace.h
+++ b/drivers/misc/cxl/trace.h
@@ -26,19 +26,20 @@
{ CXL_PSL9_DSISR_An_OC, "OC" }, \
{ CXL_PSL9_DSISR_An_S, "S" })
-#define DSISR_FLAGS \
- { CXL_PSL_DSISR_An_DS, "DS" }, \
- { CXL_PSL_DSISR_An_DM, "DM" }, \
- { CXL_PSL_DSISR_An_ST, "ST" }, \
- { CXL_PSL_DSISR_An_UR, "UR" }, \
- { CXL_PSL_DSISR_An_PE, "PE" }, \
- { CXL_PSL_DSISR_An_AE, "AE" }, \
- { CXL_PSL_DSISR_An_OC, "OC" }, \
- { CXL_PSL_DSISR_An_M, "M" }, \
- { CXL_PSL_DSISR_An_P, "P" }, \
- { CXL_PSL_DSISR_An_A, "A" }, \
- { CXL_PSL_DSISR_An_S, "S" }, \
- { CXL_PSL_DSISR_An_K, "K" }
+#define dsisr_psl8_flags(flags) \
+ __print_flags(flags, "|", \
+ { CXL_PSL_DSISR_An_DS, "DS" }, \
+ { CXL_PSL_DSISR_An_DM, "DM" }, \
+ { CXL_PSL_DSISR_An_ST, "ST" }, \
+ { CXL_PSL_DSISR_An_UR, "UR" }, \
+ { CXL_PSL_DSISR_An_PE, "PE" }, \
+ { CXL_PSL_DSISR_An_AE, "AE" }, \
+ { CXL_PSL_DSISR_An_OC, "OC" }, \
+ { CXL_PSL_DSISR_An_M, "M" }, \
+ { CXL_PSL_DSISR_An_P, "P" }, \
+ { CXL_PSL_DSISR_An_A, "A" }, \
+ { CXL_PSL_DSISR_An_S, "S" }, \
+ { CXL_PSL_DSISR_An_K, "K" })
#define TFC_FLAGS \
{ CXL_PSL_TFC_An_A, "A" }, \
@@ -163,7 +164,7 @@ TRACE_EVENT(cxl_afu_irq,
)
);
-TRACE_EVENT(cxl_psl9_irq,
+TRACE_EVENT(cxl_psl_irq,
TP_PROTO(struct cxl_context *ctx, int irq, u64 dsisr, u64 dar),
TP_ARGS(ctx, irq, dsisr, dar),
@@ -192,40 +193,8 @@ TRACE_EVENT(cxl_psl9_irq,
__entry->pe,
__entry->irq,
__entry->dsisr,
- dsisr_psl9_flags(__entry->dsisr),
- __entry->dar
- )
-);
-
-TRACE_EVENT(cxl_psl_irq,
- TP_PROTO(struct cxl_context *ctx, int irq, u64 dsisr, u64 dar),
-
- TP_ARGS(ctx, irq, dsisr, dar),
-
- TP_STRUCT__entry(
- __field(u8, card)
- __field(u8, afu)
- __field(u16, pe)
- __field(int, irq)
- __field(u64, dsisr)
- __field(u64, dar)
- ),
-
- TP_fast_assign(
- __entry->card = ctx->afu->adapter->adapter_num;
- __entry->afu = ctx->afu->slice;
- __entry->pe = ctx->pe;
- __entry->irq = irq;
- __entry->dsisr = dsisr;
- __entry->dar = dar;
- ),
-
- TP_printk("afu%i.%i pe=%i irq=%i dsisr=%s dar=0x%016llx",
- __entry->card,
- __entry->afu,
- __entry->pe,
- __entry->irq,
- __print_flags(__entry->dsisr, "|", DSISR_FLAGS),
+ cxl_is_power8() ? dsisr_psl8_flags(__entry->dsisr) :
+ dsisr_psl9_flags(__entry->dsisr),
__entry->dar
)
);
@@ -342,11 +311,59 @@ TRACE_EVENT(cxl_pte_miss,
__entry->card,
__entry->afu,
__entry->pe,
- __print_flags(__entry->dsisr, "|", DSISR_FLAGS),
+ cxl_is_power8() ? dsisr_psl8_flags(__entry->dsisr) :
+ dsisr_psl9_flags(__entry->dsisr),
+ __entry->dar
+ )
+);
+
+TRACE_EVENT(cxl_handle_mm_fault,
+ TP_PROTO(u64 dsisr, u64 dar),
+
+ TP_ARGS(dsisr, dar),
+
+ TP_STRUCT__entry(
+ __field(u64, dsisr)
+ __field(u64, dar)
+ ),
+
+ TP_fast_assign(
+ __entry->dsisr = dsisr;
+ __entry->dar = dar;
+ ),
+
+ TP_printk("dsisr=0x%016llx(%s), dar=0x%016llx",
+ __entry->dsisr,
+ cxl_is_power8() ? dsisr_psl8_flags(__entry->dsisr) :
+ dsisr_psl9_flags(__entry->dsisr),
__entry->dar
)
);
+TRACE_EVENT(cxl_lib_handle_fault,
+ TP_PROTO(u64 addr, u64 size, u64 flags),
+
+ TP_ARGS(addr, size, flags),
+
+ TP_STRUCT__entry(
+ __field(u64, addr)
+ __field(u64, size)
+ __field(u64, flags)
+ ),
+
+ TP_fast_assign(
+ __entry->addr = addr;
+ __entry->size = size;
+ __entry->flags = flags;
+ ),
+
+ TP_printk("addr=0x%016llx, size=0x%016llx, flags=0x%016llx",
+ __entry->addr,
+ __entry->size,
+ __entry->flags
+ )
+);
+
TRACE_EVENT(cxl_llcmd,
TP_PROTO(struct cxl_context *ctx, u64 cmd),
--
2.7.4
^ permalink raw reply related
* Re: [PATCH v3] powerpc/kernel/sysfs: Export ldbar spr to sysfs
From: Anju T Sudhakar @ 2018-03-13 5:43 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev, linux-kernel, maddy
In-Reply-To: <878tb5foqk.fsf@concordia.ellerman.id.au>
Hi,
On Tuesday 06 March 2018 04:35 PM, Michael Ellerman wrote:
> Anju T Sudhakar <anju@linux.vnet.ibm.com> writes:
>
>> diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
>> index 4437c70..caefb64 100644
>> --- a/arch/powerpc/kernel/sysfs.c
>> +++ b/arch/powerpc/kernel/sysfs.c
>> @@ -757,6 +759,9 @@ static int register_cpu_online(unsigned int cpu)
>> device_create_file(s, &pmc_attrs[i]);
>>
>> #ifdef CONFIG_PPC64
>> + if (cpu_has_feature(CPU_FTR_ARCH_300))
>> + device_create_file(s, &dev_attr_ldbar);
> Is this register readable in supervisor state?
This is a nice catch, thanks. :)
The guest kernel can not access the register, it is only readable in the
hypervisor state.
I will resend the patch with a condition check so that this spr will not
get registered for guest kernel.
Regards,
Anju
>
> cheers
>
^ permalink raw reply
* Re: [PATCHv4 1/3] powerpc, cpu: partially unbind the mapping between cpu logical id and its seq in dt
From: kbuild test robot @ 2018-03-13 5:06 UTC (permalink / raw)
To: Pingfan Liu; +Cc: kbuild-all, linuxppc-dev, cascardo, gpiccoli, mahesh, kexec
In-Reply-To: <1520829790-14029-2-git-send-email-kernelfans@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 2210 bytes --]
Hi Pingfan,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on v4.16-rc4]
[also build test ERROR on next-20180309]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Pingfan-Liu/powerpc-cpu-partially-unbind-the-mapping-between-cpu-logical-id-and-its-seq-in-dt/20180313-034420
config: powerpc-pq2fads_defconfig (attached as .config)
compiler: powerpc-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
make.cross ARCH=powerpc
All errors (new ones prefixed by >>):
>> arch/powerpc/kernel/prom.c:79:23: error: 'boot_cpu_count' defined but not used [-Werror=unused-variable]
static int __initdata boot_cpu_count;
^~~~~~~~~~~~~~
cc1: all warnings being treated as errors
vim +/boot_cpu_count +79 arch/powerpc/kernel/prom.c
9b6b563c Paul Mackerras 2005-10-06 71
9b6b563c Paul Mackerras 2005-10-06 72 #ifdef CONFIG_PPC64
28897731 Olof Johansson 2006-04-12 73 int __initdata iommu_is_off;
9b6b563c Paul Mackerras 2005-10-06 74 int __initdata iommu_force_on;
cf00a8d1 Paul Mackerras 2005-10-31 75 unsigned long tce_alloc_start, tce_alloc_end;
cd3db0c4 Benjamin Herrenschmidt 2010-07-06 76 u64 ppc64_rma_size;
9b6b563c Paul Mackerras 2005-10-06 77 #endif
03bf469a Benjamin Herrenschmidt 2011-05-11 78 static phys_addr_t first_memblock_size;
7ac87abb Matt Evans 2011-05-25 @79 static int __initdata boot_cpu_count;
9b6b563c Paul Mackerras 2005-10-06 80
:::::: The code at line 79 was first introduced by commit
:::::: 7ac87abb8166b99584149fcfb2efef5773a078e9 powerpc: Fix early boot accounting of CPUs
:::::: TO: Matt Evans <matt@ozlabs.org>
:::::: CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 14183 bytes --]
^ permalink raw reply
* Re: [PATCHv4 1/3] powerpc, cpu: partially unbind the mapping between cpu logical id and its seq in dt
From: Benjamin Herrenschmidt @ 2018-03-13 2:58 UTC (permalink / raw)
To: Pingfan Liu, linuxppc-dev; +Cc: kexec, mahesh, cascardo, gpiccoli, paulus, mpe
In-Reply-To: <1520829790-14029-2-git-send-email-kernelfans@gmail.com>
On Mon, 2018-03-12 at 12:43 +0800, Pingfan Liu wrote:
> For kexec -p, the boot cpu can be not the cpu0, this causes the problem
> to alloc paca[]. In theory, there is no requirement to assign cpu's logical
> id as its present seq by device tree. But we have something like
> cpu_first_thread_sibling(), which makes assumption on the mapping inside
> a core. Hence partially changing the mapping, i.e. unbind the mapping of
> core while keep the mapping inside a core. After this patch, boot-cpu
> will always be mapped into the range [0,threads_per_core).
I'm ok with the idea but not fan of the implementation:
> Signed-off-by: Pingfan Liu <kernelfans@gmail.com>
> ---
> arch/powerpc/include/asm/smp.h | 1 +
> arch/powerpc/kernel/prom.c | 25 ++++++++++++++-----------
> arch/powerpc/kernel/setup-common.c | 21 +++++++++++++++++++++
> 3 files changed, 36 insertions(+), 11 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
> index fac963e..1299100 100644
> --- a/arch/powerpc/include/asm/smp.h
> +++ b/arch/powerpc/include/asm/smp.h
> @@ -30,6 +30,7 @@
> #include <asm/percpu.h>
>
> extern int boot_cpuid;
> +extern int boot_cpuhwid;
> extern int spinning_secondaries;
>
> extern void cpu_die(void);
> diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
> index da67606..d0ebb25 100644
> --- a/arch/powerpc/kernel/prom.c
> +++ b/arch/powerpc/kernel/prom.c
> @@ -315,8 +315,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
> const __be32 *intserv;
> int i, nthreads;
> int len;
> - int found = -1;
> - int found_thread = 0;
> + bool found = false;
>
> /* We are scanning "cpu" nodes only */
> if (type == NULL || strcmp(type, "cpu") != 0)
> @@ -341,8 +340,11 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
> if (fdt_version(initial_boot_params) >= 2) {
> if (be32_to_cpu(intserv[i]) ==
> fdt_boot_cpuid_phys(initial_boot_params)) {
> - found = boot_cpu_count;
> - found_thread = i;
> + /* always map the boot-cpu logical id into the
> + * the range of [0, thread_per_core)
> + */
> + boot_cpuid = i;
> + found = true;
> }
Call it boot_thread_id
> } else {
> /*
> @@ -351,8 +353,10 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
> * off secondary threads.
> */
> if (of_get_flat_dt_prop(node,
> - "linux,boot-cpu", NULL) != NULL)
> - found = boot_cpu_count;
> + "linux,boot-cpu", NULL) != NULL) {
> + boot_cpuid = i;
> + found = true;
> + }
> }
> #ifdef CONFIG_SMP
> /* logical cpu id is always 0 on UP kernels */
> @@ -361,13 +365,12 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
> }
>
> /* Not the boot CPU */
> - if (found < 0)
> + if (!found)
> return 0;
>
> - DBG("boot cpu: logical %d physical %d\n", found,
> - be32_to_cpu(intserv[found_thread]));
> - boot_cpuid = found;
> - set_hard_smp_processor_id(found, be32_to_cpu(intserv[found_thread]));
> + boot_cpuhwid = be32_to_cpu(intserv[boot_cpuid]);
> + DBG("boot cpu: logical %d physical %d\n", boot_cpuid, boot_cpuhwid);
> + set_hard_smp_processor_id(boot_cpuid, boot_cpuhwid);
>
> /*
> * PAPR defines "logical" PVR values for cpus that
> diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
> index 66f7cc6..1a67344 100644
> --- a/arch/powerpc/kernel/setup-common.c
> +++ b/arch/powerpc/kernel/setup-common.c
> @@ -86,6 +86,7 @@ struct machdep_calls *machine_id;
> EXPORT_SYMBOL(machine_id);
>
> int boot_cpuid = -1;
> +int boot_cpuhwid = -1;
> EXPORT_SYMBOL_GPL(boot_cpuid);
>
> /*
> @@ -459,11 +460,17 @@ static void __init cpu_init_thread_core_maps(int tpc)
> void __init smp_setup_cpu_maps(void)
> {
> struct device_node *dn;
> + struct device_node *boot_dn = NULL;
> + bool handling_bootdn = true;
> int cpu = 0;
> int nthreads = 1;
>
> DBG("smp_setup_cpu_maps()\n");
>
> +again:
> + /* E.g. kexec will not boot from the 1st core. So firstly loop to find out
> + * the dn of boot-cpu, and map them onto [0, nthreads)
> + */
> for_each_node_by_type(dn, "cpu") {
> const __be32 *intserv;
> __be32 cpu_be;
> @@ -488,6 +495,16 @@ void __init smp_setup_cpu_maps(void)
>
> nthreads = len / sizeof(int);
>
> + if (handling_bootdn) {
> + if (boot_cpuid < nthreads &&
> + be32_to_cpu(intserv[boot_cpuid]) == boot_cpuhwid) {
> + boot_dn = dn;
> + }
> + if (boot_dn == NULL)
> + continue;
> + } else if (dn == boot_dn)
> + continue;
> +
> for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) {
> bool avail;
>
> @@ -509,6 +526,10 @@ void __init smp_setup_cpu_maps(void)
> of_node_put(dn);
> break;
> }
> + if (handling_bootdn) {
> + handling_bootdn = false;
> + goto again;
> + }
> }
You don't need that "again" loop and "handling_bootdn" weird boolean.
Instead, start with cpu = 1 instead of cpu = 0, and rename it to
"next_cpu".
Then, before the thread loop, check if we are on the same core
as boot_cpuhwid:
if (same_core_as_boot_cpu(intserv)) {
cpu = 0;
} else if (next_cpu < nr_cpus_ids) {
cpu = next_cpu++;
} else {
of_node_put(dn);
break;
}
>
> /* If no SMT supported, nthreads is forced to 1 */
^ permalink raw reply
* Re: [PATCH 2/2] misc: ocxl: use put_device() instead of device_unregister()
From: Andrew Donnellan @ 2018-03-13 0:26 UTC (permalink / raw)
To: Arvind Yadav, sudeep.dutt, ashutosh.dixit, arnd, gregkh, fbarrat
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <8c4d28703e408b71284af68d07c117e7b8c8a75a.1520849284.git.arvind.yadav.cs@gmail.com>
On 12/03/18 22:36, Arvind Yadav wrote:
> if device_register() returned an error! Always use put_device()
> to give up the reference initialized.
>
> Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
This looks right, thanks for picking it up.
Acked-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com>
--
Andrew Donnellan OzLabs, ADL Canberra
andrew.donnellan@au1.ibm.com IBM Australia Limited
^ permalink raw reply
* Re: [PATCH 2/3] rfi-flush: Make it possible to call setup_rfi_flush() again
From: Mauricio Faria de Oliveira @ 2018-03-12 23:08 UTC (permalink / raw)
To: Michal Suchánek, Michael Ellerman; +Cc: linuxppc-dev
In-Reply-To: <20180306135522.040707de@kitsune.suse.cz>
Hi Michael and Michal,
Got back to this; sorry for the delay.
On 03/06/2018 09:55 AM, Michal Suchánek wrote:
> Michael Ellerman<mpe@ellerman.id.au> wrote:
>> I*think* the patch below is all we need, as well as some tweaking of
>> patch 2, are you able to test and repost?
> Enabling the fallback flush always looks a bit dodgy but
> do_rfi_flush_fixups will overwrite the jump so long any other fixup is
> enabled.
I agree; the 'Using fallback displacement flush' message is misleading
(is the system slower/fallback or not? Ô_o)
The suggested patch is definitely more contained within pseries, but
the informational part seemed dodgy IMHO too.
So I wrote something with a new function parameter to force the init of
the fallback flush area (true in pseries, false in powernv). Not that
contained, but it seemed to convey the intent here in a clear way.
That's v2, just sent.
cheers,
Mauricio
^ permalink raw reply
* [PATCH v2 4/4] rfi-flush: Call setup_rfi_flush() after LPM migration
From: Mauricio Faria de Oliveira @ 2018-03-12 23:02 UTC (permalink / raw)
To: linuxppc-dev, mpe, msuchanek
In-Reply-To: <1520895778-17586-1-git-send-email-mauricfo@linux.vnet.ibm.com>
From: Michael Ellerman <mpe@ellerman.id.au>
We might have migrated to a machine that uses a different flush type,
or doesn't need flushing at all.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Mauricio Faria de Oliveira <mauricfo@linux.vnet.ibm.com>
---
arch/powerpc/platforms/pseries/mobility.c | 3 +++
arch/powerpc/platforms/pseries/pseries.h | 2 ++
arch/powerpc/platforms/pseries/setup.c | 2 +-
3 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 0f7fb71..8a8033a 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -348,6 +348,9 @@ void post_mobility_fixup(void)
printk(KERN_ERR "Post-mobility device tree update "
"failed: %d\n", rc);
+ /* Possibly switch to a new RFI flush type */
+ pseries_setup_rfi_flush();
+
return;
}
diff --git a/arch/powerpc/platforms/pseries/pseries.h b/arch/powerpc/platforms/pseries/pseries.h
index 1ae1d9f..27cdcb6 100644
--- a/arch/powerpc/platforms/pseries/pseries.h
+++ b/arch/powerpc/platforms/pseries/pseries.h
@@ -100,4 +100,6 @@ static inline unsigned long cmo_get_page_size(void)
int dlpar_workqueue_init(void);
+void pseries_setup_rfi_flush(void);
+
#endif /* _PSERIES_PSERIES_H */
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 2f82bbb..360efe7 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -459,7 +459,7 @@ static void __init find_and_init_phbs(void)
of_pci_check_probe_only();
}
-static void pseries_setup_rfi_flush(void)
+void pseries_setup_rfi_flush(void)
{
struct h_cpu_char_result result;
enum l1d_flush_type types;
--
2.7.4
^ permalink raw reply related
* [PATCH v2 3/4] rfi-flush: Allow pseries to force init of fallback flush area
From: Mauricio Faria de Oliveira @ 2018-03-12 23:02 UTC (permalink / raw)
To: linuxppc-dev, mpe, msuchanek
In-Reply-To: <1520895778-17586-1-git-send-email-mauricfo@linux.vnet.ibm.com>
This ensures the fallback flush area is always allocated at boot time
on the pseries platform, so PowerVM migration to an unpatched system
can rely on the fallback flush method.
Signed-off-by: Mauricio Faria de Oliveira <mauricfo@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/setup.h | 2 +-
arch/powerpc/kernel/setup_64.c | 5 +++--
arch/powerpc/platforms/powernv/setup.c | 3 ++-
arch/powerpc/platforms/pseries/setup.c | 4 ++--
4 files changed, 8 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index bbcdf929..efdaf10 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -49,7 +49,7 @@ enum l1d_flush_type {
L1D_FLUSH_MTTRIG = 0x8,
};
-void setup_rfi_flush(enum l1d_flush_type, bool enable);
+void setup_rfi_flush(enum l1d_flush_type, bool enable, bool force_init_fallback);
void do_rfi_flush_fixups(enum l1d_flush_type types);
#endif /* !__ASSEMBLY__ */
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index d60e2f7..cb886a8 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -881,12 +881,13 @@ static void init_fallback_flush(void)
}
}
-void setup_rfi_flush(enum l1d_flush_type types, bool enable)
+void setup_rfi_flush(enum l1d_flush_type types, bool enable, bool force_init_fallback)
{
if (types & L1D_FLUSH_FALLBACK) {
pr_info("rfi-flush: Using fallback displacement flush\n");
init_fallback_flush();
- }
+ } else if (force_init_fallback)
+ init_fallback_flush();
if (types & L1D_FLUSH_ORI)
pr_info("rfi-flush: Using ori type flush\n");
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 092715b..a4ab8f6 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -46,6 +46,7 @@ static void pnv_setup_rfi_flush(void)
struct device_node *np, *fw_features;
enum l1d_flush_type type;
int enable;
+ bool force_init_fallback = false;
/* Default to fallback in case fw-features are not available */
type = L1D_FLUSH_FALLBACK;
@@ -88,7 +89,7 @@ static void pnv_setup_rfi_flush(void)
of_node_put(fw_features);
}
- setup_rfi_flush(type, enable > 0);
+ setup_rfi_flush(type, enable > 0, force_init_fallback);
}
static void __init pnv_setup_arch(void)
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 1a52762..2f82bbb 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -463,7 +463,7 @@ static void pseries_setup_rfi_flush(void)
{
struct h_cpu_char_result result;
enum l1d_flush_type types;
- bool enable;
+ bool enable, force_init_fallback = true;
long rc;
/* Enable by default */
@@ -490,7 +490,7 @@ static void pseries_setup_rfi_flush(void)
types = L1D_FLUSH_FALLBACK;
}
- setup_rfi_flush(types, enable);
+ setup_rfi_flush(types, enable, force_init_fallback);
}
#ifdef CONFIG_PCI_IOV
--
2.7.4
^ permalink raw reply related
* [PATCH v2 2/4] rfi-flush: Make it possible to call setup_rfi_flush() again
From: Mauricio Faria de Oliveira @ 2018-03-12 23:02 UTC (permalink / raw)
To: linuxppc-dev, mpe, msuchanek
In-Reply-To: <1520895778-17586-1-git-send-email-mauricfo@linux.vnet.ibm.com>
From: Michael Ellerman <mpe@ellerman.id.au>
For PowerVM migration we want to be able to call setup_rfi_flush()
again after we've migrated the partition.
To support that we need to check that we're not trying to allocate the
fallback flush area after memblock has gone away (i.e., boot-time only).
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Mauricio Faria de Oliveira <mauricfo@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/setup.h | 2 +-
arch/powerpc/kernel/setup_64.c | 6 +++++-
2 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index 469b7fd..bbcdf929 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -49,7 +49,7 @@ enum l1d_flush_type {
L1D_FLUSH_MTTRIG = 0x8,
};
-void __init setup_rfi_flush(enum l1d_flush_type, bool enable);
+void setup_rfi_flush(enum l1d_flush_type, bool enable);
void do_rfi_flush_fixups(enum l1d_flush_type types);
#endif /* !__ASSEMBLY__ */
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 3efc01a..d60e2f7 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -860,6 +860,10 @@ static void init_fallback_flush(void)
u64 l1d_size, limit;
int cpu;
+ /* Only allocate the fallback flush area once (at boot time). */
+ if (l1d_flush_fallback_area)
+ return;
+
l1d_size = ppc64_caches.l1d.size;
limit = min(ppc64_bolted_size(), ppc64_rma_size);
@@ -877,7 +881,7 @@ static void init_fallback_flush(void)
}
}
-void __init setup_rfi_flush(enum l1d_flush_type types, bool enable)
+void setup_rfi_flush(enum l1d_flush_type types, bool enable)
{
if (types & L1D_FLUSH_FALLBACK) {
pr_info("rfi-flush: Using fallback displacement flush\n");
--
2.7.4
^ permalink raw reply related
* [PATCH v2 1/4] rfi-flush: Move the logic to avoid a redo into the debugfs code
From: Mauricio Faria de Oliveira @ 2018-03-12 23:02 UTC (permalink / raw)
To: linuxppc-dev, mpe, msuchanek
In-Reply-To: <1520895778-17586-1-git-send-email-mauricfo@linux.vnet.ibm.com>
From: Michael Ellerman <mpe@ellerman.id.au>
rfi_flush_enable() includes a check to see if we're already
enabled (or disabled), and in that case does nothing.
But that means calling setup_rfi_flush() a 2nd time doesn't actually
work, which is a bit confusing.
Move that check into the debugfs code, where it really belongs.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Mauricio Faria de Oliveira <mauricfo@linux.vnet.ibm.com>
---
arch/powerpc/kernel/setup_64.c | 13 ++++++++-----
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index c388cc3..3efc01a 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -846,9 +846,6 @@ static void do_nothing(void *unused)
void rfi_flush_enable(bool enable)
{
- if (rfi_flush == enable)
- return;
-
if (enable) {
do_rfi_flush_fixups(enabled_flush_types);
on_each_cpu(do_nothing, NULL, 1);
@@ -902,13 +899,19 @@ void __init setup_rfi_flush(enum l1d_flush_type types, bool enable)
#ifdef CONFIG_DEBUG_FS
static int rfi_flush_set(void *data, u64 val)
{
+ bool enable;
+
if (val == 1)
- rfi_flush_enable(true);
+ enable = true;
else if (val == 0)
- rfi_flush_enable(false);
+ enable = false;
else
return -EINVAL;
+ /* Only do anything if we're changing state */
+ if (enable != rfi_flush)
+ rfi_flush_enable(enable);
+
return 0;
}
--
2.7.4
^ permalink raw reply related
* [PATCH v2 0/4] Setup RFI flush after PowerVM LPM migration
From: Mauricio Faria de Oliveira @ 2018-03-12 23:02 UTC (permalink / raw)
To: linuxppc-dev, mpe, msuchanek
This patchset allows for setup_rfi_flush() to be called again
after PowerVM LPM (live partition mobility) aka LPAR migration,
in order to possibly switch to a different flush method.
The patches are mostly from Michael Ellerman, I have rebased to
powerpc/linux.git merge branch as of commit 249d7ba (March 12th),
and added one extra commit to force init of fallback flush area
on pseries.
Testing:
-------
I've disabled most code in the LPM functions migration_store()
and post_mobility_fixup() to just reach pseries_setup_rfi_flush(),
and modified pseries_setup_rfi_flush() a few times to fake the
first and non-first calls to either enable instructions or the
fallback flush method, to cover all 4 possible scenarios.
Case 1) fallback -> fallback
# dmesg | grep rfi-flush
[ 0.000000] rfi-flush: Using fallback displacement flush
[ 0.000000] rfi-flush: patched 8 locations
# echo > /sys/kernel/mobility/migration
# dmesg | grep rfi-flush
[ 0.000000] rfi-flush: Using fallback displacement flush
[ 0.000000] rfi-flush: patched 8 locations
[ 20.583029] rfi-flush: Using fallback displacement flush
[ 20.583038] rfi-flush: patched 8 locations
Case 2) instructions -> fallback
# dmesg | grep rfi-flush
[ 0.000000] rfi-flush: Using ori type flush
[ 0.000000] rfi-flush: Using mttrig type flush
[ 0.000000] rfi-flush: patched 8 locations
# echo > /sys/kernel/mobility/migration
# dmesg | grep rfi-flush
[ 0.000000] rfi-flush: Using ori type flush
[ 0.000000] rfi-flush: Using mttrig type flush
[ 0.000000] rfi-flush: patched 8 locations
[ 36.023759] rfi-flush: Using fallback displacement flush
[ 36.023764] rfi-flush: patched 8 locations
Case 3) fallback -> instructions
# dmesg | grep rfi-flush
[ 0.000000] rfi-flush: Using fallback displacement flush
[ 0.000000] rfi-flush: patched 8 locations
# echo > /sys/kernel/mobility/migration
# dmesg | grep rfi-flush
[ 0.000000] rfi-flush: Using fallback displacement flush
[ 0.000000] rfi-flush: patched 8 locations
[ 23.373037] rfi-flush: Using ori type flush
[ 23.373039] rfi-flush: Using mttrig type flush
[ 23.373044] rfi-flush: patched 8 locations
Case 4) instructions -> instructions
# dmesg | grep rfi-flush
[ 0.000000] rfi-flush: Using ori type flush
[ 0.000000] rfi-flush: Using mttrig type flush
[ 0.000000] rfi-flush: patched 8 locations
# echo > /sys/kernel/mobility/migration
# dmesg | grep rfi-flush
[ 0.000000] rfi-flush: Using ori type flush
[ 0.000000] rfi-flush: Using mttrig type flush
[ 0.000000] rfi-flush: patched 8 locations
[ 23.243564] rfi-flush: Using ori type flush
[ 23.243566] rfi-flush: Using mttrig type flush
[ 23.243570] rfi-flush: patched 8 locations
Mauricio Faria de Oliveira (1):
rfi-flush: Allow pseries to force init of fallback flush area
Michael Ellerman (3):
rfi-flush: Move the logic to avoid a redo into the debugfs code
rfi-flush: Make it possible to call setup_rfi_flush() again
rfi-flush: Call setup_rfi_flush() after LPM migration
arch/powerpc/include/asm/setup.h | 2 +-
arch/powerpc/kernel/setup_64.c | 22 +++++++++++++++-------
arch/powerpc/platforms/powernv/setup.c | 3 ++-
arch/powerpc/platforms/pseries/mobility.c | 3 +++
arch/powerpc/platforms/pseries/pseries.h | 2 ++
arch/powerpc/platforms/pseries/setup.c | 6 +++---
6 files changed, 26 insertions(+), 12 deletions(-)
--
2.7.4
^ permalink raw reply
* Re: [PATCH v3 02/10] include: Move compat_timespec/ timeval to compat_time.h
From: Deepa Dinamani @ 2018-03-12 17:59 UTC (permalink / raw)
To: Christian Borntraeger
Cc: Arnd Bergmann, Thomas Gleixner, John Stultz, Mark Rutland,
open list:RALINK MIPS ARCHITECTURE, Peter Zijlstra,
Heiko Carstens, Paul Mackerras, H. Peter Anvin, sparclinux, devel,
linux-s390, y2038 Mailman List, Helge Deller,
the arch/x86 maintainers, sebott, James E.J. Bottomley,
Will Deacon, Ingo Molnar, oprofile-list, Catalin Marinas,
Robert Richter, Chris Metcalf, Peter Oberparleiter,
Arnaldo Carvalho de Melo, Julian Wiedmann, Steven Rostedt,
Ursula Braun, gerald.schaefer, Parisc List, gregkh, cohuck,
Linux Kernel Mailing List, Ralf Baechle, Jan Hoeppner,
Stefan Haberland, Martin Schwidefsky, linuxppc-dev, David Miller
In-Reply-To: <CABeXuvrdPV0q4ufuxEnqT6T3b8pCT5RLUfuAZ_cwXr0it8gj0Q@mail.gmail.com>
I posted the updated series. I fixed up the order of include files
where I could find some order.
There have been other commits that used scripts to do such
replacements and have already stomped on the order.
For example:
commit 7c0f6ba682b9c7632072ffbedf8d328c8f3c42ba
Author: Linus Torvalds <torvalds@linux-foundation.org>
Replace <asm/uaccess.h> with <linux/uaccess.h> globally
-Deepa
On Tue, Mar 6, 2018 at 2:58 PM, Deepa Dinamani <deepa.kernel@gmail.com> wrote:
> On Tue, Mar 6, 2018 at 4:48 AM, Christian Borntraeger
> <borntraeger@de.ibm.com> wrote:
>>
>>
>> On 03/06/2018 01:46 PM, Arnd Bergmann wrote:
>>> On Mon, Mar 5, 2018 at 10:30 AM, Christian Borntraeger
>>> <borntraeger@de.ibm.com> wrote:
>>>> On 01/16/2018 03:18 AM, Deepa Dinamani wrote:
>>>>> All the current architecture specific defines for these
>>>>> are the same. Refactor these common defines to a common
>>>>> header file.
>>>>>
>>>>> The new common linux/compat_time.h is also useful as it
>>>>> will eventually be used to hold all the defines that
>>>>> are needed for compat time types that support non y2038
>>>>> safe types. New architectures need not have to define these
>>>>> new types as they will only use new y2038 safe syscalls.
>>>>> This file can be deleted after y2038 when we stop supporting
>>>>> non y2038 safe syscalls.
>>>>
>>>> You are now include a <linux/*.h> from several asm files
>>>> (
>>>> arch/arm64/include/asm/stat.h
>>>> arch/s390/include/asm/elf.h
>>>> arch/x86/include/asm/ftrace.h
>>>> arch/x86/include/asm/sys_ia32.h
>>>> )
>>>> It works, and it is done in many places, but it looks somewhat weird.
>>>> Would it make sense to have an asm-generic/compate-time.h instead? Asking for
>>>> opinions here.
>>>
>>> I don't think we have such a rule. If a header file is common to all
>>> architectures (i.e. no architecture uses a different implementation),
>>> it should be in include/linux rather than include/asm-generic, regardless
>>> of whether it can be used by assembler files or not.
>>>
>>>>> --- a/drivers/s390/net/qeth_core_main.c
>>>>> +++ b/drivers/s390/net/qeth_core_main.c
>>>>> @@ -32,7 +32,7 @@
>>>>> #include <asm/chpid.h>
>>>>> #include <asm/io.h>
>>>>> #include <asm/sysinfo.h>
>>>>> -#include <asm/compat.h>
>>>>> +#include <linux/compat.h>
>>>>> #include <asm/diag.h>
>>>>> #include <asm/cio.h>
>>>>> #include <asm/ccwdev.h>
>>>>
>>>> Can you move that into the other includes (where all the other <linux/*> includes are.
>>>
>>> Good catch, this is definitely a rule we have ;-)
>>
>> FWIW, this was also broken for
>> arch/x86/include/asm/sys_ia32.h
>
> The reason that this was done this way is because of the sed script
> mentioned in the commit text.
> I was trying to make minimal change apart from the script so that we
> don't have other changes like moving the lines to keep the patch
> simpler.
> I will fix this by hand since this is preferred.
> I will post an update.
>
> -Deepa
^ permalink raw reply
* [PATCH v4 02/10] include: Move compat_timespec/ timeval to compat_time.h
From: Deepa Dinamani @ 2018-03-12 17:52 UTC (permalink / raw)
To: arnd, tglx, john.stultz
Cc: linux-kernel, y2038, acme, benh, borntraeger, catalin.marinas,
cmetcalf, cohuck, davem, deller, devel, gerald.schaefer, gregkh,
heiko.carstens, hoeppner, hpa, jejb, jwi, linux-mips,
linux-parisc, linuxppc-dev, linux-s390, mark.rutland, mingo, mpe,
oberpar, oprofile-list, paulus, peterz, ralf, rostedt, rric,
schwidefsky, sebott, sparclinux, sth, ubraun, will.deacon, x86
In-Reply-To: <20180312175307.11032-1-deepa.kernel@gmail.com>
All the current architecture specific defines for these
are the same. Refactor these common defines to a common
header file.
The new common linux/compat_time.h is also useful as it
will eventually be used to hold all the defines that
are needed for compat time types that support non y2038
safe types. New architectures need not have to define these
new types as they will only use new y2038 safe syscalls.
This file can be deleted after y2038 when we stop supporting
non y2038 safe syscalls.
The patch also requires an operation similar to:
git grep "asm/compat\.h" | cut -d ":" -f 1 | xargs -n 1 sed -i -e "s%asm/compat.h%linux/compat.h%g"
Cc: acme@kernel.org
Cc: benh@kernel.crashing.org
Cc: borntraeger@de.ibm.com
Cc: catalin.marinas@arm.com
Cc: cmetcalf@mellanox.com
Cc: cohuck@redhat.com
Cc: davem@davemloft.net
Cc: deller@gmx.de
Cc: devel@driverdev.osuosl.org
Cc: gerald.schaefer@de.ibm.com
Cc: gregkh@linuxfoundation.org
Cc: heiko.carstens@de.ibm.com
Cc: hoeppner@linux.vnet.ibm.com
Cc: hpa@zytor.com
Cc: jejb@parisc-linux.org
Cc: jwi@linux.vnet.ibm.com
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Cc: mark.rutland@arm.com
Cc: mingo@redhat.com
Cc: mpe@ellerman.id.au
Cc: oberpar@linux.vnet.ibm.com
Cc: oprofile-list@lists.sf.net
Cc: paulus@samba.org
Cc: peterz@infradead.org
Cc: ralf@linux-mips.org
Cc: rostedt@goodmis.org
Cc: rric@kernel.org
Cc: schwidefsky@de.ibm.com
Cc: sebott@linux.vnet.ibm.com
Cc: sparclinux@vger.kernel.org
Cc: sth@linux.vnet.ibm.com
Cc: ubraun@linux.vnet.ibm.com
Cc: will.deacon@arm.com
Cc: x86@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: James Hogan <jhogan@kernel.org>
Acked-by: Helge Deller <deller@gmx.de>
---
arch/arm64/include/asm/compat.h | 11 -----------
arch/arm64/include/asm/stat.h | 1 +
arch/arm64/kernel/hw_breakpoint.c | 1 -
arch/arm64/kernel/perf_regs.c | 2 +-
arch/arm64/kernel/process.c | 1 -
arch/mips/include/asm/compat.h | 11 -----------
arch/mips/kernel/signal32.c | 2 +-
arch/parisc/include/asm/compat.h | 11 -----------
arch/powerpc/include/asm/compat.h | 11 -----------
arch/powerpc/kernel/asm-offsets.c | 2 +-
arch/powerpc/oprofile/backtrace.c | 2 +-
arch/s390/hypfs/hypfs_sprp.c | 1 -
arch/s390/include/asm/compat.h | 11 -----------
arch/s390/include/asm/elf.h | 4 ++--
arch/s390/kvm/priv.c | 1 -
arch/s390/pci/pci_clp.c | 1 -
arch/sparc/include/asm/compat.h | 11 -----------
arch/tile/include/asm/compat.h | 11 -----------
arch/x86/events/core.c | 2 +-
arch/x86/include/asm/compat.h | 11 -----------
arch/x86/include/asm/ftrace.h | 2 +-
arch/x86/include/asm/sys_ia32.h | 2 +-
arch/x86/kernel/sys_x86_64.c | 2 +-
drivers/s390/block/dasd_ioctl.c | 1 -
drivers/s390/char/fs3270.c | 1 -
drivers/s390/char/sclp_ctl.c | 1 -
drivers/s390/char/vmcp.c | 1 -
drivers/s390/cio/chsc_sch.c | 1 -
drivers/s390/net/qeth_core_main.c | 2 +-
include/linux/compat.h | 1 +
include/linux/compat_time.h | 19 +++++++++++++++++++
31 files changed, 32 insertions(+), 109 deletions(-)
create mode 100644 include/linux/compat_time.h
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index c00c62e1a4a3..0030f79808b3 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -34,7 +34,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u16 __compat_uid_t;
@@ -66,16 +65,6 @@ typedef u32 compat_ulong_t;
typedef u64 compat_u64;
typedef u32 compat_uptr_t;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
#ifdef __AARCH64EB__
short st_dev;
diff --git a/arch/arm64/include/asm/stat.h b/arch/arm64/include/asm/stat.h
index 15e35598ac40..eab738019707 100644
--- a/arch/arm64/include/asm/stat.h
+++ b/arch/arm64/include/asm/stat.h
@@ -20,6 +20,7 @@
#ifdef CONFIG_COMPAT
+#include <linux/compat_time.h>
#include <asm/compat.h>
/*
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 74bb56f656ef..413dbe530da8 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -30,7 +30,6 @@
#include <linux/smp.h>
#include <linux/uaccess.h>
-#include <asm/compat.h>
#include <asm/current.h>
#include <asm/debug-monitors.h>
#include <asm/hw_breakpoint.h>
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
index 1d091d048d04..0bbac612146e 100644
--- a/arch/arm64/kernel/perf_regs.c
+++ b/arch/arm64/kernel/perf_regs.c
@@ -1,11 +1,11 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/perf_event.h>
#include <linux/bug.h>
#include <linux/sched/task_stack.h>
-#include <asm/compat.h>
#include <asm/perf_regs.h>
#include <asm/ptrace.h>
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index c0da6efe5465..a725e81d0063 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -51,7 +51,6 @@
#include <linux/thread_info.h>
#include <asm/alternative.h>
-#include <asm/compat.h>
#include <asm/cacheflush.h>
#include <asm/exec.h>
#include <asm/fpsimd.h>
diff --git a/arch/mips/include/asm/compat.h b/arch/mips/include/asm/compat.h
index 9a0fa66b81ac..3e548ee99a2f 100644
--- a/arch/mips/include/asm/compat.h
+++ b/arch/mips/include/asm/compat.h
@@ -14,7 +14,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_suseconds_t;
@@ -46,16 +45,6 @@ typedef u32 compat_ulong_t;
typedef u64 compat_u64;
typedef u32 compat_uptr_t;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
compat_dev_t st_dev;
s32 st_pad1[3];
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index c4db910a8794..b5d9e1784aff 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -8,13 +8,13 @@
* Copyright (C) 1999, 2000 Silicon Graphics, Inc.
* Copyright (C) 2016, Imagination Technologies Ltd.
*/
+#include <linux/compat.h>
#include <linux/compiler.h>
#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/signal.h>
#include <linux/syscalls.h>
-#include <asm/compat.h>
#include <asm/compat-signal.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h
index c22db5323244..6f256e7b95e3 100644
--- a/arch/parisc/include/asm/compat.h
+++ b/arch/parisc/include/asm/compat.h
@@ -13,7 +13,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u32 __compat_uid_t;
@@ -40,16 +39,6 @@ typedef u32 compat_ulong_t;
typedef u64 compat_u64;
typedef u32 compat_uptr_t;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
compat_dev_t st_dev; /* dev_t is 32 bits on parisc */
compat_ino_t st_ino; /* 32 bits */
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 62168e1158f1..b4773c81f7d5 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -17,7 +17,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u32 __compat_uid_t;
@@ -45,16 +44,6 @@ typedef u32 compat_ulong_t;
typedef u64 compat_u64;
typedef u32 compat_uptr_t;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
compat_dev_t st_dev;
compat_ino_t st_ino;
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index ea5eb91b836e..4a314620344f 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -13,6 +13,7 @@
* 2 of the License, or (at your option) any later version.
*/
+#include <linux/compat.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
@@ -42,7 +43,6 @@
#include <asm/paca.h>
#include <asm/lppaca.h>
#include <asm/cache.h>
-#include <asm/compat.h>
#include <asm/mmu.h>
#include <asm/hvcall.h>
#include <asm/xics.h>
diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c
index ecc66d5f02c9..11ff763c03ad 100644
--- a/arch/powerpc/oprofile/backtrace.c
+++ b/arch/powerpc/oprofile/backtrace.c
@@ -11,7 +11,7 @@
#include <linux/sched.h>
#include <asm/processor.h>
#include <linux/uaccess.h>
-#include <asm/compat.h>
+#include <linux/compat.h>
#include <asm/oprofile_impl.h>
#define STACK_SP(STACK) *(STACK)
diff --git a/arch/s390/hypfs/hypfs_sprp.c b/arch/s390/hypfs/hypfs_sprp.c
index ae0ed8dd5f1b..5d85a039391c 100644
--- a/arch/s390/hypfs/hypfs_sprp.c
+++ b/arch/s390/hypfs/hypfs_sprp.c
@@ -13,7 +13,6 @@
#include <linux/string.h>
#include <linux/types.h>
#include <linux/uaccess.h>
-#include <asm/compat.h>
#include <asm/diag.h>
#include <asm/sclp.h>
#include "hypfs.h"
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 9830fb6b076e..501aaff85304 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -53,7 +53,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u16 __compat_uid_t;
@@ -97,16 +96,6 @@ typedef struct {
u32 gprs_high[NUM_GPRS];
} s390_compat_regs_high;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
compat_dev_t st_dev;
u16 __pad1;
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 1a61b1b997f2..7d22a474a040 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -125,8 +125,9 @@
* ELF register definitions..
*/
+#include <linux/compat.h>
+
#include <asm/ptrace.h>
-#include <asm/compat.h>
#include <asm/syscall.h>
#include <asm/user.h>
@@ -136,7 +137,6 @@ typedef s390_regs elf_gregset_t;
typedef s390_fp_regs compat_elf_fpregset_t;
typedef s390_compat_regs compat_elf_gregset_t;
-#include <linux/compat.h>
#include <linux/sched/mm.h> /* for task_struct */
#include <asm/mmu_context.h>
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index ebfa0442e569..a3bce0e84346 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -26,7 +26,6 @@
#include <asm/gmap.h>
#include <asm/io.h>
#include <asm/ptrace.h>
-#include <asm/compat.h>
#include <asm/sclp.h>
#include "gaccess.h"
#include "kvm-s390.h"
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 93cd0f1ca12b..19b2d2a9b43d 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -19,7 +19,6 @@
#include <linux/uaccess.h>
#include <asm/pci_debug.h>
#include <asm/pci_clp.h>
-#include <asm/compat.h>
#include <asm/clp.h>
#include <uapi/asm/clp.h>
diff --git a/arch/sparc/include/asm/compat.h b/arch/sparc/include/asm/compat.h
index 615283e16f22..844a89739e76 100644
--- a/arch/sparc/include/asm/compat.h
+++ b/arch/sparc/include/asm/compat.h
@@ -11,7 +11,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u16 __compat_uid_t;
@@ -39,16 +38,6 @@ typedef u32 compat_ulong_t;
typedef u64 compat_u64;
typedef u32 compat_uptr_t;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
compat_dev_t st_dev;
compat_ino_t st_ino;
diff --git a/arch/tile/include/asm/compat.h b/arch/tile/include/asm/compat.h
index 769ff6ac0bf5..06188e0da2de 100644
--- a/arch/tile/include/asm/compat.h
+++ b/arch/tile/include/asm/compat.h
@@ -29,7 +29,6 @@ typedef u32 compat_ulong_t;
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
typedef s32 compat_off_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef u32 compat_ino_t;
typedef u32 compat_caddr_t;
@@ -59,16 +58,6 @@ typedef unsigned long compat_elf_greg_t;
#define COMPAT_ELF_NGREG (sizeof(struct pt_regs) / sizeof(compat_elf_greg_t))
typedef compat_elf_greg_t compat_elf_gregset_t[COMPAT_ELF_NGREG];
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
#define compat_stat stat
#define compat_statfs statfs
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 140d33288e78..6b8961912781 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2391,7 +2391,7 @@ static unsigned long get_segment_base(unsigned int segment)
#ifdef CONFIG_IA32_EMULATION
-#include <asm/compat.h>
+#include <linux/compat.h>
static inline int
perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *entry)
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index e1c8dab86670..7cd314b71c51 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -17,7 +17,6 @@
typedef u32 compat_size_t;
typedef s32 compat_ssize_t;
-typedef s32 compat_time_t;
typedef s32 compat_clock_t;
typedef s32 compat_pid_t;
typedef u16 __compat_uid_t;
@@ -46,16 +45,6 @@ typedef u32 compat_u32;
typedef u64 __attribute__((aligned(4))) compat_u64;
typedef u32 compat_uptr_t;
-struct compat_timespec {
- compat_time_t tv_sec;
- s32 tv_nsec;
-};
-
-struct compat_timeval {
- compat_time_t tv_sec;
- s32 tv_usec;
-};
-
struct compat_stat {
compat_dev_t st_dev;
u16 __pad1;
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 09ad88572746..db25aa15b705 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -49,7 +49,7 @@ int ftrace_int3_handler(struct pt_regs *regs);
#if !defined(__ASSEMBLY__) && !defined(COMPILE_OFFSETS)
#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_IA32_EMULATION)
-#include <asm/compat.h>
+#include <linux/compat.h>
/*
* Because ia32 syscalls do not map to x86_64 syscall numbers
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index 82c34ee25a65..8c4083dcd901 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -12,11 +12,11 @@
#ifdef CONFIG_COMPAT
+#include <linux/compat.h>
#include <linux/compiler.h>
#include <linux/linkage.h>
#include <linux/types.h>
#include <linux/signal.h>
-#include <asm/compat.h>
#include <asm/ia32.h>
/* ia32/sys_ia32.c */
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index 676774b9bb8d..6cba5755958c 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -1,4 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
+#include <linux/compat.h>
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
@@ -19,7 +20,6 @@
#include <linux/elf.h>
#include <asm/elf.h>
-#include <asm/compat.h>
#include <asm/ia32.h>
#include <asm/syscalls.h>
#include <asm/mpx.h>
diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c
index 7bdc6aaa0ba3..2016e0ed5865 100644
--- a/drivers/s390/block/dasd_ioctl.c
+++ b/drivers/s390/block/dasd_ioctl.c
@@ -18,7 +18,6 @@
#include <linux/fs.h>
#include <linux/blkpg.h>
#include <linux/slab.h>
-#include <asm/compat.h>
#include <asm/ccwdev.h>
#include <asm/schid.h>
#include <asm/cmb.h>
diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c
index 61822480a2a0..16a4e8528bbc 100644
--- a/drivers/s390/char/fs3270.c
+++ b/drivers/s390/char/fs3270.c
@@ -19,7 +19,6 @@
#include <linux/slab.h>
#include <linux/types.h>
-#include <asm/compat.h>
#include <asm/ccwdev.h>
#include <asm/cio.h>
#include <asm/ebcdic.h>
diff --git a/drivers/s390/char/sclp_ctl.c b/drivers/s390/char/sclp_ctl.c
index a78cea0c3a09..248b5db3eaa8 100644
--- a/drivers/s390/char/sclp_ctl.c
+++ b/drivers/s390/char/sclp_ctl.c
@@ -14,7 +14,6 @@
#include <linux/init.h>
#include <linux/ioctl.h>
#include <linux/fs.h>
-#include <asm/compat.h>
#include <asm/sclp_ctl.h>
#include <asm/sclp.h>
diff --git a/drivers/s390/char/vmcp.c b/drivers/s390/char/vmcp.c
index 17e411c57576..948ce82a7725 100644
--- a/drivers/s390/char/vmcp.c
+++ b/drivers/s390/char/vmcp.c
@@ -23,7 +23,6 @@
#include <linux/mutex.h>
#include <linux/cma.h>
#include <linux/mm.h>
-#include <asm/compat.h>
#include <asm/cpcmd.h>
#include <asm/debug.h>
#include <asm/vmcp.h>
diff --git a/drivers/s390/cio/chsc_sch.c b/drivers/s390/cio/chsc_sch.c
index 0015729d917d..8d9f36625ba5 100644
--- a/drivers/s390/cio/chsc_sch.c
+++ b/drivers/s390/cio/chsc_sch.c
@@ -16,7 +16,6 @@
#include <linux/miscdevice.h>
#include <linux/kernel_stat.h>
-#include <asm/compat.h>
#include <asm/cio.h>
#include <asm/chsc.h>
#include <asm/isc.h>
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index c8b308cfabf1..d3529ef6e0f7 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -10,6 +10,7 @@
#define KMSG_COMPONENT "qeth"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+#include <linux/compat.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/string.h>
@@ -32,7 +33,6 @@
#include <asm/chpid.h>
#include <asm/io.h>
#include <asm/sysinfo.h>
-#include <asm/compat.h>
#include <asm/diag.h>
#include <asm/cio.h>
#include <asm/ccwdev.h>
diff --git a/include/linux/compat.h b/include/linux/compat.h
index bdf1908a392e..0eb4a3a8f62e 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -7,6 +7,7 @@
*/
#include <linux/types.h>
+#include <linux/compat_time.h>
#include <linux/stat.h>
#include <linux/param.h> /* for HZ */
diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h
new file mode 100644
index 000000000000..56a54a1e4355
--- /dev/null
+++ b/include/linux/compat_time.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_COMPAT_TIME_H
+#define _LINUX_COMPAT_TIME_H
+
+#include <linux/types.h>
+
+typedef s32 compat_time_t;
+
+struct compat_timespec {
+ compat_time_t tv_sec;
+ s32 tv_nsec;
+};
+
+struct compat_timeval {
+ compat_time_t tv_sec;
+ s32 tv_usec;
+};
+
+#endif /* _LINUX_COMPAT_TIME_H */
--
2.14.1
^ permalink raw reply related
* [PATCH v4 00/10] posix_clocks: Prepare syscalls for 64 bit time_t conversion
From: Deepa Dinamani @ 2018-03-12 17:52 UTC (permalink / raw)
To: arnd, tglx, john.stultz
Cc: linux-kernel, y2038, acme, benh, borntraeger, catalin.marinas,
cmetcalf, cohuck, davem, deller, devel, gerald.schaefer, gregkh,
heiko.carstens, hoeppner, hpa, jejb, jwi, linux-api, linux-arch,
linux-mips, linux-parisc, linuxppc-dev, linux-s390, mark.rutland,
mingo, mpe, oberpar, oprofile-list, paulus, peterz, ralf, rostedt,
rric, schwidefsky, sebott, sparclinux, sth, ubraun, will.deacon,
x86
The series is a preparation series for individual architectures
to use 64 bit time_t syscalls in compat and 32 bit emulation modes.
This is a follow up to the series Arnd Bergmann posted:
https://sourceware.org/ml/libc-alpha/2015-05/msg00070.html [1]
Thomas, Arnd, this seems ready to be merged now.
Can you help get this merged?
Big picture is as per the lwn article:
https://lwn.net/Articles/643234/ [2]
The series is directed at converting posix clock syscalls:
clock_gettime, clock_settime, clock_getres and clock_nanosleep
to use a new data structure __kernel_timespec at syscall boundaries.
__kernel_timespec maintains 64 bit time_t across all execution modes.
vdso will be handled as part of each architecture when they enable
support for 64 bit time_t.
The compat syscalls are repurposed to provide backward compatibility
by using them as native syscalls as well for 32 bit architectures.
They will continue to use timespec at syscall boundaries.
CONFIG_64_BIT_TIME controls whether the syscalls use __kernel_timespec
or timespec at syscall boundaries.
The series does the following:
1. Enable compat syscalls on 32 bit architectures.
2. Add a new __kernel_timespec type to be used as the data structure
for all the new syscalls.
3. Add new config CONFIG_64BIT_TIME(intead of the CONFIG_COMPAT_TIME in
[1] and [2] to switch to new definition of __kernel_timespec. It is
the same as struct timespec otherwise.
4. Add new CONFIG_32BIT_TIME to conditionally compile compat syscalls.
* Changes since v3:
* Updated include file ordering
* Changes since v2:
* Dropped the ARCH_HAS_64BIT_TIME config.
* Fixed zeroing out of higher order bits of tv_nsec for real.
* Addressed minor review comments from v1.
* Changes since v1:
* Introduce CONFIG_32BIT_TIME
* Fixed zeroing out of higher order bits of tv_nsec
* Included Arnd's changes to fix up use of compat headers
I decided against using LEGACY_TIME_SYSCALLS to conditionally compile
legacy time syscalls such as sys_nanosleep because this will need to
enclose compat_sys_nanosleep as well. So, defining it as
config LEGACY_TIME_SYSCALLS
def_bool 64BIT || !64BIT_TIME
will not include compat_sys_nanosleep. We will instead need a new config to
exclusively mark legacy syscalls.
Deepa Dinamani (10):
compat: Make compat helpers independent of CONFIG_COMPAT
include: Move compat_timespec/ timeval to compat_time.h
compat: enable compat_get/put_timespec64 always
arch: introduce CONFIG_64BIT_TIME
arch: Introduce CONFIG_COMPAT_32BIT_TIME
posix-clocks: Make compat syscalls depend on CONFIG_COMPAT_32BIT_TIME
include: Add new y2038 safe __kernel_timespec
fix get_timespec64() for y2038 safe compat interfaces
change time types to new y2038 safe __kernel_* types
nanosleep: change time types to safe __kernel_* types
arch/Kconfig | 15 +++++++++
arch/arm64/include/asm/compat.h | 11 -------
arch/arm64/include/asm/stat.h | 1 +
arch/arm64/kernel/hw_breakpoint.c | 1 -
arch/arm64/kernel/perf_regs.c | 2 +-
arch/arm64/kernel/process.c | 1 -
arch/mips/include/asm/compat.h | 11 -------
arch/mips/kernel/signal32.c | 2 +-
arch/parisc/include/asm/compat.h | 11 -------
arch/powerpc/include/asm/compat.h | 11 -------
arch/powerpc/kernel/asm-offsets.c | 2 +-
arch/powerpc/oprofile/backtrace.c | 2 +-
arch/s390/hypfs/hypfs_sprp.c | 1 -
arch/s390/include/asm/compat.h | 11 -------
arch/s390/include/asm/elf.h | 4 +--
arch/s390/kvm/priv.c | 1 -
arch/s390/pci/pci_clp.c | 1 -
arch/sparc/include/asm/compat.h | 11 -------
arch/tile/include/asm/compat.h | 11 -------
arch/x86/events/core.c | 2 +-
arch/x86/include/asm/compat.h | 11 -------
arch/x86/include/asm/ftrace.h | 2 +-
arch/x86/include/asm/sys_ia32.h | 2 +-
arch/x86/kernel/sys_x86_64.c | 2 +-
drivers/s390/block/dasd_ioctl.c | 1 -
drivers/s390/char/fs3270.c | 1 -
drivers/s390/char/sclp_ctl.c | 1 -
drivers/s390/char/vmcp.c | 1 -
drivers/s390/cio/chsc_sch.c | 1 -
drivers/s390/net/qeth_core_main.c | 2 +-
include/linux/compat.h | 11 ++++---
include/linux/compat_time.h | 23 ++++++++++++++
include/linux/restart_block.h | 7 ++--
include/linux/syscalls.h | 12 +++----
include/linux/time.h | 4 +--
include/linux/time64.h | 10 +++++-
include/uapi/asm-generic/posix_types.h | 1 +
include/uapi/linux/time.h | 7 ++++
kernel/compat.c | 52 +++++-------------------------
kernel/time/hrtimer.c | 10 ++++--
kernel/time/posix-stubs.c | 12 ++++---
kernel/time/posix-timers.c | 24 ++++++++++----
kernel/time/time.c | 58 +++++++++++++++++++++++++++++++---
43 files changed, 177 insertions(+), 190 deletions(-)
create mode 100644 include/linux/compat_time.h
base-commit: 61530b14b059d4838dcc2186e9de9d57e195ce55
--
2.14.1
Cc: acme@kernel.org
Cc: benh@kernel.crashing.org
Cc: borntraeger@de.ibm.com
Cc: catalin.marinas@arm.com
Cc: cmetcalf@mellanox.com
Cc: cohuck@redhat.com
Cc: davem@davemloft.net
Cc: deller@gmx.de
Cc: devel@driverdev.osuosl.org
Cc: gerald.schaefer@de.ibm.com
Cc: gregkh@linuxfoundation.org
Cc: heiko.carstens@de.ibm.com
Cc: hoeppner@linux.vnet.ibm.com
Cc: hpa@zytor.com
Cc: jejb@parisc-linux.org
Cc: jwi@linux.vnet.ibm.com
Cc: linux-api@vger.kernel.org
Cc: linux-arch@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-parisc@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Cc: mark.rutland@arm.com
Cc: mingo@redhat.com
Cc: mpe@ellerman.id.au
Cc: oberpar@linux.vnet.ibm.com
Cc: oprofile-list@lists.sf.net
Cc: paulus@samba.org
Cc: peterz@infradead.org
Cc: ralf@linux-mips.org
Cc: rostedt@goodmis.org
Cc: rric@kernel.org
Cc: schwidefsky@de.ibm.com
Cc: sebott@linux.vnet.ibm.com
Cc: sparclinux@vger.kernel.org
Cc: sth@linux.vnet.ibm.com
Cc: ubraun@linux.vnet.ibm.com
Cc: will.deacon@arm.com
Cc: x86@kernel.org
^ permalink raw reply
* Re: [PATCH] x86, powerpc : pkey-mprotect must allow pkey-0
From: Dave Hansen @ 2018-03-12 15:46 UTC (permalink / raw)
To: Ram Pai, Michael Ellerman
Cc: mingo, akpm, linuxppc-dev, linux-mm, x86, linux-arch,
linux-kernel, benh, paulus, khandual, aneesh.kumar, bsingharora,
hbabu, mhocko, bauerman, ebiederm, corbet, arnd, fweimer,
msuchanek, Ulrich.Weigand
In-Reply-To: <20180309200631.GS1060@ram.oc3035372033.ibm.com>
On 03/09/2018 12:06 PM, Ram Pai wrote:
> On Fri, Mar 09, 2018 at 09:19:53PM +1100, Michael Ellerman wrote:
>> Ram Pai <linuxram@us.ibm.com> writes:
>>
>>> Once an address range is associated with an allocated pkey, it cannot be
>>> reverted back to key-0. There is no valid reason for the above behavior. On
>>> the contrary applications need the ability to do so.
>> Please explain this in much more detail. Is it an ABI change?
> Not necessarily an ABI change. older binary applications will continue
> to work. It can be considered as a bug-fix.
Yeah, agreed. I do not think this is an ABI change.
^ permalink raw reply
* Re: [PATCH v2] On ppc64le we HAVE_RELIABLE_STACKTRACE
From: Josh Poimboeuf @ 2018-03-12 15:35 UTC (permalink / raw)
To: Torsten Duwe
Cc: Michael Ellerman, Jiri Kosina, linuxppc-dev, linux-kernel,
Nicholas Piggin, live-patching
In-Reply-To: <20180309174718.2700b29e@blackhole.lan>
On Fri, Mar 09, 2018 at 05:47:18PM +0100, Torsten Duwe wrote:
> On Thu, 8 Mar 2018 10:26:16 -0600
> Josh Poimboeuf <jpoimboe@redhat.com> wrote:
>
> > This doesn't seem to address some of my previous concerns:
>
> You're right. That discussion quickly headed towards objtool
> and I forgot about this one paragraph with the remarks.
>
> > - Bailing on interrupt/exception frames
>
> That is a good question. My current code keeps unwinding as long
> as the trace looks sane. If the exception frame has a valid code
> pointer in the LR slot it will continue. Couldn't there be cases
> where this is desirable?
I thought we established in the previous discussion that this could
cause some functions to get skipped in the stack trace:
https://lkml.kernel.org/r/20171219214652.u7qeb7fxov62ttke@treble
> Should this be configurable? Not that
> I have an idea how this situation could occur for a thread
> that is current or sleeping...
Page faults and preemption.
> Michael, Balbir: is that possible? Any Idea how to reliably detect
> an exception frame? My approach would be to look at the next return
> address and compare it to the usual suspects (i.e. collect all
> "b ret" addresses in the EXCEPTION_COMMON macro, for BookS).
It looks like show_stack() already knows how to do this:
/*
* See if this is an exception frame.
* We look for the "regshere" marker in the current frame.
*/
if (validate_sp(sp, tsk, STACK_INT_FRAME_SIZE)
&& stack[STACK_FRAME_MARKER] == STACK_FRAME_REGS_MARKER) {
So you could do something similar.
> > - Function graph tracing return address conversion
> >
> > - kretprobes return address conversion
>
> You mean like in arch/x86/kernel/unwind_frame.c the call to
> ftrace_graph_ret_addr ?
>
> Forgive me my directness but I don't see why these should be handled in
> arch-dependent code, other than maybe a hook, if inevitable, that calls
> back into the graph tracer / kretprobes in order to get the proper
> address,
I don't really follow, where exactly would you propose calling
ftrace_graph_ret_addr() from?
> or simply call the trace unreliable in case it finds such a
> return address.
If you're going to make livepatch incompatible with function graph
tracing, there needs to be a good justification for it (and we'd need to
make sure existing users are fine with it).
--
Josh
^ permalink raw reply
* Linux 4.16: Reported regressions as of , 2018-03-12 (Was: Linux 4.16-rc5)
From: Thorsten Leemhuis @ 2018-03-12 14:03 UTC (permalink / raw)
To: Linus Torvalds, Linux Kernel Mailing List, linuxppc-dev,
Jonathan Corbet
In-Reply-To: <CA+55aFxXAMHeD8zz1BLv9r_2rjWJ6xE=cNGVAoWOvQJog7oz9A@mail.gmail.com>
On 12.03.2018 01:42, Linus Torvalds wrote:
> This continue to be pretty normal - this rc is slightly larger than
> rc4 was, but that looks like one of the normal fluctuations
Hi! Find below my fourth regression report for Linux 4.16. It lists 9
regressions I'm currently aware of. 1 was fixed since last weeks report.
To anyone reading this: Are you aware of any other regressions that got
introduced this development cycle? Then please let me know by mail (a
simple bounce or forward to the sender of this email address is enough!).
For details see http://bit.ly/lnxregtrackid And please tell me if there
is anything in the report that shouldn't be there.
Ciao, Thorsten
== Current regressions ==
Dell R640 does not boot due to SCSI/SATA failure
- Status: WIP; some other changed planed for 4.17 solve this regression,
but there is a discussion if they are too big for 4.16-rc
- Cause: 84676c1f21e8
- Reported: 2018-02-22
https://marc.info/?l=linux-kernel&m=151931128006031
- Last known developer activity:
https://marc.info/?i=1520515113.20980.31.camel%40gmail.com
- Last relevant activity:
https://marc.info/?l=linux-kernel&m=152026091325037
- Linux-Regression-ID: 15a115
[mm, mlock, vmscan] 9c4e6b1a70: stress-ng.hdd.ops_per_sec -7.9% regression
- Status: looks stalled; side note: lkp-robot warned about something
else triggered by the same commit:
https://lkml.kernel.org/r/20180302093940.GE25699@yexl-desktop is related
- Cause: 9c4e6b1a7027f102990c0395296015a812525f4d
- Reported: 2018-02-25
https://marc.info/?l=linux-kernel&m=151956997301994
- Note: performance regression found by lkp-robot
aim7.jobs-per-min -18.0% regression
- Status: looks stalled after some discussions happened the week before last
- Cause: c0cef30e4ff0dc025f4a1660b8f0ba43ed58426e
- Reported: 2018-02-25
https://marc.info/?l=linux-kernel&m=151957120702272&w=2
- Note: performance regression found by lkp-robot
Interrupt storm after suspend causes one busy kworker
- Status: Waiting for data from reporter
- Reported: 2018-02-25
https://bugzilla.kernel.org/show_bug.cgi?id=198929
- Linux-Regression-ID: 41c451
hci_bcm: Streamline runtime PM code change for 4.16 kernel breaks
bluetooth on ASUS T100TA
- Status: WIP
- Cause: 43fff768346810042836df325d736bd2c2a634a7
- Reported: 2018-03-01
https://bugzilla.kernel.org/show_bug.cgi?id=198953
Error updating SMART data during runtime and could not connect to lv
["Possible Regression"]
- Status: Brand new
- Reported: 2018-03-11
https://marc.info/?l=linux-kernel&m=152075643627082
https://bugzilla.kernel.org/show_bug.cgi?id=199077
Regression from efi: call get_event_log before ExitBootServices
- Status: WIP, looks like a firmware issue that gets triggerd
- Cause: 33b6d03469b2
- Reported: 2018-03-06
https://marc.info/?l=linux-kernel&m=152035206220237&w=2
15% longer running times on lvm2 test suite
- Status: Quite new
- Cause: 44c02a2c3dc55835e9f0d8ef73966406cd805001
- Reported: 2018-03-11
https://marc.info/?l=linux-kernel&m=152077333230274
== Regressions with fixes heading mainline ==
[amdgpu CARRIZO] disabled backlight after S3 resume
- Status: Alex provided a patch "drm/amdgpu: save/restore backlight
level in legacy dce code"; assuming he'll send it upstream
- Cause: 4ec6ecf48c64d1da82a008f6fb0be86c4044287d
- Reported: 2018-03-07
https://bugzilla.kernel.org/show_bug.cgi?id=199047
== Fixed since last report ==
selftests: memory-hotplug: fix emit_tests regression
- Status: Fixed by https://git.kernel.org/torvalds/c/ba004a2955f7
- Cause: 16c513b13477
https://marc.info/?l=linux-kernel&m=151993543423651
^ permalink raw reply
* Re: [PATCH] powerpc/mm: Fix section mismatch warning in stop_machine_change_mapping()
From: Mauricio Faria de Oliveira @ 2018-03-12 12:28 UTC (permalink / raw)
To: Balbir Singh
Cc: open list:LINUX FOR POWERPC (32-BIT AND 64-BIT), Michael Ellerman,
Aneesh Kumar KV, Nicholas Piggin
In-Reply-To: <CAKTCnzmdNx01cx94J3mn0auDFrRuOs1PvwsxvOt9VK0AtQf7eA@mail.gmail.com>
Balbir,
On 03/11/2018 03:23 AM, Balbir Singh wrote:
> Looks reasonable, I'd recommend trying to compile with MEMORY_HOTPLUG
> and MEMORY_HOTREMOVE enabled/disabled as well
Thanks for reviewing.
I should have mentioned it :) I did that (disable CONFIG_MEMORY_HOTPLUG)
and all the related functions are not included in vmlinux, since they
are guarded under that config option.
cheers,
Mauricio
^ permalink raw reply
* [PATCH 2/2] misc: ocxl: use put_device() instead of device_unregister()
From: Arvind Yadav @ 2018-03-12 11:36 UTC (permalink / raw)
To: sudeep.dutt, ashutosh.dixit, arnd, gregkh, fbarrat,
andrew.donnellan
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <cover.1520849284.git.arvind.yadav.cs@gmail.com>
if device_register() returned an error! Always use put_device()
to give up the reference initialized.
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
---
drivers/misc/ocxl/pci.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/misc/ocxl/pci.c b/drivers/misc/ocxl/pci.c
index 0051d9e..21f4254 100644
--- a/drivers/misc/ocxl/pci.c
+++ b/drivers/misc/ocxl/pci.c
@@ -519,7 +519,7 @@ static struct ocxl_fn *init_function(struct pci_dev *dev)
rc = device_register(&fn->dev);
if (rc) {
deconfigure_function(fn);
- device_unregister(&fn->dev);
+ put_device(&fn->dev);
return ERR_PTR(rc);
}
return fn;
--
1.9.1
^ permalink raw reply related
* [PATCH 1/2] misc: mic: Release reference count and memory for VOP device
From: Arvind Yadav @ 2018-03-12 11:36 UTC (permalink / raw)
To: sudeep.dutt, ashutosh.dixit, arnd, gregkh, fbarrat,
andrew.donnellan
Cc: linux-kernel, linuxppc-dev
In-Reply-To: <cover.1520849284.git.arvind.yadav.cs@gmail.com>
Never directly free @dev after calling device_register(),
even if it returned an error! Always use put_device() to
give up the reference initialized.
Release allocated memory for vop device in vop_release_dev().
Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
---
drivers/misc/mic/bus/vop_bus.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/misc/mic/bus/vop_bus.c b/drivers/misc/mic/bus/vop_bus.c
index fd7f2a6..e5bb9c7 100644
--- a/drivers/misc/mic/bus/vop_bus.c
+++ b/drivers/misc/mic/bus/vop_bus.c
@@ -135,7 +135,9 @@ void vop_unregister_driver(struct vop_driver *driver)
static void vop_release_dev(struct device *d)
{
- put_device(d);
+ struct vop_device *dev = dev_to_vop(d);
+
+ kfree(dev);
}
struct vop_device *
@@ -174,7 +176,7 @@ struct vop_device *
goto free_vdev;
return vdev;
free_vdev:
- kfree(vdev);
+ put_device(&vdev->dev);
return ERR_PTR(ret);
}
EXPORT_SYMBOL_GPL(vop_register_device);
--
1.9.1
^ permalink raw reply related
* [PATCH 0/2] misc: use put_device() instead of kfree()
From: Arvind Yadav @ 2018-03-12 11:36 UTC (permalink / raw)
To: sudeep.dutt, ashutosh.dixit, arnd, gregkh, fbarrat,
andrew.donnellan
Cc: linux-kernel, linuxppc-dev
Never directly free @dev after calling device_register(), even
if it returned an error! Always use put_device() to give up the
reference initialized.
Arvind Yadav (2):
[PATCH 1/2] misc: mic: Release reference count and memory for VOP device
[PATCH 2/2] misc: ocxl: use put_device() instead of device_unregister()
drivers/misc/mic/bus/vop_bus.c | 6 ++++--
drivers/misc/ocxl/pci.c | 2 +-
2 files changed, 5 insertions(+), 3 deletions(-)
--
1.9.1
^ permalink raw reply
* [PATCH] macintosh/adb: Use C99 initializers for struct adb_driver instances
From: Finn Thain @ 2018-03-12 3:01 UTC (permalink / raw)
To: Jiri Kosina; +Cc: Benjamin Herrenschmidt, linuxppc-dev, linux-kernel
Hopefully this will make it easier for the next reader who needs
to check these pointers. No change to object files.
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
---
drivers/macintosh/adb-iop.c | 14 +++++++-------
drivers/macintosh/macio-adb.c | 15 +++++++--------
drivers/macintosh/via-macii.c | 14 +++++++-------
drivers/macintosh/via-pmu.c | 14 +++++++-------
drivers/macintosh/via-pmu68k.c | 14 +++++++-------
5 files changed, 35 insertions(+), 36 deletions(-)
diff --git a/drivers/macintosh/adb-iop.c b/drivers/macintosh/adb-iop.c
index 15db69d8ba69..ca623e6446e4 100644
--- a/drivers/macintosh/adb-iop.c
+++ b/drivers/macintosh/adb-iop.c
@@ -53,13 +53,13 @@ static void adb_iop_poll(void);
static int adb_iop_reset_bus(void);
struct adb_driver adb_iop_driver = {
- "ISM IOP",
- adb_iop_probe,
- adb_iop_init,
- adb_iop_send_request,
- adb_iop_autopoll,
- adb_iop_poll,
- adb_iop_reset_bus
+ .name = "ISM IOP",
+ .probe = adb_iop_probe,
+ .init = adb_iop_init,
+ .send_request = adb_iop_send_request,
+ .autopoll = adb_iop_autopoll,
+ .poll = adb_iop_poll,
+ .reset_bus = adb_iop_reset_bus
};
static void adb_iop_end_req(struct adb_request *req, int state)
diff --git a/drivers/macintosh/macio-adb.c b/drivers/macintosh/macio-adb.c
index 9a6223add30e..eb3adfb7f88d 100644
--- a/drivers/macintosh/macio-adb.c
+++ b/drivers/macintosh/macio-adb.c
@@ -70,14 +70,13 @@ static void macio_adb_poll(void);
static int macio_adb_reset_bus(void);
struct adb_driver macio_adb_driver = {
- "MACIO",
- macio_probe,
- macio_init,
- macio_send_request,
- /*macio_write,*/
- macio_adb_autopoll,
- macio_adb_poll,
- macio_adb_reset_bus
+ .name = "MACIO",
+ .probe = macio_probe,
+ .init = macio_init,
+ .send_request = macio_send_request,
+ .autopoll = macio_adb_autopoll,
+ .poll = macio_adb_poll,
+ .reset_bus = macio_adb_reset_bus,
};
int macio_probe(void)
diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
index 4ba06a1695ea..cf6f7d52d6be 100644
--- a/drivers/macintosh/via-macii.c
+++ b/drivers/macintosh/via-macii.c
@@ -91,13 +91,13 @@ static void macii_poll(void);
static int macii_reset_bus(void);
struct adb_driver via_macii_driver = {
- "Mac II",
- macii_probe,
- macii_init,
- macii_send_request,
- macii_autopoll,
- macii_poll,
- macii_reset_bus
+ .name = "Mac II",
+ .probe = macii_probe,
+ .init = macii_init,
+ .send_request = macii_send_request,
+ .autopoll = macii_autopoll,
+ .poll = macii_poll,
+ .reset_bus = macii_reset_bus,
};
static enum macii_state {
diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
index c4c2b3b85ebc..8da474899d79 100644
--- a/drivers/macintosh/via-pmu.c
+++ b/drivers/macintosh/via-pmu.c
@@ -199,13 +199,13 @@ static const struct file_operations pmu_options_proc_fops;
#ifdef CONFIG_ADB
struct adb_driver via_pmu_driver = {
- "PMU",
- pmu_probe,
- pmu_init,
- pmu_send_request,
- pmu_adb_autopoll,
- pmu_poll_adb,
- pmu_adb_reset_bus
+ .name = "PMU",
+ .probe = pmu_probe,
+ .init = pmu_init,
+ .send_request = pmu_send_request,
+ .autopoll = pmu_adb_autopoll,
+ .poll = pmu_poll_adb,
+ .reset_bus = pmu_adb_reset_bus,
};
#endif /* CONFIG_ADB */
diff --git a/drivers/macintosh/via-pmu68k.c b/drivers/macintosh/via-pmu68k.c
index 7d9c4baf8c11..d545ed45e482 100644
--- a/drivers/macintosh/via-pmu68k.c
+++ b/drivers/macintosh/via-pmu68k.c
@@ -120,13 +120,13 @@ static void pmu_enable_backlight(int on);
static void pmu_set_brightness(int level);
struct adb_driver via_pmu_driver = {
- "68K PMU",
- pmu_probe,
- pmu_init,
- pmu_send_request,
- pmu_autopoll,
- pmu_poll,
- pmu_reset_bus
+ .name = "68K PMU",
+ .probe = pmu_probe,
+ .init = pmu_init,
+ .send_request = pmu_send_request,
+ .autopoll = pmu_autopoll,
+ .poll = pmu_poll,
+ .reset_bus = pmu_reset_bus,
};
/*
--
2.16.1
^ permalink raw reply related
* PASEMI: PCI_SCAN_ALL_PCIE_DEVS
From: Christian Zigotzky @ 2018-03-12 5:21 UTC (permalink / raw)
To: linuxppc-dev, Olof Johansson
Hi All,
Could you please add Olof=E2=80=98s patch. Without this patch, we have to al=
ways add 'pci=3Dpcie_scan_all' to the kernel boot arguments. Please add it.
Olof's patch for P.A. Semi boards:
---
arch/powerpc/platforms/pasemi/pci.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/platforms/pasemi/pci.c b/arch/powerpc/platforms/pa=
semi/pci.c
index 5ff6108..ea54ed2 100644
--- a/arch/powerpc/platforms/pasemi/pci.c
+++ b/arch/powerpc/platforms/pasemi/pci.c
@@ -224,6 +224,8 @@ void __init pas_pci_init(void)
return;
}
+ pci_set_flags(PCI_SCAN_ALL_PCIE_DEVS);
+
for (np =3D NULL; (np =3D of_get_next_child(root, np)) !=3D NULL;)
if (np->name && !strcmp(np->name, "pxp") && !pas_add_bridge(np))
of_node_get(np);
---
Thanks,
Christian=
^ permalink raw reply related
* [PATCHv4 3/3] ppc64 boot: Wait for boot cpu to show up if nr_cpus limit is about to hit.
From: Pingfan Liu @ 2018-03-12 4:43 UTC (permalink / raw)
To: linuxppc-dev; +Cc: kexec, mahesh, cascardo, gpiccoli, paulus, benh, mpe
In-Reply-To: <1520829790-14029-1-git-send-email-kernelfans@gmail.com>
From: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
The kernel boot parameter 'nr_cpus=' allows one to specify number of
possible cpus in the system. In the normal scenario the first cpu (cpu0)
that shows up is the boot cpu and hence it gets covered under nr_cpus
limit.
But this assumption will be broken in kdump scenario where kdump kenrel
after a crash can boot up on an non-zero boot cpu. The paca structure
allocation depends on value of nr_cpus and is indexed using logical cpu
ids. This definetly will be an issue if boot cpu id > nr_cpus
This patch modifies allocate_pacas() and smp_setup_cpu_maps() to
accommodate boot cpu for the case where boot_cpuid > nr_cpu_ids.
This change would help to reduce the memory reservation requirement for
kdump on ppc64.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Tested-by: Guilherme G. Piccoli <gpiccoli@linux.vnet.ibm.com>
Signed-off-by: Pingfan Liu <kernelfans@gmail.com> (separate the logical for cpu id mapping)
Signed-off-by: Pingfan Liu <kernelfans@gmail.com>
---
arch/powerpc/include/asm/paca.h | 3 +++
arch/powerpc/kernel/paca.c | 19 ++++++++++++++-----
2 files changed, 17 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index b62c310..49ab29d 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -49,6 +49,9 @@ extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */
#define get_lppaca() (get_paca()->lppaca_ptr)
#define get_slb_shadow() (get_paca()->slb_shadow_ptr)
+/* Maximum number of threads per core. */
+#define MAX_SMT 8
+
struct task_struct;
/*
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 95ffedf..13be6ab 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -209,6 +209,7 @@ void __init allocate_pacas(void)
{
u64 limit;
int cpu;
+ unsigned int nr_cpus_aligned;
#ifdef CONFIG_PPC_BOOK3S_64
/*
@@ -220,20 +221,28 @@ void __init allocate_pacas(void)
limit = ppc64_rma_size;
#endif
- paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpu_ids);
+ /*
+ * Alloc the paca[] align up to SMT threads.
+ * This will help us to prepare for a situation where
+ * boot cpu id > nr_cpus.
+ * We keep the schema of nr_cpus in kernel cmdline, but
+ * waste a bit memory
+ */
+ nr_cpus_aligned = _ALIGN_UP(nr_cpu_ids, MAX_SMT);
+ paca_size = PAGE_ALIGN(sizeof(struct paca_struct) * nr_cpus_aligned);
paca = __va(memblock_alloc_base(paca_size, PAGE_SIZE, limit));
memset(paca, 0, paca_size);
printk(KERN_DEBUG "Allocated %u bytes for %u pacas at %p\n",
- paca_size, nr_cpu_ids, paca);
+ paca_size, nr_cpus_aligned, paca);
- allocate_lppacas(nr_cpu_ids, limit);
+ allocate_lppacas(nr_cpus_aligned, limit);
- allocate_slb_shadows(nr_cpu_ids, limit);
+ allocate_slb_shadows(nr_cpus_aligned, limit);
/* Can't use for_each_*_cpu, as they aren't functional yet */
- for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+ for (cpu = 0; cpu < nr_cpus_aligned; cpu++)
initialise_paca(&paca[cpu], cpu);
}
--
2.7.4
^ permalink raw reply related
* [PATCHv4 2/3] powerpc, cpu: handling the special case when boot_cpuid greater than nr_cpus
From: Pingfan Liu @ 2018-03-12 4:43 UTC (permalink / raw)
To: linuxppc-dev; +Cc: kexec, mahesh, cascardo, gpiccoli, paulus, benh, mpe
In-Reply-To: <1520829790-14029-1-git-send-email-kernelfans@gmail.com>
For kexec -p, after boot_cpuid is mapping into the range of [0,
threads_per_core), then if nr_cpus is small, we will have the bitmap
[0,..., nr_cpus, ..., boot_cpuid, ...). This patch chooses cpus inside
the range of [boot_cpuid - nr_cpus +1, ..., boot_cpuid] to be online.
With this patch and the next, on a P9 machine with thread_per_core=4,
and set nr_cpus=2 for the crash kernel.
After
taskset -c 11 sh -c "echo c > /proc/sysrq-trigger"
Then
kdump:/sys/devices/system/cpu# cat possible
2-3
kdump:/sys/devices/system/cpu# cat present
2-3
kdump:/sys/devices/system/cpu# cat online
2-3
Signed-off-by: Pingfan Liu <kernelfans@gmail.com>
---
arch/powerpc/kernel/setup-common.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 1a67344..6920b5e 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -462,6 +462,8 @@ void __init smp_setup_cpu_maps(void)
struct device_node *dn;
struct device_node *boot_dn = NULL;
bool handling_bootdn = true;
+ int head_thread = 0;
+ int online_cnt = 0;
int cpu = 0;
int nthreads = 1;
@@ -499,13 +501,19 @@ void __init smp_setup_cpu_maps(void)
if (boot_cpuid < nthreads &&
be32_to_cpu(intserv[boot_cpuid]) == boot_cpuhwid) {
boot_dn = dn;
+ /* choose a bunch of continous threads */
+ if (boot_cpuid > nr_cpu_ids - 1) {
+ head_thread = boot_cpuid - nr_cpu_ids + 1;
+ /* keep the mapping of logical and thread */
+ cpu = head_thread;
+ }
}
if (boot_dn == NULL)
continue;
} else if (dn == boot_dn)
continue;
- for (j = 0; j < nthreads && cpu < nr_cpu_ids; j++) {
+ for (j = head_thread; j < nthreads && online_cnt < nr_cpu_ids; j++) {
bool avail;
DBG(" thread %d -> cpu %d (hard id %d)\n",
@@ -520,13 +528,15 @@ void __init smp_setup_cpu_maps(void)
set_hard_smp_processor_id(cpu, be32_to_cpu(intserv[j]));
set_cpu_possible(cpu, true);
cpu++;
+ online_cnt++;
}
- if (cpu >= nr_cpu_ids) {
+ if (online_cnt >= nr_cpu_ids) {
of_node_put(dn);
break;
}
if (handling_bootdn) {
+ head_thread = 0;
handling_bootdn = false;
goto again;
}
--
2.7.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox