* [PATCH v5 29/31] powerpc/fadump: consider f/w load area
From: Hari Bathini @ 2019-08-20 12:07 UTC (permalink / raw)
To: linuxppc-dev
Cc: Ananth N Mavinakayanahalli, Mahesh J Salgaonkar, Vasant Hegde,
Oliver, Nicholas Piggin, Daniel Axtens
In-Reply-To: <156630261682.8896.3418665808003586786.stgit@hbathini.in.ibm.com>
OPAL loads kernel & initrd at 512MB offset (256MB size), also exported
as ibm,opal/dump/fw-load-area. So, if boot memory size of FADump is
less than 768MB, kernel memory to be exported as '/proc/vmcore' would
be overwritten by f/w while loading kernel & initrd. To avoid such a
scenario, enforce a minimum boot memory size of 768MB on OPAL platform
and skip using FADump if a newer F/W version loads kernel & initrd
above 768MB.
Also, irrespective of RMA size, set the minimum boot memory size
expected on pseries platform at 320MB. This is to avoid inflating the
minimum memory requirements on systems with 512M/1024M RMA size.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
arch/powerpc/kernel/fadump-common.h | 11 +---------
arch/powerpc/kernel/fadump.c | 11 +++++++++-
arch/powerpc/platforms/powernv/opal-fadump.c | 29 ++++++++++++++++++++++++++
arch/powerpc/platforms/powernv/opal-fadump.h | 7 ++++++
arch/powerpc/platforms/pseries/rtas-fadump.c | 6 +++++
arch/powerpc/platforms/pseries/rtas-fadump.h | 9 ++++++++
6 files changed, 62 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/kernel/fadump-common.h b/arch/powerpc/kernel/fadump-common.h
index ba8481b..55e4f25 100644
--- a/arch/powerpc/kernel/fadump-common.h
+++ b/arch/powerpc/kernel/fadump-common.h
@@ -22,16 +22,6 @@
#define RMA_START 0x0
#define RMA_END (ppc64_rma_size)
-/*
- * On some Power systems where RMO is 128MB, it still requires minimum of
- * 256MB for kernel to boot successfully. When kdump infrastructure is
- * configured to save vmcore over network, we run into OOM issue while
- * loading modules related to network setup. Hence we need additional 64M
- * of memory to avoid OOM issue.
- */
-#define MIN_BOOT_MEM (((RMA_END < (0x1UL << 28)) ? (0x1UL << 28) : RMA_END) \
- + (0x1UL << 26))
-
/* The upper limit percentage for user specified boot memory size (25%) */
#define MAX_BOOT_MEM_RATIO 4
@@ -139,6 +129,7 @@ struct fadump_ops {
ulong (*fadump_init_mem_struct)(struct fw_dump *fadump_config);
ulong (*fadump_get_metadata_size)(void);
int (*fadump_setup_metadata)(struct fw_dump *fadump_config);
+ ulong (*fadump_get_bootmem_min)(void);
int (*fadump_register)(struct fw_dump *fadump_config);
int (*fadump_unregister)(struct fw_dump *fadump_config);
int (*fadump_invalidate)(struct fw_dump *fadump_config);
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 43038f5..4b168c4 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -238,7 +238,8 @@ static inline unsigned long fadump_calculate_reserve_size(void)
if (memory_limit && size > memory_limit)
size = memory_limit;
- return (size > MIN_BOOT_MEM ? size : MIN_BOOT_MEM);
+ return (size > fw_dump.ops->fadump_get_bootmem_min() ? size :
+ fw_dump.ops->fadump_get_bootmem_min());
}
/*
@@ -291,6 +292,14 @@ int __init fadump_reserve_mem(void)
ALIGN(fw_dump.boot_memory_size,
FADUMP_CMA_ALIGNMENT);
#endif
+
+ if (fw_dump.boot_memory_size <
+ fw_dump.ops->fadump_get_bootmem_min()) {
+ pr_err("Can't enable fadump with boot memory size (0x%lx) less than 0x%lx\n",
+ fw_dump.boot_memory_size,
+ fw_dump.ops->fadump_get_bootmem_min());
+ goto error_out;
+ }
}
/*
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
index 58faa38..50cf9e6 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.c
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -11,6 +11,7 @@
#include <linux/string.h>
#include <linux/seq_file.h>
+#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/libfdt.h>
#include <linux/mm.h>
@@ -271,6 +272,11 @@ static int opal_fadump_setup_metadata(struct fw_dump *fadump_conf)
return err;
}
+static ulong opal_fadump_get_bootmem_min(void)
+{
+ return OPAL_FADUMP_MIN_BOOT_MEM;
+}
+
static int opal_fadump_register(struct fw_dump *fadump_conf)
{
int i, err = -EIO;
@@ -587,6 +593,7 @@ static struct fadump_ops opal_fadump_ops = {
.fadump_init_mem_struct = opal_fadump_init_mem_struct,
.fadump_get_metadata_size = opal_fadump_get_metadata_size,
.fadump_setup_metadata = opal_fadump_setup_metadata,
+ .fadump_get_bootmem_min = opal_fadump_get_bootmem_min,
.fadump_register = opal_fadump_register,
.fadump_unregister = opal_fadump_unregister,
.fadump_invalidate = opal_fadump_invalidate,
@@ -600,6 +607,7 @@ int __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, ulong node)
{
unsigned long dn;
const __be32 *prop;
+ int i, len;
/*
* Check if Firmware-Assisted Dump is supported. if yes, check
@@ -616,6 +624,27 @@ int __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, ulong node)
return 1;
}
+ prop = of_get_flat_dt_prop(dn, "fw-load-area", &len);
+ if (prop) {
+ /*
+ * Each f/w load area is an (address,size) pair,
+ * 2 cells each, totalling 4 cells per range.
+ */
+ for (i = 0; i < len / (sizeof(*prop) * 4); i++) {
+ u64 base, end;
+
+ base = of_read_number(prop + (i * 4) + 0, 2);
+ end = base;
+ end += of_read_number(prop + (i * 4) + 2, 2);
+ if (end > OPAL_FADUMP_MIN_BOOT_MEM) {
+ pr_err("F/W load area: 0x%llx-0x%llx\n",
+ base, end);
+ pr_err("F/W version not supported!\n");
+ return 1;
+ }
+ }
+ }
+
fadump_conf->ops = &opal_fadump_ops;
fadump_conf->fadump_supported = 1;
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.h b/arch/powerpc/platforms/powernv/opal-fadump.h
index b1a340b..ae71a16 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.h
+++ b/arch/powerpc/platforms/powernv/opal-fadump.h
@@ -11,6 +11,13 @@
#include <asm/reg.h>
+/*
+ * With kernel & initrd loaded at 512MB (with 256MB size), enforce a minimum
+ * boot memory size of 768MB to ensure f/w loading kernel and initrd doesn't
+ * mess with crash'ed kernel's memory during MPIPL.
+ */
+#define OPAL_FADUMP_MIN_BOOT_MEM (0x30000000UL)
+
/* OPAL FADump structure format version */
#define OPAL_FADUMP_VERSION 0x1
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.c b/arch/powerpc/platforms/pseries/rtas-fadump.c
index 6164c5a..7dee6d0 100644
--- a/arch/powerpc/platforms/pseries/rtas-fadump.c
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.c
@@ -136,6 +136,11 @@ static int rtas_fadump_setup_metadata(struct fw_dump *fadump_conf)
return 0;
}
+static ulong rtas_fadump_get_bootmem_min(void)
+{
+ return RTAS_FADUMP_MIN_BOOT_MEM;
+}
+
static int rtas_fadump_register(struct fw_dump *fadump_conf)
{
int rc, err = -EIO;
@@ -507,6 +512,7 @@ static struct fadump_ops rtas_fadump_ops = {
.fadump_init_mem_struct = rtas_fadump_init_mem_struct,
.fadump_get_metadata_size = rtas_fadump_get_metadata_size,
.fadump_setup_metadata = rtas_fadump_setup_metadata,
+ .fadump_get_bootmem_min = rtas_fadump_get_bootmem_min,
.fadump_register = rtas_fadump_register,
.fadump_unregister = rtas_fadump_unregister,
.fadump_invalidate = rtas_fadump_invalidate,
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.h b/arch/powerpc/platforms/pseries/rtas-fadump.h
index a3a2918..feaeb75 100644
--- a/arch/powerpc/platforms/pseries/rtas-fadump.h
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.h
@@ -12,6 +12,15 @@
#ifndef __PPC64_RTAS_FA_DUMP_H__
#define __PPC64_RTAS_FA_DUMP_H__
+/*
+ * On some Power systems where RMO is 128MB, it still requires minimum of
+ * 256MB for kernel to boot successfully. When kdump infrastructure is
+ * configured to save vmcore over network, we run into OOM issue while
+ * loading modules related to network setup. Hence we need additional 64M
+ * of memory to avoid OOM issue.
+ */
+#define RTAS_FADUMP_MIN_BOOT_MEM ((0x1UL << 28) + (0x1UL << 26))
+
/* Firmware provided dump sections */
#define RTAS_FADUMP_CPU_STATE_DATA 0x0001
#define RTAS_FADUMP_HPTE_REGION 0x0002
^ permalink raw reply related
* [PATCH v5 30/31] powernv/fadump: update documentation about option to release opalcore
From: Hari Bathini @ 2019-08-20 12:07 UTC (permalink / raw)
To: linuxppc-dev
Cc: Ananth N Mavinakayanahalli, Mahesh J Salgaonkar, Vasant Hegde,
Oliver, Nicholas Piggin, Daniel Axtens
In-Reply-To: <156630261682.8896.3418665808003586786.stgit@hbathini.in.ibm.com>
With /sys/firmware/opal/core support available on OPAL based machines
and an option to the release memory used by kernel in exporting this
core file, update FADump documentation with these details.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
Documentation/powerpc/firmware-assisted-dump.rst | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/Documentation/powerpc/firmware-assisted-dump.rst b/Documentation/powerpc/firmware-assisted-dump.rst
index 23b04a6..ec9fa12 100644
--- a/Documentation/powerpc/firmware-assisted-dump.rst
+++ b/Documentation/powerpc/firmware-assisted-dump.rst
@@ -110,6 +110,16 @@ capture kernel boot to process this crash data. Kernel config
option CONFIG_PRESERVE_FA_DUMP has to be enabled on such kernel
to ensure that crash data is preserved to process later.
+-- On OPAL based machines (PowerNV), if the kernel is build with
+ CONFIG_OPAL_CORE=y, OPAL memory at the time of crash is also
+ exported as /sys/firmware/opal/core file. This procfs file is
+ helpful in debugging OPAL crashes with GDB. The kernel memory
+ used for exporting this procfs file can be released by echo'ing
+ '1' to /sys/kernel/fadump_release_opalcore node.
+
+ e.g.
+ # echo 1 > /sys/kernel/fadump_release_opalcore
+
Implementation details:
-----------------------
@@ -273,6 +283,15 @@ Here is the list of files under kernel sysfs:
enhanced to use this interface to release the memory reserved for
dump and continue without 2nd reboot.
+ /sys/kernel/fadump_release_opalcore
+
+ This file is available only on OPAL based machines when FADump is
+ active during capture kernel. This is used to release the memory
+ used by the kernel to export /sys/firmware/opal/core file. To
+ release this memory, echo '1' to it:
+
+ echo 1 > /sys/kernel/fadump_release_opalcore
+
Here is the list of files under powerpc debugfs:
(Assuming debugfs is mounted on /sys/kernel/debug directory.)
^ permalink raw reply related
* [PATCH v5 31/31] powernv/fadump: support holes in kernel boot memory area
From: Hari Bathini @ 2019-08-20 12:07 UTC (permalink / raw)
To: linuxppc-dev
Cc: Ananth N Mavinakayanahalli, Mahesh J Salgaonkar, Vasant Hegde,
Oliver, Nicholas Piggin, Daniel Axtens
In-Reply-To: <156630261682.8896.3418665808003586786.stgit@hbathini.in.ibm.com>
With support to copy multiple kernel boot memory regions owing to copy
size limitation, also handle holes in the memory area to be preserved.
Support as many as 128 kernel boot memory regions. This allows having
an adequate FADump capture kernel size for different scenarios.
Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
---
arch/powerpc/kernel/fadump-common.c | 15 ++
arch/powerpc/kernel/fadump-common.h | 12 ++
arch/powerpc/kernel/fadump.c | 178 ++++++++++++++++++++++----
arch/powerpc/platforms/powernv/opal-fadump.c | 56 ++++----
arch/powerpc/platforms/powernv/opal-fadump.h | 5 -
arch/powerpc/platforms/pseries/rtas-fadump.c | 14 ++
arch/powerpc/platforms/pseries/rtas-fadump.h | 5 +
7 files changed, 222 insertions(+), 63 deletions(-)
diff --git a/arch/powerpc/kernel/fadump-common.c b/arch/powerpc/kernel/fadump-common.c
index 7f39e4f..82862de 100644
--- a/arch/powerpc/kernel/fadump-common.c
+++ b/arch/powerpc/kernel/fadump-common.c
@@ -121,10 +121,19 @@ static int is_fadump_memory_area_contiguous(unsigned long d_start,
*/
int is_fadump_boot_mem_contiguous(struct fw_dump *fadump_conf)
{
- unsigned long d_start = RMA_START;
- unsigned long d_end = RMA_START + fadump_conf->boot_memory_size;
+ int i, ret = 0;
+ unsigned long d_start, d_end;
- return is_fadump_memory_area_contiguous(d_start, d_end);
+ for (i = 0; i < fadump_conf->boot_mem_regs_cnt; i++) {
+ d_start = fadump_conf->boot_mem_addr[i];
+ d_end = d_start + fadump_conf->boot_mem_sz[i];
+
+ ret = is_fadump_memory_area_contiguous(d_start, d_end);
+ if (!ret)
+ break;
+ }
+
+ return ret;
}
/*
diff --git a/arch/powerpc/kernel/fadump-common.h b/arch/powerpc/kernel/fadump-common.h
index 55e4f25..8da8900 100644
--- a/arch/powerpc/kernel/fadump-common.h
+++ b/arch/powerpc/kernel/fadump-common.h
@@ -12,6 +12,9 @@
#ifndef __PPC64_FA_DUMP_INTERNAL_H__
#define __PPC64_FA_DUMP_INTERNAL_H__
+/* Maximum number of memory regions kernel supports */
+#define FADUMP_MAX_MEM_REGS 128
+
#ifndef CONFIG_PRESERVE_FA_DUMP
/*
* The RMA region will be saved for later dumping when kernel crashes.
@@ -106,12 +109,21 @@ struct fw_dump {
unsigned long hpte_region_size;
unsigned long boot_mem_dest_addr;
+ unsigned long boot_mem_addr[FADUMP_MAX_MEM_REGS];
+ unsigned long boot_mem_sz[FADUMP_MAX_MEM_REGS];
+ unsigned long boot_mem_regs_cnt;
+ unsigned long boot_mem_top;
unsigned long boot_memory_size;
unsigned long fadumphdr_addr;
unsigned long cpu_notes_buf;
unsigned long cpu_notes_buf_size;
+ /*
+ * Maximum size supported by firmware to copy from source to
+ * destination address per entry.
+ */
+ unsigned long max_copy_size;
u64 kernel_metadata;
int ibm_configure_kernel_dump;
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 4b168c4..4b1bb3c 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -129,6 +129,7 @@ int is_fadump_memory_area(u64 addr, ulong size)
{
u64 d_start = fw_dump.reserve_dump_area_start;
u64 d_end = d_start + fw_dump.reserve_dump_area_size;
+ u64 b_end = fw_dump.boot_mem_top;
if (!fw_dump.dump_registered)
return 0;
@@ -136,7 +137,7 @@ int is_fadump_memory_area(u64 addr, ulong size)
if (((addr + size) > d_start) && (addr <= d_end))
return 1;
- return (addr + size) > RMA_START && addr <= fw_dump.boot_memory_size;
+ return (((addr + size) > RMA_START) && (addr <= b_end));
}
int should_fadump_crash(void)
@@ -154,6 +155,8 @@ int is_fadump_active(void)
/* Print firmware assisted dump configurations for debugging purpose. */
static void fadump_show_config(void)
{
+ int i;
+
pr_debug("Support for firmware-assisted dump (fadump): %s\n",
(fw_dump.fadump_supported ? "present" : "no support"));
@@ -167,7 +170,13 @@ static void fadump_show_config(void)
pr_debug("Dump section sizes:\n");
pr_debug(" CPU state data size: %lx\n", fw_dump.cpu_state_data_size);
pr_debug(" HPTE region size : %lx\n", fw_dump.hpte_region_size);
- pr_debug("Boot memory size : %lx\n", fw_dump.boot_memory_size);
+ pr_debug(" Boot memory size : %lx\n", fw_dump.boot_memory_size);
+ pr_debug(" Boot memory top : %lx\n", fw_dump.boot_mem_top);
+ pr_debug("Boot meory regions count : %lx\n", fw_dump.boot_mem_regs_cnt);
+ for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
+ pr_debug("%d. base = %lx, size = %lx\n", (i+1),
+ fw_dump.boot_mem_addr[i], fw_dump.boot_mem_sz[i]);
+ }
}
/**
@@ -266,6 +275,88 @@ static unsigned long get_fadump_area_size(void)
return size;
}
+static int __init add_boot_mem_region(unsigned long rstart,
+ unsigned long rsize)
+{
+ int i = fw_dump.boot_mem_regs_cnt++;
+
+ if (fw_dump.boot_mem_regs_cnt > FADUMP_MAX_MEM_REGS) {
+ fw_dump.boot_mem_regs_cnt = FADUMP_MAX_MEM_REGS;
+ return 0;
+ }
+
+ pr_debug("Added boot memory range[%d] [%#016lx-%#016lx)\n",
+ i, rstart, (rstart + rsize));
+ fw_dump.boot_mem_addr[i] = rstart;
+ fw_dump.boot_mem_sz[i] = rsize;
+ return 1;
+}
+
+/*
+ * Firmware usually has a hard limit on the data it can copy per region.
+ * Honour that by splitting a memory range into multiple regions.
+ */
+static int __init add_boot_mem_regions(unsigned long mstart,
+ unsigned long msize)
+{
+ unsigned long rstart, rsize, max_size;
+ int ret = 1;
+
+ rstart = mstart;
+ max_size = fw_dump.max_copy_size ? fw_dump.max_copy_size : msize;
+ while (msize) {
+ if (msize > max_size)
+ rsize = max_size;
+ else
+ rsize = msize;
+
+ ret = add_boot_mem_region(rstart, rsize);
+ if (!ret)
+ break;
+
+ msize -= rsize;
+ rstart += rsize;
+ }
+
+ return ret;
+}
+
+static int __init fadump_get_boot_mem_regions(void)
+{
+ int ret = 1;
+ struct memblock_region *reg;
+ unsigned long base, size, cur_size, hole_size, last_end;
+ unsigned long mem_size = fw_dump.boot_memory_size;
+
+ fw_dump.boot_mem_regs_cnt = 0;
+
+ last_end = 0;
+ hole_size = 0;
+ cur_size = 0;
+ for_each_memblock(memory, reg) {
+ base = reg->base;
+ size = reg->size;
+ hole_size += (base - last_end);
+
+ if ((cur_size + size) >= mem_size) {
+ size = (mem_size - cur_size);
+ ret = add_boot_mem_regions(base, size);
+ break;
+ }
+
+ mem_size -= size;
+ cur_size += size;
+ ret = add_boot_mem_regions(base, size);
+ if (!ret)
+ break;
+
+ last_end = base + size;
+ }
+ fw_dump.boot_mem_top = fw_dump.boot_memory_size + hole_size;
+
+ return ret;
+}
+
int __init fadump_reserve_mem(void)
{
int ret = 1;
@@ -300,6 +391,11 @@ int __init fadump_reserve_mem(void)
fw_dump.ops->fadump_get_bootmem_min());
goto error_out;
}
+
+ if (!fadump_get_boot_mem_regions()) {
+ pr_err("Too many holes in boot memory area to enable fadump\n");
+ goto error_out;
+ }
}
/*
@@ -323,7 +419,8 @@ int __init fadump_reserve_mem(void)
else
memory_boundary = memblock_end_of_DRAM();
- base = fw_dump.boot_memory_size;
+ base = fw_dump.boot_mem_top;
+ base = PAGE_ALIGN(base);
size = get_fadump_area_size();
fw_dump.reserve_dump_area_size = size;
if (fw_dump.dump_active) {
@@ -625,37 +722,39 @@ static int fadump_init_elfcore_header(char *bufp)
static int fadump_setup_crash_memory_ranges(void)
{
struct memblock_region *reg;
- unsigned long long start, end;
- int ret;
+ unsigned long long start, end, offset;
+ int i, ret;
pr_debug("Setup crash memory ranges.\n");
crash_mrange_info.mem_range_cnt = 0;
+ offset = fw_dump.boot_mem_top;
/*
- * add the first memory chunk (RMA_START through boot_memory_size) as
- * a separate memory chunk. The reason is, at the time crash firmware
- * will move the content of this memory chunk to different location
- * specified during fadump registration. We need to create a separate
- * program header for this chunk with the correct offset.
+ * Boot memory region(s) registered with firmware are moved to
+ * a different location at the time of crash. Create separate program
+ * header(s) for this memory chunk(s) with the correct offset.
*/
- ret = fadump_add_mem_range(&crash_mrange_info,
- RMA_START, fw_dump.boot_memory_size);
- if (ret)
- return ret;
+ for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
+ start = fw_dump.boot_mem_addr[i];
+ end = start + fw_dump.boot_mem_sz[i];
+ ret = fadump_add_mem_range(&crash_mrange_info, start, end);
+ if (ret)
+ return ret;
+ }
for_each_memblock(memory, reg) {
start = (unsigned long long)reg->base;
end = start + (unsigned long long)reg->size;
/*
- * skip the first memory chunk that is already added (RMA_START
+ * Skip the first memory chunk that is already added (RMA_START
* through boot_memory_size). This logic needs a relook if and
* when RMA_START changes to a non-zero value.
*/
BUILD_BUG_ON(RMA_START != 0);
- if (start < fw_dump.boot_memory_size) {
- if (end > fw_dump.boot_memory_size)
- start = fw_dump.boot_memory_size;
+ if (start < offset) {
+ if (end > offset)
+ start = offset;
else
continue;
}
@@ -676,17 +775,35 @@ static int fadump_setup_crash_memory_ranges(void)
*/
static inline unsigned long fadump_relocate(unsigned long paddr)
{
- if (paddr > RMA_START && paddr < fw_dump.boot_memory_size)
- return fw_dump.boot_mem_dest_addr + paddr;
- else
- return paddr;
+ unsigned long raddr, rstart, rend, rlast, hole_size;
+ int i;
+
+ hole_size = 0;
+ rlast = 0;
+ raddr = paddr;
+ for (i = 0; i < fw_dump.boot_mem_regs_cnt; i++) {
+ rstart = fw_dump.boot_mem_addr[i];
+ rend = rstart + fw_dump.boot_mem_sz[i];
+ hole_size += (rstart - rlast);
+
+ if (paddr >= rstart && paddr < rend) {
+ raddr += fw_dump.boot_mem_dest_addr - hole_size;
+ break;
+ }
+
+ rlast = rend;
+ }
+
+ pr_debug("vmcoreinfo: paddr = 0x%lx, raddr = 0x%lx\n", paddr, raddr);
+ return raddr;
}
static int fadump_create_elfcore_headers(char *bufp)
{
struct elfhdr *elf;
struct elf_phdr *phdr;
- int i;
+ unsigned long long raddr, offset;
+ int i, j;
fadump_init_elfcore_header(bufp);
elf = (struct elfhdr *)bufp;
@@ -729,7 +846,9 @@ static int fadump_create_elfcore_headers(char *bufp)
(elf->e_phnum)++;
/* setup PT_LOAD sections. */
-
+ j = 0;
+ offset = 0;
+ raddr = fw_dump.boot_mem_addr[0];
for (i = 0; i < crash_mrange_info.mem_range_cnt; i++) {
unsigned long long mbase, msize;
mbase = crash_mrange_info.mem_ranges[i].base;
@@ -744,13 +863,17 @@ static int fadump_create_elfcore_headers(char *bufp)
phdr->p_flags = PF_R|PF_W|PF_X;
phdr->p_offset = mbase;
- if (mbase == RMA_START) {
+ if (mbase == raddr) {
/*
* The entire RMA region will be moved by firmware
* to the specified destination_address. Hence set
* the correct offset.
*/
- phdr->p_offset = fw_dump.boot_mem_dest_addr;
+ phdr->p_offset = fw_dump.boot_mem_dest_addr + offset;
+ if (j < (fw_dump.boot_mem_regs_cnt - 1)) {
+ offset += fw_dump.boot_mem_sz[j];
+ raddr = fw_dump.boot_mem_addr[++j];
+ }
}
phdr->p_paddr = mbase;
@@ -1033,7 +1156,8 @@ static void fadump_invalidate_release_mem(void)
fadump_cleanup();
mutex_unlock(&fadump_mutex);
- fadump_release_memory(fw_dump.boot_memory_size, memblock_end_of_DRAM());
+ fadump_release_memory(PAGE_ALIGN(fw_dump.boot_mem_top),
+ memblock_end_of_DRAM());
if (fw_dump.cpu_notes_buf) {
fadump_cpu_notes_buf_free(
(unsigned long)__va(fw_dump.cpu_notes_buf),
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.c b/arch/powerpc/platforms/powernv/opal-fadump.c
index 50cf9e6..593da18 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.c
+++ b/arch/powerpc/platforms/powernv/opal-fadump.c
@@ -120,19 +120,29 @@ static void opal_fadump_update_config(struct fw_dump *fadump_conf,
static void opal_fadump_get_config(struct fw_dump *fadump_conf,
const struct opal_fadump_mem_struct *fdm)
{
+ unsigned long base, size, last_end, hole_size;
int i;
if (!fadump_conf->dump_active)
return;
+ last_end = 0;
+ hole_size = 0;
fadump_conf->boot_memory_size = 0;
pr_debug("Boot memory regions:\n");
for (i = 0; i < fdm->region_cnt; i++) {
- pr_debug("\t%d. base: 0x%llx, size: 0x%llx\n",
- (i + 1), fdm->rgn[i].src, fdm->rgn[i].size);
+ base = fdm->rgn[i].src;
+ size = fdm->rgn[i].size;
+ pr_debug("\t%d. base: 0x%lx, size: 0x%lx\n",
+ (i + 1), base, size);
- fadump_conf->boot_memory_size += fdm->rgn[i].size;
+ fadump_conf->boot_mem_addr[i] = base;
+ fadump_conf->boot_mem_sz[i] = size;
+ fadump_conf->boot_memory_size += size;
+ hole_size += (base - last_end);
+
+ last_end = base + size;
}
/*
@@ -165,6 +175,8 @@ static void opal_fadump_get_config(struct fw_dump *fadump_conf,
pr_warn(" But the sanity of the '/proc/vmcore' file depends on whether the above region(s) have any kernel pages or not.\n");
}
+ fadump_conf->boot_mem_top = (fadump_conf->boot_memory_size + hole_size);
+ fadump_conf->boot_mem_regs_cnt = fdm->region_cnt;
opal_fadump_update_config(fadump_conf, fdm);
}
@@ -179,34 +191,20 @@ static void opal_fadump_init_metadata(struct opal_fadump_mem_struct *fdm)
static ulong opal_fadump_init_mem_struct(struct fw_dump *fadump_conf)
{
- ulong src_addr, dest_addr;
- int max_copy_size, cur_size, size;
+ ulong addr = fadump_conf->reserve_dump_area_start;
+ int i;
opal_fdm = __va(fadump_conf->kernel_metadata);
opal_fadump_init_metadata(opal_fdm);
- /*
- * Firmware currently supports only 32-bit value for size,
- * align it to pagesize and request firmware to copy multiple
- * kernel boot memory regions.
- */
- max_copy_size = _ALIGN_DOWN(U32_MAX, PAGE_SIZE);
-
/* Boot memory regions */
- src_addr = RMA_START;
- dest_addr = fadump_conf->reserve_dump_area_start;
- size = fadump_conf->boot_memory_size;
- while (size) {
- cur_size = size > max_copy_size ? max_copy_size : size;
-
- opal_fdm->rgn[opal_fdm->region_cnt].src = src_addr;
- opal_fdm->rgn[opal_fdm->region_cnt].dest = dest_addr;
- opal_fdm->rgn[opal_fdm->region_cnt].size = cur_size;
+ for (i = 0; i < fadump_conf->boot_mem_regs_cnt; i++) {
+ opal_fdm->rgn[i].src = fadump_conf->boot_mem_addr[i];
+ opal_fdm->rgn[i].dest = addr;
+ opal_fdm->rgn[i].size = fadump_conf->boot_mem_sz[i];
opal_fdm->region_cnt++;
- dest_addr += cur_size;
- src_addr += cur_size;
- size -= cur_size;
+ addr += fadump_conf->boot_mem_sz[i];
}
/*
@@ -218,7 +216,7 @@ static ulong opal_fadump_init_mem_struct(struct fw_dump *fadump_conf)
opal_fadump_update_config(fadump_conf, opal_fdm);
- return dest_addr;
+ return addr;
}
static ulong opal_fadump_get_metadata_size(void)
@@ -263,7 +261,7 @@ static int opal_fadump_setup_metadata(struct fw_dump *fadump_conf)
* by a kernel that intends to preserve crash'ed kernel's memory.
*/
ret = opal_mpipl_register_tag(OPAL_MPIPL_TAG_BOOT_MEM,
- fadump_conf->boot_memory_size);
+ fadump_conf->boot_mem_top);
if (ret != OPAL_SUCCESS) {
pr_err("Failed to set boot memory tag!\n");
err = -EPERM;
@@ -649,6 +647,12 @@ int __init opal_fadump_dt_scan(struct fw_dump *fadump_conf, ulong node)
fadump_conf->fadump_supported = 1;
/*
+ * Firmware currently supports only 32-bit value for size,
+ * align it to pagesize.
+ */
+ fadump_conf->max_copy_size = _ALIGN_DOWN(U32_MAX, PAGE_SIZE);
+
+ /*
* Check if dump has been initiated on last reboot.
*/
prop = of_get_flat_dt_prop(dn, "mpipl-boot", NULL);
diff --git a/arch/powerpc/platforms/powernv/opal-fadump.h b/arch/powerpc/platforms/powernv/opal-fadump.h
index ae71a16..3b0c4fb 100644
--- a/arch/powerpc/platforms/powernv/opal-fadump.h
+++ b/arch/powerpc/platforms/powernv/opal-fadump.h
@@ -21,9 +21,6 @@
/* OPAL FADump structure format version */
#define OPAL_FADUMP_VERSION 0x1
-/* Maximum number of memory regions kernel supports */
-#define OPAL_FADUMP_MAX_MEM_REGS 128
-
/*
* FADump memory structure for storing kernel metadata needed to
* register-for/process crash dump. The address of this structure will
@@ -36,7 +33,7 @@ struct opal_fadump_mem_struct {
u16 region_cnt; /* number of regions */
u16 registered_regions; /* Regions registered for MPIPL */
u64 fadumphdr_addr;
- struct opal_mpipl_region rgn[OPAL_FADUMP_MAX_MEM_REGS];
+ struct opal_mpipl_region rgn[FADUMP_MAX_MEM_REGS];
} __attribute__((packed));
/*
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.c b/arch/powerpc/platforms/pseries/rtas-fadump.c
index 7dee6d0..5ea8360 100644
--- a/arch/powerpc/platforms/pseries/rtas-fadump.c
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.c
@@ -46,7 +46,13 @@ static void rtas_fadump_update_config(struct fw_dump *fadump_conf,
static void rtas_fadump_get_config(struct fw_dump *fadump_conf,
const struct rtas_fadump_mem_struct *fdm)
{
- fadump_conf->boot_memory_size = be64_to_cpu(fdm->rmr_region.source_len);
+ fadump_conf->boot_mem_addr[0] =
+ be64_to_cpu(fdm->rmr_region.source_address);
+ fadump_conf->boot_mem_sz[0] = be64_to_cpu(fdm->rmr_region.source_len);
+ fadump_conf->boot_memory_size = fadump_conf->boot_mem_sz[0];
+
+ fadump_conf->boot_mem_top = fadump_conf->boot_memory_size;
+ fadump_conf->boot_mem_regs_cnt = 1;
/*
* Start address of reserve dump area (permanent reservation) for
@@ -111,8 +117,7 @@ static ulong rtas_fadump_init_mem_struct(struct fw_dump *fadump_conf)
fdm.rmr_region.source_data_type =
cpu_to_be16(RTAS_FADUMP_REAL_MODE_REGION);
fdm.rmr_region.source_address = cpu_to_be64(RMA_START);
- fdm.rmr_region.source_len =
- cpu_to_be64(fadump_conf->boot_memory_size);
+ fdm.rmr_region.source_len = cpu_to_be64(fadump_conf->boot_memory_size);
fdm.rmr_region.destination_address = cpu_to_be64(addr);
addr += fadump_conf->boot_memory_size;
@@ -541,6 +546,9 @@ int __init rtas_fadump_dt_scan(struct fw_dump *fadump_conf, ulong node)
fadump_conf->ops = &rtas_fadump_ops;
fadump_conf->fadump_supported = 1;
+ /* Firmware supports 64-bit value for size, align it to pagesize. */
+ fadump_conf->max_copy_size = _ALIGN_DOWN(U64_MAX, PAGE_SIZE);
+
/*
* The 'ibm,kernel-dump' rtas node is present only if there is
* dump data waiting for us.
diff --git a/arch/powerpc/platforms/pseries/rtas-fadump.h b/arch/powerpc/platforms/pseries/rtas-fadump.h
index feaeb75..fad87b3 100644
--- a/arch/powerpc/platforms/pseries/rtas-fadump.h
+++ b/arch/powerpc/platforms/pseries/rtas-fadump.h
@@ -72,6 +72,11 @@ struct rtas_fadump_mem_struct {
/* Kernel dump sections */
struct rtas_fadump_section cpu_state_data;
struct rtas_fadump_section hpte_region;
+
+ /*
+ * TODO: Extend multiple boot memory regions support in the kernel
+ * for this platform.
+ */
struct rtas_fadump_section rmr_region;
};
^ permalink raw reply related
* [bug report] hwmon: (ibmpowernv) Add attributes to enable/disable sensor groups
From: Dan Carpenter @ 2019-08-20 12:34 UTC (permalink / raw)
To: shilpa.bhat; +Cc: linuxppc-dev
Hello Shilpasri G Bhat,
The patch e0da99123f3c: "hwmon: (ibmpowernv) Add attributes to
enable/disable sensor groups" from Jul 24, 2018, leads to the
following static checker warning:
drivers/hwmon/ibmpowernv.c:353 init_sensor_group_data()
warn: missing error code here? 'sgrp()' failed. 'ret' = '0'
drivers/hwmon/ibmpowernv.c
334 static int init_sensor_group_data(struct platform_device *pdev,
335 struct platform_data *pdata)
336 {
337 struct sensor_group_data *sgrp_data;
338 struct device_node *groups, *sgrp;
339 int count = 0, ret = 0;
340 enum sensors type;
341
342 groups = of_find_compatible_node(NULL, NULL, "ibm,opal-sensor-group");
343 if (!groups)
344 return ret;
To me the intent would be more clear if we said "return 0;". I look at
that I think maybe it's a bug.
345
346 for_each_child_of_node(groups, sgrp) {
347 type = get_sensor_type(sgrp);
348 if (type != MAX_SENSOR_TYPE)
349 pdata->nr_sensor_groups++;
350 }
351
352 if (!pdata->nr_sensor_groups)
353 goto out;
And here? Is this still a success path?
354
355 sgrp_data = devm_kcalloc(&pdev->dev, pdata->nr_sensor_groups,
356 sizeof(*sgrp_data), GFP_KERNEL);
357 if (!sgrp_data) {
358 ret = -ENOMEM;
359 goto out;
360 }
361
362 for_each_child_of_node(groups, sgrp) {
363 u32 gid;
364
365 type = get_sensor_type(sgrp);
regards,
dan carpenter
^ permalink raw reply
* Re: [PATCH] powerpc: Don't add -mabi= flags when building with Clang
From: Segher Boessenkool @ 2019-08-20 12:40 UTC (permalink / raw)
To: Nathan Chancellor
Cc: linux-kernel, clang-built-linux, Paul Mackerras, linuxppc-dev
In-Reply-To: <20190820031538.GC30221@archlinux-threadripper>
On Mon, Aug 19, 2019 at 08:15:38PM -0700, Nathan Chancellor wrote:
> On Mon, Aug 19, 2019 at 04:19:31AM -0500, Segher Boessenkool wrote:
> > On Sun, Aug 18, 2019 at 12:13:21PM -0700, Nathan Chancellor wrote:
> > > When building pseries_defconfig, building vdso32 errors out:
> > >
> > > error: unknown target ABI 'elfv1'
> > >
> > > Commit 4dc831aa8813 ("powerpc: Fix compiling a BE kernel with a
> > > powerpc64le toolchain") added these flags to fix building GCC but
> > > clang is multitargeted and does not need these flags. The ABI is
> > > properly set based on the target triple, which is derived from
> > > CROSS_COMPILE.
> >
> > You mean that LLVM does not *allow* you to select a different ABI, or
> > different ABI options, you always have to use the default. (Everything
> > else you say is true for GCC as well).
>
> I need to improve the wording of the commit message as it is really that
> clang does not allow a different ABI to be selected for 32-bit PowerPC,
> as the setABI function is not overridden and it defaults to false.
> GCC appears to just silently ignores this flag (I think it is the
> SUBSUBTARGET_OVERRIDE_OPTIONS macro in gcc/config/rs6000/linux64.h).
What flag? -mabi=elfv[12]?
(Only irrelevant things are ever ignored; otherwise, please do a bug
report).
> It can be changed for 64-bit PowerPC it seems but it doesn't need to be
> with clang because everything is set properly internally (I'll find a
> better way to clearly word that as I am sure I'm not quite getting that
> subtlety right).
You can have elfv2 on BE, and e.g. the sysv ABI on LE. Neither of those
is tested a lot.
> > (-mabi= does not set a "target ABI", fwiw, it is more subtle; please see
> > the documentation. Unless LLVM is incompatible in that respect as well?)
>
> Are you referring to the error message?
Yup.
> I suppose I could file an LLVM
> bug report on that but that message applies to all of the '-mabi='
> options, which may refer to a target ABI.
That depends on what you call "an ABI", I guess. You can call any ABI
variant a separate ABI: you'll have to rebuild all of userland. You can
also says ELFv1 and ELFv2 are pretty much the same thing, which is true
as well. The way -mabi= is defined is the latter:
'-mabi=ABI-TYPE'
Extend the current ABI with a particular extension, or remove such
extension. Valid values are 'altivec', 'no-altivec',
'ibmlongdouble', 'ieeelongdouble', 'elfv1', 'elfv2'.
Segher
^ permalink raw reply
* Re: [PATCH v4 1/2] powerpc/time: Only set CONFIG_ARCH_HAS_SCALED_CPUTIME on PPC64
From: Michael Ellerman @ 2019-08-20 12:42 UTC (permalink / raw)
To: Christophe Leroy, Nicholas Piggin
Cc: linux-kernel, Paul Mackerras, Frederic Weisbecker, linuxppc-dev
In-Reply-To: <26969bb5-c01b-0674-5773-027f1851bd44@c-s.fr>
Christophe Leroy <christophe.leroy@c-s.fr> writes:
> Hi Nick,
>
>
> Le 07/06/2018 à 03:43, Nicholas Piggin a écrit :
>> On Wed, 6 Jun 2018 14:21:08 +0000 (UTC)
>> Christophe Leroy <christophe.leroy@c-s.fr> wrote:
>>
>>> scaled cputime is only meaningfull when the processor has
>>> SPURR and/or PURR, which means only on PPC64.
>>>
>
> [...]
>
>>
>> I wonder if we could make this depend on PPC_PSERIES or even
>> PPC_SPLPAR as well? (That would be for a later patch)
>
> Can we go further on this ?
>
> Do we know exactly which configuration support scaled cputime, in
> extenso have SPRN_SPURR and/or SPRN_PURR ?
PURR is Power5/6/7/8/9 and PA6T (pasemi). SPURR is Power6/7/8/9.
So we could easily flip PPC64 for PPC_BOOK3S_64, which would mean 64-bit
Book3E CPUs don't get that overhead.
Beyond that is not so simple. We probably don't need that selected for
bare metal kernels (powernv). But in practice all the distros build a
multi platform kernel with powernv+pseries anyway.
We could turn it off on G5s (PPC970), by making it depend on POWERNV ||
PSERIES || PPC_PASEMI, but I'm not sure if it's worth the trouble.
cheers
^ permalink raw reply
* [PATCH v2 02/12] powerpc/ps3: replace __ioremap() by ioremap_prot()
From: Christophe Leroy @ 2019-08-20 14:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
hch
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1566309262.git.christophe.leroy@c-s.fr>
__ioremap() is similar to ioremap_prot() except that ioremap_prot()
does a few sanity changes in addition.
The flags used by PS3 are not impacted by those changes so for
PS3 both functions are equivalent.
At the same time, drop parts of the comment that have been invalid
since commit e58e87adc8bf ("powerpc/mm: Update _PAGE_KERNEL_RO")
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/platforms/ps3/spu.c | 10 +++-------
1 file changed, 3 insertions(+), 7 deletions(-)
diff --git a/arch/powerpc/platforms/ps3/spu.c b/arch/powerpc/platforms/ps3/spu.c
index bdaeaecdc06b..1193c294b8d0 100644
--- a/arch/powerpc/platforms/ps3/spu.c
+++ b/arch/powerpc/platforms/ps3/spu.c
@@ -184,10 +184,7 @@ static void spu_unmap(struct spu *spu)
* setup_areas - Map the spu regions into the address space.
*
* The current HV requires the spu shadow regs to be mapped with the
- * PTE page protection bits set as read-only (PP=3). This implementation
- * uses the low level __ioremap() to bypass the page protection settings
- * inforced by ioremap_prot() to get the needed PTE bits set for the
- * shadow regs.
+ * PTE page protection bits set as read-only.
*/
static int __init setup_areas(struct spu *spu)
@@ -195,9 +192,8 @@ static int __init setup_areas(struct spu *spu)
struct table {char* name; unsigned long addr; unsigned long size;};
unsigned long shadow_flags = pgprot_val(pgprot_noncached_wc(PAGE_KERNEL_RO));
- spu_pdata(spu)->shadow = __ioremap(spu_pdata(spu)->shadow_addr,
- sizeof(struct spe_shadow),
- shadow_flags);
+ spu_pdata(spu)->shadow = ioremap_prot(spu_pdata(spu)->shadow_addr,
+ sizeof(struct spe_shadow), shadow_flags);
if (!spu_pdata(spu)->shadow) {
pr_debug("%s:%d: ioremap shadow failed\n", __func__, __LINE__);
goto fail_ioremap;
--
2.13.3
^ permalink raw reply related
* [PATCH v2 03/12] powerpc/mm: drop ppc_md.iounmap() and __iounmap()
From: Christophe Leroy @ 2019-08-20 14:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
hch
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1566309262.git.christophe.leroy@c-s.fr>
ppc_md.iounmap() is never set, drop it.
Once ppc_md.iounmap() is gone, iounmap() remains the only user of
__iounmap() and iounmap() does nothing else than calling __iounmap().
So drop iounmap() and make __iounmap() the new iounmap().
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/io.h | 5 -----
arch/powerpc/include/asm/machdep.h | 2 --
arch/powerpc/mm/pgtable_64.c | 11 +----------
3 files changed, 1 insertion(+), 17 deletions(-)
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 23e5d5d16c7e..02d6256fe1ea 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -712,9 +712,6 @@ static inline void iosync(void)
* * __ioremap_caller is the same as above but takes an explicit caller
* reference rather than using __builtin_return_address(0)
*
- * * __iounmap, is the low level implementation used by iounmap and cannot
- * be hooked (but can be used by a hook on iounmap)
- *
*/
extern void __iomem *ioremap(phys_addr_t address, unsigned long size);
extern void __iomem *ioremap_prot(phys_addr_t address, unsigned long size,
@@ -734,8 +731,6 @@ extern void __iomem *__ioremap(phys_addr_t, unsigned long size,
extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size,
pgprot_t prot, void *caller);
-extern void __iounmap(volatile void __iomem *addr);
-
extern void __iomem * __ioremap_at(phys_addr_t pa, void *ea,
unsigned long size, pgprot_t prot);
extern void __iounmap_at(void *ea, unsigned long size);
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index c43d6eca9edd..3370df4bdaa0 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -33,8 +33,6 @@ struct machdep_calls {
#ifdef CONFIG_PPC64
void __iomem * (*ioremap)(phys_addr_t addr, unsigned long size,
pgprot_t prot, void *caller);
- void (*iounmap)(volatile void __iomem *token);
-
#ifdef CONFIG_PM
void (*iommu_save)(void);
void (*iommu_restore)(void);
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 9ad59b733984..57cdd6182932 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -266,7 +266,7 @@ void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size,
* Unmap an IO region and remove it from imalloc'd list.
* Access to IO memory should be serialized by driver.
*/
-void __iounmap(volatile void __iomem *token)
+void iounmap(volatile void __iomem *token)
{
void *addr;
@@ -283,21 +283,12 @@ void __iounmap(volatile void __iomem *token)
vunmap(addr);
}
-void iounmap(volatile void __iomem *token)
-{
- if (ppc_md.iounmap)
- ppc_md.iounmap(token);
- else
- __iounmap(token);
-}
-
EXPORT_SYMBOL(ioremap);
EXPORT_SYMBOL(ioremap_wc);
EXPORT_SYMBOL(ioremap_prot);
EXPORT_SYMBOL(__ioremap);
EXPORT_SYMBOL(__ioremap_at);
EXPORT_SYMBOL(iounmap);
-EXPORT_SYMBOL(__iounmap);
EXPORT_SYMBOL(__iounmap_at);
#ifndef __PAGETABLE_PUD_FOLDED
--
2.13.3
^ permalink raw reply related
* [PATCH v2 01/12] powerpc: remove the ppc44x ocm.c file
From: Christophe Leroy @ 2019-08-20 14:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
hch
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1566309262.git.christophe.leroy@c-s.fr>
From: Christoph Hellwig <hch@lst.de>
The on chip memory allocator is entirely unused in the kernel tree.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/configs/ppc40x_defconfig | 1 -
arch/powerpc/include/asm/ppc4xx_ocm.h | 31 ---
arch/powerpc/platforms/44x/Kconfig | 8 -
arch/powerpc/platforms/4xx/Makefile | 1 -
arch/powerpc/platforms/4xx/ocm.c | 390 ----------------------------------
5 files changed, 431 deletions(-)
delete mode 100644 arch/powerpc/include/asm/ppc4xx_ocm.h
delete mode 100644 arch/powerpc/platforms/4xx/ocm.c
diff --git a/arch/powerpc/configs/ppc40x_defconfig b/arch/powerpc/configs/ppc40x_defconfig
index 8f136b52198b..a5f683aed328 100644
--- a/arch/powerpc/configs/ppc40x_defconfig
+++ b/arch/powerpc/configs/ppc40x_defconfig
@@ -84,4 +84,3 @@ CONFIG_CRYPTO_ECB=y
CONFIG_CRYPTO_PCBC=y
CONFIG_CRYPTO_MD5=y
CONFIG_CRYPTO_DES=y
-CONFIG_PPC4xx_OCM=y
diff --git a/arch/powerpc/include/asm/ppc4xx_ocm.h b/arch/powerpc/include/asm/ppc4xx_ocm.h
deleted file mode 100644
index fc4db6dcde84..000000000000
--- a/arch/powerpc/include/asm/ppc4xx_ocm.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * PowerPC 4xx OCM memory allocation support
- *
- * (C) Copyright 2009, Applied Micro Circuits Corporation
- * Victor Gallardo (vgallardo@amcc.com)
- *
- * See file CREDITS for list of people who contributed to this
- * project.
- */
-
-#ifndef __ASM_POWERPC_PPC4XX_OCM_H__
-#define __ASM_POWERPC_PPC4XX_OCM_H__
-
-#define PPC4XX_OCM_NON_CACHED 0
-#define PPC4XX_OCM_CACHED 1
-
-#if defined(CONFIG_PPC4xx_OCM)
-
-void *ppc4xx_ocm_alloc(phys_addr_t *phys, int size, int align,
- int flags, const char *owner);
-void ppc4xx_ocm_free(const void *virt);
-
-#else
-
-#define ppc4xx_ocm_alloc(phys, size, align, flags, owner) NULL
-#define ppc4xx_ocm_free(addr) ((void)0)
-
-#endif /* CONFIG_PPC4xx_OCM */
-
-#endif /* __ASM_POWERPC_PPC4XX_OCM_H__ */
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index b369ed4e3675..25ebe634a661 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -272,14 +272,6 @@ config PPC4xx_GPIO
help
Enable gpiolib support for ppc440 based boards
-config PPC4xx_OCM
- bool "PPC4xx On Chip Memory (OCM) support"
- depends on 4xx
- select PPC_LIB_RHEAP
- help
- Enable OCM support for PowerPC 4xx platforms with on chip memory,
- OCM provides the fast place for memory access to improve performance.
-
# 44x specific CPU modules, selected based on the board above.
config 440EP
bool
diff --git a/arch/powerpc/platforms/4xx/Makefile b/arch/powerpc/platforms/4xx/Makefile
index f5ae27ca131b..d009d2e0b9e8 100644
--- a/arch/powerpc/platforms/4xx/Makefile
+++ b/arch/powerpc/platforms/4xx/Makefile
@@ -1,6 +1,5 @@
# SPDX-License-Identifier: GPL-2.0-only
obj-y += uic.o machine_check.o
-obj-$(CONFIG_PPC4xx_OCM) += ocm.o
obj-$(CONFIG_4xx_SOC) += soc.o
obj-$(CONFIG_PCI) += pci.o
obj-$(CONFIG_PPC4xx_HSTA_MSI) += hsta_msi.o
diff --git a/arch/powerpc/platforms/4xx/ocm.c b/arch/powerpc/platforms/4xx/ocm.c
deleted file mode 100644
index ba3257406ced..000000000000
--- a/arch/powerpc/platforms/4xx/ocm.c
+++ /dev/null
@@ -1,390 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * PowerPC 4xx OCM memory allocation support
- *
- * (C) Copyright 2009, Applied Micro Circuits Corporation
- * Victor Gallardo (vgallardo@amcc.com)
- *
- * See file CREDITS for list of people who contributed to this
- * project.
- */
-
-#include <linux/kernel.h>
-#include <linux/dma-mapping.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <asm/rheap.h>
-#include <asm/ppc4xx_ocm.h>
-#include <linux/slab.h>
-#include <linux/debugfs.h>
-
-#define OCM_DISABLED 0
-#define OCM_ENABLED 1
-
-struct ocm_block {
- struct list_head list;
- void __iomem *addr;
- int size;
- const char *owner;
-};
-
-/* non-cached or cached region */
-struct ocm_region {
- phys_addr_t phys;
- void __iomem *virt;
-
- int memtotal;
- int memfree;
-
- rh_info_t *rh;
- struct list_head list;
-};
-
-struct ocm_info {
- int index;
- int status;
- int ready;
-
- phys_addr_t phys;
-
- int alignment;
- int memtotal;
- int cache_size;
-
- struct ocm_region nc; /* non-cached region */
- struct ocm_region c; /* cached region */
-};
-
-static struct ocm_info *ocm_nodes;
-static int ocm_count;
-
-static struct ocm_info *ocm_get_node(unsigned int index)
-{
- if (index >= ocm_count) {
- printk(KERN_ERR "PPC4XX OCM: invalid index");
- return NULL;
- }
-
- return &ocm_nodes[index];
-}
-
-static int ocm_free_region(struct ocm_region *ocm_reg, const void *addr)
-{
- struct ocm_block *blk, *tmp;
- unsigned long offset;
-
- if (!ocm_reg->virt)
- return 0;
-
- list_for_each_entry_safe(blk, tmp, &ocm_reg->list, list) {
- if (blk->addr == addr) {
- offset = addr - ocm_reg->virt;
- ocm_reg->memfree += blk->size;
- rh_free(ocm_reg->rh, offset);
- list_del(&blk->list);
- kfree(blk);
- return 1;
- }
- }
-
- return 0;
-}
-
-static void __init ocm_init_node(int count, struct device_node *node)
-{
- struct ocm_info *ocm;
-
- const unsigned int *cell_index;
- const unsigned int *cache_size;
- int len;
-
- struct resource rsrc;
-
- ocm = ocm_get_node(count);
-
- cell_index = of_get_property(node, "cell-index", &len);
- if (!cell_index) {
- printk(KERN_ERR "PPC4XX OCM: missing cell-index property");
- return;
- }
- ocm->index = *cell_index;
-
- if (of_device_is_available(node))
- ocm->status = OCM_ENABLED;
-
- cache_size = of_get_property(node, "cached-region-size", &len);
- if (cache_size)
- ocm->cache_size = *cache_size;
-
- if (of_address_to_resource(node, 0, &rsrc)) {
- printk(KERN_ERR "PPC4XX OCM%d: could not get resource address\n",
- ocm->index);
- return;
- }
-
- ocm->phys = rsrc.start;
- ocm->memtotal = (rsrc.end - rsrc.start + 1);
-
- printk(KERN_INFO "PPC4XX OCM%d: %d Bytes (%s)\n",
- ocm->index, ocm->memtotal,
- (ocm->status == OCM_DISABLED) ? "disabled" : "enabled");
-
- if (ocm->status == OCM_DISABLED)
- return;
-
- /* request region */
-
- if (!request_mem_region(ocm->phys, ocm->memtotal, "ppc4xx_ocm")) {
- printk(KERN_ERR "PPC4XX OCM%d: could not request region\n",
- ocm->index);
- return;
- }
-
- /* Configure non-cached and cached regions */
-
- ocm->nc.phys = ocm->phys;
- ocm->nc.memtotal = ocm->memtotal - ocm->cache_size;
- ocm->nc.memfree = ocm->nc.memtotal;
-
- ocm->c.phys = ocm->phys + ocm->nc.memtotal;
- ocm->c.memtotal = ocm->cache_size;
- ocm->c.memfree = ocm->c.memtotal;
-
- if (ocm->nc.memtotal == 0)
- ocm->nc.phys = 0;
-
- if (ocm->c.memtotal == 0)
- ocm->c.phys = 0;
-
- printk(KERN_INFO "PPC4XX OCM%d: %d Bytes (non-cached)\n",
- ocm->index, ocm->nc.memtotal);
-
- printk(KERN_INFO "PPC4XX OCM%d: %d Bytes (cached)\n",
- ocm->index, ocm->c.memtotal);
-
- /* ioremap the non-cached region */
- if (ocm->nc.memtotal) {
- ocm->nc.virt = __ioremap(ocm->nc.phys, ocm->nc.memtotal,
- _PAGE_EXEC | pgprot_val(PAGE_KERNEL_NCG));
-
- if (!ocm->nc.virt) {
- printk(KERN_ERR
- "PPC4XX OCM%d: failed to ioremap non-cached memory\n",
- ocm->index);
- ocm->nc.memfree = 0;
- return;
- }
- }
-
- /* ioremap the cached region */
-
- if (ocm->c.memtotal) {
- ocm->c.virt = __ioremap(ocm->c.phys, ocm->c.memtotal,
- _PAGE_EXEC | pgprot_val(PAGE_KERNEL));
-
- if (!ocm->c.virt) {
- printk(KERN_ERR
- "PPC4XX OCM%d: failed to ioremap cached memory\n",
- ocm->index);
- ocm->c.memfree = 0;
- return;
- }
- }
-
- /* Create Remote Heaps */
-
- ocm->alignment = 4; /* default 4 byte alignment */
-
- if (ocm->nc.virt) {
- ocm->nc.rh = rh_create(ocm->alignment);
- rh_attach_region(ocm->nc.rh, 0, ocm->nc.memtotal);
- }
-
- if (ocm->c.virt) {
- ocm->c.rh = rh_create(ocm->alignment);
- rh_attach_region(ocm->c.rh, 0, ocm->c.memtotal);
- }
-
- INIT_LIST_HEAD(&ocm->nc.list);
- INIT_LIST_HEAD(&ocm->c.list);
-
- ocm->ready = 1;
-}
-
-static int ocm_debugfs_show(struct seq_file *m, void *v)
-{
- struct ocm_block *blk, *tmp;
- unsigned int i;
-
- for (i = 0; i < ocm_count; i++) {
- struct ocm_info *ocm = ocm_get_node(i);
-
- if (!ocm || !ocm->ready)
- continue;
-
- seq_printf(m, "PPC4XX OCM : %d\n", ocm->index);
- seq_printf(m, "PhysAddr : %pa\n", &(ocm->phys));
- seq_printf(m, "MemTotal : %d Bytes\n", ocm->memtotal);
- seq_printf(m, "MemTotal(NC) : %d Bytes\n", ocm->nc.memtotal);
- seq_printf(m, "MemTotal(C) : %d Bytes\n\n", ocm->c.memtotal);
-
- seq_printf(m, "NC.PhysAddr : %pa\n", &(ocm->nc.phys));
- seq_printf(m, "NC.VirtAddr : 0x%p\n", ocm->nc.virt);
- seq_printf(m, "NC.MemTotal : %d Bytes\n", ocm->nc.memtotal);
- seq_printf(m, "NC.MemFree : %d Bytes\n", ocm->nc.memfree);
-
- list_for_each_entry_safe(blk, tmp, &ocm->nc.list, list) {
- seq_printf(m, "NC.MemUsed : %d Bytes (%s)\n",
- blk->size, blk->owner);
- }
-
- seq_printf(m, "\nC.PhysAddr : %pa\n", &(ocm->c.phys));
- seq_printf(m, "C.VirtAddr : 0x%p\n", ocm->c.virt);
- seq_printf(m, "C.MemTotal : %d Bytes\n", ocm->c.memtotal);
- seq_printf(m, "C.MemFree : %d Bytes\n", ocm->c.memfree);
-
- list_for_each_entry_safe(blk, tmp, &ocm->c.list, list) {
- seq_printf(m, "C.MemUsed : %d Bytes (%s)\n",
- blk->size, blk->owner);
- }
-
- seq_putc(m, '\n');
- }
-
- return 0;
-}
-
-static int ocm_debugfs_open(struct inode *inode, struct file *file)
-{
- return single_open(file, ocm_debugfs_show, NULL);
-}
-
-static const struct file_operations ocm_debugfs_fops = {
- .open = ocm_debugfs_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
-};
-
-static int ocm_debugfs_init(void)
-{
- struct dentry *junk;
-
- junk = debugfs_create_dir("ppc4xx_ocm", 0);
- if (!junk) {
- printk(KERN_ALERT "debugfs ppc4xx ocm: failed to create dir\n");
- return -1;
- }
-
- if (debugfs_create_file("info", 0644, junk, NULL, &ocm_debugfs_fops)) {
- printk(KERN_ALERT "debugfs ppc4xx ocm: failed to create file\n");
- return -1;
- }
-
- return 0;
-}
-
-void *ppc4xx_ocm_alloc(phys_addr_t *phys, int size, int align,
- int flags, const char *owner)
-{
- void __iomem *addr = NULL;
- unsigned long offset;
- struct ocm_info *ocm;
- struct ocm_region *ocm_reg;
- struct ocm_block *ocm_blk;
- int i;
-
- for (i = 0; i < ocm_count; i++) {
- ocm = ocm_get_node(i);
-
- if (!ocm || !ocm->ready)
- continue;
-
- if (flags == PPC4XX_OCM_NON_CACHED)
- ocm_reg = &ocm->nc;
- else
- ocm_reg = &ocm->c;
-
- if (!ocm_reg->virt)
- continue;
-
- if (align < ocm->alignment)
- align = ocm->alignment;
-
- offset = rh_alloc_align(ocm_reg->rh, size, align, NULL);
-
- if (IS_ERR_VALUE(offset))
- continue;
-
- ocm_blk = kzalloc(sizeof(*ocm_blk), GFP_KERNEL);
- if (!ocm_blk) {
- rh_free(ocm_reg->rh, offset);
- break;
- }
-
- *phys = ocm_reg->phys + offset;
- addr = ocm_reg->virt + offset;
- size = ALIGN(size, align);
-
- ocm_blk->addr = addr;
- ocm_blk->size = size;
- ocm_blk->owner = owner;
- list_add_tail(&ocm_blk->list, &ocm_reg->list);
-
- ocm_reg->memfree -= size;
-
- break;
- }
-
- return addr;
-}
-
-void ppc4xx_ocm_free(const void *addr)
-{
- int i;
-
- if (!addr)
- return;
-
- for (i = 0; i < ocm_count; i++) {
- struct ocm_info *ocm = ocm_get_node(i);
-
- if (!ocm || !ocm->ready)
- continue;
-
- if (ocm_free_region(&ocm->nc, addr) ||
- ocm_free_region(&ocm->c, addr))
- return;
- }
-}
-
-static int __init ppc4xx_ocm_init(void)
-{
- struct device_node *np;
- int count;
-
- count = 0;
- for_each_compatible_node(np, NULL, "ibm,ocm")
- count++;
-
- if (!count)
- return 0;
-
- ocm_nodes = kzalloc((count * sizeof(struct ocm_info)), GFP_KERNEL);
- if (!ocm_nodes)
- return -ENOMEM;
-
- ocm_count = count;
- count = 0;
-
- for_each_compatible_node(np, NULL, "ibm,ocm") {
- ocm_init_node(count, np);
- count++;
- }
-
- ocm_debugfs_init();
-
- return 0;
-}
-
-arch_initcall(ppc4xx_ocm_init);
--
2.13.3
^ permalink raw reply related
* [PATCH v2 00/12] powerpc/mm: cleanup and refactoring in ioremap
From: Christophe Leroy @ 2019-08-20 14:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
hch
Cc: linuxppc-dev, linux-kernel
The purpose of this series is to cleanup and refactor ioremap.
At the time being, ioremap is duplicated in PPC32 and PPC64.
In addition, some additional duplication also appear within PPC64.
First part of this series drops as much as unused functions.
Then io-workaround is reworked to avoid indirect function call.
Then common parts of PPC32 and PPC64 are regrouped into a new file
called ioremap.c
Then other parts linked to ioremap are respectively moved out of
pgtable_32/64.c
The last part of the series tries to refactor ioremap_range() and
make use of ioremap_page_range() for all, then separates the early
path from the regular ioremap.
A future follow-up of this series will be to try and eliminate the
early ioremap part and use the generic early_ioremap instead.
v2:
- dropped the change of ioremap_bot growing direction for PPC64 and
kept separate __ioremap_caller() and friends.
- separating more clearly early_ioremap() from regular ioremap()
- addressed received comments.
Christophe Leroy (12):
powerpc: remove the ppc44x ocm.c file
powerpc/ps3: replace __ioremap() by ioremap_prot()
powerpc/mm: drop ppc_md.iounmap() and __iounmap()
powerpc/mm: drop function __ioremap()
powerpc/mm: rework io-workaround invocation.
powerpc/mm: move common 32/64 bits ioremap functions into ioremap.c
powerpc/mm: move ioremap_prot() into ioremap.c
powerpc/mm: make ioremap_bot common to all
powerpc/mm: Move ioremap functions out of pgtable_32/64.c
powerpc/mm: refactor ioremap_range() and use ioremap_page_range()
powerpc/mm: refactor ioremap vm area setup.
powerpc/mm: split out early ioremap path.
arch/powerpc/configs/ppc40x_defconfig | 1 -
arch/powerpc/include/asm/book3s/32/pgtable.h | 6 +-
arch/powerpc/include/asm/book3s/64/pgtable.h | 2 +-
arch/powerpc/include/asm/book3s/64/radix.h | 3 -
arch/powerpc/include/asm/io-workarounds.h | 20 ++
arch/powerpc/include/asm/io.h | 16 +-
arch/powerpc/include/asm/machdep.h | 4 -
arch/powerpc/include/asm/nohash/32/pgtable.h | 6 +-
arch/powerpc/include/asm/nohash/64/pgtable.h | 1 +
arch/powerpc/include/asm/pgtable.h | 2 +
arch/powerpc/include/asm/ppc4xx_ocm.h | 31 ---
arch/powerpc/kernel/io-workarounds.c | 13 +-
arch/powerpc/mm/Makefile | 2 +-
arch/powerpc/mm/book3s64/pgtable.c | 21 --
arch/powerpc/mm/book3s64/radix_pgtable.c | 20 --
arch/powerpc/mm/ioremap.c | 99 +++++++
arch/powerpc/mm/ioremap_32.c | 92 +++++++
arch/powerpc/mm/ioremap_64.c | 113 ++++++++
arch/powerpc/mm/mmu_decl.h | 1 -
arch/powerpc/mm/nohash/tlb.c | 2 +
arch/powerpc/mm/pgtable_32.c | 153 -----------
arch/powerpc/mm/pgtable_64.c | 203 +-------------
arch/powerpc/platforms/44x/Kconfig | 8 -
arch/powerpc/platforms/4xx/Makefile | 1 -
arch/powerpc/platforms/4xx/ocm.c | 390 ---------------------------
arch/powerpc/platforms/ps3/spu.c | 10 +-
26 files changed, 353 insertions(+), 867 deletions(-)
delete mode 100644 arch/powerpc/include/asm/ppc4xx_ocm.h
create mode 100644 arch/powerpc/mm/ioremap.c
create mode 100644 arch/powerpc/mm/ioremap_32.c
create mode 100644 arch/powerpc/mm/ioremap_64.c
delete mode 100644 arch/powerpc/platforms/4xx/ocm.c
--
2.13.3
^ permalink raw reply
* [PATCH v2 04/12] powerpc/mm: drop function __ioremap()
From: Christophe Leroy @ 2019-08-20 14:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
hch
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1566309262.git.christophe.leroy@c-s.fr>
__ioremap() is not used anymore, drop it.
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/io.h | 6 ------
arch/powerpc/mm/pgtable_32.c | 11 ++---------
arch/powerpc/mm/pgtable_64.c | 7 -------
3 files changed, 2 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 02d6256fe1ea..8e65ba59f06a 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -705,10 +705,6 @@ static inline void iosync(void)
* create hand-made mappings for use only by the PCI code and cannot
* currently be hooked. Must be page aligned.
*
- * * __ioremap is the low level implementation used by ioremap and
- * ioremap_prot and cannot be hooked (but can be used by a hook on one
- * of the previous ones)
- *
* * __ioremap_caller is the same as above but takes an explicit caller
* reference rather than using __builtin_return_address(0)
*
@@ -726,8 +722,6 @@ void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size);
extern void iounmap(volatile void __iomem *addr);
-extern void __iomem *__ioremap(phys_addr_t, unsigned long size,
- unsigned long flags);
extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size,
pgprot_t prot, void *caller);
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 35cb96cfc258..848ee4a30dd1 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -92,12 +92,6 @@ ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
EXPORT_SYMBOL(ioremap_prot);
void __iomem *
-__ioremap(phys_addr_t addr, unsigned long size, unsigned long flags)
-{
- return __ioremap_caller(addr, size, __pgprot(flags), __builtin_return_address(0));
-}
-
-void __iomem *
__ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *caller)
{
unsigned long v, i;
@@ -127,8 +121,8 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call
*/
if (slab_is_available() && p <= virt_to_phys(high_memory - 1) &&
page_is_ram(__phys_to_pfn(p))) {
- printk("__ioremap(): phys addr 0x%llx is RAM lr %ps\n",
- (unsigned long long)p, __builtin_return_address(0));
+ pr_warn("%s(): phys addr 0x%llx is RAM lr %ps\n", __func__,
+ (unsigned long long)p, __builtin_return_address(0));
return NULL;
}
#endif
@@ -171,7 +165,6 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call
out:
return (void __iomem *) (v + ((unsigned long)addr & ~PAGE_MASK));
}
-EXPORT_SYMBOL(__ioremap);
void iounmap(volatile void __iomem *addr)
{
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 57cdd6182932..2882419737b9 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -203,12 +203,6 @@ void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size,
return ret;
}
-void __iomem * __ioremap(phys_addr_t addr, unsigned long size,
- unsigned long flags)
-{
- return __ioremap_caller(addr, size, __pgprot(flags), __builtin_return_address(0));
-}
-
void __iomem * ioremap(phys_addr_t addr, unsigned long size)
{
pgprot_t prot = pgprot_noncached(PAGE_KERNEL);
@@ -286,7 +280,6 @@ void iounmap(volatile void __iomem *token)
EXPORT_SYMBOL(ioremap);
EXPORT_SYMBOL(ioremap_wc);
EXPORT_SYMBOL(ioremap_prot);
-EXPORT_SYMBOL(__ioremap);
EXPORT_SYMBOL(__ioremap_at);
EXPORT_SYMBOL(iounmap);
EXPORT_SYMBOL(__iounmap_at);
--
2.13.3
^ permalink raw reply related
* [PATCH v2 07/12] powerpc/mm: move ioremap_prot() into ioremap.c
From: Christophe Leroy @ 2019-08-20 14:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
hch
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1566309262.git.christophe.leroy@c-s.fr>
Both ioremap_prot() are idenfical, move them into ioremap.c
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/mm/ioremap.c | 19 +++++++++++++++++++
arch/powerpc/mm/pgtable_32.c | 17 -----------------
arch/powerpc/mm/pgtable_64.c | 24 ------------------------
3 files changed, 19 insertions(+), 41 deletions(-)
diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c
index 7f1d462e7745..3d388aaa3ee6 100644
--- a/arch/powerpc/mm/ioremap.c
+++ b/arch/powerpc/mm/ioremap.c
@@ -34,3 +34,22 @@ void __iomem *ioremap_coherent(phys_addr_t addr, unsigned long size)
return iowa_ioremap(addr, size, prot, caller);
return __ioremap_caller(addr, size, prot, caller);
}
+
+void __iomem *ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
+{
+ pte_t pte = __pte(flags);
+ void *caller = __builtin_return_address(0);
+
+ /* writeable implies dirty for kernel addresses */
+ if (pte_write(pte))
+ pte = pte_mkdirty(pte);
+
+ /* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */
+ pte = pte_exprotect(pte);
+ pte = pte_mkprivileged(pte);
+
+ if (iowa_is_active())
+ return iowa_ioremap(addr, size, pte_pgprot(pte), caller);
+ return __ioremap_caller(addr, size, pte_pgprot(pte), caller);
+}
+EXPORT_SYMBOL(ioremap_prot);
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 3a4972007ec0..b0f2d45da232 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -48,23 +48,6 @@ ioremap_wt(phys_addr_t addr, unsigned long size)
EXPORT_SYMBOL(ioremap_wt);
void __iomem *
-ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
-{
- pte_t pte = __pte(flags);
-
- /* writeable implies dirty for kernel addresses */
- if (pte_write(pte))
- pte = pte_mkdirty(pte);
-
- /* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */
- pte = pte_exprotect(pte);
- pte = pte_mkprivileged(pte);
-
- return __ioremap_caller(addr, size, pte_pgprot(pte), __builtin_return_address(0));
-}
-EXPORT_SYMBOL(ioremap_prot);
-
-void __iomem *
__ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *caller)
{
unsigned long v, i;
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 358233ea8d85..2b9078e1bc43 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -203,29 +203,6 @@ void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size,
return ret;
}
-void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size,
- unsigned long flags)
-{
- pte_t pte = __pte(flags);
- void *caller = __builtin_return_address(0);
-
- /* writeable implies dirty for kernel addresses */
- if (pte_write(pte))
- pte = pte_mkdirty(pte);
-
- /* we don't want to let _PAGE_EXEC leak out */
- pte = pte_exprotect(pte);
- /*
- * Force kernel mapping.
- */
- pte = pte_mkprivileged(pte);
-
- if (iowa_is_active())
- return iowa_ioremap(addr, size, pte_pgprot(pte), caller);
- return __ioremap_caller(addr, size, pte_pgprot(pte), caller);
-}
-
-
/*
* Unmap an IO region and remove it from imalloc'd list.
* Access to IO memory should be serialized by driver.
@@ -247,7 +224,6 @@ void iounmap(volatile void __iomem *token)
vunmap(addr);
}
-EXPORT_SYMBOL(ioremap_prot);
EXPORT_SYMBOL(__ioremap_at);
EXPORT_SYMBOL(iounmap);
EXPORT_SYMBOL(__iounmap_at);
--
2.13.3
^ permalink raw reply related
* [PATCH v2 06/12] powerpc/mm: move common 32/64 bits ioremap functions into ioremap.c
From: Christophe Leroy @ 2019-08-20 14:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
hch
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1566309262.git.christophe.leroy@c-s.fr>
ioremap(), ioremap_wc() and ioremap_coherent() are now identical on
PPC32 and PPC64 as iowa_is_active() will always return false on
PPC32. Move them into a new common location called ioremap.c
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/mm/Makefile | 2 +-
arch/powerpc/mm/ioremap.c | 36 ++++++++++++++++++++++++++++++++++++
arch/powerpc/mm/pgtable_32.c | 27 ---------------------------
arch/powerpc/mm/pgtable_64.c | 33 ---------------------------------
4 files changed, 37 insertions(+), 61 deletions(-)
create mode 100644 arch/powerpc/mm/ioremap.c
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 0f499db315d6..29c682fe9144 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -7,7 +7,7 @@ ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
obj-y := fault.o mem.o pgtable.o mmap.o \
init_$(BITS).o pgtable_$(BITS).o \
- pgtable-frag.o \
+ pgtable-frag.o ioremap.o \
init-common.o mmu_context.o drmem.o
obj-$(CONFIG_PPC_MMU_NOHASH) += nohash/
obj-$(CONFIG_PPC_BOOK3S_32) += book3s32/
diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c
new file mode 100644
index 000000000000..7f1d462e7745
--- /dev/null
+++ b/arch/powerpc/mm/ioremap.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/io.h>
+#include <asm/io-workarounds.h>
+
+void __iomem *ioremap(phys_addr_t addr, unsigned long size)
+{
+ pgprot_t prot = pgprot_noncached(PAGE_KERNEL);
+ void *caller = __builtin_return_address(0);
+
+ if (iowa_is_active())
+ return iowa_ioremap(addr, size, prot, caller);
+ return __ioremap_caller(addr, size, prot, caller);
+}
+EXPORT_SYMBOL(ioremap);
+
+void __iomem *ioremap_wc(phys_addr_t addr, unsigned long size)
+{
+ pgprot_t prot = pgprot_noncached_wc(PAGE_KERNEL);
+ void *caller = __builtin_return_address(0);
+
+ if (iowa_is_active())
+ return iowa_ioremap(addr, size, prot, caller);
+ return __ioremap_caller(addr, size, prot, caller);
+}
+EXPORT_SYMBOL(ioremap_wc);
+
+void __iomem *ioremap_coherent(phys_addr_t addr, unsigned long size)
+{
+ pgprot_t prot = pgprot_cached(PAGE_KERNEL);
+ void *caller = __builtin_return_address(0);
+
+ if (iowa_is_active())
+ return iowa_ioremap(addr, size, prot, caller);
+ return __ioremap_caller(addr, size, prot, caller);
+}
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 848ee4a30dd1..3a4972007ec0 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -39,24 +39,6 @@ EXPORT_SYMBOL(ioremap_bot); /* aka VMALLOC_END */
extern char etext[], _stext[], _sinittext[], _einittext[];
void __iomem *
-ioremap(phys_addr_t addr, unsigned long size)
-{
- pgprot_t prot = pgprot_noncached(PAGE_KERNEL);
-
- return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
-}
-EXPORT_SYMBOL(ioremap);
-
-void __iomem *
-ioremap_wc(phys_addr_t addr, unsigned long size)
-{
- pgprot_t prot = pgprot_noncached_wc(PAGE_KERNEL);
-
- return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
-}
-EXPORT_SYMBOL(ioremap_wc);
-
-void __iomem *
ioremap_wt(phys_addr_t addr, unsigned long size)
{
pgprot_t prot = pgprot_cached_wthru(PAGE_KERNEL);
@@ -66,15 +48,6 @@ ioremap_wt(phys_addr_t addr, unsigned long size)
EXPORT_SYMBOL(ioremap_wt);
void __iomem *
-ioremap_coherent(phys_addr_t addr, unsigned long size)
-{
- pgprot_t prot = pgprot_cached(PAGE_KERNEL);
-
- return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
-}
-EXPORT_SYMBOL(ioremap_coherent);
-
-void __iomem *
ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
{
pte_t pte = __pte(flags);
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 0a147daeb0f2..358233ea8d85 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -35,7 +35,6 @@
#include <asm/page.h>
#include <asm/prom.h>
#include <asm/io.h>
-#include <asm/io-workarounds.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
@@ -204,36 +203,6 @@ void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size,
return ret;
}
-void __iomem * ioremap(phys_addr_t addr, unsigned long size)
-{
- pgprot_t prot = pgprot_noncached(PAGE_KERNEL);
- void *caller = __builtin_return_address(0);
-
- if (iowa_is_active())
- return iowa_ioremap(addr, size, prot, caller);
- return __ioremap_caller(addr, size, prot, caller);
-}
-
-void __iomem * ioremap_wc(phys_addr_t addr, unsigned long size)
-{
- pgprot_t prot = pgprot_noncached_wc(PAGE_KERNEL);
- void *caller = __builtin_return_address(0);
-
- if (iowa_is_active())
- return iowa_ioremap(addr, size, prot, caller);
- return __ioremap_caller(addr, size, prot, caller);
-}
-
-void __iomem *ioremap_coherent(phys_addr_t addr, unsigned long size)
-{
- pgprot_t prot = pgprot_cached(PAGE_KERNEL);
- void *caller = __builtin_return_address(0);
-
- if (iowa_is_active())
- return iowa_ioremap(addr, size, prot, caller);
- return __ioremap_caller(addr, size, prot, caller);
-}
-
void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size,
unsigned long flags)
{
@@ -278,8 +247,6 @@ void iounmap(volatile void __iomem *token)
vunmap(addr);
}
-EXPORT_SYMBOL(ioremap);
-EXPORT_SYMBOL(ioremap_wc);
EXPORT_SYMBOL(ioremap_prot);
EXPORT_SYMBOL(__ioremap_at);
EXPORT_SYMBOL(iounmap);
--
2.13.3
^ permalink raw reply related
* [PATCH v2 08/12] powerpc/mm: make ioremap_bot common to all
From: Christophe Leroy @ 2019-08-20 14:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
hch
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1566309262.git.christophe.leroy@c-s.fr>
Drop multiple definitions of ioremap_bot and make one common to
all subarches.
Only CONFIG_PPC_BOOK3E_64 had a global static init value for
ioremap_bot. Now ioremap_bot is set in early_init_mmu_global().
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/book3s/32/pgtable.h | 2 --
arch/powerpc/include/asm/book3s/64/pgtable.h | 1 -
arch/powerpc/include/asm/nohash/32/pgtable.h | 2 --
arch/powerpc/include/asm/pgtable.h | 2 ++
arch/powerpc/mm/ioremap.c | 3 +++
arch/powerpc/mm/mmu_decl.h | 1 -
arch/powerpc/mm/nohash/tlb.c | 2 ++
arch/powerpc/mm/pgtable_32.c | 3 ---
arch/powerpc/mm/pgtable_64.c | 3 ---
9 files changed, 7 insertions(+), 12 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 838de59f6754..aa1bc5f8da90 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -201,8 +201,6 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
#include <linux/sched.h>
#include <linux/threads.h>
-extern unsigned long ioremap_bot;
-
/* Bits to mask out from a PGD to get to the PUD page */
#define PGD_MASKED_BITS 0
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 8308f32e9782..11819e3c755e 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -289,7 +289,6 @@ extern unsigned long __kernel_io_end;
#define KERN_IO_END __kernel_io_end
extern struct page *vmemmap;
-extern unsigned long ioremap_bot;
extern unsigned long pci_io_base;
#endif /* __ASSEMBLY__ */
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 0284f8f5305f..7ce2a7c9fade 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -11,8 +11,6 @@
#include <asm/mmu.h> /* For sub-arch specific PPC_PIN_SIZE */
#include <asm/asm-405.h>
-extern unsigned long ioremap_bot;
-
#ifdef CONFIG_44x
extern int icache_44x_need_flush;
#endif
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index c58ba7963688..c54bb68c1354 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -68,6 +68,8 @@ extern pgd_t swapper_pg_dir[];
extern void paging_init(void);
+extern unsigned long ioremap_bot;
+
/*
* kern_addr_valid is intended to indicate whether an address is a valid
* kernel address. Most 32-bit archs define it as always true (like this)
diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c
index 3d388aaa3ee6..eaf5f8a4a63f 100644
--- a/arch/powerpc/mm/ioremap.c
+++ b/arch/powerpc/mm/ioremap.c
@@ -3,6 +3,9 @@
#include <linux/io.h>
#include <asm/io-workarounds.h>
+unsigned long ioremap_bot;
+EXPORT_SYMBOL(ioremap_bot);
+
void __iomem *ioremap(phys_addr_t addr, unsigned long size)
{
pgprot_t prot = pgprot_noncached(PAGE_KERNEL);
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 32c1a191c28a..6ee64d5e2824 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -108,7 +108,6 @@ extern u8 early_hash[];
#endif /* CONFIG_PPC32 */
-extern unsigned long ioremap_bot;
extern unsigned long __max_low_memory;
extern phys_addr_t __initial_memory_limit_addr;
extern phys_addr_t total_memory;
diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c
index bf60983a58c7..696f568253a0 100644
--- a/arch/powerpc/mm/nohash/tlb.c
+++ b/arch/powerpc/mm/nohash/tlb.c
@@ -703,6 +703,8 @@ static void __init early_init_mmu_global(void)
* for use by the TLB miss code
*/
linear_map_top = memblock_end_of_DRAM();
+
+ ioremap_bot = IOREMAP_BASE;
}
static void __init early_mmu_set_memory_limit(void)
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index b0f2d45da232..daab57c78b22 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -33,9 +33,6 @@
#include <mm/mmu_decl.h>
-unsigned long ioremap_bot;
-EXPORT_SYMBOL(ioremap_bot); /* aka VMALLOC_END */
-
extern char etext[], _stext[], _sinittext[], _einittext[];
void __iomem *
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 2b9078e1bc43..d865e053052d 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -98,9 +98,6 @@ unsigned long __pte_frag_nr;
EXPORT_SYMBOL(__pte_frag_nr);
unsigned long __pte_frag_size_shift;
EXPORT_SYMBOL(__pte_frag_size_shift);
-unsigned long ioremap_bot;
-#else /* !CONFIG_PPC_BOOK3S_64 */
-unsigned long ioremap_bot = IOREMAP_BASE;
#endif
int __weak ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot, int nid)
--
2.13.3
^ permalink raw reply related
* [PATCH v2 05/12] powerpc/mm: rework io-workaround invocation.
From: Christophe Leroy @ 2019-08-20 14:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
hch
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1566309262.git.christophe.leroy@c-s.fr>
ppc_md.ioremap() is only used for I/O workaround on CELL platform,
so indirect function call can be avoided.
This patch reworks the io-workaround and ioremap() functions to
use the global 'io_workaround_inited' flag for the activation
of io-workaround.
When CONFIG_PPC_IO_WORKAROUNDS or CONFIG_PPC_INDIRECT_MMIO are not
selected, the I/O workaround ioremap() voids and the global flag is
not used.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/io-workarounds.h | 20 ++++++++++++++++++++
arch/powerpc/include/asm/machdep.h | 2 --
arch/powerpc/kernel/io-workarounds.c | 13 +++++--------
arch/powerpc/mm/pgtable_64.c | 17 +++++++++--------
4 files changed, 34 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/include/asm/io-workarounds.h b/arch/powerpc/include/asm/io-workarounds.h
index 01567ea4ceaf..3cce499fbe27 100644
--- a/arch/powerpc/include/asm/io-workarounds.h
+++ b/arch/powerpc/include/asm/io-workarounds.h
@@ -8,6 +8,7 @@
#ifndef _IO_WORKAROUNDS_H
#define _IO_WORKAROUNDS_H
+#ifdef CONFIG_PPC_IO_WORKAROUNDS
#include <linux/io.h>
#include <asm/pci-bridge.h>
@@ -32,4 +33,23 @@ extern int spiderpci_iowa_init(struct iowa_bus *, void *);
#define SPIDER_PCI_DUMMY_READ 0x0810
#define SPIDER_PCI_DUMMY_READ_BASE 0x0814
+#endif
+
+#if defined(CONFIG_PPC_IO_WORKAROUNDS) && defined(CONFIG_PPC_INDIRECT_MMIO)
+extern bool io_workaround_inited;
+
+static inline bool iowa_is_active(void)
+{
+ return unlikely(io_workaround_inited);
+}
+#else
+static inline bool iowa_is_active(void)
+{
+ return false;
+}
+#endif
+
+void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
+ pgprot_t prot, void *caller);
+
#endif /* _IO_WORKAROUNDS_H */
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 3370df4bdaa0..657ec893bdcb 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -31,8 +31,6 @@ struct pci_host_bridge;
struct machdep_calls {
char *name;
#ifdef CONFIG_PPC64
- void __iomem * (*ioremap)(phys_addr_t addr, unsigned long size,
- pgprot_t prot, void *caller);
#ifdef CONFIG_PM
void (*iommu_save)(void);
void (*iommu_restore)(void);
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
index fbd2d0007c52..0276bc8c8969 100644
--- a/arch/powerpc/kernel/io-workarounds.c
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -149,8 +149,8 @@ static const struct ppc_pci_io iowa_pci_io = {
};
#ifdef CONFIG_PPC_INDIRECT_MMIO
-static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
- pgprot_t prot, void *caller)
+void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
+ pgprot_t prot, void *caller)
{
struct iowa_bus *bus;
void __iomem *res = __ioremap_caller(addr, size, prot, caller);
@@ -163,20 +163,17 @@ static void __iomem *iowa_ioremap(phys_addr_t addr, unsigned long size,
}
return res;
}
-#else /* CONFIG_PPC_INDIRECT_MMIO */
-#define iowa_ioremap NULL
#endif /* !CONFIG_PPC_INDIRECT_MMIO */
+bool io_workaround_inited;
+
/* Enable IO workaround */
static void io_workaround_init(void)
{
- static int io_workaround_inited;
-
if (io_workaround_inited)
return;
ppc_pci_io = iowa_pci_io;
- ppc_md.ioremap = iowa_ioremap;
- io_workaround_inited = 1;
+ io_workaround_inited = true;
}
/* Register new bus to support workaround */
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 2882419737b9..0a147daeb0f2 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -35,6 +35,7 @@
#include <asm/page.h>
#include <asm/prom.h>
#include <asm/io.h>
+#include <asm/io-workarounds.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
@@ -208,8 +209,8 @@ void __iomem * ioremap(phys_addr_t addr, unsigned long size)
pgprot_t prot = pgprot_noncached(PAGE_KERNEL);
void *caller = __builtin_return_address(0);
- if (ppc_md.ioremap)
- return ppc_md.ioremap(addr, size, prot, caller);
+ if (iowa_is_active())
+ return iowa_ioremap(addr, size, prot, caller);
return __ioremap_caller(addr, size, prot, caller);
}
@@ -218,8 +219,8 @@ void __iomem * ioremap_wc(phys_addr_t addr, unsigned long size)
pgprot_t prot = pgprot_noncached_wc(PAGE_KERNEL);
void *caller = __builtin_return_address(0);
- if (ppc_md.ioremap)
- return ppc_md.ioremap(addr, size, prot, caller);
+ if (iowa_is_active())
+ return iowa_ioremap(addr, size, prot, caller);
return __ioremap_caller(addr, size, prot, caller);
}
@@ -228,8 +229,8 @@ void __iomem *ioremap_coherent(phys_addr_t addr, unsigned long size)
pgprot_t prot = pgprot_cached(PAGE_KERNEL);
void *caller = __builtin_return_address(0);
- if (ppc_md.ioremap)
- return ppc_md.ioremap(addr, size, prot, caller);
+ if (iowa_is_active())
+ return iowa_ioremap(addr, size, prot, caller);
return __ioremap_caller(addr, size, prot, caller);
}
@@ -250,8 +251,8 @@ void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size,
*/
pte = pte_mkprivileged(pte);
- if (ppc_md.ioremap)
- return ppc_md.ioremap(addr, size, pte_pgprot(pte), caller);
+ if (iowa_is_active())
+ return iowa_ioremap(addr, size, pte_pgprot(pte), caller);
return __ioremap_caller(addr, size, pte_pgprot(pte), caller);
}
--
2.13.3
^ permalink raw reply related
* [PATCH v2 09/12] powerpc/mm: Move ioremap functions out of pgtable_32/64.c
From: Christophe Leroy @ 2019-08-20 14:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
hch
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1566309262.git.christophe.leroy@c-s.fr>
Create ioremap_32.c and ioremap_64.c and move respective ioremap
functions out of pgtable_32.c and pgtable_64.c
In the meantime, fix a few comments and changes a printk() to
pr_warn(). Also fix a few oversplitted lines.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/mm/Makefile | 2 +-
arch/powerpc/mm/ioremap_32.c | 104 +++++++++++++++++++++++++++++++++++
arch/powerpc/mm/ioremap_64.c | 123 +++++++++++++++++++++++++++++++++++++++++
arch/powerpc/mm/pgtable_32.c | 99 ---------------------------------
arch/powerpc/mm/pgtable_64.c | 128 +------------------------------------------
5 files changed, 229 insertions(+), 227 deletions(-)
create mode 100644 arch/powerpc/mm/ioremap_32.c
create mode 100644 arch/powerpc/mm/ioremap_64.c
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 29c682fe9144..5e147986400d 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -7,7 +7,7 @@ ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
obj-y := fault.o mem.o pgtable.o mmap.o \
init_$(BITS).o pgtable_$(BITS).o \
- pgtable-frag.o ioremap.o \
+ pgtable-frag.o ioremap.o ioremap_$(BITS).o \
init-common.o mmu_context.o drmem.o
obj-$(CONFIG_PPC_MMU_NOHASH) += nohash/
obj-$(CONFIG_PPC_BOOK3S_32) += book3s32/
diff --git a/arch/powerpc/mm/ioremap_32.c b/arch/powerpc/mm/ioremap_32.c
new file mode 100644
index 000000000000..fb43ba71aa54
--- /dev/null
+++ b/arch/powerpc/mm/ioremap_32.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+#include <mm/mmu_decl.h>
+
+void __iomem *ioremap_wt(phys_addr_t addr, unsigned long size)
+{
+ pgprot_t prot = pgprot_cached_wthru(PAGE_KERNEL);
+
+ return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wt);
+
+void __iomem *
+__ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *caller)
+{
+ unsigned long v, i;
+ phys_addr_t p;
+ int err;
+
+ /*
+ * Choose an address to map it to.
+ * Once the vmalloc system is running, we use it.
+ * Before then, we use space going down from IOREMAP_TOP
+ * (ioremap_bot records where we're up to).
+ */
+ p = addr & PAGE_MASK;
+ size = PAGE_ALIGN(addr + size) - p;
+
+ /*
+ * If the address lies within the first 16 MB, assume it's in ISA
+ * memory space
+ */
+ if (p < 16 * 1024 * 1024)
+ p += _ISA_MEM_BASE;
+
+#ifndef CONFIG_CRASH_DUMP
+ /*
+ * Don't allow anybody to remap normal RAM that we're using.
+ * mem_init() sets high_memory so only do the check after that.
+ */
+ if (slab_is_available() && p <= virt_to_phys(high_memory - 1) &&
+ page_is_ram(__phys_to_pfn(p))) {
+ pr_warn("%s(): phys addr 0x%llx is RAM lr %ps\n", __func__,
+ (unsigned long long)p, __builtin_return_address(0));
+ return NULL;
+ }
+#endif
+
+ if (size == 0)
+ return NULL;
+
+ /*
+ * Is it already mapped? Perhaps overlapped by a previous
+ * mapping.
+ */
+ v = p_block_mapped(p);
+ if (v)
+ goto out;
+
+ if (slab_is_available()) {
+ struct vm_struct *area;
+ area = get_vm_area_caller(size, VM_IOREMAP, caller);
+ if (area == 0)
+ return NULL;
+ area->phys_addr = p;
+ v = (unsigned long)area->addr;
+ } else {
+ v = (ioremap_bot -= size);
+ }
+
+ /*
+ * Should check if it is a candidate for a BAT mapping
+ */
+
+ err = 0;
+ for (i = 0; i < size && err == 0; i += PAGE_SIZE)
+ err = map_kernel_page(v + i, p + i, prot);
+ if (err) {
+ if (slab_is_available())
+ vunmap((void *)v);
+ return NULL;
+ }
+
+out:
+ return (void __iomem *)(v + ((unsigned long)addr & ~PAGE_MASK));
+}
+
+void iounmap(volatile void __iomem *addr)
+{
+ /*
+ * If mapped by BATs then there is nothing to do.
+ * Calling vfree() generates a benign warning.
+ */
+ if (v_block_mapped((unsigned long)addr))
+ return;
+
+ if (addr > high_memory && (unsigned long)addr < ioremap_bot)
+ vunmap((void *)(PAGE_MASK & (unsigned long)addr));
+}
+EXPORT_SYMBOL(iounmap);
diff --git a/arch/powerpc/mm/ioremap_64.c b/arch/powerpc/mm/ioremap_64.c
new file mode 100644
index 000000000000..57f3b096143c
--- /dev/null
+++ b/arch/powerpc/mm/ioremap_64.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+int __weak ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size,
+ pgprot_t prot, int nid)
+{
+ unsigned long i;
+
+ for (i = 0; i < size; i += PAGE_SIZE) {
+ int err = map_kernel_page(ea + i, pa + i, prot);
+ if (err) {
+ if (slab_is_available())
+ unmap_kernel_range(ea, size);
+ else
+ WARN_ON_ONCE(1); /* Should clean up */
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * Low level function to establish the page tables for an IO mapping
+ */
+void __iomem *__ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_t prot)
+{
+ /* We don't support the 4K PFN hack with ioremap */
+ if (pgprot_val(prot) & H_PAGE_4K_PFN)
+ return NULL;
+
+ if ((ea + size) >= (void *)IOREMAP_END) {
+ pr_warn("Outside the supported range\n");
+ return NULL;
+ }
+
+ WARN_ON(pa & ~PAGE_MASK);
+ WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
+ WARN_ON(size & ~PAGE_MASK);
+
+ if (ioremap_range((unsigned long)ea, pa, size, prot, NUMA_NO_NODE))
+ return NULL;
+
+ return (void __iomem *)ea;
+}
+EXPORT_SYMBOL(__ioremap_at);
+
+/**
+ * Low level function to tear down the page tables for an IO mapping. This is
+ * used for mappings that are manipulated manually, like partial unmapping of
+ * PCI IOs or ISA space.
+ */
+void __iounmap_at(void *ea, unsigned long size)
+{
+ WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
+ WARN_ON(size & ~PAGE_MASK);
+
+ unmap_kernel_range((unsigned long)ea, size);
+}
+EXPORT_SYMBOL(__iounmap_at);
+
+void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size,
+ pgprot_t prot, void *caller)
+{
+ phys_addr_t paligned;
+ void __iomem *ret;
+
+ /*
+ * Choose an address to map it to. Once the vmalloc system is running,
+ * we use it. Before that, we map using addresses going up from
+ * ioremap_bot. vmalloc will use the addresses from IOREMAP_BASE
+ * through ioremap_bot.
+ */
+ paligned = addr & PAGE_MASK;
+ size = PAGE_ALIGN(addr + size) - paligned;
+
+ if (size == 0 || paligned == 0)
+ return NULL;
+
+ if (slab_is_available()) {
+ struct vm_struct *area;
+
+ area = __get_vm_area_caller(size, VM_IOREMAP, ioremap_bot,
+ IOREMAP_END, caller);
+ if (area == NULL)
+ return NULL;
+
+ area->phys_addr = paligned;
+ ret = __ioremap_at(paligned, area->addr, size, prot);
+ } else {
+ ret = __ioremap_at(paligned, (void *)ioremap_bot, size, prot);
+ if (ret)
+ ioremap_bot += size;
+ }
+
+ if (ret)
+ ret += addr & ~PAGE_MASK;
+ return ret;
+}
+
+/*
+ * Unmap an IO region and remove it from vmalloc'd list.
+ * Access to IO memory should be serialized by driver.
+ */
+void iounmap(volatile void __iomem *token)
+{
+ void *addr;
+
+ if (!slab_is_available())
+ return;
+
+ addr = (void *)((unsigned long __force)PCI_FIX_ADDR(token) & PAGE_MASK);
+
+ if ((unsigned long)addr < ioremap_bot) {
+ pr_warn("Attempt to iounmap early bolted mapping at 0x%p\n", addr);
+ return;
+ }
+ vunmap(addr);
+}
+EXPORT_SYMBOL(iounmap);
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index daab57c78b22..6223d4c17301 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -27,7 +27,6 @@
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/fixmap.h>
-#include <asm/io.h>
#include <asm/setup.h>
#include <asm/sections.h>
@@ -35,104 +34,6 @@
extern char etext[], _stext[], _sinittext[], _einittext[];
-void __iomem *
-ioremap_wt(phys_addr_t addr, unsigned long size)
-{
- pgprot_t prot = pgprot_cached_wthru(PAGE_KERNEL);
-
- return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
-}
-EXPORT_SYMBOL(ioremap_wt);
-
-void __iomem *
-__ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *caller)
-{
- unsigned long v, i;
- phys_addr_t p;
- int err;
-
- /*
- * Choose an address to map it to.
- * Once the vmalloc system is running, we use it.
- * Before then, we use space going down from IOREMAP_TOP
- * (ioremap_bot records where we're up to).
- */
- p = addr & PAGE_MASK;
- size = PAGE_ALIGN(addr + size) - p;
-
- /*
- * If the address lies within the first 16 MB, assume it's in ISA
- * memory space
- */
- if (p < 16*1024*1024)
- p += _ISA_MEM_BASE;
-
-#ifndef CONFIG_CRASH_DUMP
- /*
- * Don't allow anybody to remap normal RAM that we're using.
- * mem_init() sets high_memory so only do the check after that.
- */
- if (slab_is_available() && p <= virt_to_phys(high_memory - 1) &&
- page_is_ram(__phys_to_pfn(p))) {
- pr_warn("%s(): phys addr 0x%llx is RAM lr %ps\n", __func__,
- (unsigned long long)p, __builtin_return_address(0));
- return NULL;
- }
-#endif
-
- if (size == 0)
- return NULL;
-
- /*
- * Is it already mapped? Perhaps overlapped by a previous
- * mapping.
- */
- v = p_block_mapped(p);
- if (v)
- goto out;
-
- if (slab_is_available()) {
- struct vm_struct *area;
- area = get_vm_area_caller(size, VM_IOREMAP, caller);
- if (area == 0)
- return NULL;
- area->phys_addr = p;
- v = (unsigned long) area->addr;
- } else {
- v = (ioremap_bot -= size);
- }
-
- /*
- * Should check if it is a candidate for a BAT mapping
- */
-
- err = 0;
- for (i = 0; i < size && err == 0; i += PAGE_SIZE)
- err = map_kernel_page(v + i, p + i, prot);
- if (err) {
- if (slab_is_available())
- vunmap((void *)v);
- return NULL;
- }
-
-out:
- return (void __iomem *) (v + ((unsigned long)addr & ~PAGE_MASK));
-}
-
-void iounmap(volatile void __iomem *addr)
-{
- /*
- * If mapped by BATs then there is nothing to do.
- * Calling vfree() generates a benign warning.
- */
- if (v_block_mapped((unsigned long)addr))
- return;
-
- if (addr > high_memory && (unsigned long) addr < ioremap_bot)
- vunmap((void *) (PAGE_MASK & (unsigned long)addr));
-}
-EXPORT_SYMBOL(iounmap);
-
static void __init *early_alloc_pgtable(unsigned long size)
{
void *ptr = memblock_alloc(size, size);
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index d865e053052d..e78832dce7bb 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-or-later
/*
- * This file contains ioremap and related functions for 64-bit machines.
+ * This file contains pgtable related functions for 64-bit machines.
*
* Derived from arch/ppc64/mm/init.c
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -34,7 +34,6 @@
#include <asm/pgalloc.h>
#include <asm/page.h>
#include <asm/prom.h>
-#include <asm/io.h>
#include <asm/mmu_context.h>
#include <asm/pgtable.h>
#include <asm/mmu.h>
@@ -100,131 +99,6 @@ unsigned long __pte_frag_size_shift;
EXPORT_SYMBOL(__pte_frag_size_shift);
#endif
-int __weak ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot, int nid)
-{
- unsigned long i;
-
- for (i = 0; i < size; i += PAGE_SIZE) {
- int err = map_kernel_page(ea + i, pa + i, prot);
- if (err) {
- if (slab_is_available())
- unmap_kernel_range(ea, size);
- else
- WARN_ON_ONCE(1); /* Should clean up */
- return err;
- }
- }
-
- return 0;
-}
-
-/**
- * __ioremap_at - Low level function to establish the page tables
- * for an IO mapping
- */
-void __iomem *__ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_t prot)
-{
- /* We don't support the 4K PFN hack with ioremap */
- if (pgprot_val(prot) & H_PAGE_4K_PFN)
- return NULL;
-
- if ((ea + size) >= (void *)IOREMAP_END) {
- pr_warn("Outside the supported range\n");
- return NULL;
- }
-
- WARN_ON(pa & ~PAGE_MASK);
- WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
- WARN_ON(size & ~PAGE_MASK);
-
- if (ioremap_range((unsigned long)ea, pa, size, prot, NUMA_NO_NODE))
- return NULL;
-
- return (void __iomem *)ea;
-}
-
-/**
- * __iounmap_from - Low level function to tear down the page tables
- * for an IO mapping. This is used for mappings that
- * are manipulated manually, like partial unmapping of
- * PCI IOs or ISA space.
- */
-void __iounmap_at(void *ea, unsigned long size)
-{
- WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
- WARN_ON(size & ~PAGE_MASK);
-
- unmap_kernel_range((unsigned long)ea, size);
-}
-
-void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size,
- pgprot_t prot, void *caller)
-{
- phys_addr_t paligned;
- void __iomem *ret;
-
- /*
- * Choose an address to map it to.
- * Once the imalloc system is running, we use it.
- * Before that, we map using addresses going
- * up from ioremap_bot. imalloc will use
- * the addresses from ioremap_bot through
- * IMALLOC_END
- *
- */
- paligned = addr & PAGE_MASK;
- size = PAGE_ALIGN(addr + size) - paligned;
-
- if ((size == 0) || (paligned == 0))
- return NULL;
-
- if (slab_is_available()) {
- struct vm_struct *area;
-
- area = __get_vm_area_caller(size, VM_IOREMAP,
- ioremap_bot, IOREMAP_END,
- caller);
- if (area == NULL)
- return NULL;
-
- area->phys_addr = paligned;
- ret = __ioremap_at(paligned, area->addr, size, prot);
- } else {
- ret = __ioremap_at(paligned, (void *)ioremap_bot, size, prot);
- if (ret)
- ioremap_bot += size;
- }
-
- if (ret)
- ret += addr & ~PAGE_MASK;
- return ret;
-}
-
-/*
- * Unmap an IO region and remove it from imalloc'd list.
- * Access to IO memory should be serialized by driver.
- */
-void iounmap(volatile void __iomem *token)
-{
- void *addr;
-
- if (!slab_is_available())
- return;
-
- addr = (void *) ((unsigned long __force)
- PCI_FIX_ADDR(token) & PAGE_MASK);
- if ((unsigned long)addr < ioremap_bot) {
- printk(KERN_WARNING "Attempt to iounmap early bolted mapping"
- " at 0x%p\n", addr);
- return;
- }
- vunmap(addr);
-}
-
-EXPORT_SYMBOL(__ioremap_at);
-EXPORT_SYMBOL(iounmap);
-EXPORT_SYMBOL(__iounmap_at);
-
#ifndef __PAGETABLE_PUD_FOLDED
/* 4 level page table */
struct page *pgd_page(pgd_t pgd)
--
2.13.3
^ permalink raw reply related
* [PATCH v2 10/12] powerpc/mm: refactor ioremap_range() and use ioremap_page_range()
From: Christophe Leroy @ 2019-08-20 14:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
hch
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1566309262.git.christophe.leroy@c-s.fr>
book3s64's ioremap_range() is almost same as fallback ioremap_range(),
except that it calls radix__ioremap_range() when radix is enabled.
radix__ioremap_range() is also very similar to the other ones, expect
that it calls ioremap_page_range when slab is available.
PPC32 __ioremap_caller() have a loop doing the same thing as
ioremap_range() so use it on PPC32 as well.
Lets keep only one version of ioremap_range() which calls
ioremap_page_range() on all platforms when slab is available.
At the same time, drop the nid parameter which is not used.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/book3s/64/radix.h | 3 ---
arch/powerpc/include/asm/io.h | 2 ++
arch/powerpc/mm/book3s64/pgtable.c | 21 ---------------------
arch/powerpc/mm/book3s64/radix_pgtable.c | 20 --------------------
arch/powerpc/mm/ioremap.c | 24 ++++++++++++++++++++++++
arch/powerpc/mm/ioremap_32.c | 6 ++----
arch/powerpc/mm/ioremap_64.c | 21 +--------------------
7 files changed, 29 insertions(+), 68 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index e04a839cb5b9..574eca33f893 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -266,9 +266,6 @@ extern void radix__vmemmap_remove_mapping(unsigned long start,
extern int radix__map_kernel_page(unsigned long ea, unsigned long pa,
pgprot_t flags, unsigned int psz);
-extern int radix__ioremap_range(unsigned long ea, phys_addr_t pa,
- unsigned long size, pgprot_t prot, int nid);
-
static inline unsigned long radix__get_tree_size(void)
{
unsigned long rts_field;
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 8e65ba59f06a..8e00d95f9600 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -722,6 +722,8 @@ void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size);
extern void iounmap(volatile void __iomem *addr);
+int ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot);
+
extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size,
pgprot_t prot, void *caller);
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 7d0e0d0d22c4..4c8bed856533 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -446,24 +446,3 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
return true;
}
-
-int ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot, int nid)
-{
- unsigned long i;
-
- if (radix_enabled())
- return radix__ioremap_range(ea, pa, size, prot, nid);
-
- for (i = 0; i < size; i += PAGE_SIZE) {
- int err = map_kernel_page(ea + i, pa + i, prot);
- if (err) {
- if (slab_is_available())
- unmap_kernel_range(ea, size);
- else
- WARN_ON_ONCE(1); /* Should clean up */
- return err;
- }
- }
-
- return 0;
-}
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index b4ca9e95e678..01d47a763a8d 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -1218,26 +1218,6 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
return 1;
}
-int radix__ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size,
- pgprot_t prot, int nid)
-{
- if (likely(slab_is_available())) {
- int err = ioremap_page_range(ea, ea + size, pa, prot);
- if (err)
- unmap_kernel_range(ea, size);
- return err;
- } else {
- unsigned long i;
-
- for (i = 0; i < size; i += PAGE_SIZE) {
- int err = map_kernel_page(ea + i, pa + i, prot);
- if (WARN_ON_ONCE(err)) /* Should clean up */
- return err;
- }
- return 0;
- }
-}
-
int __init arch_ioremap_p4d_supported(void)
{
return 0;
diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c
index eaf5f8a4a63f..50ee6544d0b7 100644
--- a/arch/powerpc/mm/ioremap.c
+++ b/arch/powerpc/mm/ioremap.c
@@ -1,6 +1,8 @@
// SPDX-License-Identifier: GPL-2.0-or-later
#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
#include <asm/io-workarounds.h>
unsigned long ioremap_bot;
@@ -56,3 +58,25 @@ void __iomem *ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long f
return __ioremap_caller(addr, size, pte_pgprot(pte), caller);
}
EXPORT_SYMBOL(ioremap_prot);
+
+int ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot)
+{
+ unsigned long i;
+
+ if (slab_is_available()) {
+ int err = ioremap_page_range(ea, ea + size, pa, prot);
+
+ if (err)
+ unmap_kernel_range(ea, size);
+ return err;
+ }
+
+ for (i = 0; i < size; i += PAGE_SIZE) {
+ int err = map_kernel_page(ea + i, pa + i, prot);
+
+ if (WARN_ON_ONCE(err)) /* Should clean up */
+ return err;
+ }
+
+ return 0;
+}
diff --git a/arch/powerpc/mm/ioremap_32.c b/arch/powerpc/mm/ioremap_32.c
index fb43ba71aa54..85b90a62e084 100644
--- a/arch/powerpc/mm/ioremap_32.c
+++ b/arch/powerpc/mm/ioremap_32.c
@@ -17,7 +17,7 @@ EXPORT_SYMBOL(ioremap_wt);
void __iomem *
__ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *caller)
{
- unsigned long v, i;
+ unsigned long v;
phys_addr_t p;
int err;
@@ -76,9 +76,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call
* Should check if it is a candidate for a BAT mapping
*/
- err = 0;
- for (i = 0; i < size && err == 0; i += PAGE_SIZE)
- err = map_kernel_page(v + i, p + i, prot);
+ err = ioremap_range((unsigned long)v, p, size, prot);
if (err) {
if (slab_is_available())
vunmap((void *)v);
diff --git a/arch/powerpc/mm/ioremap_64.c b/arch/powerpc/mm/ioremap_64.c
index 57f3b096143c..d132ce1e538d 100644
--- a/arch/powerpc/mm/ioremap_64.c
+++ b/arch/powerpc/mm/ioremap_64.c
@@ -4,25 +4,6 @@
#include <linux/slab.h>
#include <linux/vmalloc.h>
-int __weak ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size,
- pgprot_t prot, int nid)
-{
- unsigned long i;
-
- for (i = 0; i < size; i += PAGE_SIZE) {
- int err = map_kernel_page(ea + i, pa + i, prot);
- if (err) {
- if (slab_is_available())
- unmap_kernel_range(ea, size);
- else
- WARN_ON_ONCE(1); /* Should clean up */
- return err;
- }
- }
-
- return 0;
-}
-
/**
* Low level function to establish the page tables for an IO mapping
*/
@@ -41,7 +22,7 @@ void __iomem *__ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_
WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
WARN_ON(size & ~PAGE_MASK);
- if (ioremap_range((unsigned long)ea, pa, size, prot, NUMA_NO_NODE))
+ if (ioremap_range((unsigned long)ea, pa, size, prot))
return NULL;
return (void __iomem *)ea;
--
2.13.3
^ permalink raw reply related
* [PATCH v2 11/12] powerpc/mm: refactor ioremap vm area setup.
From: Christophe Leroy @ 2019-08-20 14:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
hch
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1566309262.git.christophe.leroy@c-s.fr>
PPC32 and PPC64 are doing the same once SLAB is available.
Create a do_ioremap() function that calls get_vm_area and
do the mapping.
For PPC64, we add the 4K PFN hack sanity check to __ioremap_caller()
in order to avoid using __ioremap_at(). Other checks in __ioremap_at()
are irrelevant for __ioremap_caller().
On PPC64, VM area is allocated in the range [ioremap_bot ; IOREMAP_END]
On PPC32, VM area is allocated in the range [VMALLOC_START ; VMALLOC_END]
Lets define IOREMAP_START is ioremap_bot for PPC64, and alias
IOREMAP_START/END to VMALLOC_START/END on PPC32
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/book3s/32/pgtable.h | 4 ++++
arch/powerpc/include/asm/book3s/64/pgtable.h | 1 +
arch/powerpc/include/asm/io.h | 2 ++
arch/powerpc/include/asm/nohash/32/pgtable.h | 4 ++++
arch/powerpc/include/asm/nohash/64/pgtable.h | 1 +
arch/powerpc/mm/ioremap.c | 20 ++++++++++++++++++++
arch/powerpc/mm/ioremap_32.c | 15 ++++-----------
arch/powerpc/mm/ioremap_64.c | 17 +++++++----------
8 files changed, 43 insertions(+), 21 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index aa1bc5f8da90..331a29a501a1 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -165,6 +165,10 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
#define IOREMAP_TOP KVIRT_TOP
#endif
+/* PPC32 shares vmalloc area with ioremap */
+#define IOREMAP_START VMALLOC_START
+#define IOREMAP_END VMALLOC_END
+
/*
* Just any arbitrary offset to the start of the vmalloc VM area: the
* current 16MB value just means that there will be a 64MB "hole" after the
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 11819e3c755e..9eedb4aa6600 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -316,6 +316,7 @@ extern unsigned long pci_io_base;
#define PHB_IO_BASE (ISA_IO_END)
#define PHB_IO_END (KERN_IO_START + FULL_IO_SIZE)
#define IOREMAP_BASE (PHB_IO_END)
+#define IOREMAP_START (ioremap_bot)
#define IOREMAP_END (KERN_IO_END)
/* Advertise special mapping type for AGP */
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 8e00d95f9600..dc529ea0fffa 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -723,6 +723,8 @@ void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size);
extern void iounmap(volatile void __iomem *addr);
int ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot);
+void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
+ pgprot_t prot, void *caller);
extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size,
pgprot_t prot, void *caller);
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 7ce2a7c9fade..3e1a4c1e40f0 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -93,6 +93,10 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
#define IOREMAP_TOP KVIRT_TOP
#endif
+/* PPC32 shares vmalloc area with ioremap */
+#define IOREMAP_START VMALLOC_START
+#define IOREMAP_END VMALLOC_END
+
/*
* Just any arbitrary offset to the start of the vmalloc VM area: the
* current 16MB value just means that there will be a 64MB "hole" after the
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index b9f66cf15c31..9a33b8bd842d 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -53,6 +53,7 @@
#define PHB_IO_BASE (ISA_IO_END)
#define PHB_IO_END (KERN_IO_START + FULL_IO_SIZE)
#define IOREMAP_BASE (PHB_IO_END)
+#define IOREMAP_START (ioremap_bot)
#define IOREMAP_END (KERN_VIRT_START + KERN_VIRT_SIZE)
diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c
index 50ee6544d0b7..57630325846c 100644
--- a/arch/powerpc/mm/ioremap.c
+++ b/arch/powerpc/mm/ioremap.c
@@ -80,3 +80,23 @@ int ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t
return 0;
}
+
+void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
+ pgprot_t prot, void *caller)
+{
+ struct vm_struct *area;
+ int ret;
+
+ area = __get_vm_area_caller(size, VM_IOREMAP, IOREMAP_START, IOREMAP_END, caller);
+ if (area == NULL)
+ return NULL;
+
+ area->phys_addr = pa;
+ ret = ioremap_range((unsigned long)area->addr, pa, size, prot);
+ if (!ret)
+ return (void __iomem *)area->addr + offset;
+
+ free_vm_area(area);
+
+ return NULL;
+}
diff --git a/arch/powerpc/mm/ioremap_32.c b/arch/powerpc/mm/ioremap_32.c
index 85b90a62e084..fcf343dbf2bf 100644
--- a/arch/powerpc/mm/ioremap_32.c
+++ b/arch/powerpc/mm/ioremap_32.c
@@ -18,7 +18,7 @@ void __iomem *
__ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *caller)
{
unsigned long v;
- phys_addr_t p;
+ phys_addr_t p, offset;
int err;
/*
@@ -28,6 +28,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call
* (ioremap_bot records where we're up to).
*/
p = addr & PAGE_MASK;
+ offset = addr & ~PAGE_MASK;
size = PAGE_ALIGN(addr + size) - p;
/*
@@ -62,12 +63,7 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call
goto out;
if (slab_is_available()) {
- struct vm_struct *area;
- area = get_vm_area_caller(size, VM_IOREMAP, caller);
- if (area == 0)
- return NULL;
- area->phys_addr = p;
- v = (unsigned long)area->addr;
+ return do_ioremap(p, offset, size, prot, caller);
} else {
v = (ioremap_bot -= size);
}
@@ -77,11 +73,8 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call
*/
err = ioremap_range((unsigned long)v, p, size, prot);
- if (err) {
- if (slab_is_available())
- vunmap((void *)v);
+ if (err)
return NULL;
- }
out:
return (void __iomem *)(v + ((unsigned long)addr & ~PAGE_MASK));
diff --git a/arch/powerpc/mm/ioremap_64.c b/arch/powerpc/mm/ioremap_64.c
index d132ce1e538d..e37b68b7f0e8 100644
--- a/arch/powerpc/mm/ioremap_64.c
+++ b/arch/powerpc/mm/ioremap_64.c
@@ -46,9 +46,13 @@ EXPORT_SYMBOL(__iounmap_at);
void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size,
pgprot_t prot, void *caller)
{
- phys_addr_t paligned;
+ phys_addr_t paligned, offset;
void __iomem *ret;
+ /* We don't support the 4K PFN hack with ioremap */
+ if (pgprot_val(prot) & H_PAGE_4K_PFN)
+ return NULL;
+
/*
* Choose an address to map it to. Once the vmalloc system is running,
* we use it. Before that, we map using addresses going up from
@@ -56,21 +60,14 @@ void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size,
* through ioremap_bot.
*/
paligned = addr & PAGE_MASK;
+ offset = addr & ~PAGE_MASK;
size = PAGE_ALIGN(addr + size) - paligned;
if (size == 0 || paligned == 0)
return NULL;
if (slab_is_available()) {
- struct vm_struct *area;
-
- area = __get_vm_area_caller(size, VM_IOREMAP, ioremap_bot,
- IOREMAP_END, caller);
- if (area == NULL)
- return NULL;
-
- area->phys_addr = paligned;
- ret = __ioremap_at(paligned, area->addr, size, prot);
+ return do_ioremap(paligned, offset, size, prot, caller);
} else {
ret = __ioremap_at(paligned, (void *)ioremap_bot, size, prot);
if (ret)
--
2.13.3
^ permalink raw reply related
* [PATCH v2 12/12] powerpc/mm: split out early ioremap path.
From: Christophe Leroy @ 2019-08-20 14:07 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, npiggin,
hch
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1566309262.git.christophe.leroy@c-s.fr>
ioremap does things differently depending on whether
SLAB is available or not at different levels.
Try to separate the early path from the beginning.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/io.h | 3 ++-
arch/powerpc/mm/ioremap.c | 17 +++++++----------
arch/powerpc/mm/ioremap_32.c | 13 +++++--------
arch/powerpc/mm/ioremap_64.c | 30 +++++++++++++++++++++---------
4 files changed, 35 insertions(+), 28 deletions(-)
diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index dc529ea0fffa..a63ec938636d 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -722,7 +722,8 @@ void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size);
extern void iounmap(volatile void __iomem *addr);
-int ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot);
+int early_ioremap_range(unsigned long ea, phys_addr_t pa,
+ unsigned long size, pgprot_t prot);
void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
pgprot_t prot, void *caller);
diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c
index 57630325846c..fc669643ce6a 100644
--- a/arch/powerpc/mm/ioremap.c
+++ b/arch/powerpc/mm/ioremap.c
@@ -59,18 +59,11 @@ void __iomem *ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long f
}
EXPORT_SYMBOL(ioremap_prot);
-int ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot)
+int early_ioremap_range(unsigned long ea, phys_addr_t pa,
+ unsigned long size, pgprot_t prot)
{
unsigned long i;
- if (slab_is_available()) {
- int err = ioremap_page_range(ea, ea + size, pa, prot);
-
- if (err)
- unmap_kernel_range(ea, size);
- return err;
- }
-
for (i = 0; i < size; i += PAGE_SIZE) {
int err = map_kernel_page(ea + i, pa + i, prot);
@@ -86,16 +79,20 @@ void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
{
struct vm_struct *area;
int ret;
+ unsigned long va;
area = __get_vm_area_caller(size, VM_IOREMAP, IOREMAP_START, IOREMAP_END, caller);
if (area == NULL)
return NULL;
area->phys_addr = pa;
- ret = ioremap_range((unsigned long)area->addr, pa, size, prot);
+ va = (unsigned long)area->addr;
+
+ ret = ioremap_page_range(va, va + size, pa, prot);
if (!ret)
return (void __iomem *)area->addr + offset;
+ unmap_kernel_range(va, size);
free_vm_area(area);
return NULL;
diff --git a/arch/powerpc/mm/ioremap_32.c b/arch/powerpc/mm/ioremap_32.c
index fcf343dbf2bf..f36121f25243 100644
--- a/arch/powerpc/mm/ioremap_32.c
+++ b/arch/powerpc/mm/ioremap_32.c
@@ -60,24 +60,21 @@ __ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *call
*/
v = p_block_mapped(p);
if (v)
- goto out;
+ return (void __iomem *)v + offset;
- if (slab_is_available()) {
+ if (slab_is_available())
return do_ioremap(p, offset, size, prot, caller);
- } else {
- v = (ioremap_bot -= size);
- }
/*
* Should check if it is a candidate for a BAT mapping
*/
- err = ioremap_range((unsigned long)v, p, size, prot);
+ err = early_ioremap_range(ioremap_bot - size, p, size, prot);
if (err)
return NULL;
+ ioremap_bot -= size;
-out:
- return (void __iomem *)(v + ((unsigned long)addr & ~PAGE_MASK));
+ return (void __iomem *)ioremap_bot + offset;
}
void iounmap(volatile void __iomem *addr)
diff --git a/arch/powerpc/mm/ioremap_64.c b/arch/powerpc/mm/ioremap_64.c
index e37b68b7f0e8..fd29e51700cd 100644
--- a/arch/powerpc/mm/ioremap_64.c
+++ b/arch/powerpc/mm/ioremap_64.c
@@ -9,6 +9,9 @@
*/
void __iomem *__ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_t prot)
{
+ int ret;
+ unsigned long va = (unsigned long)ea;
+
/* We don't support the 4K PFN hack with ioremap */
if (pgprot_val(prot) & H_PAGE_4K_PFN)
return NULL;
@@ -22,7 +25,15 @@ void __iomem *__ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_
WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
WARN_ON(size & ~PAGE_MASK);
- if (ioremap_range((unsigned long)ea, pa, size, prot))
+ if (slab_is_available()) {
+ ret = ioremap_page_range(va, va + size, pa, prot);
+ if (ret)
+ unmap_kernel_range(va, size);
+ } else {
+ ret = early_ioremap_range(va, pa, size, prot);
+ }
+
+ if (ret)
return NULL;
return (void __iomem *)ea;
@@ -48,6 +59,7 @@ void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size,
{
phys_addr_t paligned, offset;
void __iomem *ret;
+ int err;
/* We don't support the 4K PFN hack with ioremap */
if (pgprot_val(prot) & H_PAGE_4K_PFN)
@@ -66,16 +78,16 @@ void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size,
if (size == 0 || paligned == 0)
return NULL;
- if (slab_is_available()) {
+ if (slab_is_available())
return do_ioremap(paligned, offset, size, prot, caller);
- } else {
- ret = __ioremap_at(paligned, (void *)ioremap_bot, size, prot);
- if (ret)
- ioremap_bot += size;
- }
- if (ret)
- ret += addr & ~PAGE_MASK;
+ err = early_ioremap_range(ioremap_bot, paligned, size, prot);
+ if (err)
+ return NULL;
+
+ ret = (void __iomem *)ioremap_bot + offset;
+ ioremap_bot += size;
+
return ret;
}
--
2.13.3
^ permalink raw reply related
* [PATCH v4 1/3] powerpc: rewrite LOAD_REG_IMMEDIATE() as an intelligent macro
From: Christophe Leroy @ 2019-08-20 14:34 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, segher
Cc: linuxppc-dev, linux-kernel
Today LOAD_REG_IMMEDIATE() is a basic #define which loads all
parts on a value into a register, including the parts that are NUL.
This means always 2 instructions on PPC32 and always 5 instructions
on PPC64. And those instructions cannot run in parallele as they are
updating the same register.
Ex: LOAD_REG_IMMEDIATE(r1,THREAD_SIZE) in head_64.S results in:
3c 20 00 00 lis r1,0
60 21 00 00 ori r1,r1,0
78 21 07 c6 rldicr r1,r1,32,31
64 21 00 00 oris r1,r1,0
60 21 40 00 ori r1,r1,16384
Rewrite LOAD_REG_IMMEDIATE() with GAS macro in order to skip
the parts that are NUL.
Rename existing LOAD_REG_IMMEDIATE() as LOAD_REG_IMMEDIATE_SYM()
and use that one for loading value of symbols which are not known
at compile time.
Now LOAD_REG_IMMEDIATE(r1,THREAD_SIZE) in head_64.S results in:
38 20 40 00 li r1,16384
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v2: Fixed the test from (\x) & 0xffffffff to (\x) >= 0x80000000 || (\x) < -0x80000000 in __LOAD_REG_IMMEDIATE()
v3: Replaced rldicr by sldi as suggested by Segher for readability
v4: Changed oris by ori for the LSB.
---
arch/powerpc/include/asm/ppc_asm.h | 42 +++++++++++++++++++++++++++++++-----
arch/powerpc/kernel/exceptions-64e.S | 10 ++++-----
arch/powerpc/kernel/head_64.S | 2 +-
3 files changed, 43 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index e0637730a8e7..20a00209c965 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -311,13 +311,43 @@ GLUE(.,name):
addis reg,reg,(name - 0b)@ha; \
addi reg,reg,(name - 0b)@l;
-#ifdef __powerpc64__
-#ifdef HAVE_AS_ATHIGH
+#if defined(__powerpc64__) && defined(HAVE_AS_ATHIGH)
#define __AS_ATHIGH high
#else
#define __AS_ATHIGH h
#endif
-#define LOAD_REG_IMMEDIATE(reg,expr) \
+
+.macro __LOAD_REG_IMMEDIATE_32 r, x
+ .if (\x) >= 0x8000 || (\x) < -0x8000
+ lis \r, (\x)@__AS_ATHIGH
+ .if (\x) & 0xffff != 0
+ ori \r, \r, (\x)@l
+ .endif
+ .else
+ li \r, (\x)@l
+ .endif
+.endm
+
+.macro __LOAD_REG_IMMEDIATE r, x
+ .if (\x) >= 0x80000000 || (\x) < -0x80000000
+ __LOAD_REG_IMMEDIATE_32 \r, (\x) >> 32
+ sldi \r, \r, 32
+ .if (\x) & 0xffff0000 != 0
+ oris \r, \r, (\x)@__AS_ATHIGH
+ .endif
+ .if (\x) & 0xffff != 0
+ ori \r, \r, (\x)@l
+ .endif
+ .else
+ __LOAD_REG_IMMEDIATE_32 \r, \x
+ .endif
+.endm
+
+#ifdef __powerpc64__
+
+#define LOAD_REG_IMMEDIATE(reg, expr) __LOAD_REG_IMMEDIATE reg, expr
+
+#define LOAD_REG_IMMEDIATE_SYM(reg,expr) \
lis reg,(expr)@highest; \
ori reg,reg,(expr)@higher; \
rldicr reg,reg,32,31; \
@@ -335,11 +365,13 @@ GLUE(.,name):
#else /* 32-bit */
-#define LOAD_REG_IMMEDIATE(reg,expr) \
+#define LOAD_REG_IMMEDIATE(reg, expr) __LOAD_REG_IMMEDIATE_32 reg, expr
+
+#define LOAD_REG_IMMEDIATE_SYM(reg,expr) \
lis reg,(expr)@ha; \
addi reg,reg,(expr)@l;
-#define LOAD_REG_ADDR(reg,name) LOAD_REG_IMMEDIATE(reg, name)
+#define LOAD_REG_ADDR(reg,name) LOAD_REG_IMMEDIATE_SYM(reg, name)
#define LOAD_REG_ADDRBASE(reg, name) lis reg,name@ha
#define ADDROFF(name) name@l
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 1cfb3da4a84a..898aae6da167 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -751,8 +751,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
ld r14,interrupt_base_book3e@got(r15)
ld r15,__end_interrupts@got(r15)
#else
- LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
- LOAD_REG_IMMEDIATE(r15,__end_interrupts)
+ LOAD_REG_IMMEDIATE_SYM(r14,interrupt_base_book3e)
+ LOAD_REG_IMMEDIATE_SYM(r15,__end_interrupts)
#endif
cmpld cr0,r10,r14
cmpld cr1,r10,r15
@@ -821,8 +821,8 @@ kernel_dbg_exc:
ld r14,interrupt_base_book3e@got(r15)
ld r15,__end_interrupts@got(r15)
#else
- LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
- LOAD_REG_IMMEDIATE(r15,__end_interrupts)
+ LOAD_REG_IMMEDIATE_SYM(r14,interrupt_base_book3e)
+ LOAD_REG_IMMEDIATE_SYM(r15,__end_interrupts)
#endif
cmpld cr0,r10,r14
cmpld cr1,r10,r15
@@ -1449,7 +1449,7 @@ a2_tlbinit_code_start:
a2_tlbinit_after_linear_map:
/* Now we branch the new virtual address mapped by this entry */
- LOAD_REG_IMMEDIATE(r3,1f)
+ LOAD_REG_IMMEDIATE_SYM(r3,1f)
mtctr r3
bctr
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 91d297e696dd..1fd44761e997 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -635,7 +635,7 @@ __after_prom_start:
sub r5,r5,r11
#else
/* just copy interrupts */
- LOAD_REG_IMMEDIATE(r5, FIXED_SYMBOL_ABS_ADDR(__end_interrupts))
+ LOAD_REG_IMMEDIATE_SYM(r5, FIXED_SYMBOL_ABS_ADDR(__end_interrupts))
#endif
b 5f
3:
--
2.13.3
^ permalink raw reply related
* [PATCH v4 2/3] powerpc/32: replace LOAD_MSR_KERNEL() by LOAD_REG_IMMEDIATE()
From: Christophe Leroy @ 2019-08-20 14:34 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, segher
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <d60ce8dd3a383c7adbfc322bf1d53d81724a6000.1566311636.git.christophe.leroy@c-s.fr>
LOAD_MSR_KERNEL() and LOAD_REG_IMMEDIATE() are doing the same thing
in the same way. Drop LOAD_MSR_KERNEL()
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v2: no change
v3: no change
v4: no change
---
arch/powerpc/kernel/entry_32.S | 18 +++++++++---------
arch/powerpc/kernel/head_32.h | 21 ++++-----------------
2 files changed, 13 insertions(+), 26 deletions(-)
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 54fab22c9a43..972b05504a0a 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -230,7 +230,7 @@ transfer_to_handler_cont:
*/
lis r12,reenable_mmu@h
ori r12,r12,reenable_mmu@l
- LOAD_MSR_KERNEL(r0, MSR_KERNEL)
+ LOAD_REG_IMMEDIATE(r0, MSR_KERNEL)
mtspr SPRN_SRR0,r12
mtspr SPRN_SRR1,r0
SYNC
@@ -304,7 +304,7 @@ stack_ovf:
addi r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
lis r9,StackOverflow@ha
addi r9,r9,StackOverflow@l
- LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)
#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
mtspr SPRN_NRI, r0
#endif
@@ -324,7 +324,7 @@ trace_syscall_entry_irq_off:
bl trace_hardirqs_on
/* Now enable for real */
- LOAD_MSR_KERNEL(r10, MSR_KERNEL | MSR_EE)
+ LOAD_REG_IMMEDIATE(r10, MSR_KERNEL | MSR_EE)
mtmsr r10
REST_GPR(0, r1)
@@ -394,7 +394,7 @@ ret_from_syscall:
#endif
mr r6,r3
/* disable interrupts so current_thread_info()->flags can't change */
- LOAD_MSR_KERNEL(r10,MSR_KERNEL) /* doesn't include MSR_EE */
+ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL) /* doesn't include MSR_EE */
/* Note: We don't bother telling lockdep about it */
SYNC
MTMSRD(r10)
@@ -824,7 +824,7 @@ ret_from_except:
* can't change between when we test it and when we return
* from the interrupt. */
/* Note: We don't bother telling lockdep about it */
- LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)
SYNC /* Some chip revs have problems here... */
MTMSRD(r10) /* disable interrupts */
@@ -991,7 +991,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
* can restart the exception exit path at the label
* exc_exit_restart below. -- paulus
*/
- LOAD_MSR_KERNEL(r10,MSR_KERNEL & ~MSR_RI)
+ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL & ~MSR_RI)
SYNC
MTMSRD(r10) /* clear the RI bit */
.globl exc_exit_restart
@@ -1066,7 +1066,7 @@ exc_exit_restart_end:
REST_NVGPRS(r1); \
lwz r3,_MSR(r1); \
andi. r3,r3,MSR_PR; \
- LOAD_MSR_KERNEL(r10,MSR_KERNEL); \
+ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL); \
bne user_exc_return; \
lwz r0,GPR0(r1); \
lwz r2,GPR2(r1); \
@@ -1236,7 +1236,7 @@ recheck:
* neither. Those disable/enable cycles used to peek at
* TI_FLAGS aren't advertised.
*/
- LOAD_MSR_KERNEL(r10,MSR_KERNEL)
+ LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)
SYNC
MTMSRD(r10) /* disable interrupts */
lwz r9,TI_FLAGS(r2)
@@ -1329,7 +1329,7 @@ _GLOBAL(enter_rtas)
lwz r4,RTASBASE(r4)
mfmsr r9
stw r9,8(r1)
- LOAD_MSR_KERNEL(r0,MSR_KERNEL)
+ LOAD_REG_IMMEDIATE(r0,MSR_KERNEL)
SYNC /* disable interrupts so SRR0/1 */
MTMSRD(r0) /* don't get trashed */
li r9,MSR_KERNEL & ~(MSR_IR|MSR_DR)
diff --git a/arch/powerpc/kernel/head_32.h b/arch/powerpc/kernel/head_32.h
index 4a692553651f..8abc7783dbe5 100644
--- a/arch/powerpc/kernel/head_32.h
+++ b/arch/powerpc/kernel/head_32.h
@@ -5,19 +5,6 @@
#include <asm/ptrace.h> /* for STACK_FRAME_REGS_MARKER */
/*
- * MSR_KERNEL is > 0x8000 on 4xx/Book-E since it include MSR_CE.
- */
-.macro __LOAD_MSR_KERNEL r, x
-.if \x >= 0x8000
- lis \r, (\x)@h
- ori \r, \r, (\x)@l
-.else
- li \r, (\x)
-.endif
-.endm
-#define LOAD_MSR_KERNEL(r, x) __LOAD_MSR_KERNEL r, x
-
-/*
* Exception entry code. This code runs with address translation
* turned off, i.e. using physical addresses.
* We assume sprg3 has the physical address of the current
@@ -92,7 +79,7 @@
#ifdef CONFIG_40x
rlwinm r9,r9,0,14,12 /* clear MSR_WE (necessary?) */
#else
- LOAD_MSR_KERNEL(r10, MSR_KERNEL & ~(MSR_IR|MSR_DR)) /* can take exceptions */
+ LOAD_REG_IMMEDIATE(r10, MSR_KERNEL & ~(MSR_IR|MSR_DR)) /* can take exceptions */
MTMSRD(r10) /* (except for mach check in rtas) */
#endif
lis r10,STACK_FRAME_REGS_MARKER@ha /* exception frame marker */
@@ -140,10 +127,10 @@
* otherwise we might risk taking an interrupt before we tell lockdep
* they are enabled.
*/
- LOAD_MSR_KERNEL(r10, MSR_KERNEL)
+ LOAD_REG_IMMEDIATE(r10, MSR_KERNEL)
rlwimi r10, r9, 0, MSR_EE
#else
- LOAD_MSR_KERNEL(r10, MSR_KERNEL | MSR_EE)
+ LOAD_REG_IMMEDIATE(r10, MSR_KERNEL | MSR_EE)
#endif
#if defined(CONFIG_PPC_8xx) && defined(CONFIG_PERF_EVENTS)
mtspr SPRN_NRI, r0
@@ -187,7 +174,7 @@
#define EXC_XFER_TEMPLATE(hdlr, trap, msr, tfer, ret) \
li r10,trap; \
stw r10,_TRAP(r11); \
- LOAD_MSR_KERNEL(r10, msr); \
+ LOAD_REG_IMMEDIATE(r10, msr); \
bl tfer; \
.long hdlr; \
.long ret
--
2.13.3
^ permalink raw reply related
* [PATCH v4 3/3] powerpc/64: optimise LOAD_REG_IMMEDIATE_SYM()
From: Christophe Leroy @ 2019-08-20 14:34 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, segher
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <d60ce8dd3a383c7adbfc322bf1d53d81724a6000.1566311636.git.christophe.leroy@c-s.fr>
Optimise LOAD_REG_IMMEDIATE_SYM() using a temporary register to
parallelise operations.
It reduces the path from 5 to 3 instructions.
Suggested-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
v3: new
v4: fixed the registers of lis/ori to match rldimi args (tmp is upper part, reg is lower part)
---
arch/powerpc/include/asm/ppc_asm.h | 12 ++++++------
arch/powerpc/kernel/exceptions-64e.S | 22 +++++++++++++---------
arch/powerpc/kernel/head_64.S | 2 +-
3 files changed, 20 insertions(+), 16 deletions(-)
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 20a00209c965..dd3b191bdcea 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -347,12 +347,12 @@ GLUE(.,name):
#define LOAD_REG_IMMEDIATE(reg, expr) __LOAD_REG_IMMEDIATE reg, expr
-#define LOAD_REG_IMMEDIATE_SYM(reg,expr) \
- lis reg,(expr)@highest; \
- ori reg,reg,(expr)@higher; \
- rldicr reg,reg,32,31; \
- oris reg,reg,(expr)@__AS_ATHIGH; \
- ori reg,reg,(expr)@l;
+#define LOAD_REG_IMMEDIATE_SYM(reg, tmp, expr) \
+ lis tmp, (expr)@highest; \
+ lis reg, (expr)@__AS_ATHIGH; \
+ ori tmp, tmp, (expr)@higher; \
+ ori reg, reg, (expr)@l; \
+ rldimi reg, tmp, 32, 0
#define LOAD_REG_ADDR(reg,name) \
ld reg,name@got(r2)
diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index 898aae6da167..829950b96d29 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -750,12 +750,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
ld r15,PACATOC(r13)
ld r14,interrupt_base_book3e@got(r15)
ld r15,__end_interrupts@got(r15)
-#else
- LOAD_REG_IMMEDIATE_SYM(r14,interrupt_base_book3e)
- LOAD_REG_IMMEDIATE_SYM(r15,__end_interrupts)
-#endif
cmpld cr0,r10,r14
cmpld cr1,r10,r15
+#else
+ LOAD_REG_IMMEDIATE_SYM(r14, r15, interrupt_base_book3e)
+ cmpld cr0, r10, r14
+ LOAD_REG_IMMEDIATE_SYM(r14, r15, __end_interrupts)
+ cmpld cr1, r10, r14
+#endif
blt+ cr0,1f
bge+ cr1,1f
@@ -820,12 +822,14 @@ kernel_dbg_exc:
ld r15,PACATOC(r13)
ld r14,interrupt_base_book3e@got(r15)
ld r15,__end_interrupts@got(r15)
-#else
- LOAD_REG_IMMEDIATE_SYM(r14,interrupt_base_book3e)
- LOAD_REG_IMMEDIATE_SYM(r15,__end_interrupts)
-#endif
cmpld cr0,r10,r14
cmpld cr1,r10,r15
+#else
+ LOAD_REG_IMMEDIATE_SYM(r14, r15, interrupt_base_book3e)
+ cmpld cr0, r10, r14
+ LOAD_REG_IMMEDIATE_SYM(r14, r15,__end_interrupts)
+ cmpld cr1, r10, r14
+#endif
blt+ cr0,1f
bge+ cr1,1f
@@ -1449,7 +1453,7 @@ a2_tlbinit_code_start:
a2_tlbinit_after_linear_map:
/* Now we branch the new virtual address mapped by this entry */
- LOAD_REG_IMMEDIATE_SYM(r3,1f)
+ LOAD_REG_IMMEDIATE_SYM(r3, r5, 1f)
mtctr r3
bctr
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 1fd44761e997..0f2d61af47cc 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -635,7 +635,7 @@ __after_prom_start:
sub r5,r5,r11
#else
/* just copy interrupts */
- LOAD_REG_IMMEDIATE_SYM(r5, FIXED_SYMBOL_ABS_ADDR(__end_interrupts))
+ LOAD_REG_IMMEDIATE_SYM(r5, r11, FIXED_SYMBOL_ABS_ADDR(__end_interrupts))
#endif
b 5f
3:
--
2.13.3
^ permalink raw reply related
* [PATCH v2 00/11] Raspberry Pi 4 DMA addressing support
From: Nicolas Saenz Julienne @ 2019-08-20 14:58 UTC (permalink / raw)
To: catalin.marinas, hch, wahrenst, marc.zyngier, robh+dt,
Robin Murphy, linux-arm-kernel, devicetree, linux-arch, iommu,
linux-mm, linux-riscv
Cc: phill, linux-s390, f.fainelli, frowand.list, linuxppc-dev,
linux-kernel, eric, mbrugger, linux-rpi-kernel, akpm, will,
nsaenzjulienne, m.szyprowski
Hi all,
this series attempts to address some issues we found while bringing up
the new Raspberry Pi 4 in arm64 and it's intended to serve as a follow
up of these discussions:
v1: https://lkml.org/lkml/2019/7/31/922
RFC: https://lkml.org/lkml/2019/7/17/476
The new Raspberry Pi 4 has up to 4GB of memory but most peripherals can
only address the first GB: their DMA address range is
0xc0000000-0xfc000000 which is aliased to the first GB of physical
memory 0x00000000-0x3c000000. Note that only some peripherals have these
limitations: the PCIe, V3D, GENET, and 40-bit DMA channels have a wider
view of the address space by virtue of being hooked up trough a second
interconnect.
Part of this is solved in arm32 by setting up the machine specific
'.dma_zone_size = SZ_1G', which takes care of reserving the coherent
memory area at the right spot. That said no buffer bouncing (needed for
dma streaming) is available at the moment, but that's a story for
another series.
Unfortunately there is no such thing as 'dma_zone_size' in arm64. Only
ZONE_DMA32 is created which is interpreted by dma-direct and the arm64
arch code as if all peripherals where be able to address the first 4GB
of memory.
In the light of this, the series implements the following changes:
- Create generic 'dma_zone_size' in order for hardware description code
to set it up when needed.
- Add a function in early_init_dt_scan() to setup 'dma_zone_size' for
the RPi4.
- Create both DMA zones in arm64, ZONE_DMA will contain the area
addressable by all peripherals and ZONE_DMA32 the rest of the 32 bit
addressable memory. ZONE_DMA32 might be left empty.
- Reserve the CMA area in a place suitable for all peripherals.
- Inform dma-direct of the new runtime calculated min_mask.
This series has been tested on multiple devices both by checking the
zones setup matches the expectations and by double-checking physical
addresses on pages allocated on the three relevant areas GFP_DMA,
GFP_DMA32, GFP_KERNEL:
- On an RPi4 with variations on the ram memory size. But also forcing
the situation where all three memory zones are nonempty by setting a 3G
ZONE_DMA32 ceiling on a 4G setup. Both with and without NUMA support.
- On a Synquacer box[1] with 32G of memory.
- On an ACPI based Huawei TaiShan server[2] with 256G of memory.
- On a QEMU virtual machine running arm64's OpenSUSE Tumbleweed.
That's all.
Regards,
Nicolas
[1] https://www.96boards.org/product/developerbox/
[2] https://e.huawei.com/en/products/cloud-computing-dc/servers/taishan-server/taishan-2280-v2
---
Changes in v2:
- More in depth testing.
- Create new global 'dma_zone_size'.
- New approach to getting the dma_zone_size, instead of parsing the dts
we hardcode it conditionally to the machine compatible name.
- Fix ZONE_DMA and ZONE_DMA32 split, now ZONE_DMA32 remains empty if
ZONE_DMA fits the whole 32 bit addressable space.
- Take into account devices with DMA offset.
- Rename new dma-direct variable to zone_dma_bits.
- Try new approach by merging both ZONE_DMA and ZONE_DMA32 comments
in mmzone.h, add new up to date examples.
Nicolas Saenz Julienne (11):
asm-generic: add dma_zone_size
arm: use generic dma_zone_size
of/fdt: add of_fdt_machine_is_compatible function
of/fdt: add early_init_dt_get_dma_zone_size()
arm64: mm: use arm64_dma_phys_limit instead of calling
max_zone_dma_phys()
arm64: rename variables used to calculate ZONE_DMA32's size
arm64: re-introduce max_zone_dma_phys()
arm64: use both ZONE_DMA and ZONE_DMA32
dma-direct: turn ARCH_ZONE_DMA_BITS into a variable
arm64: edit zone_dma_bits to fine tune dma-direct min mask
mm: refresh ZONE_DMA and ZONE_DMA32 comments in 'enum zone_type'
arch/arm/include/asm/dma.h | 8 ++--
arch/arm/mm/init.c | 12 ++----
arch/arm64/Kconfig | 4 ++
arch/arm64/mm/init.c | 73 +++++++++++++++++++++++++--------
arch/powerpc/include/asm/page.h | 9 ----
arch/powerpc/mm/mem.c | 16 +++++---
arch/s390/include/asm/page.h | 2 -
arch/s390/mm/init.c | 1 +
drivers/of/fdt.c | 15 +++++++
include/asm-generic/dma.h | 8 +++-
include/linux/dma-direct.h | 2 +
include/linux/mmzone.h | 46 ++++++++++++---------
kernel/dma/direct.c | 13 +++---
mm/page_alloc.c | 3 ++
14 files changed, 140 insertions(+), 72 deletions(-)
--
2.22.0
^ permalink raw reply
* [PATCH v2 09/11] dma-direct: turn ARCH_ZONE_DMA_BITS into a variable
From: Nicolas Saenz Julienne @ 2019-08-20 14:58 UTC (permalink / raw)
To: catalin.marinas, hch, wahrenst, marc.zyngier, robh+dt,
Robin Murphy, linux-arm-kernel, devicetree, linux-arch, iommu,
linux-mm, linux-riscv, Marek Szyprowski
Cc: phill, linux-s390, f.fainelli, Vasily Gorbik,
Christian Borntraeger, frowand.list, linuxppc-dev, Heiko Carstens,
linux-kernel, eric, mbrugger, Paul Mackerras, linux-rpi-kernel,
akpm, will, nsaenzjulienne
In-Reply-To: <20190820145821.27214-1-nsaenzjulienne@suse.de>
Some architectures, notably arm64, are interested in tweaking this
depending on their runtime dma addressing limitations.
Signed-off-by: Nicolas Saenz Julienne <nsaenzjulienne@suse.de>
---
Changes in v2:
- Rename new variable to zone_dma_bits
- Update comment with Christoph's suggestion
- Remove old powerpc comment
arch/powerpc/include/asm/page.h | 9 ---------
arch/powerpc/mm/mem.c | 16 +++++++++++-----
arch/s390/include/asm/page.h | 2 --
arch/s390/mm/init.c | 1 +
include/linux/dma-direct.h | 2 ++
kernel/dma/direct.c | 13 ++++++-------
6 files changed, 20 insertions(+), 23 deletions(-)
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 0d52f57fca04..73668a21ae78 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -319,13 +319,4 @@ struct vm_area_struct;
#endif /* __ASSEMBLY__ */
#include <asm/slice.h>
-/*
- * Allow 30-bit DMA for very limited Broadcom wifi chips on many powerbooks.
- */
-#ifdef CONFIG_PPC32
-#define ARCH_ZONE_DMA_BITS 30
-#else
-#define ARCH_ZONE_DMA_BITS 31
-#endif
-
#endif /* _ASM_POWERPC_PAGE_H */
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 9191a66b3bc5..2a69f87585df 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -31,6 +31,7 @@
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/memremap.h>
+#include <linux/dma-direct.h>
#include <asm/pgalloc.h>
#include <asm/prom.h>
@@ -201,10 +202,10 @@ static int __init mark_nonram_nosave(void)
* everything else. GFP_DMA32 page allocations automatically fall back to
* ZONE_DMA.
*
- * By using 31-bit unconditionally, we can exploit ARCH_ZONE_DMA_BITS to
- * inform the generic DMA mapping code. 32-bit only devices (if not handled
- * by an IOMMU anyway) will take a first dip into ZONE_NORMAL and get
- * otherwise served by ZONE_DMA.
+ * By using 31-bit unconditionally, we can exploit zone_dma_bits to inform the
+ * generic DMA mapping code. 32-bit only devices (if not handled by an IOMMU
+ * anyway) will take a first dip into ZONE_NORMAL and get otherwise served by
+ * ZONE_DMA.
*/
static unsigned long max_zone_pfns[MAX_NR_ZONES];
@@ -237,9 +238,14 @@ void __init paging_init(void)
printk(KERN_DEBUG "Memory hole size: %ldMB\n",
(long int)((top_of_ram - total_ram) >> 20));
+ if (IS_ENABLED(CONFIG_PPC32))
+ zone_dma_bits = 30;
+ else
+ zone_dma_bits = 31;
+
#ifdef CONFIG_ZONE_DMA
max_zone_pfns[ZONE_DMA] = min(max_low_pfn,
- 1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT));
+ 1UL << (zone_dma_bits - PAGE_SHIFT));
#endif
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
#ifdef CONFIG_HIGHMEM
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 823578c6b9e2..a4d38092530a 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -177,8 +177,6 @@ static inline int devmem_is_allowed(unsigned long pfn)
#define VM_DATA_DEFAULT_FLAGS (VM_READ | VM_WRITE | \
VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-#define ARCH_ZONE_DMA_BITS 31
-
#include <asm-generic/memory_model.h>
#include <asm-generic/getorder.h>
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 20340a03ad90..bd98465b8b9f 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -118,6 +118,7 @@ void __init paging_init(void)
sparse_memory_present_with_active_regions(MAX_NUMNODES);
sparse_init();
+ zone_dma_bits = 31;
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS);
max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index adf993a3bd58..d03af3605460 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -5,6 +5,8 @@
#include <linux/dma-mapping.h>
#include <linux/mem_encrypt.h>
+extern unsigned int zone_dma_bits;
+
#ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
#include <asm/dma-direct.h>
#else
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 795c9b095d75..b23cd65f26e0 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -16,12 +16,11 @@
#include <linux/swiotlb.h>
/*
- * Most architectures use ZONE_DMA for the first 16 Megabytes, but
- * some use it for entirely different regions:
+ * Most architectures use ZONE_DMA for the first 16 Megabytes, but some use it
+ * it for entirely different regions. In that case the arch code needs to
+ * override the variable below for dma-direct to work properly.
*/
-#ifndef ARCH_ZONE_DMA_BITS
-#define ARCH_ZONE_DMA_BITS 24
-#endif
+unsigned int zone_dma_bits __ro_after_init = 24;
static void report_addr(struct device *dev, dma_addr_t dma_addr, size_t size)
{
@@ -69,7 +68,7 @@ static gfp_t __dma_direct_optimal_gfp_mask(struct device *dev, u64 dma_mask,
* Note that GFP_DMA32 and GFP_DMA are no ops without the corresponding
* zones.
*/
- if (*phys_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
+ if (*phys_mask <= DMA_BIT_MASK(zone_dma_bits))
return GFP_DMA;
if (*phys_mask <= DMA_BIT_MASK(32))
return GFP_DMA32;
@@ -387,7 +386,7 @@ int dma_direct_supported(struct device *dev, u64 mask)
u64 min_mask;
if (IS_ENABLED(CONFIG_ZONE_DMA))
- min_mask = DMA_BIT_MASK(ARCH_ZONE_DMA_BITS);
+ min_mask = DMA_BIT_MASK(zone_dma_bits);
else
min_mask = DMA_BIT_MASK(32);
--
2.22.0
^ permalink raw reply related
* [PATCH] powerpc/fadump: when fadump is supported register the fadump sysfs files.
From: Michal Suchanek @ 2019-08-20 15:06 UTC (permalink / raw)
To: linuxppc-dev
Cc: Yangtao Li, Mahesh Salgaonkar, linux-kernel, Paul Mackerras,
Hari Bathini, Thomas Gleixner, Michal Suchanek
Currently it is not possible to distinguish the case when fadump is
supported by firmware and disabled in kernel and completely unsupported
using the kernel sysfs interface. User can investigate the devicetree
but it is more reasonable to provide sysfs files in case we get some
fadumpv2 in the future.
With this patch sysfs files are available whenever fadump is supported
by firmware.
Signed-off-by: Michal Suchanek <msuchanek@suse.de>
---
arch/powerpc/kernel/fadump.c | 32 ++++++++++++++++++--------------
1 file changed, 18 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 4eab97292cc2..f35ab2433a9b 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -1671,13 +1671,9 @@ static void fadump_init_files(void)
*/
int __init setup_fadump(void)
{
- if (!fw_dump.fadump_enabled)
- return 0;
-
- if (!fw_dump.fadump_supported) {
+ if (!fw_dump.fadump_supported && fw_dump.fadump_enabled) {
printk(KERN_ERR "Firmware-assisted dump is not supported on"
" this hardware\n");
- return 0;
}
fadump_show_config();
@@ -1685,18 +1681,26 @@ int __init setup_fadump(void)
* If dump data is available then see if it is valid and prepare for
* saving it to the disk.
*/
- if (fw_dump.dump_active) {
+ if (fw_dump.fadump_enabled) {
+ if (fw_dump.dump_active) {
+ /*
+ * if dump process fails then invalidate the
+ * registration and release memory before proceeding
+ * for re-registration.
+ */
+ if (process_fadump(fdm_active) < 0)
+ fadump_invalidate_release_mem();
+ }
/*
- * if dump process fails then invalidate the registration
- * and release memory before proceeding for re-registration.
+ * Initialize the kernel dump memory structure for FAD
+ * registration.
*/
- if (process_fadump(fdm_active) < 0)
- fadump_invalidate_release_mem();
+ else if (fw_dump.reserve_dump_area_size)
+ init_fadump_mem_struct(&fdm,
+ fw_dump.reserve_dump_area_start);
}
- /* Initialize the kernel dump memory structure for FAD registration. */
- else if (fw_dump.reserve_dump_area_size)
- init_fadump_mem_struct(&fdm, fw_dump.reserve_dump_area_start);
- fadump_init_files();
+ if (fw_dump.fadump_supported)
+ fadump_init_files();
return 1;
}
--
2.22.0
^ 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