* [PATCH 06/13] kallsyms: only build {, module_}kallsyms_on_each_symbol when required
From: Christoph Hellwig @ 2021-02-02 12:13 UTC (permalink / raw)
To: Frederic Barrat, Andrew Donnellan, Maarten Lankhorst,
Maxime Ripard, Thomas Zimmermann, David Airlie, Daniel Vetter,
Jessica Yu, Josh Poimboeuf, Jiri Kosina, Miroslav Benes,
Petr Mladek, Joe Lawrence
Cc: Michal Marek, linux-kbuild, Masahiro Yamada, linux-kernel,
dri-devel, live-patching, linuxppc-dev
In-Reply-To: <20210202121334.1361503-1-hch@lst.de>
kallsyms_on_each_symbol and module_kallsyms_on_each_symbol are only used
by the livepatching code, so don't build them if livepatching is not
enabled.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
include/linux/kallsyms.h | 17 ++++-------------
include/linux/module.h | 16 ++++------------
kernel/kallsyms.c | 2 ++
kernel/module.c | 2 ++
4 files changed, 12 insertions(+), 25 deletions(-)
diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index 481273f0c72d42..465060acc9816f 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -71,15 +71,14 @@ static inline void *dereference_symbol_descriptor(void *ptr)
return ptr;
}
-#ifdef CONFIG_KALLSYMS
-/* Lookup the address for a symbol. Returns 0 if not found. */
-unsigned long kallsyms_lookup_name(const char *name);
-
-/* Call a function on each kallsyms symbol in the core kernel */
int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
unsigned long),
void *data);
+#ifdef CONFIG_KALLSYMS
+/* Lookup the address for a symbol. Returns 0 if not found. */
+unsigned long kallsyms_lookup_name(const char *name);
+
extern int kallsyms_lookup_size_offset(unsigned long addr,
unsigned long *symbolsize,
unsigned long *offset);
@@ -108,14 +107,6 @@ static inline unsigned long kallsyms_lookup_name(const char *name)
return 0;
}
-static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *,
- struct module *,
- unsigned long),
- void *data)
-{
- return 0;
-}
-
static inline int kallsyms_lookup_size_offset(unsigned long addr,
unsigned long *symbolsize,
unsigned long *offset)
diff --git a/include/linux/module.h b/include/linux/module.h
index a64aa84d1b182c..3ea4ffae608f97 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -608,10 +608,6 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
/* Look for this name: can be of form module:name. */
unsigned long module_kallsyms_lookup_name(const char *name);
-int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
- struct module *, unsigned long),
- void *data);
-
extern void __noreturn __module_put_and_exit(struct module *mod,
long code);
#define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code)
@@ -795,14 +791,6 @@ static inline unsigned long module_kallsyms_lookup_name(const char *name)
return 0;
}
-static inline int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
- struct module *,
- unsigned long),
- void *data)
-{
- return 0;
-}
-
static inline int register_module_notifier(struct notifier_block *nb)
{
/* no events will happen anyway, so this can always succeed */
@@ -891,4 +879,8 @@ static inline bool module_sig_ok(struct module *module)
}
#endif /* CONFIG_MODULE_SIG */
+int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
+ struct module *, unsigned long),
+ void *data);
+
#endif /* _LINUX_MODULE_H */
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index a0d3f0865916f9..8043a90aa50ed3 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -177,6 +177,7 @@ unsigned long kallsyms_lookup_name(const char *name)
return module_kallsyms_lookup_name(name);
}
+#ifdef CONFIG_LIVEPATCH
/*
* Iterate over all symbols in vmlinux. For symbols from modules use
* module_kallsyms_on_each_symbol instead.
@@ -198,6 +199,7 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
}
return 0;
}
+#endif /* CONFIG_LIVEPATCH */
static unsigned long get_symbol_pos(unsigned long addr,
unsigned long *symbolsize,
diff --git a/kernel/module.c b/kernel/module.c
index 25345792c770d1..470fd9d9d68f97 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -4366,6 +4366,7 @@ unsigned long module_kallsyms_lookup_name(const char *name)
return ret;
}
+#ifdef CONFIG_LIVEPATCH
int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
struct module *, unsigned long),
void *data)
@@ -4396,6 +4397,7 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
mutex_unlock(&module_mutex);
return ret;
}
+#endif /* CONFIG_LIVEPATCH */
#endif /* CONFIG_KALLSYMS */
/* Maximum number of characters written by module_flags() */
--
2.29.2
^ permalink raw reply related
* [PATCH 05/13] kallsyms: refactor {,module_}kallsyms_on_each_symbol
From: Christoph Hellwig @ 2021-02-02 12:13 UTC (permalink / raw)
To: Frederic Barrat, Andrew Donnellan, Maarten Lankhorst,
Maxime Ripard, Thomas Zimmermann, David Airlie, Daniel Vetter,
Jessica Yu, Josh Poimboeuf, Jiri Kosina, Miroslav Benes,
Petr Mladek, Joe Lawrence
Cc: Michal Marek, linux-kbuild, Masahiro Yamada, linux-kernel,
dri-devel, live-patching, linuxppc-dev
In-Reply-To: <20210202121334.1361503-1-hch@lst.de>
Require an explicit call to module_kallsyms_on_each_symbol to look
for symbols in modules instead of the call from kallsyms_on_each_symbol,
and acquire module_mutex inside of module_kallsyms_on_each_symbol instead
of leaving that up to the caller. Note that this slightly changes the
behavior for the livepatch code in that the symbols from vmlinux are not
iterated anymore if objname is set, but that actually is the desired
behavior in this case.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Miroslav Benes <mbenes@suse.cz>
---
kernel/kallsyms.c | 6 +++++-
kernel/livepatch/core.c | 2 --
kernel/module.c | 13 ++++---------
3 files changed, 9 insertions(+), 12 deletions(-)
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index fe9de067771c34..a0d3f0865916f9 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -177,6 +177,10 @@ unsigned long kallsyms_lookup_name(const char *name)
return module_kallsyms_lookup_name(name);
}
+/*
+ * Iterate over all symbols in vmlinux. For symbols from modules use
+ * module_kallsyms_on_each_symbol instead.
+ */
int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
unsigned long),
void *data)
@@ -192,7 +196,7 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
if (ret != 0)
return ret;
}
- return module_kallsyms_on_each_symbol(fn, data);
+ return 0;
}
static unsigned long get_symbol_pos(unsigned long addr,
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index 262cd9b003b9f0..335d988bd81117 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -164,12 +164,10 @@ static int klp_find_object_symbol(const char *objname, const char *name,
.pos = sympos,
};
- mutex_lock(&module_mutex);
if (objname)
module_kallsyms_on_each_symbol(klp_find_callback, &args);
else
kallsyms_on_each_symbol(klp_find_callback, &args);
- mutex_unlock(&module_mutex);
/*
* Ensure an address was found. If sympos is 0, ensure symbol is unique;
diff --git a/kernel/module.c b/kernel/module.c
index 6772fb2680eb3e..25345792c770d1 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -255,11 +255,6 @@ static void mod_update_bounds(struct module *mod)
struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */
#endif /* CONFIG_KGDB_KDB */
-static void module_assert_mutex(void)
-{
- lockdep_assert_held(&module_mutex);
-}
-
static void module_assert_mutex_or_preempt(void)
{
#ifdef CONFIG_LOCKDEP
@@ -4379,8 +4374,7 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
unsigned int i;
int ret;
- module_assert_mutex();
-
+ mutex_lock(&module_mutex);
list_for_each_entry(mod, &modules, list) {
/* We hold module_mutex: no need for rcu_dereference_sched */
struct mod_kallsyms *kallsyms = mod->kallsyms;
@@ -4396,10 +4390,11 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
ret = fn(data, kallsyms_symbol_name(kallsyms, i),
mod, kallsyms_symbol_value(sym));
if (ret != 0)
- return ret;
+ break;
}
}
- return 0;
+ mutex_unlock(&module_mutex);
+ return ret;
}
#endif /* CONFIG_KALLSYMS */
--
2.29.2
^ permalink raw reply related
* [PATCH 04/13] module: use RCU to synchronize find_module
From: Christoph Hellwig @ 2021-02-02 12:13 UTC (permalink / raw)
To: Frederic Barrat, Andrew Donnellan, Maarten Lankhorst,
Maxime Ripard, Thomas Zimmermann, David Airlie, Daniel Vetter,
Jessica Yu, Josh Poimboeuf, Jiri Kosina, Miroslav Benes,
Petr Mladek, Joe Lawrence
Cc: Michal Marek, linux-kbuild, Masahiro Yamada, linux-kernel,
dri-devel, live-patching, linuxppc-dev
In-Reply-To: <20210202121334.1361503-1-hch@lst.de>
Allow for a RCU-sched critical section around find_module, following
the lower level find_module_all helper, and switch the two callers
outside of module.c to use such a RCU-sched critical section instead
of module_mutex.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Acked-by: Miroslav Benes <mbenes@suse.cz>
---
include/linux/module.h | 2 +-
kernel/livepatch/core.c | 5 +++--
kernel/module.c | 1 -
kernel/trace/trace_kprobe.c | 4 ++--
4 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/include/linux/module.h b/include/linux/module.h
index 7a0bcb5b1ffccd..a64aa84d1b182c 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -586,7 +586,7 @@ static inline bool within_module(unsigned long addr, const struct module *mod)
return within_module_init(addr, mod) || within_module_core(addr, mod);
}
-/* Search for module by name: must hold module_mutex. */
+/* Search for module by name: must be in a RCU-sched critical section. */
struct module *find_module(const char *name);
struct symsearch {
diff --git a/kernel/livepatch/core.c b/kernel/livepatch/core.c
index f76fdb9255323d..262cd9b003b9f0 100644
--- a/kernel/livepatch/core.c
+++ b/kernel/livepatch/core.c
@@ -19,6 +19,7 @@
#include <linux/moduleloader.h>
#include <linux/completion.h>
#include <linux/memory.h>
+#include <linux/rcupdate.h>
#include <asm/cacheflush.h>
#include "core.h"
#include "patch.h"
@@ -57,7 +58,7 @@ static void klp_find_object_module(struct klp_object *obj)
if (!klp_is_module(obj))
return;
- mutex_lock(&module_mutex);
+ rcu_read_lock_sched();
/*
* We do not want to block removal of patched modules and therefore
* we do not take a reference here. The patches are removed by
@@ -74,7 +75,7 @@ static void klp_find_object_module(struct klp_object *obj)
if (mod && mod->klp_alive)
obj->mod = mod;
- mutex_unlock(&module_mutex);
+ rcu_read_unlock_sched();
}
static bool klp_initialized(void)
diff --git a/kernel/module.c b/kernel/module.c
index 981302f616b411..6772fb2680eb3e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -668,7 +668,6 @@ static struct module *find_module_all(const char *name, size_t len,
struct module *find_module(const char *name)
{
- module_assert_mutex();
return find_module_all(name, strlen(name), false);
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index e6fba1798771b4..3137992baa5e7a 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -124,9 +124,9 @@ static nokprobe_inline bool trace_kprobe_module_exist(struct trace_kprobe *tk)
if (!p)
return true;
*p = '\0';
- mutex_lock(&module_mutex);
+ rcu_read_lock_sched();
ret = !!find_module(tk->symbol);
- mutex_unlock(&module_mutex);
+ rcu_read_unlock_sched();
*p = ':';
return ret;
--
2.29.2
^ permalink raw reply related
* [PATCH 01/13] powerpc/powernv: remove get_cxl_module
From: Christoph Hellwig @ 2021-02-02 12:13 UTC (permalink / raw)
To: Frederic Barrat, Andrew Donnellan, Maarten Lankhorst,
Maxime Ripard, Thomas Zimmermann, David Airlie, Daniel Vetter,
Jessica Yu, Josh Poimboeuf, Jiri Kosina, Miroslav Benes,
Petr Mladek, Joe Lawrence
Cc: Michal Marek, linux-kbuild, Masahiro Yamada, linux-kernel,
dri-devel, live-patching, linuxppc-dev
In-Reply-To: <20210202121334.1361503-1-hch@lst.de>
The static inline get_cxl_module function is entirely unused since commit
8bf6b91a5125a ("Revert "powerpc/powernv: Add support for the cxl kernel
api on the real phb"), so remove it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Andrew Donnellan <ajd@linux.ibm.com>
---
arch/powerpc/platforms/powernv/pci-cxl.c | 22 ----------------------
1 file changed, 22 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/pci-cxl.c b/arch/powerpc/platforms/powernv/pci-cxl.c
index 8c739c94ed28d6..53172862d23bd3 100644
--- a/arch/powerpc/platforms/powernv/pci-cxl.c
+++ b/arch/powerpc/platforms/powernv/pci-cxl.c
@@ -150,25 +150,3 @@ int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
return 0;
}
EXPORT_SYMBOL(pnv_cxl_ioda_msi_setup);
-
-#if IS_MODULE(CONFIG_CXL)
-static inline int get_cxl_module(void)
-{
- struct module *cxl_module;
-
- mutex_lock(&module_mutex);
-
- cxl_module = find_module("cxl");
- if (cxl_module)
- __module_get(cxl_module);
-
- mutex_unlock(&module_mutex);
-
- if (!cxl_module)
- return -ENODEV;
-
- return 0;
-}
-#else
-static inline int get_cxl_module(void) { return 0; }
-#endif
--
2.29.2
^ permalink raw reply related
* [PATCH 02/13] drm: remove drm_fb_helper_modinit
From: Christoph Hellwig @ 2021-02-02 12:13 UTC (permalink / raw)
To: Frederic Barrat, Andrew Donnellan, Maarten Lankhorst,
Maxime Ripard, Thomas Zimmermann, David Airlie, Daniel Vetter,
Jessica Yu, Josh Poimboeuf, Jiri Kosina, Miroslav Benes,
Petr Mladek, Joe Lawrence
Cc: Michal Marek, linux-kbuild, Masahiro Yamada, linux-kernel,
dri-devel, live-patching, linuxppc-dev
In-Reply-To: <20210202121334.1361503-1-hch@lst.de>
drm_fb_helper_modinit has a lot of boilerplate for what is not very
simple functionality. Just open code it in the only caller using
IS_ENABLED and IS_MODULE, and skip the find_module check as a
request_module is harmless if the module is already loaded (and not
other caller has this find_module check either).
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
drivers/gpu/drm/drm_crtc_helper_internal.h | 10 ---------
drivers/gpu/drm/drm_fb_helper.c | 21 ------------------
drivers/gpu/drm/drm_kms_helper_common.c | 25 +++++++++++-----------
3 files changed, 12 insertions(+), 44 deletions(-)
diff --git a/drivers/gpu/drm/drm_crtc_helper_internal.h b/drivers/gpu/drm/drm_crtc_helper_internal.h
index 25ce42e799952c..61e09f8a8d0ff0 100644
--- a/drivers/gpu/drm/drm_crtc_helper_internal.h
+++ b/drivers/gpu/drm/drm_crtc_helper_internal.h
@@ -32,16 +32,6 @@
#include <drm/drm_encoder.h>
#include <drm/drm_modes.h>
-/* drm_fb_helper.c */
-#ifdef CONFIG_DRM_FBDEV_EMULATION
-int drm_fb_helper_modinit(void);
-#else
-static inline int drm_fb_helper_modinit(void)
-{
- return 0;
-}
-#endif
-
/* drm_dp_aux_dev.c */
#ifdef CONFIG_DRM_DP_AUX_CHARDEV
int drm_dp_aux_dev_init(void);
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 4b81195106875d..0b9f1ae1b7864c 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -2499,24 +2499,3 @@ void drm_fbdev_generic_setup(struct drm_device *dev,
drm_client_register(&fb_helper->client);
}
EXPORT_SYMBOL(drm_fbdev_generic_setup);
-
-/* The Kconfig DRM_KMS_HELPER selects FRAMEBUFFER_CONSOLE (if !EXPERT)
- * but the module doesn't depend on any fb console symbols. At least
- * attempt to load fbcon to avoid leaving the system without a usable console.
- */
-int __init drm_fb_helper_modinit(void)
-{
-#if defined(CONFIG_FRAMEBUFFER_CONSOLE_MODULE) && !defined(CONFIG_EXPERT)
- const char name[] = "fbcon";
- struct module *fbcon;
-
- mutex_lock(&module_mutex);
- fbcon = find_module(name);
- mutex_unlock(&module_mutex);
-
- if (!fbcon)
- request_module_nowait(name);
-#endif
- return 0;
-}
-EXPORT_SYMBOL(drm_fb_helper_modinit);
diff --git a/drivers/gpu/drm/drm_kms_helper_common.c b/drivers/gpu/drm/drm_kms_helper_common.c
index 221a8528c9937a..f933da1656eb52 100644
--- a/drivers/gpu/drm/drm_kms_helper_common.c
+++ b/drivers/gpu/drm/drm_kms_helper_common.c
@@ -64,19 +64,18 @@ MODULE_PARM_DESC(edid_firmware,
static int __init drm_kms_helper_init(void)
{
- int ret;
-
- /* Call init functions from specific kms helpers here */
- ret = drm_fb_helper_modinit();
- if (ret < 0)
- goto out;
-
- ret = drm_dp_aux_dev_init();
- if (ret < 0)
- goto out;
-
-out:
- return ret;
+ /*
+ * The Kconfig DRM_KMS_HELPER selects FRAMEBUFFER_CONSOLE (if !EXPERT)
+ * but the module doesn't depend on any fb console symbols. At least
+ * attempt to load fbcon to avoid leaving the system without a usable
+ * console.
+ */
+ if (IS_ENABLED(CONFIG_DRM_FBDEV_EMULATION) &&
+ IS_MODULE(CONFIG_FRAMEBUFFER_CONSOLE) &&
+ !IS_ENABLED(CONFIG_EXPERT))
+ request_module_nowait("fbcon");
+
+ return drm_dp_aux_dev_init();
}
static void __exit drm_kms_helper_exit(void)
--
2.29.2
^ permalink raw reply related
* module loader dead code removal and cleanups v3
From: Christoph Hellwig @ 2021-02-02 12:13 UTC (permalink / raw)
To: Frederic Barrat, Andrew Donnellan, Maarten Lankhorst,
Maxime Ripard, Thomas Zimmermann, David Airlie, Daniel Vetter,
Jessica Yu, Josh Poimboeuf, Jiri Kosina, Miroslav Benes,
Petr Mladek, Joe Lawrence
Cc: Michal Marek, linux-kbuild, Masahiro Yamada, linux-kernel,
dri-devel, live-patching, linuxppc-dev
Hi all,
this series removes support for long term unused export types and
cleans up various loose ends in the module loader.
Changes since v2:
- clean up klp_find_object_symbol a bit
- remove the now unused module_assert_mutex helper
Changes since v1:
- move struct symsearch to module.c
- rework drm to not call find_module at all
- allow RCU-sched locking for find_module
- keep find_module as a public API instead of module_loaded
- update a few comments and commit logs
Diffstat:
^ permalink raw reply
* [PATCH 03/13] module: unexport find_module and module_mutex
From: Christoph Hellwig @ 2021-02-02 12:13 UTC (permalink / raw)
To: Frederic Barrat, Andrew Donnellan, Maarten Lankhorst,
Maxime Ripard, Thomas Zimmermann, David Airlie, Daniel Vetter,
Jessica Yu, Josh Poimboeuf, Jiri Kosina, Miroslav Benes,
Petr Mladek, Joe Lawrence
Cc: Michal Marek, linux-kbuild, Masahiro Yamada, linux-kernel,
dri-devel, live-patching, linuxppc-dev
In-Reply-To: <20210202121334.1361503-1-hch@lst.de>
find_module is not used by modular code any more, and random driver code
has no business calling it to start with.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Miroslav Benes <mbenes@suse.cz>
---
kernel/module.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/kernel/module.c b/kernel/module.c
index 4bf30e4b3eaaa1..981302f616b411 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -88,7 +88,6 @@
* (delete and add uses RCU list operations).
*/
DEFINE_MUTEX(module_mutex);
-EXPORT_SYMBOL_GPL(module_mutex);
static LIST_HEAD(modules);
/* Work queue for freeing init sections in success case */
@@ -672,7 +671,6 @@ struct module *find_module(const char *name)
module_assert_mutex();
return find_module_all(name, strlen(name), false);
}
-EXPORT_SYMBOL_GPL(find_module);
#ifdef CONFIG_SMP
--
2.29.2
^ permalink raw reply related
* Re: [PATCH v12 01/14] ARM: mm: add missing pud_page define to 2-level page tables
From: Russell King - ARM Linux admin @ 2021-02-02 12:07 UTC (permalink / raw)
To: Ding Tianhong
Cc: linux-arch, linux-kernel, Nicholas Piggin, Christoph Hellwig,
linux-mm, Jonathan Cameron, Andrew Morton, Rick Edgecombe,
linuxppc-dev, linux-arm-kernel
In-Reply-To: <d1f661f2-f473-1dd8-94cc-fe76714249b5@huawei.com>
On Tue, Feb 02, 2021 at 07:47:04PM +0800, Ding Tianhong wrote:
> On 2021/2/2 19:13, Russell King - ARM Linux admin wrote:
> > On Tue, Feb 02, 2021 at 09:05:02PM +1000, Nicholas Piggin wrote:
> >> diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
> >> index c02f24400369..d63a5bb6bd0c 100644
> >> --- a/arch/arm/include/asm/pgtable.h
> >> +++ b/arch/arm/include/asm/pgtable.h
> >> @@ -166,6 +166,9 @@ extern struct page *empty_zero_page;
> >>
> >> extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
> >>
> >> +#define pud_page(pud) pmd_page(__pmd(pud_val(pud)))
> >> +#define pud_write(pud) pmd_write(__pmd(pud_val(pud)))
> >
> > As there is no PUD, does it really make sense to return a valid
> > struct page (which will be the PTE page) for pud_page(), which is
> > several tables above?
> >
> --- a/arch/arm/include/asm/pgtable-2level.h
> +++ b/arch/arm/include/asm/pgtable-2level.h
>
> +static inline int pud_none(pud_t pud)
> +{
> + return 0;
> +}
>
> I think it could be fix like this.
We already have that.
--
RMK's Patch system: https://www.armlinux.org.uk/developer/patches/
FTTP is here! 40Mbps down 10Mbps up. Decent connectivity at last!
^ permalink raw reply
* Re: [PATCH v12 01/14] ARM: mm: add missing pud_page define to 2-level page tables
From: Ding Tianhong @ 2021-02-02 11:48 UTC (permalink / raw)
To: Russell King - ARM Linux admin, Nicholas Piggin
Cc: linux-arch, linux-kernel, Christoph Hellwig, linux-mm,
Jonathan Cameron, Andrew Morton, Rick Edgecombe, linuxppc-dev,
linux-arm-kernel
In-Reply-To: <d1f661f2-f473-1dd8-94cc-fe76714249b5@huawei.com>
On 2021/2/2 19:47, Ding Tianhong wrote:
> On 2021/2/2 19:13, Russell King - ARM Linux admin wrote:
>> On Tue, Feb 02, 2021 at 09:05:02PM +1000, Nicholas Piggin wrote:
>>> diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
>>> index c02f24400369..d63a5bb6bd0c 100644
>>> --- a/arch/arm/include/asm/pgtable.h
>>> +++ b/arch/arm/include/asm/pgtable.h
>>> @@ -166,6 +166,9 @@ extern struct page *empty_zero_page;
>>>
>>> extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
>>>
>>> +#define pud_page(pud) pmd_page(__pmd(pud_val(pud)))
>>> +#define pud_write(pud) pmd_write(__pmd(pud_val(pud)))
>>
>> As there is no PUD, does it really make sense to return a valid
>> struct page (which will be the PTE page) for pud_page(), which is
>> several tables above?
>>
> --- a/arch/arm/include/asm/pgtable-2level.h
> +++ b/arch/arm/include/asm/pgtable-2level.h
>
> +static inline int pud_none(pud_t pud)
> +{
> + return 0;
> +}
>
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h>
+static inline int pud_page(pud_t pud)
+{
+ return 0;
+}
> I think it could be fix like this.
>
> Ding
>
^ permalink raw reply
* Re: [PATCH v12 01/14] ARM: mm: add missing pud_page define to 2-level page tables
From: Ding Tianhong @ 2021-02-02 11:47 UTC (permalink / raw)
To: Russell King - ARM Linux admin, Nicholas Piggin
Cc: linux-arch, linux-kernel, Christoph Hellwig, linux-mm,
Jonathan Cameron, Andrew Morton, Rick Edgecombe, linuxppc-dev,
linux-arm-kernel
In-Reply-To: <20210202111319.GL1463@shell.armlinux.org.uk>
On 2021/2/2 19:13, Russell King - ARM Linux admin wrote:
> On Tue, Feb 02, 2021 at 09:05:02PM +1000, Nicholas Piggin wrote:
>> diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
>> index c02f24400369..d63a5bb6bd0c 100644
>> --- a/arch/arm/include/asm/pgtable.h
>> +++ b/arch/arm/include/asm/pgtable.h
>> @@ -166,6 +166,9 @@ extern struct page *empty_zero_page;
>>
>> extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
>>
>> +#define pud_page(pud) pmd_page(__pmd(pud_val(pud)))
>> +#define pud_write(pud) pmd_write(__pmd(pud_val(pud)))
>
> As there is no PUD, does it really make sense to return a valid
> struct page (which will be the PTE page) for pud_page(), which is
> several tables above?
>
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
+static inline int pud_none(pud_t pud)
+{
+ return 0;
+}
I think it could be fix like this.
Ding
^ permalink raw reply
* Re: [PATCH v12 01/14] ARM: mm: add missing pud_page define to 2-level page tables
From: Russell King - ARM Linux admin @ 2021-02-02 11:13 UTC (permalink / raw)
To: Nicholas Piggin
Cc: linux-arch, Ding Tianhong, linux-kernel, Christoph Hellwig,
linux-mm, Jonathan Cameron, Andrew Morton, Rick Edgecombe,
linuxppc-dev, linux-arm-kernel
In-Reply-To: <20210202110515.3575274-2-npiggin@gmail.com>
On Tue, Feb 02, 2021 at 09:05:02PM +1000, Nicholas Piggin wrote:
> diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
> index c02f24400369..d63a5bb6bd0c 100644
> --- a/arch/arm/include/asm/pgtable.h
> +++ b/arch/arm/include/asm/pgtable.h
> @@ -166,6 +166,9 @@ extern struct page *empty_zero_page;
>
> extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
>
> +#define pud_page(pud) pmd_page(__pmd(pud_val(pud)))
> +#define pud_write(pud) pmd_write(__pmd(pud_val(pud)))
As there is no PUD, does it really make sense to return a valid
struct page (which will be the PTE page) for pud_page(), which is
several tables above?
--
RMK's Patch system: https://www.armlinux.org.uk/developer/patches/
FTTP is here! 40Mbps down 10Mbps up. Decent connectivity at last!
^ permalink raw reply
* Re: [PATCH] powerpc/64/signal: Fix regression in __kernel_sigtramp_rt64 semantics
From: Michael Ellerman @ 2021-02-02 11:18 UTC (permalink / raw)
To: Nicholas Piggin, linuxppc-dev, Raoni Fassina Firmino
In-Reply-To: <1612251472.a7pzsfoixm.astroid@bobo.none>
Nicholas Piggin <npiggin@gmail.com> writes:
> Excerpts from Raoni Fassina Firmino's message of February 2, 2021 6:05 am:
>> Tested on powerpc64 and powerpc64le, with a glibc build and running the
>> affected glibc's testcase[2], inspected that glibc's backtrace() now gives
>> the correct result and gdb backtrace also keeps working as before.
>>
>> I believe this should be backported to releases 5.9 and 5.10 as userspace
>> is affected in this releases.
>>
>> ---- 8< ----
>
> Thanks for this, I don't know the glibc code but the kernel change seems
> okay to me.
I turned this into an Acked-by from you.
>> A Change[1] in __kernel_sigtramp_rt64 VDSO and trampoline code introduced a
>> regression in the way glibc's backtrace()[2] detects the signal-handler
>> stack frame. Apart from the practical implications, __kernel_sigtram_rt64
>> was a VDSO with the semantics that it is a function you can call from
>> userspace to end a signal handling. Now this semantics are no longer
>> valid.
>>
>> I believe the aforementioned change affects all releases since 5.9.
>>
>> This patch tries to fix both the semantics and practical aspect of
>> __kernel_sigtramp_rt64 returning it to the previous code, whilst keeping
>> the intended behavior from[1] by adding a new symbol to serve as the jump
>> target from the kernel to the trampoline. Now the trampoline has two parts,
>> an new entry point and the old return point.
>>
>> [1] commit 0138ba5783ae0dcc799ad401a1e8ac8333790df9 ("powerpc/64/signal:
>> Balance return predictor stack in signal trampoline")
>> [2] https://lists.ozlabs.org/pipermail/linuxppc-dev/2021-January/223194.html
>>
>> Fixes: 0138ba5783ae ("powerpc/64/signal: Balance return predictor stack in signal trampoline")
>> Signed-off-by: Raoni Fassina Firmino <raoni@linux.ibm.com>
>> ---
>> arch/powerpc/kernel/vdso64/sigtramp.S | 9 ++++++++-
>> arch/powerpc/kernel/vdso64/vdso64.lds.S | 2 +-
>> 2 files changed, 9 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/powerpc/kernel/vdso64/sigtramp.S b/arch/powerpc/kernel/vdso64/sigtramp.S
>> index bbf68cd01088..f0fd8d2a9fc4 100644
>> --- a/arch/powerpc/kernel/vdso64/sigtramp.S
>> +++ b/arch/powerpc/kernel/vdso64/sigtramp.S
>> @@ -15,11 +15,18 @@
>>
>> .text
>>
>> +/* __kernel_start_sigtramp_rt64 and __kernel_sigtramp_rt64 together
>> + are one function split in two parts. The kernel jumps to the former
>> + and the signal handler indirectly (by blr) returns to the latter.
>> + __kernel_sigtramp_rt64 needs to point to the return address so
>> + glibc can correctly identify the trampoline stack frame. */
>
> Are you planning to update glibc to cope with this as well? Any idea
> about musl? If so, including version numbers would be good (not that
> it's really a problem to carry this patch around).
>
> I was just about to ask to turn the comment into kernel style, but the
> whole file has this style so nevermind about that! :)
Yeah, copying the existing style was the right thing to do.
... but I really can't deal with that comment style so I reformatted it
to match kernel style :)
Parts of that file use two-space indents as well, the whole thing could
do with a pass through clang-format or similar one day.
cheers
^ permalink raw reply
* [PATCH v12 14/14] powerpc/64s/radix: Enable huge vmalloc mappings
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Ding Tianhong, linux-kernel, Nicholas Piggin,
Christoph Hellwig, Jonathan Cameron, Rick Edgecombe, linuxppc-dev
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
This reduces TLB misses by nearly 30x on a `git diff` workload on a
2-node POWER9 (59,800 -> 2,100) and reduces CPU cycles by 0.54%, due
to vfs hashes being allocated with 2MB pages.
Cc: linuxppc-dev@lists.ozlabs.org
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
.../admin-guide/kernel-parameters.txt | 2 ++
arch/powerpc/Kconfig | 1 +
arch/powerpc/kernel/module.c | 21 +++++++++++++++----
3 files changed, 20 insertions(+), 4 deletions(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a10b545c2070..d62df53e5200 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3225,6 +3225,8 @@
nohugeiomap [KNL,X86,PPC,ARM64] Disable kernel huge I/O mappings.
+ nohugevmalloc [PPC] Disable kernel huge vmalloc mappings.
+
nosmt [KNL,S390] Disable symmetric multithreading (SMT).
Equivalent to smt=1.
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 107bb4319e0e..781da6829ab7 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -181,6 +181,7 @@ config PPC
select GENERIC_GETTIMEOFDAY
select HAVE_ARCH_AUDITSYSCALL
select HAVE_ARCH_HUGE_VMAP if PPC_BOOK3S_64 && PPC_RADIX_MMU
+ select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP
select HAVE_ARCH_JUMP_LABEL
select HAVE_ARCH_KASAN if PPC32 && PPC_PAGE_SHIFT <= 14
select HAVE_ARCH_KASAN_VMALLOC if PPC32 && PPC_PAGE_SHIFT <= 14
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index a211b0253cdb..07026335d24d 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -87,13 +87,26 @@ int module_finalize(const Elf_Ehdr *hdr,
return 0;
}
-#ifdef MODULES_VADDR
void *module_alloc(unsigned long size)
{
+ unsigned long start = VMALLOC_START;
+ unsigned long end = VMALLOC_END;
+
+#ifdef MODULES_VADDR
BUILD_BUG_ON(TASK_SIZE > MODULES_VADDR);
+ start = MODULES_VADDR;
+ end = MODULES_END;
+#endif
+
+ /*
+ * Don't do huge page allocations for modules yet until more testing
+ * is done. STRICT_MODULE_RWX may require extra work to support this
+ * too.
+ */
- return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, GFP_KERNEL,
- PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
+ return __vmalloc_node_range(size, 1, start, end, GFP_KERNEL,
+ PAGE_KERNEL_EXEC,
+ VM_NO_HUGE_VMAP | VM_FLUSH_RESET_PERMS,
+ NUMA_NO_NODE,
__builtin_return_address(0));
}
-#endif
--
2.23.0
^ permalink raw reply related
* [PATCH v12 13/14] mm/vmalloc: Hugepage vmalloc mappings
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Ding Tianhong, linux-kernel, Nicholas Piggin,
Christoph Hellwig, Jonathan Cameron, Rick Edgecombe, linuxppc-dev
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
Support huge page vmalloc mappings. Config option HAVE_ARCH_HUGE_VMALLOC
enables support on architectures that define HAVE_ARCH_HUGE_VMAP and
supports PMD sized vmap mappings.
vmalloc will attempt to allocate PMD-sized pages if allocating PMD size
or larger, and fall back to small pages if that was unsuccessful.
Architectures must ensure that any arch specific vmalloc allocations
that require PAGE_SIZE mappings (e.g., module allocations vs strict
module rwx) use the VM_NOHUGE flag to inhibit larger mappings.
This can result in more internal fragmentation and memory overhead for a
given allocation, an option nohugevmalloc is added to disable at boot.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/Kconfig | 11 ++
include/linux/vmalloc.h | 21 ++++
mm/page_alloc.c | 5 +-
mm/vmalloc.c | 215 +++++++++++++++++++++++++++++++---------
4 files changed, 205 insertions(+), 47 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 24862d15f3a3..eef170e0c9b8 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -724,6 +724,17 @@ config HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
config HAVE_ARCH_HUGE_VMAP
bool
+#
+# Archs that select this would be capable of PMD-sized vmaps (i.e.,
+# arch_vmap_pmd_supported() returns true), and they must make no assumptions
+# that vmalloc memory is mapped with PAGE_SIZE ptes. The VM_NO_HUGE_VMAP flag
+# can be used to prohibit arch-specific allocations from using hugepages to
+# help with this (e.g., modules may require it).
+#
+config HAVE_ARCH_HUGE_VMALLOC
+ depends on HAVE_ARCH_HUGE_VMAP
+ bool
+
config ARCH_WANT_HUGE_PMD_SHARE
bool
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 99ea72d547dc..93270adf5db5 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -25,6 +25,7 @@ struct notifier_block; /* in notifier.h */
#define VM_NO_GUARD 0x00000040 /* don't add guard page */
#define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */
#define VM_MAP_PUT_PAGES 0x00000100 /* put pages and free array in vfree */
+#define VM_NO_HUGE_VMAP 0x00000200 /* force PAGE_SIZE pte mapping */
/*
* VM_KASAN is used slighly differently depending on CONFIG_KASAN_VMALLOC.
@@ -59,6 +60,9 @@ struct vm_struct {
unsigned long size;
unsigned long flags;
struct page **pages;
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+ unsigned int page_order;
+#endif
unsigned int nr_pages;
phys_addr_t phys_addr;
const void *caller;
@@ -193,6 +197,22 @@ void free_vm_area(struct vm_struct *area);
extern struct vm_struct *remove_vm_area(const void *addr);
extern struct vm_struct *find_vm_area(const void *addr);
+static inline bool is_vm_area_hugepages(const void *addr)
+{
+ /*
+ * This may not 100% tell if the area is mapped with > PAGE_SIZE
+ * page table entries, if for some reason the architecture indicates
+ * larger sizes are available but decides not to use them, nothing
+ * prevents that. This only indicates the size of the physical page
+ * allocated in the vmalloc layer.
+ */
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+ return find_vm_area(addr)->page_order > 0;
+#else
+ return false;
+#endif
+}
+
#ifdef CONFIG_MMU
int vmap_range(unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
@@ -210,6 +230,7 @@ static inline void set_vm_flush_reset_perms(void *addr)
if (vm)
vm->flags |= VM_FLUSH_RESET_PERMS;
}
+
#else
static inline int
map_kernel_range_noflush(unsigned long start, unsigned long size,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 519a60d5b6f7..1116ce45744b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -72,6 +72,7 @@
#include <linux/padata.h>
#include <linux/khugepaged.h>
#include <linux/buffer_head.h>
+#include <linux/vmalloc.h>
#include <asm/sections.h>
#include <asm/tlbflush.h>
@@ -8240,6 +8241,7 @@ void *__init alloc_large_system_hash(const char *tablename,
void *table = NULL;
gfp_t gfp_flags;
bool virt;
+ bool huge;
/* allow the kernel cmdline to have a say */
if (!numentries) {
@@ -8307,6 +8309,7 @@ void *__init alloc_large_system_hash(const char *tablename,
} else if (get_order(size) >= MAX_ORDER || hashdist) {
table = __vmalloc(size, gfp_flags);
virt = true;
+ huge = is_vm_area_hugepages(table);
} else {
/*
* If bucketsize is not a power-of-two, we may free
@@ -8323,7 +8326,7 @@ void *__init alloc_large_system_hash(const char *tablename,
pr_info("%s hash table entries: %ld (order: %d, %lu bytes, %s)\n",
tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size,
- virt ? "vmalloc" : "linear");
+ virt ? (huge ? "vmalloc hugepage" : "vmalloc") : "linear");
if (_hash_shift)
*_hash_shift = log2qty;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 47ab4338cfff..e9a28de04182 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -42,6 +42,19 @@
#include "internal.h"
#include "pgalloc-track.h"
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+static bool __ro_after_init vmap_allow_huge = true;
+
+static int __init set_nohugevmalloc(char *str)
+{
+ vmap_allow_huge = false;
+ return 0;
+}
+early_param("nohugevmalloc", set_nohugevmalloc);
+#else /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */
+static const bool vmap_allow_huge = false;
+#endif /* CONFIG_HAVE_ARCH_HUGE_VMALLOC */
+
bool is_vmalloc_addr(const void *x)
{
unsigned long addr = (unsigned long)x;
@@ -483,31 +496,12 @@ static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr,
return 0;
}
-/**
- * map_kernel_range_noflush - map kernel VM area with the specified pages
- * @addr: start of the VM area to map
- * @size: size of the VM area to map
- * @prot: page protection flags to use
- * @pages: pages to map
- *
- * Map PFN_UP(@size) pages at @addr. The VM area @addr and @size specify should
- * have been allocated using get_vm_area() and its friends.
- *
- * NOTE:
- * This function does NOT do any cache flushing. The caller is responsible for
- * calling flush_cache_vmap() on to-be-mapped areas before calling this
- * function.
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int map_kernel_range_noflush(unsigned long addr, unsigned long size,
- pgprot_t prot, struct page **pages)
+static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end,
+ pgprot_t prot, struct page **pages)
{
unsigned long start = addr;
- unsigned long end = addr + size;
- unsigned long next;
pgd_t *pgd;
+ unsigned long next;
int err = 0;
int nr = 0;
pgtbl_mod_mask mask = 0;
@@ -529,6 +523,66 @@ int map_kernel_range_noflush(unsigned long addr, unsigned long size,
return 0;
}
+static int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
+ pgprot_t prot, struct page **pages, unsigned int page_shift)
+{
+ unsigned int i, nr = (end - addr) >> PAGE_SHIFT;
+
+ WARN_ON(page_shift < PAGE_SHIFT);
+
+ if (!IS_ENABLED(CONFIG_HAVE_ARCH_HUGE_VMALLOC) ||
+ page_shift == PAGE_SHIFT)
+ return vmap_small_pages_range_noflush(addr, end, prot, pages);
+
+ for (i = 0; i < nr; i += 1U << (page_shift - PAGE_SHIFT)) {
+ int err;
+
+ err = vmap_range_noflush(addr, addr + (1UL << page_shift),
+ __pa(page_address(pages[i])), prot,
+ page_shift);
+ if (err)
+ return err;
+
+ addr += 1UL << page_shift;
+ }
+
+ return 0;
+}
+
+static int vmap_pages_range(unsigned long addr, unsigned long end,
+ pgprot_t prot, struct page **pages, unsigned int page_shift)
+{
+ int err;
+
+ err = vmap_pages_range_noflush(addr, end, prot, pages, page_shift);
+ flush_cache_vmap(addr, end);
+ return err;
+}
+
+/**
+ * map_kernel_range_noflush - map kernel VM area with the specified pages
+ * @addr: start of the VM area to map
+ * @size: size of the VM area to map
+ * @prot: page protection flags to use
+ * @pages: pages to map
+ *
+ * Map PFN_UP(@size) pages at @addr. The VM area @addr and @size specify should
+ * have been allocated using get_vm_area() and its friends.
+ *
+ * NOTE:
+ * This function does NOT do any cache flushing. The caller is responsible for
+ * calling flush_cache_vmap() on to-be-mapped areas before calling this
+ * function.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int map_kernel_range_noflush(unsigned long addr, unsigned long size,
+ pgprot_t prot, struct page **pages)
+{
+ return vmap_pages_range_noflush(addr, addr + size, prot, pages, PAGE_SHIFT);
+}
+
int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot,
struct page **pages)
{
@@ -2112,6 +2166,24 @@ EXPORT_SYMBOL(vm_map_ram);
static struct vm_struct *vmlist __initdata;
+static inline unsigned int vm_area_page_order(struct vm_struct *vm)
+{
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+ return vm->page_order;
+#else
+ return 0;
+#endif
+}
+
+static inline void set_vm_area_page_order(struct vm_struct *vm, unsigned int order)
+{
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC
+ vm->page_order = order;
+#else
+ BUG_ON(order != 0);
+#endif
+}
+
/**
* vm_area_add_early - add vmap area early during boot
* @vm: vm_struct to add
@@ -2422,6 +2494,7 @@ static inline void set_area_direct_map(const struct vm_struct *area,
{
int i;
+ /* HUGE_VMALLOC passes small pages to set_direct_map */
for (i = 0; i < area->nr_pages; i++)
if (page_address(area->pages[i]))
set_direct_map(area->pages[i]);
@@ -2431,6 +2504,7 @@ static inline void set_area_direct_map(const struct vm_struct *area,
static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
{
unsigned long start = ULONG_MAX, end = 0;
+ unsigned int page_order = vm_area_page_order(area);
int flush_reset = area->flags & VM_FLUSH_RESET_PERMS;
int flush_dmap = 0;
int i;
@@ -2455,11 +2529,14 @@ static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages)
* map. Find the start and end range of the direct mappings to make sure
* the vm_unmap_aliases() flush includes the direct map.
*/
- for (i = 0; i < area->nr_pages; i++) {
+ for (i = 0; i < area->nr_pages; i += 1U << page_order) {
unsigned long addr = (unsigned long)page_address(area->pages[i]);
if (addr) {
+ unsigned long page_size;
+
+ page_size = PAGE_SIZE << page_order;
start = min(addr, start);
- end = max(addr + PAGE_SIZE, end);
+ end = max(addr + page_size, end);
flush_dmap = 1;
}
}
@@ -2500,13 +2577,14 @@ static void __vunmap(const void *addr, int deallocate_pages)
vm_remove_mappings(area, deallocate_pages);
if (deallocate_pages) {
+ unsigned int page_order = vm_area_page_order(area);
int i;
- for (i = 0; i < area->nr_pages; i++) {
+ for (i = 0; i < area->nr_pages; i += 1U << page_order) {
struct page *page = area->pages[i];
BUG_ON(!page);
- __free_pages(page, 0);
+ __free_pages(page, page_order);
}
atomic_long_sub(area->nr_pages, &nr_vmalloc_pages);
@@ -2697,15 +2775,19 @@ EXPORT_SYMBOL_GPL(vmap_pfn);
#endif /* CONFIG_VMAP_PFN */
static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
- pgprot_t prot, int node)
+ pgprot_t prot, unsigned int page_shift,
+ int node)
{
const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
- unsigned int nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
+ unsigned long addr = (unsigned long)area->addr;
+ unsigned long size = get_vm_area_size(area);
unsigned long array_size;
- unsigned int i;
+ unsigned int nr_small_pages = size >> PAGE_SHIFT;
+ unsigned int page_order;
struct page **pages;
+ unsigned int i;
- array_size = (unsigned long)nr_pages * sizeof(struct page *);
+ array_size = (unsigned long)nr_small_pages * sizeof(struct page *);
gfp_mask |= __GFP_NOWARN;
if (!(gfp_mask & (GFP_DMA | GFP_DMA32)))
gfp_mask |= __GFP_HIGHMEM;
@@ -2724,30 +2806,37 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
}
area->pages = pages;
- area->nr_pages = nr_pages;
+ area->nr_pages = nr_small_pages;
+ set_vm_area_page_order(area, page_shift - PAGE_SHIFT);
- for (i = 0; i < area->nr_pages; i++) {
- struct page *page;
+ page_order = vm_area_page_order(area);
- if (node == NUMA_NO_NODE)
- page = alloc_page(gfp_mask);
- else
- page = alloc_pages_node(node, gfp_mask, 0);
+ /*
+ * Careful, we allocate and map page_order pages, but tracking is done
+ * per PAGE_SIZE page so as to keep the vm_struct APIs independent of
+ * the physical/mapped size.
+ */
+ for (i = 0; i < area->nr_pages; i += 1U << page_order) {
+ struct page *page;
+ int p;
+ page = alloc_pages_node(node, gfp_mask, page_order);
if (unlikely(!page)) {
/* Successfully allocated i pages, free them in __vfree() */
area->nr_pages = i;
atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
goto fail;
}
- area->pages[i] = page;
+
+ for (p = 0; p < (1U << page_order); p++)
+ area->pages[i + p] = page + p;
+
if (gfpflags_allow_blocking(gfp_mask))
cond_resched();
}
atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
- if (map_kernel_range((unsigned long)area->addr, get_vm_area_size(area),
- prot, pages) < 0)
+ if (vmap_pages_range(addr, addr + size, prot, pages, page_shift) < 0)
goto fail;
return area->addr;
@@ -2755,7 +2844,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
fail:
warn_alloc(gfp_mask, NULL,
"vmalloc: allocation failure, allocated %ld of %ld bytes",
- (area->nr_pages*PAGE_SIZE), area->size);
+ (area->nr_pages*PAGE_SIZE), size);
__vfree(area->addr);
return NULL;
}
@@ -2786,19 +2875,43 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
struct vm_struct *area;
void *addr;
unsigned long real_size = size;
+ unsigned long real_align = align;
+ unsigned int shift = PAGE_SHIFT;
- size = PAGE_ALIGN(size);
if (!size || (size >> PAGE_SHIFT) > totalram_pages())
goto fail;
- area = __get_vm_area_node(real_size, align, VM_ALLOC | VM_UNINITIALIZED |
+ if (vmap_allow_huge && !(vm_flags & VM_NO_HUGE_VMAP) &&
+ arch_vmap_pmd_supported(prot)) {
+ unsigned long size_per_node;
+
+ /*
+ * Try huge pages. Only try for PAGE_KERNEL allocations,
+ * others like modules don't yet expect huge pages in
+ * their allocations due to apply_to_page_range not
+ * supporting them.
+ */
+
+ size_per_node = size;
+ if (node == NUMA_NO_NODE)
+ size_per_node /= num_online_nodes();
+ if (size_per_node >= PMD_SIZE) {
+ shift = PMD_SHIFT;
+ align = max(real_align, 1UL << shift);
+ size = ALIGN(real_size, 1UL << shift);
+ }
+ }
+
+again:
+ size = PAGE_ALIGN(size);
+ area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED |
vm_flags, start, end, node, gfp_mask, caller);
if (!area)
goto fail;
- addr = __vmalloc_area_node(area, gfp_mask, prot, node);
+ addr = __vmalloc_area_node(area, gfp_mask, prot, shift, node);
if (!addr)
- return NULL;
+ goto fail;
/*
* In this function, newly allocated vm_struct has VM_UNINITIALIZED
@@ -2812,8 +2925,18 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
return addr;
fail:
- warn_alloc(gfp_mask, NULL,
+ if (shift > PAGE_SHIFT) {
+ shift = PAGE_SHIFT;
+ align = real_align;
+ size = real_size;
+ goto again;
+ }
+
+ if (!area) {
+ /* Warn for area allocation, page allocations already warn */
+ warn_alloc(gfp_mask, NULL,
"vmalloc: allocation failure: %lu bytes", real_size);
+ }
return NULL;
}
--
2.23.0
^ permalink raw reply related
* [PATCH v12 12/14] mm/vmalloc: add vmap_range_noflush variant
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Ding Tianhong, linux-kernel, Nicholas Piggin,
Christoph Hellwig, Jonathan Cameron, Rick Edgecombe, linuxppc-dev,
Christoph Hellwig
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
As a side-effect, the order of flush_cache_vmap() and
arch_sync_kernel_mappings() calls are switched, but that now matches
the other callers in this file.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
mm/vmalloc.c | 16 +++++++++++++---
1 file changed, 13 insertions(+), 3 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index f043386bb51d..47ab4338cfff 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -240,7 +240,7 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
return 0;
}
-int vmap_range(unsigned long addr, unsigned long end,
+static int vmap_range_noflush(unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
unsigned int max_page_shift)
{
@@ -263,14 +263,24 @@ int vmap_range(unsigned long addr, unsigned long end,
break;
} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
- flush_cache_vmap(start, end);
-
if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
arch_sync_kernel_mappings(start, end);
return err;
}
+int vmap_range(unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
+{
+ int err;
+
+ err = vmap_range_noflush(addr, end, phys_addr, prot, max_page_shift);
+ flush_cache_vmap(addr, end);
+
+ return err;
+}
+
static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
pgtbl_mod_mask *mask)
{
--
2.23.0
^ permalink raw reply related
* [PATCH v12 11/14] mm: Move vmap_range from mm/ioremap.c to mm/vmalloc.c
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Ding Tianhong, linux-kernel, Nicholas Piggin,
Christoph Hellwig, Jonathan Cameron, Rick Edgecombe, linuxppc-dev,
Christoph Hellwig
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
This is a generic kernel virtual memory mapper, not specific to ioremap.
Code is unchanged other than making vmap_range non-static.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
include/linux/vmalloc.h | 3 +
mm/ioremap.c | 203 ----------------------------------------
mm/vmalloc.c | 202 +++++++++++++++++++++++++++++++++++++++
3 files changed, 205 insertions(+), 203 deletions(-)
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 9f7b8b00101b..99ea72d547dc 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -194,6 +194,9 @@ extern struct vm_struct *remove_vm_area(const void *addr);
extern struct vm_struct *find_vm_area(const void *addr);
#ifdef CONFIG_MMU
+int vmap_range(unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift);
extern int map_kernel_range_noflush(unsigned long start, unsigned long size,
pgprot_t prot, struct page **pages);
int map_kernel_range(unsigned long start, unsigned long size, pgprot_t prot,
diff --git a/mm/ioremap.c b/mm/ioremap.c
index 3264d0203785..d1dcc7e744ac 100644
--- a/mm/ioremap.c
+++ b/mm/ioremap.c
@@ -28,209 +28,6 @@ early_param("nohugeiomap", set_nohugeiomap);
static const bool iomap_max_page_shift = PAGE_SHIFT;
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
-static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
-{
- pte_t *pte;
- u64 pfn;
-
- pfn = phys_addr >> PAGE_SHIFT;
- pte = pte_alloc_kernel_track(pmd, addr, mask);
- if (!pte)
- return -ENOMEM;
- do {
- BUG_ON(!pte_none(*pte));
- set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
- pfn++;
- } while (pte++, addr += PAGE_SIZE, addr != end);
- *mask |= PGTBL_PTE_MODIFIED;
- return 0;
-}
-
-static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot,
- unsigned int max_page_shift)
-{
- if (max_page_shift < PMD_SHIFT)
- return 0;
-
- if (!arch_vmap_pmd_supported(prot))
- return 0;
-
- if ((end - addr) != PMD_SIZE)
- return 0;
-
- if (!IS_ALIGNED(addr, PMD_SIZE))
- return 0;
-
- if (!IS_ALIGNED(phys_addr, PMD_SIZE))
- return 0;
-
- if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr))
- return 0;
-
- return pmd_set_huge(pmd, phys_addr, prot);
-}
-
-static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot,
- unsigned int max_page_shift, pgtbl_mod_mask *mask)
-{
- pmd_t *pmd;
- unsigned long next;
-
- pmd = pmd_alloc_track(&init_mm, pud, addr, mask);
- if (!pmd)
- return -ENOMEM;
- do {
- next = pmd_addr_end(addr, end);
-
- if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot,
- max_page_shift)) {
- *mask |= PGTBL_PMD_MODIFIED;
- continue;
- }
-
- if (vmap_pte_range(pmd, addr, next, phys_addr, prot, mask))
- return -ENOMEM;
- } while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
- return 0;
-}
-
-static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot,
- unsigned int max_page_shift)
-{
- if (max_page_shift < PUD_SHIFT)
- return 0;
-
- if (!arch_vmap_pud_supported(prot))
- return 0;
-
- if ((end - addr) != PUD_SIZE)
- return 0;
-
- if (!IS_ALIGNED(addr, PUD_SIZE))
- return 0;
-
- if (!IS_ALIGNED(phys_addr, PUD_SIZE))
- return 0;
-
- if (pud_present(*pud) && !pud_free_pmd_page(pud, addr))
- return 0;
-
- return pud_set_huge(pud, phys_addr, prot);
-}
-
-static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot,
- unsigned int max_page_shift, pgtbl_mod_mask *mask)
-{
- pud_t *pud;
- unsigned long next;
-
- pud = pud_alloc_track(&init_mm, p4d, addr, mask);
- if (!pud)
- return -ENOMEM;
- do {
- next = pud_addr_end(addr, end);
-
- if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot,
- max_page_shift)) {
- *mask |= PGTBL_PUD_MODIFIED;
- continue;
- }
-
- if (vmap_pmd_range(pud, addr, next, phys_addr, prot,
- max_page_shift, mask))
- return -ENOMEM;
- } while (pud++, phys_addr += (next - addr), addr = next, addr != end);
- return 0;
-}
-
-static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot,
- unsigned int max_page_shift)
-{
- if (max_page_shift < P4D_SHIFT)
- return 0;
-
- if (!arch_vmap_p4d_supported(prot))
- return 0;
-
- if ((end - addr) != P4D_SIZE)
- return 0;
-
- if (!IS_ALIGNED(addr, P4D_SIZE))
- return 0;
-
- if (!IS_ALIGNED(phys_addr, P4D_SIZE))
- return 0;
-
- if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr))
- return 0;
-
- return p4d_set_huge(p4d, phys_addr, prot);
-}
-
-static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot,
- unsigned int max_page_shift, pgtbl_mod_mask *mask)
-{
- p4d_t *p4d;
- unsigned long next;
-
- p4d = p4d_alloc_track(&init_mm, pgd, addr, mask);
- if (!p4d)
- return -ENOMEM;
- do {
- next = p4d_addr_end(addr, end);
-
- if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot,
- max_page_shift)) {
- *mask |= PGTBL_P4D_MODIFIED;
- continue;
- }
-
- if (vmap_pud_range(p4d, addr, next, phys_addr, prot,
- max_page_shift, mask))
- return -ENOMEM;
- } while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
- return 0;
-}
-
-static int vmap_range(unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot,
- unsigned int max_page_shift)
-{
- pgd_t *pgd;
- unsigned long start;
- unsigned long next;
- int err;
- pgtbl_mod_mask mask = 0;
-
- might_sleep();
- BUG_ON(addr >= end);
-
- start = addr;
- pgd = pgd_offset_k(addr);
- do {
- next = pgd_addr_end(addr, end);
- err = vmap_p4d_range(pgd, addr, next, phys_addr, prot,
- max_page_shift, &mask);
- if (err)
- break;
- } while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
-
- flush_cache_vmap(start, end);
-
- if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
- arch_sync_kernel_mappings(start, end);
-
- return err;
-}
-
int ioremap_page_range(unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 7f2f36116980..f043386bb51d 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -68,6 +68,208 @@ static void free_work(struct work_struct *w)
}
/*** Page table manipulation functions ***/
+static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ pgtbl_mod_mask *mask)
+{
+ pte_t *pte;
+ u64 pfn;
+
+ pfn = phys_addr >> PAGE_SHIFT;
+ pte = pte_alloc_kernel_track(pmd, addr, mask);
+ if (!pte)
+ return -ENOMEM;
+ do {
+ BUG_ON(!pte_none(*pte));
+ set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
+ pfn++;
+ } while (pte++, addr += PAGE_SIZE, addr != end);
+ *mask |= PGTBL_PTE_MODIFIED;
+ return 0;
+}
+
+static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
+{
+ if (max_page_shift < PMD_SHIFT)
+ return 0;
+
+ if (!arch_vmap_pmd_supported(prot))
+ return 0;
+
+ if ((end - addr) != PMD_SIZE)
+ return 0;
+
+ if (!IS_ALIGNED(addr, PMD_SIZE))
+ return 0;
+
+ if (!IS_ALIGNED(phys_addr, PMD_SIZE))
+ return 0;
+
+ if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr))
+ return 0;
+
+ return pmd_set_huge(pmd, phys_addr, prot);
+}
+
+static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift, pgtbl_mod_mask *mask)
+{
+ pmd_t *pmd;
+ unsigned long next;
+
+ pmd = pmd_alloc_track(&init_mm, pud, addr, mask);
+ if (!pmd)
+ return -ENOMEM;
+ do {
+ next = pmd_addr_end(addr, end);
+
+ if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot,
+ max_page_shift)) {
+ *mask |= PGTBL_PMD_MODIFIED;
+ continue;
+ }
+
+ if (vmap_pte_range(pmd, addr, next, phys_addr, prot, mask))
+ return -ENOMEM;
+ } while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
+ return 0;
+}
+
+static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
+{
+ if (max_page_shift < PUD_SHIFT)
+ return 0;
+
+ if (!arch_vmap_pud_supported(prot))
+ return 0;
+
+ if ((end - addr) != PUD_SIZE)
+ return 0;
+
+ if (!IS_ALIGNED(addr, PUD_SIZE))
+ return 0;
+
+ if (!IS_ALIGNED(phys_addr, PUD_SIZE))
+ return 0;
+
+ if (pud_present(*pud) && !pud_free_pmd_page(pud, addr))
+ return 0;
+
+ return pud_set_huge(pud, phys_addr, prot);
+}
+
+static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift, pgtbl_mod_mask *mask)
+{
+ pud_t *pud;
+ unsigned long next;
+
+ pud = pud_alloc_track(&init_mm, p4d, addr, mask);
+ if (!pud)
+ return -ENOMEM;
+ do {
+ next = pud_addr_end(addr, end);
+
+ if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot,
+ max_page_shift)) {
+ *mask |= PGTBL_PUD_MODIFIED;
+ continue;
+ }
+
+ if (vmap_pmd_range(pud, addr, next, phys_addr, prot,
+ max_page_shift, mask))
+ return -ENOMEM;
+ } while (pud++, phys_addr += (next - addr), addr = next, addr != end);
+ return 0;
+}
+
+static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
+{
+ if (max_page_shift < P4D_SHIFT)
+ return 0;
+
+ if (!arch_vmap_p4d_supported(prot))
+ return 0;
+
+ if ((end - addr) != P4D_SIZE)
+ return 0;
+
+ if (!IS_ALIGNED(addr, P4D_SIZE))
+ return 0;
+
+ if (!IS_ALIGNED(phys_addr, P4D_SIZE))
+ return 0;
+
+ if (p4d_present(*p4d) && !p4d_free_pud_page(p4d, addr))
+ return 0;
+
+ return p4d_set_huge(p4d, phys_addr, prot);
+}
+
+static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift, pgtbl_mod_mask *mask)
+{
+ p4d_t *p4d;
+ unsigned long next;
+
+ p4d = p4d_alloc_track(&init_mm, pgd, addr, mask);
+ if (!p4d)
+ return -ENOMEM;
+ do {
+ next = p4d_addr_end(addr, end);
+
+ if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot,
+ max_page_shift)) {
+ *mask |= PGTBL_P4D_MODIFIED;
+ continue;
+ }
+
+ if (vmap_pud_range(p4d, addr, next, phys_addr, prot,
+ max_page_shift, mask))
+ return -ENOMEM;
+ } while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
+ return 0;
+}
+
+int vmap_range(unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
+{
+ pgd_t *pgd;
+ unsigned long start;
+ unsigned long next;
+ int err;
+ pgtbl_mod_mask mask = 0;
+
+ might_sleep();
+ BUG_ON(addr >= end);
+
+ start = addr;
+ pgd = pgd_offset_k(addr);
+ do {
+ next = pgd_addr_end(addr, end);
+ err = vmap_p4d_range(pgd, addr, next, phys_addr, prot,
+ max_page_shift, &mask);
+ if (err)
+ break;
+ } while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
+
+ flush_cache_vmap(start, end);
+
+ if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
+ arch_sync_kernel_mappings(start, end);
+
+ return err;
+}
static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
pgtbl_mod_mask *mask)
--
2.23.0
^ permalink raw reply related
* [PATCH v12 10/14] mm/vmalloc: provide fallback arch huge vmap support functions
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Ding Tianhong, linux-kernel, Nicholas Piggin,
Christoph Hellwig, Jonathan Cameron, Rick Edgecombe, linuxppc-dev,
Christoph Hellwig
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
If an architecture doesn't support a particular page table level as
a huge vmap page size then allow it to skip defining the support
query function.
Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/arm64/include/asm/vmalloc.h | 7 +++----
arch/powerpc/include/asm/vmalloc.h | 7 +++----
arch/x86/include/asm/vmalloc.h | 13 +++++--------
include/linux/vmalloc.h | 24 ++++++++++++++++++++----
4 files changed, 31 insertions(+), 20 deletions(-)
diff --git a/arch/arm64/include/asm/vmalloc.h b/arch/arm64/include/asm/vmalloc.h
index fc9a12d6cc1a..7a22aeea9bb5 100644
--- a/arch/arm64/include/asm/vmalloc.h
+++ b/arch/arm64/include/asm/vmalloc.h
@@ -4,11 +4,8 @@
#include <asm/page.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-static inline bool arch_vmap_p4d_supported(pgprot_t prot)
-{
- return false;
-}
+#define arch_vmap_pud_supported arch_vmap_pud_supported
static inline bool arch_vmap_pud_supported(pgprot_t prot)
{
/*
@@ -19,11 +16,13 @@ static inline bool arch_vmap_pud_supported(pgprot_t prot)
!IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
}
+#define arch_vmap_pmd_supported arch_vmap_pmd_supported
static inline bool arch_vmap_pmd_supported(pgprot_t prot)
{
/* See arch_vmap_pud_supported() */
return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
}
+
#endif
#endif /* _ASM_ARM64_VMALLOC_H */
diff --git a/arch/powerpc/include/asm/vmalloc.h b/arch/powerpc/include/asm/vmalloc.h
index 3f0c153befb0..4c69ece52a31 100644
--- a/arch/powerpc/include/asm/vmalloc.h
+++ b/arch/powerpc/include/asm/vmalloc.h
@@ -5,21 +5,20 @@
#include <asm/page.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-static inline bool arch_vmap_p4d_supported(pgprot_t prot)
-{
- return false;
-}
+#define arch_vmap_pud_supported arch_vmap_pud_supported
static inline bool arch_vmap_pud_supported(pgprot_t prot)
{
/* HPT does not cope with large pages in the vmalloc area */
return radix_enabled();
}
+#define arch_vmap_pmd_supported arch_vmap_pmd_supported
static inline bool arch_vmap_pmd_supported(pgprot_t prot)
{
return radix_enabled();
}
+
#endif
#endif /* _ASM_POWERPC_VMALLOC_H */
diff --git a/arch/x86/include/asm/vmalloc.h b/arch/x86/include/asm/vmalloc.h
index e714b00fc0ca..49ce331f3ac6 100644
--- a/arch/x86/include/asm/vmalloc.h
+++ b/arch/x86/include/asm/vmalloc.h
@@ -6,24 +6,21 @@
#include <asm/pgtable_areas.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-static inline bool arch_vmap_p4d_supported(pgprot_t prot)
-{
- return false;
-}
+#ifdef CONFIG_X86_64
+#define arch_vmap_pud_supported arch_vmap_pud_supported
static inline bool arch_vmap_pud_supported(pgprot_t prot)
{
-#ifdef CONFIG_X86_64
return boot_cpu_has(X86_FEATURE_GBPAGES);
-#else
- return false;
-#endif
}
+#endif
+#define arch_vmap_pmd_supported arch_vmap_pmd_supported
static inline bool arch_vmap_pmd_supported(pgprot_t prot)
{
return boot_cpu_has(X86_FEATURE_PSE);
}
+
#endif
#endif /* _ASM_X86_VMALLOC_H */
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 00bd62bd701e..9f7b8b00101b 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -83,10 +83,26 @@ struct vmap_area {
};
};
-#ifndef CONFIG_HAVE_ARCH_HUGE_VMAP
-static inline bool arch_vmap_p4d_supported(pgprot_t prot) { return false; }
-static inline bool arch_vmap_pud_supported(pgprot_t prot) { return false; }
-static inline bool arch_vmap_pmd_supported(pgprot_t prot) { return false; }
+/* archs that select HAVE_ARCH_HUGE_VMAP should override one or more of these */
+#ifndef arch_vmap_p4d_supported
+static inline bool arch_vmap_p4d_supported(pgprot_t prot)
+{
+ return false;
+}
+#endif
+
+#ifndef arch_vmap_pud_supported
+static inline bool arch_vmap_pud_supported(pgprot_t prot)
+{
+ return false;
+}
+#endif
+
+#ifndef arch_vmap_pmd_supported
+static inline bool arch_vmap_pmd_supported(pgprot_t prot)
+{
+ return false;
+}
#endif
/*
--
2.23.0
^ permalink raw reply related
* [PATCH v12 09/14] x86: inline huge vmap supported functions
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, x86, H. Peter Anvin, Ding Tianhong, linux-kernel,
Nicholas Piggin, Christoph Hellwig, Ingo Molnar, Borislav Petkov,
Jonathan Cameron, Thomas Gleixner, Rick Edgecombe, linuxppc-dev
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
This allows unsupported levels to be constant folded away, and so
p4d_free_pud_page can be removed because it's no longer linked to.
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: x86@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/x86/include/asm/vmalloc.h | 22 +++++++++++++++++++---
arch/x86/mm/ioremap.c | 21 ---------------------
arch/x86/mm/pgtable.c | 13 -------------
3 files changed, 19 insertions(+), 37 deletions(-)
diff --git a/arch/x86/include/asm/vmalloc.h b/arch/x86/include/asm/vmalloc.h
index 094ea2b565f3..e714b00fc0ca 100644
--- a/arch/x86/include/asm/vmalloc.h
+++ b/arch/x86/include/asm/vmalloc.h
@@ -1,13 +1,29 @@
#ifndef _ASM_X86_VMALLOC_H
#define _ASM_X86_VMALLOC_H
+#include <asm/cpufeature.h>
#include <asm/page.h>
#include <asm/pgtable_areas.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-bool arch_vmap_p4d_supported(pgprot_t prot);
-bool arch_vmap_pud_supported(pgprot_t prot);
-bool arch_vmap_pmd_supported(pgprot_t prot);
+static inline bool arch_vmap_p4d_supported(pgprot_t prot)
+{
+ return false;
+}
+
+static inline bool arch_vmap_pud_supported(pgprot_t prot)
+{
+#ifdef CONFIG_X86_64
+ return boot_cpu_has(X86_FEATURE_GBPAGES);
+#else
+ return false;
+#endif
+}
+
+static inline bool arch_vmap_pmd_supported(pgprot_t prot)
+{
+ return boot_cpu_has(X86_FEATURE_PSE);
+}
#endif
#endif /* _ASM_X86_VMALLOC_H */
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index fbaf0c447986..12c686c65ea9 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -481,27 +481,6 @@ void iounmap(volatile void __iomem *addr)
}
EXPORT_SYMBOL(iounmap);
-#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-bool arch_vmap_p4d_supported(pgprot_t prot)
-{
- return false;
-}
-
-bool arch_vmap_pud_supported(pgprot_t prot)
-{
-#ifdef CONFIG_X86_64
- return boot_cpu_has(X86_FEATURE_GBPAGES);
-#else
- return false;
-#endif
-}
-
-bool arch_vmap_pmd_supported(pgprot_t prot)
-{
- return boot_cpu_has(X86_FEATURE_PSE);
-}
-#endif
-
/*
* Convert a physical pointer to a virtual kernel pointer for /dev/mem
* access
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index f6a9e2e36642..d27cf69e811d 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -780,14 +780,6 @@ int pmd_clear_huge(pmd_t *pmd)
return 0;
}
-/*
- * Until we support 512GB pages, skip them in the vmap area.
- */
-int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
-{
- return 0;
-}
-
#ifdef CONFIG_X86_64
/**
* pud_free_pmd_page - Clear pud entry and free pmd page.
@@ -861,11 +853,6 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
#else /* !CONFIG_X86_64 */
-int pud_free_pmd_page(pud_t *pud, unsigned long addr)
-{
- return pud_none(*pud);
-}
-
/*
* Disable free page handling on x86-PAE. This assures that ioremap()
* does not update sync'd pmd entries. See vmalloc_sync_one().
--
2.23.0
^ permalink raw reply related
* [PATCH v12 08/14] arm64: inline huge vmap supported functions
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Will Deacon, Catalin Marinas, Ding Tianhong,
linux-kernel, Nicholas Piggin, Christoph Hellwig,
Jonathan Cameron, Rick Edgecombe, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
This allows unsupported levels to be constant folded away, and so
p4d_free_pud_page can be removed because it's no longer linked to.
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/arm64/include/asm/vmalloc.h | 23 ++++++++++++++++++++---
arch/arm64/mm/mmu.c | 26 --------------------------
2 files changed, 20 insertions(+), 29 deletions(-)
diff --git a/arch/arm64/include/asm/vmalloc.h b/arch/arm64/include/asm/vmalloc.h
index 597b40405319..fc9a12d6cc1a 100644
--- a/arch/arm64/include/asm/vmalloc.h
+++ b/arch/arm64/include/asm/vmalloc.h
@@ -4,9 +4,26 @@
#include <asm/page.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-bool arch_vmap_p4d_supported(pgprot_t prot);
-bool arch_vmap_pud_supported(pgprot_t prot);
-bool arch_vmap_pmd_supported(pgprot_t prot);
+static inline bool arch_vmap_p4d_supported(pgprot_t prot)
+{
+ return false;
+}
+
+static inline bool arch_vmap_pud_supported(pgprot_t prot)
+{
+ /*
+ * Only 4k granule supports level 1 block mappings.
+ * SW table walks can't handle removal of intermediate entries.
+ */
+ return IS_ENABLED(CONFIG_ARM64_4K_PAGES) &&
+ !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
+}
+
+static inline bool arch_vmap_pmd_supported(pgprot_t prot)
+{
+ /* See arch_vmap_pud_supported() */
+ return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
+}
#endif
#endif /* _ASM_ARM64_VMALLOC_H */
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 1613d290cbd1..ab9ba7c36dae 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1313,27 +1313,6 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
return dt_virt;
}
-bool arch_vmap_p4d_supported(pgprot_t prot)
-{
- return false;
-}
-
-bool arch_vmap_pud_supported(pgprot_t prot)
-{
- /*
- * Only 4k granule supports level 1 block mappings.
- * SW table walks can't handle removal of intermediate entries.
- */
- return IS_ENABLED(CONFIG_ARM64_4K_PAGES) &&
- !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
-}
-
-bool arch_vmap_pmd_supported(pgprot_t prot)
-{
- /* See arch_vmap_pud_supported() */
- return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
-}
-
int pud_set_huge(pud_t *pudp, phys_addr_t phys, pgprot_t prot)
{
pud_t new_pud = pfn_pud(__phys_to_pfn(phys), mk_pud_sect_prot(prot));
@@ -1425,11 +1404,6 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr)
return 1;
}
-int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
-{
- return 0; /* Don't attempt a block mapping */
-}
-
#ifdef CONFIG_MEMORY_HOTPLUG
static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
{
--
2.23.0
^ permalink raw reply related
* [PATCH v12 07/14] powerpc: inline huge vmap supported functions
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Ding Tianhong, linux-kernel, Nicholas Piggin,
Christoph Hellwig, Jonathan Cameron, Rick Edgecombe, linuxppc-dev
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
This allows unsupported levels to be constant folded away, and so
p4d_free_pud_page can be removed because it's no longer linked to.
Cc: linuxppc-dev@lists.ozlabs.org
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/vmalloc.h | 19 ++++++++++++++++---
arch/powerpc/mm/book3s64/radix_pgtable.c | 21 ---------------------
2 files changed, 16 insertions(+), 24 deletions(-)
diff --git a/arch/powerpc/include/asm/vmalloc.h b/arch/powerpc/include/asm/vmalloc.h
index 105abb73f075..3f0c153befb0 100644
--- a/arch/powerpc/include/asm/vmalloc.h
+++ b/arch/powerpc/include/asm/vmalloc.h
@@ -1,12 +1,25 @@
#ifndef _ASM_POWERPC_VMALLOC_H
#define _ASM_POWERPC_VMALLOC_H
+#include <asm/mmu.h>
#include <asm/page.h>
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-bool arch_vmap_p4d_supported(pgprot_t prot);
-bool arch_vmap_pud_supported(pgprot_t prot);
-bool arch_vmap_pmd_supported(pgprot_t prot);
+static inline bool arch_vmap_p4d_supported(pgprot_t prot)
+{
+ return false;
+}
+
+static inline bool arch_vmap_pud_supported(pgprot_t prot)
+{
+ /* HPT does not cope with large pages in the vmalloc area */
+ return radix_enabled();
+}
+
+static inline bool arch_vmap_pmd_supported(pgprot_t prot)
+{
+ return radix_enabled();
+}
#endif
#endif /* _ASM_POWERPC_VMALLOC_H */
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 743807fc210f..8da62afccee5 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -1082,22 +1082,6 @@ void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
set_pte_at(mm, addr, ptep, pte);
}
-bool arch_vmap_pud_supported(pgprot_t prot)
-{
- /* HPT does not cope with large pages in the vmalloc area */
- return radix_enabled();
-}
-
-bool arch_vmap_pmd_supported(pgprot_t prot)
-{
- return radix_enabled();
-}
-
-int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
-{
- return 0;
-}
-
int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
{
pte_t *ptep = (pte_t *)pud;
@@ -1181,8 +1165,3 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
return 1;
}
-
-bool arch_vmap_p4d_supported(pgprot_t prot)
-{
- return false;
-}
--
2.23.0
^ permalink raw reply related
* [PATCH v12 06/14] mm: HUGE_VMAP arch support cleanup
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, x86, H. Peter Anvin, Will Deacon, Catalin Marinas,
Ding Tianhong, linux-kernel, Nicholas Piggin, Christoph Hellwig,
Ingo Molnar, Borislav Petkov, Jonathan Cameron, Thomas Gleixner,
Rick Edgecombe, linuxppc-dev, linux-arm-kernel
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
This changes the awkward approach where architectures provide init
functions to determine which levels they can provide large mappings for,
to one where the arch is queried for each call.
This removes code and indirection, and allows constant-folding of dead
code for unsupported levels.
This also adds a prot argument to the arch query. This is unused
currently but could help with some architectures (e.g., some powerpc
processors can't map uncacheable memory with large pages).
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: x86@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Reviewed-by: Ding Tianhong <dingtianhong@huawei.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com> [arm64]
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/arm64/include/asm/vmalloc.h | 8 ++
arch/arm64/mm/mmu.c | 10 +--
arch/powerpc/include/asm/vmalloc.h | 8 ++
arch/powerpc/mm/book3s64/radix_pgtable.c | 8 +-
arch/x86/include/asm/vmalloc.h | 7 ++
arch/x86/mm/ioremap.c | 12 +--
include/linux/io.h | 9 ---
include/linux/vmalloc.h | 6 ++
init/main.c | 1 -
mm/debug_vm_pgtable.c | 4 +-
mm/ioremap.c | 94 ++++++++++--------------
11 files changed, 87 insertions(+), 80 deletions(-)
diff --git a/arch/arm64/include/asm/vmalloc.h b/arch/arm64/include/asm/vmalloc.h
index 2ca708ab9b20..597b40405319 100644
--- a/arch/arm64/include/asm/vmalloc.h
+++ b/arch/arm64/include/asm/vmalloc.h
@@ -1,4 +1,12 @@
#ifndef _ASM_ARM64_VMALLOC_H
#define _ASM_ARM64_VMALLOC_H
+#include <asm/page.h>
+
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+bool arch_vmap_p4d_supported(pgprot_t prot);
+bool arch_vmap_pud_supported(pgprot_t prot);
+bool arch_vmap_pmd_supported(pgprot_t prot);
+#endif
+
#endif /* _ASM_ARM64_VMALLOC_H */
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index ae0c3d023824..1613d290cbd1 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1313,12 +1313,12 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot)
return dt_virt;
}
-int __init arch_ioremap_p4d_supported(void)
+bool arch_vmap_p4d_supported(pgprot_t prot)
{
- return 0;
+ return false;
}
-int __init arch_ioremap_pud_supported(void)
+bool arch_vmap_pud_supported(pgprot_t prot)
{
/*
* Only 4k granule supports level 1 block mappings.
@@ -1328,9 +1328,9 @@ int __init arch_ioremap_pud_supported(void)
!IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
}
-int __init arch_ioremap_pmd_supported(void)
+bool arch_vmap_pmd_supported(pgprot_t prot)
{
- /* See arch_ioremap_pud_supported() */
+ /* See arch_vmap_pud_supported() */
return !IS_ENABLED(CONFIG_PTDUMP_DEBUGFS);
}
diff --git a/arch/powerpc/include/asm/vmalloc.h b/arch/powerpc/include/asm/vmalloc.h
index b992dfaaa161..105abb73f075 100644
--- a/arch/powerpc/include/asm/vmalloc.h
+++ b/arch/powerpc/include/asm/vmalloc.h
@@ -1,4 +1,12 @@
#ifndef _ASM_POWERPC_VMALLOC_H
#define _ASM_POWERPC_VMALLOC_H
+#include <asm/page.h>
+
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+bool arch_vmap_p4d_supported(pgprot_t prot);
+bool arch_vmap_pud_supported(pgprot_t prot);
+bool arch_vmap_pmd_supported(pgprot_t prot);
+#endif
+
#endif /* _ASM_POWERPC_VMALLOC_H */
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 98f0b243c1ab..743807fc210f 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -1082,13 +1082,13 @@ void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
set_pte_at(mm, addr, ptep, pte);
}
-int __init arch_ioremap_pud_supported(void)
+bool arch_vmap_pud_supported(pgprot_t prot)
{
/* HPT does not cope with large pages in the vmalloc area */
return radix_enabled();
}
-int __init arch_ioremap_pmd_supported(void)
+bool arch_vmap_pmd_supported(pgprot_t prot)
{
return radix_enabled();
}
@@ -1182,7 +1182,7 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
return 1;
}
-int __init arch_ioremap_p4d_supported(void)
+bool arch_vmap_p4d_supported(pgprot_t prot)
{
- return 0;
+ return false;
}
diff --git a/arch/x86/include/asm/vmalloc.h b/arch/x86/include/asm/vmalloc.h
index 29837740b520..094ea2b565f3 100644
--- a/arch/x86/include/asm/vmalloc.h
+++ b/arch/x86/include/asm/vmalloc.h
@@ -1,6 +1,13 @@
#ifndef _ASM_X86_VMALLOC_H
#define _ASM_X86_VMALLOC_H
+#include <asm/page.h>
#include <asm/pgtable_areas.h>
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+bool arch_vmap_p4d_supported(pgprot_t prot);
+bool arch_vmap_pud_supported(pgprot_t prot);
+bool arch_vmap_pmd_supported(pgprot_t prot);
+#endif
+
#endif /* _ASM_X86_VMALLOC_H */
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 9e5ccc56f8e0..fbaf0c447986 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -481,24 +481,26 @@ void iounmap(volatile void __iomem *addr)
}
EXPORT_SYMBOL(iounmap);
-int __init arch_ioremap_p4d_supported(void)
+#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+bool arch_vmap_p4d_supported(pgprot_t prot)
{
- return 0;
+ return false;
}
-int __init arch_ioremap_pud_supported(void)
+bool arch_vmap_pud_supported(pgprot_t prot)
{
#ifdef CONFIG_X86_64
return boot_cpu_has(X86_FEATURE_GBPAGES);
#else
- return 0;
+ return false;
#endif
}
-int __init arch_ioremap_pmd_supported(void)
+bool arch_vmap_pmd_supported(pgprot_t prot)
{
return boot_cpu_has(X86_FEATURE_PSE);
}
+#endif
/*
* Convert a physical pointer to a virtual kernel pointer for /dev/mem
diff --git a/include/linux/io.h b/include/linux/io.h
index 8394c56babc2..f1effd4d7a3c 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -31,15 +31,6 @@ static inline int ioremap_page_range(unsigned long addr, unsigned long end,
}
#endif
-#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-void __init ioremap_huge_init(void);
-int arch_ioremap_p4d_supported(void);
-int arch_ioremap_pud_supported(void);
-int arch_ioremap_pmd_supported(void);
-#else
-static inline void ioremap_huge_init(void) { }
-#endif
-
/*
* Managed iomap interface
*/
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 80c0181c411d..00bd62bd701e 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -83,6 +83,12 @@ struct vmap_area {
};
};
+#ifndef CONFIG_HAVE_ARCH_HUGE_VMAP
+static inline bool arch_vmap_p4d_supported(pgprot_t prot) { return false; }
+static inline bool arch_vmap_pud_supported(pgprot_t prot) { return false; }
+static inline bool arch_vmap_pmd_supported(pgprot_t prot) { return false; }
+#endif
+
/*
* Highlevel APIs for driver use
*/
diff --git a/init/main.c b/init/main.c
index c68d784376ca..bf9389e5b2e4 100644
--- a/init/main.c
+++ b/init/main.c
@@ -834,7 +834,6 @@ static void __init mm_init(void)
pgtable_init();
debug_objects_mem_init();
vmalloc_init();
- ioremap_huge_init();
/* Should be run before the first non-init thread is created */
init_espfix_bsp();
/* Should be run after espfix64 is set up. */
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index c05d9dcf7891..38345e76bd26 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -218,7 +218,7 @@ static void __init pmd_huge_tests(pmd_t *pmdp, unsigned long pfn, pgprot_t prot)
{
pmd_t pmd;
- if (!arch_ioremap_pmd_supported())
+ if (!arch_vmap_pmd_supported())
return;
pr_debug("Validating PMD huge\n");
@@ -340,7 +340,7 @@ static void __init pud_huge_tests(pud_t *pudp, unsigned long pfn, pgprot_t prot)
{
pud_t pud;
- if (!arch_ioremap_pud_supported())
+ if (!arch_vmap_pud_supported())
return;
pr_debug("Validating PUD huge\n");
diff --git a/mm/ioremap.c b/mm/ioremap.c
index 3f4d36f9745a..3264d0203785 100644
--- a/mm/ioremap.c
+++ b/mm/ioremap.c
@@ -16,49 +16,16 @@
#include "pgalloc-track.h"
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-static int __read_mostly ioremap_p4d_capable;
-static int __read_mostly ioremap_pud_capable;
-static int __read_mostly ioremap_pmd_capable;
-static int __read_mostly ioremap_huge_disabled;
+static bool __ro_after_init iomap_max_page_shift = PAGE_SHIFT;
static int __init set_nohugeiomap(char *str)
{
- ioremap_huge_disabled = 1;
+ iomap_max_page_shift = P4D_SHIFT;
return 0;
}
early_param("nohugeiomap", set_nohugeiomap);
-
-void __init ioremap_huge_init(void)
-{
- if (!ioremap_huge_disabled) {
- if (arch_ioremap_p4d_supported())
- ioremap_p4d_capable = 1;
- if (arch_ioremap_pud_supported())
- ioremap_pud_capable = 1;
- if (arch_ioremap_pmd_supported())
- ioremap_pmd_capable = 1;
- }
-}
-
-static inline int ioremap_p4d_enabled(void)
-{
- return ioremap_p4d_capable;
-}
-
-static inline int ioremap_pud_enabled(void)
-{
- return ioremap_pud_capable;
-}
-
-static inline int ioremap_pmd_enabled(void)
-{
- return ioremap_pmd_capable;
-}
-
-#else /* !CONFIG_HAVE_ARCH_HUGE_VMAP */
-static inline int ioremap_p4d_enabled(void) { return 0; }
-static inline int ioremap_pud_enabled(void) { return 0; }
-static inline int ioremap_pmd_enabled(void) { return 0; }
+#else /* CONFIG_HAVE_ARCH_HUGE_VMAP */
+static const bool iomap_max_page_shift = PAGE_SHIFT;
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
@@ -82,9 +49,13 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
}
static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot)
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
{
- if (!ioremap_pmd_enabled())
+ if (max_page_shift < PMD_SHIFT)
+ return 0;
+
+ if (!arch_vmap_pmd_supported(prot))
return 0;
if ((end - addr) != PMD_SIZE)
@@ -104,7 +75,7 @@ static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+ unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
pmd_t *pmd;
unsigned long next;
@@ -115,7 +86,8 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
do {
next = pmd_addr_end(addr, end);
- if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot)) {
+ if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot,
+ max_page_shift)) {
*mask |= PGTBL_PMD_MODIFIED;
continue;
}
@@ -127,9 +99,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
}
static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot)
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
{
- if (!ioremap_pud_enabled())
+ if (max_page_shift < PUD_SHIFT)
+ return 0;
+
+ if (!arch_vmap_pud_supported(prot))
return 0;
if ((end - addr) != PUD_SIZE)
@@ -149,7 +125,7 @@ static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+ unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
pud_t *pud;
unsigned long next;
@@ -160,21 +136,27 @@ static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
do {
next = pud_addr_end(addr, end);
- if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot)) {
+ if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot,
+ max_page_shift)) {
*mask |= PGTBL_PUD_MODIFIED;
continue;
}
- if (vmap_pmd_range(pud, addr, next, phys_addr, prot, mask))
+ if (vmap_pmd_range(pud, addr, next, phys_addr, prot,
+ max_page_shift, mask))
return -ENOMEM;
} while (pud++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
}
static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot)
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
{
- if (!ioremap_p4d_enabled())
+ if (max_page_shift < P4D_SHIFT)
+ return 0;
+
+ if (!arch_vmap_p4d_supported(prot))
return 0;
if ((end - addr) != P4D_SIZE)
@@ -194,7 +176,7 @@ static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+ unsigned int max_page_shift, pgtbl_mod_mask *mask)
{
p4d_t *p4d;
unsigned long next;
@@ -205,19 +187,22 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
do {
next = p4d_addr_end(addr, end);
- if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot)) {
+ if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot,
+ max_page_shift)) {
*mask |= PGTBL_P4D_MODIFIED;
continue;
}
- if (vmap_pud_range(p4d, addr, next, phys_addr, prot, mask))
+ if (vmap_pud_range(p4d, addr, next, phys_addr, prot,
+ max_page_shift, mask))
return -ENOMEM;
} while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
}
static int vmap_range(unsigned long addr, unsigned long end,
- phys_addr_t phys_addr, pgprot_t prot)
+ phys_addr_t phys_addr, pgprot_t prot,
+ unsigned int max_page_shift)
{
pgd_t *pgd;
unsigned long start;
@@ -232,7 +217,8 @@ static int vmap_range(unsigned long addr, unsigned long end,
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
- err = vmap_p4d_range(pgd, addr, next, phys_addr, prot, &mask);
+ err = vmap_p4d_range(pgd, addr, next, phys_addr, prot,
+ max_page_shift, &mask);
if (err)
break;
} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
@@ -248,7 +234,7 @@ static int vmap_range(unsigned long addr, unsigned long end,
int ioremap_page_range(unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
- return vmap_range(addr, end, phys_addr, prot);
+ return vmap_range(addr, end, phys_addr, prot, iomap_max_page_shift);
}
#ifdef CONFIG_GENERIC_IOREMAP
--
2.23.0
^ permalink raw reply related
* [PATCH v12 05/14] mm/ioremap: rename ioremap_*_range to vmap_*_range
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Miaohe Lin, Ding Tianhong, linux-kernel,
Nicholas Piggin, Christoph Hellwig, Jonathan Cameron,
Rick Edgecombe, linuxppc-dev, Christoph Hellwig
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
This will be used as a generic kernel virtual mapping function, so
re-name it in preparation.
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
mm/ioremap.c | 64 +++++++++++++++++++++++++++-------------------------
1 file changed, 33 insertions(+), 31 deletions(-)
diff --git a/mm/ioremap.c b/mm/ioremap.c
index 5fa1ab41d152..3f4d36f9745a 100644
--- a/mm/ioremap.c
+++ b/mm/ioremap.c
@@ -61,9 +61,9 @@ static inline int ioremap_pud_enabled(void) { return 0; }
static inline int ioremap_pmd_enabled(void) { return 0; }
#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */
-static int ioremap_pte_range(pmd_t *pmd, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ pgtbl_mod_mask *mask)
{
pte_t *pte;
u64 pfn;
@@ -81,9 +81,8 @@ static int ioremap_pte_range(pmd_t *pmd, unsigned long addr,
return 0;
}
-static int ioremap_try_huge_pmd(pmd_t *pmd, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr,
- pgprot_t prot)
+static int vmap_try_huge_pmd(pmd_t *pmd, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot)
{
if (!ioremap_pmd_enabled())
return 0;
@@ -103,9 +102,9 @@ static int ioremap_try_huge_pmd(pmd_t *pmd, unsigned long addr,
return pmd_set_huge(pmd, phys_addr, prot);
}
-static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ pgtbl_mod_mask *mask)
{
pmd_t *pmd;
unsigned long next;
@@ -116,20 +115,19 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
do {
next = pmd_addr_end(addr, end);
- if (ioremap_try_huge_pmd(pmd, addr, next, phys_addr, prot)) {
+ if (vmap_try_huge_pmd(pmd, addr, next, phys_addr, prot)) {
*mask |= PGTBL_PMD_MODIFIED;
continue;
}
- if (ioremap_pte_range(pmd, addr, next, phys_addr, prot, mask))
+ if (vmap_pte_range(pmd, addr, next, phys_addr, prot, mask))
return -ENOMEM;
} while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
}
-static int ioremap_try_huge_pud(pud_t *pud, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr,
- pgprot_t prot)
+static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot)
{
if (!ioremap_pud_enabled())
return 0;
@@ -149,9 +147,9 @@ static int ioremap_try_huge_pud(pud_t *pud, unsigned long addr,
return pud_set_huge(pud, phys_addr, prot);
}
-static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ pgtbl_mod_mask *mask)
{
pud_t *pud;
unsigned long next;
@@ -162,20 +160,19 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
do {
next = pud_addr_end(addr, end);
- if (ioremap_try_huge_pud(pud, addr, next, phys_addr, prot)) {
+ if (vmap_try_huge_pud(pud, addr, next, phys_addr, prot)) {
*mask |= PGTBL_PUD_MODIFIED;
continue;
}
- if (ioremap_pmd_range(pud, addr, next, phys_addr, prot, mask))
+ if (vmap_pmd_range(pud, addr, next, phys_addr, prot, mask))
return -ENOMEM;
} while (pud++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
}
-static int ioremap_try_huge_p4d(p4d_t *p4d, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr,
- pgprot_t prot)
+static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot)
{
if (!ioremap_p4d_enabled())
return 0;
@@ -195,9 +192,9 @@ static int ioremap_try_huge_p4d(p4d_t *p4d, unsigned long addr,
return p4d_set_huge(p4d, phys_addr, prot);
}
-static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot,
- pgtbl_mod_mask *mask)
+static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot,
+ pgtbl_mod_mask *mask)
{
p4d_t *p4d;
unsigned long next;
@@ -208,19 +205,19 @@ static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
do {
next = p4d_addr_end(addr, end);
- if (ioremap_try_huge_p4d(p4d, addr, next, phys_addr, prot)) {
+ if (vmap_try_huge_p4d(p4d, addr, next, phys_addr, prot)) {
*mask |= PGTBL_P4D_MODIFIED;
continue;
}
- if (ioremap_pud_range(p4d, addr, next, phys_addr, prot, mask))
+ if (vmap_pud_range(p4d, addr, next, phys_addr, prot, mask))
return -ENOMEM;
} while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
return 0;
}
-int ioremap_page_range(unsigned long addr,
- unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
+static int vmap_range(unsigned long addr, unsigned long end,
+ phys_addr_t phys_addr, pgprot_t prot)
{
pgd_t *pgd;
unsigned long start;
@@ -235,8 +232,7 @@ int ioremap_page_range(unsigned long addr,
pgd = pgd_offset_k(addr);
do {
next = pgd_addr_end(addr, end);
- err = ioremap_p4d_range(pgd, addr, next, phys_addr, prot,
- &mask);
+ err = vmap_p4d_range(pgd, addr, next, phys_addr, prot, &mask);
if (err)
break;
} while (pgd++, phys_addr += (next - addr), addr = next, addr != end);
@@ -249,6 +245,12 @@ int ioremap_page_range(unsigned long addr,
return err;
}
+int ioremap_page_range(unsigned long addr,
+ unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
+{
+ return vmap_range(addr, end, phys_addr, prot);
+}
+
#ifdef CONFIG_GENERIC_IOREMAP
void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot)
{
--
2.23.0
^ permalink raw reply related
* [PATCH v12 04/14] mm/vmalloc: rename vmap_*_range vmap_pages_*_range
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Miaohe Lin, Ding Tianhong, linux-kernel,
Nicholas Piggin, Christoph Hellwig, Jonathan Cameron,
Rick Edgecombe, linuxppc-dev, Christoph Hellwig
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
The vmalloc mapper operates on a struct page * array rather than a
linear physical address, re-name it to make this distinction clear.
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
mm/vmalloc.c | 16 ++++++++--------
1 file changed, 8 insertions(+), 8 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 62372f9e0167..7f2f36116980 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -189,7 +189,7 @@ void unmap_kernel_range_noflush(unsigned long start, unsigned long size)
arch_sync_kernel_mappings(start, end);
}
-static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
+static int vmap_pages_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr,
pgtbl_mod_mask *mask)
{
@@ -217,7 +217,7 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
return 0;
}
-static int vmap_pmd_range(pud_t *pud, unsigned long addr,
+static int vmap_pages_pmd_range(pud_t *pud, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr,
pgtbl_mod_mask *mask)
{
@@ -229,13 +229,13 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr,
return -ENOMEM;
do {
next = pmd_addr_end(addr, end);
- if (vmap_pte_range(pmd, addr, next, prot, pages, nr, mask))
+ if (vmap_pages_pte_range(pmd, addr, next, prot, pages, nr, mask))
return -ENOMEM;
} while (pmd++, addr = next, addr != end);
return 0;
}
-static int vmap_pud_range(p4d_t *p4d, unsigned long addr,
+static int vmap_pages_pud_range(p4d_t *p4d, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr,
pgtbl_mod_mask *mask)
{
@@ -247,13 +247,13 @@ static int vmap_pud_range(p4d_t *p4d, unsigned long addr,
return -ENOMEM;
do {
next = pud_addr_end(addr, end);
- if (vmap_pmd_range(pud, addr, next, prot, pages, nr, mask))
+ if (vmap_pages_pmd_range(pud, addr, next, prot, pages, nr, mask))
return -ENOMEM;
} while (pud++, addr = next, addr != end);
return 0;
}
-static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
+static int vmap_pages_p4d_range(pgd_t *pgd, unsigned long addr,
unsigned long end, pgprot_t prot, struct page **pages, int *nr,
pgtbl_mod_mask *mask)
{
@@ -265,7 +265,7 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr,
return -ENOMEM;
do {
next = p4d_addr_end(addr, end);
- if (vmap_pud_range(p4d, addr, next, prot, pages, nr, mask))
+ if (vmap_pages_pud_range(p4d, addr, next, prot, pages, nr, mask))
return -ENOMEM;
} while (p4d++, addr = next, addr != end);
return 0;
@@ -306,7 +306,7 @@ int map_kernel_range_noflush(unsigned long addr, unsigned long size,
next = pgd_addr_end(addr, end);
if (pgd_bad(*pgd))
mask |= PGTBL_PGD_MODIFIED;
- err = vmap_p4d_range(pgd, addr, next, prot, pages, &nr, &mask);
+ err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask);
if (err)
return err;
} while (pgd++, addr = next, addr != end);
--
2.23.0
^ permalink raw reply related
* [PATCH v12 03/14] mm: apply_to_pte_range warn and fail if a large pte is encountered
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Miaohe Lin, Ding Tianhong, linux-kernel,
Nicholas Piggin, Christoph Hellwig, Jonathan Cameron,
Rick Edgecombe, linuxppc-dev, Christoph Hellwig
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
apply_to_pte_range might mistake a large pte for bad, or treat it as a
page table, resulting in a crash or corruption. Add a test to warn and
return error if large entries are found.
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
mm/memory.c | 66 +++++++++++++++++++++++++++++++++++++++--------------
1 file changed, 49 insertions(+), 17 deletions(-)
diff --git a/mm/memory.c b/mm/memory.c
index feff48e1465a..672e39a72788 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2440,13 +2440,21 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
}
do {
next = pmd_addr_end(addr, end);
- if (create || !pmd_none_or_clear_bad(pmd)) {
- err = apply_to_pte_range(mm, pmd, addr, next, fn, data,
- create, mask);
- if (err)
- break;
+ if (pmd_none(*pmd) && !create)
+ continue;
+ if (WARN_ON_ONCE(pmd_leaf(*pmd)))
+ return -EINVAL;
+ if (!pmd_none(*pmd) && WARN_ON_ONCE(pmd_bad(*pmd))) {
+ if (!create)
+ continue;
+ pmd_clear_bad(pmd);
}
+ err = apply_to_pte_range(mm, pmd, addr, next,
+ fn, data, create, mask);
+ if (err)
+ break;
} while (pmd++, addr = next, addr != end);
+
return err;
}
@@ -2468,13 +2476,21 @@ static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
}
do {
next = pud_addr_end(addr, end);
- if (create || !pud_none_or_clear_bad(pud)) {
- err = apply_to_pmd_range(mm, pud, addr, next, fn, data,
- create, mask);
- if (err)
- break;
+ if (pud_none(*pud) && !create)
+ continue;
+ if (WARN_ON_ONCE(pud_leaf(*pud)))
+ return -EINVAL;
+ if (!pud_none(*pud) && WARN_ON_ONCE(pud_bad(*pud))) {
+ if (!create)
+ continue;
+ pud_clear_bad(pud);
}
+ err = apply_to_pmd_range(mm, pud, addr, next,
+ fn, data, create, mask);
+ if (err)
+ break;
} while (pud++, addr = next, addr != end);
+
return err;
}
@@ -2496,13 +2512,21 @@ static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
}
do {
next = p4d_addr_end(addr, end);
- if (create || !p4d_none_or_clear_bad(p4d)) {
- err = apply_to_pud_range(mm, p4d, addr, next, fn, data,
- create, mask);
- if (err)
- break;
+ if (p4d_none(*p4d) && !create)
+ continue;
+ if (WARN_ON_ONCE(p4d_leaf(*p4d)))
+ return -EINVAL;
+ if (!p4d_none(*p4d) && WARN_ON_ONCE(p4d_bad(*p4d))) {
+ if (!create)
+ continue;
+ p4d_clear_bad(p4d);
}
+ err = apply_to_pud_range(mm, p4d, addr, next,
+ fn, data, create, mask);
+ if (err)
+ break;
} while (p4d++, addr = next, addr != end);
+
return err;
}
@@ -2522,9 +2546,17 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
pgd = pgd_offset(mm, addr);
do {
next = pgd_addr_end(addr, end);
- if (!create && pgd_none_or_clear_bad(pgd))
+ if (pgd_none(*pgd) && !create)
continue;
- err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask);
+ if (WARN_ON_ONCE(pgd_leaf(*pgd)))
+ return -EINVAL;
+ if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) {
+ if (!create)
+ continue;
+ pgd_clear_bad(pgd);
+ }
+ err = apply_to_p4d_range(mm, pgd, addr, next,
+ fn, data, create, &mask);
if (err)
break;
} while (pgd++, addr = next, addr != end);
--
2.23.0
^ permalink raw reply related
* [PATCH v12 02/14] mm/vmalloc: fix HUGE_VMAP regression by enabling huge pages in vmalloc_to_page
From: Nicholas Piggin @ 2021-02-02 11:05 UTC (permalink / raw)
To: linux-mm, Andrew Morton
Cc: linux-arch, Miaohe Lin, Ding Tianhong, linux-kernel,
Nicholas Piggin, Christoph Hellwig, Jonathan Cameron,
Rick Edgecombe, linuxppc-dev, Christoph Hellwig
In-Reply-To: <20210202110515.3575274-1-npiggin@gmail.com>
vmalloc_to_page returns NULL for addresses mapped by larger pages[*].
Whether or not a vmap is huge depends on the architecture details,
alignments, boot options, etc., which the caller can not be expected
to know. Therefore HUGE_VMAP is a regression for vmalloc_to_page.
This change teaches vmalloc_to_page about larger pages, and returns
the struct page that corresponds to the offset within the large page.
This makes the API agnostic to mapping implementation details.
[*] As explained by commit 029c54b095995 ("mm/vmalloc.c: huge-vmap:
fail gracefully on unexpected huge vmap mappings")
Reviewed-by: Miaohe Lin <linmiaohe@huawei.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
mm/vmalloc.c | 41 ++++++++++++++++++++++++++---------------
1 file changed, 26 insertions(+), 15 deletions(-)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index e6f352bf0498..62372f9e0167 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -34,7 +34,7 @@
#include <linux/bitops.h>
#include <linux/rbtree_augmented.h>
#include <linux/overflow.h>
-
+#include <linux/pgtable.h>
#include <linux/uaccess.h>
#include <asm/tlbflush.h>
#include <asm/shmparam.h>
@@ -343,7 +343,9 @@ int is_vmalloc_or_module_addr(const void *x)
}
/*
- * Walk a vmap address to the struct page it maps.
+ * Walk a vmap address to the struct page it maps. Huge vmap mappings will
+ * return the tail page that corresponds to the base page address, which
+ * matches small vmap mappings.
*/
struct page *vmalloc_to_page(const void *vmalloc_addr)
{
@@ -363,25 +365,33 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
if (pgd_none(*pgd))
return NULL;
+ if (WARN_ON_ONCE(pgd_leaf(*pgd)))
+ return NULL; /* XXX: no allowance for huge pgd */
+ if (WARN_ON_ONCE(pgd_bad(*pgd)))
+ return NULL;
+
p4d = p4d_offset(pgd, addr);
if (p4d_none(*p4d))
return NULL;
- pud = pud_offset(p4d, addr);
+ if (p4d_leaf(*p4d))
+ return p4d_page(*p4d) + ((addr & ~P4D_MASK) >> PAGE_SHIFT);
+ if (WARN_ON_ONCE(p4d_bad(*p4d)))
+ return NULL;
- /*
- * Don't dereference bad PUD or PMD (below) entries. This will also
- * identify huge mappings, which we may encounter on architectures
- * that define CONFIG_HAVE_ARCH_HUGE_VMAP=y. Such regions will be
- * identified as vmalloc addresses by is_vmalloc_addr(), but are
- * not [unambiguously] associated with a struct page, so there is
- * no correct value to return for them.
- */
- WARN_ON_ONCE(pud_bad(*pud));
- if (pud_none(*pud) || pud_bad(*pud))
+ pud = pud_offset(p4d, addr);
+ if (pud_none(*pud))
+ return NULL;
+ if (pud_leaf(*pud))
+ return pud_page(*pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+ if (WARN_ON_ONCE(pud_bad(*pud)))
return NULL;
+
pmd = pmd_offset(pud, addr);
- WARN_ON_ONCE(pmd_bad(*pmd));
- if (pmd_none(*pmd) || pmd_bad(*pmd))
+ if (pmd_none(*pmd))
+ return NULL;
+ if (pmd_leaf(*pmd))
+ return pmd_page(*pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+ if (WARN_ON_ONCE(pmd_bad(*pmd)))
return NULL;
ptep = pte_offset_map(pmd, addr);
@@ -389,6 +399,7 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
if (pte_present(pte))
page = pte_page(pte);
pte_unmap(ptep);
+
return page;
}
EXPORT_SYMBOL(vmalloc_to_page);
--
2.23.0
^ 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