diff mbox series

[v2,bpf-next,2/3] mm, xen: Separate xen use cases from ioremap.

Message ID 20240223235728.13981-3-alexei.starovoitov@gmail.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series mm: Cleanup and identify various users of kernel virtual address space | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-11 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-12 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-19 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-17 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-20 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-18 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-34 success Logs for x86_64-llvm-17 / veristat
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-16 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-21 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-22 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-32 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-33 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-35 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-42 success Logs for x86_64-llvm-18 / veristat
bpf/vmtest-bpf-next-VM_Test-30 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-31 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-7 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / test (test_maps, false, 360) / test_maps on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-36 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18 and -O2 optimization
bpf/vmtest-bpf-next-VM_Test-37 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-41 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-38 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-40 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-15 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-39 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17 and -O2 optimization
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 14193 this patch: 14193
netdev/build_tools success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers warning 8 maintainers not CCed: hpa@zytor.com oleksandr_tyshchenko@epam.com mingo@redhat.com dave.hansen@linux.intel.com x86@kernel.org tglx@linutronix.de rdunlap@infradead.org bp@alien8.de
netdev/build_clang success Errors and warnings before: 3076 this patch: 3076
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 15305 this patch: 15305
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 43 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 2 this patch: 2
netdev/source_inline success Was 0 now: 0

Commit Message

Alexei Starovoitov Feb. 23, 2024, 11:57 p.m. UTC 
From: Alexei Starovoitov <ast@kernel.org>

xen grant table and xenbus ring are not ioremap the way arch specific code is using it,
so let's add VM_XEN flag to separate them from VM_IOREMAP users.
xen will not and should not be calling ioremap_page_range() on that range.
/proc/vmallocinfo will print such region as "xen" instead of "ioremap" as well.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/xen/grant-table.c         | 2 +-
 drivers/xen/xenbus/xenbus_client.c | 2 +-
 include/linux/vmalloc.h            | 1 +
 mm/vmalloc.c                       | 7 +++++--
 4 files changed, 8 insertions(+), 4 deletions(-)

Comments

Christoph Hellwig Feb. 26, 2024, 10:51 a.m. UTC | #1 
On Fri, Feb 23, 2024 at 03:57:27PM -0800, Alexei Starovoitov wrote:
> From: Alexei Starovoitov <ast@kernel.org>
> 
> xen grant table and xenbus ring are not ioremap the way arch specific code is using it,
> so let's add VM_XEN flag to separate them from VM_IOREMAP users.
> xen will not and should not be calling ioremap_page_range() on that range.
> /proc/vmallocinfo will print such region as "xen" instead of "ioremap" as well.

Splitting this out is a good idea, but XEN seems a bit of a too
generit time.  Probably GRANT_TABLE or XEN_GRANT_TABLE if that isn't
too long would be better.  Maybe the Xen maintainers have an idea.

Also more overlong commit message lines here, I'm not going to complain
on the third patch if they show up again :)
Mike Rapoport March 4, 2024, 7:54 a.m. UTC | #2 
On Fri, Feb 23, 2024 at 03:57:27PM -0800, Alexei Starovoitov wrote:
> From: Alexei Starovoitov <ast@kernel.org>
> 
> xen grant table and xenbus ring are not ioremap the way arch specific code is using it,
> so let's add VM_XEN flag to separate them from VM_IOREMAP users.
> xen will not and should not be calling ioremap_page_range() on that range.
> /proc/vmallocinfo will print such region as "xen" instead of "ioremap" as well.
> 
> Signed-off-by: Alexei Starovoitov <ast@kernel.org>
> ---
>  arch/x86/xen/grant-table.c         | 2 +-
>  drivers/xen/xenbus/xenbus_client.c | 2 +-
>  include/linux/vmalloc.h            | 1 +
>  mm/vmalloc.c                       | 7 +++++--
>  4 files changed, 8 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
> index 1e681bf62561..b816db0349c4 100644
> --- a/arch/x86/xen/grant-table.c
> +++ b/arch/x86/xen/grant-table.c
> @@ -104,7 +104,7 @@ static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames)
>  	area->ptes = kmalloc_array(nr_frames, sizeof(*area->ptes), GFP_KERNEL);
>  	if (area->ptes == NULL)
>  		return -ENOMEM;
> -	area->area = get_vm_area(PAGE_SIZE * nr_frames, VM_IOREMAP);
> +	area->area = get_vm_area(PAGE_SIZE * nr_frames, VM_XEN);
>  	if (!area->area)
>  		goto out_free_ptes;
>  	if (apply_to_page_range(&init_mm, (unsigned long)area->area->addr,
> diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
> index 32835b4b9bc5..b9c81a2d578b 100644
> --- a/drivers/xen/xenbus/xenbus_client.c
> +++ b/drivers/xen/xenbus/xenbus_client.c
> @@ -758,7 +758,7 @@ static int xenbus_map_ring_pv(struct xenbus_device *dev,
>  	bool leaked = false;
>  	int err = -ENOMEM;
>  
> -	area = get_vm_area(XEN_PAGE_SIZE * nr_grefs, VM_IOREMAP);
> +	area = get_vm_area(XEN_PAGE_SIZE * nr_grefs, VM_XEN);
>  	if (!area)
>  		return -ENOMEM;
>  	if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
> diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
> index c720be70c8dd..223e51c243bc 100644
> --- a/include/linux/vmalloc.h
> +++ b/include/linux/vmalloc.h
> @@ -28,6 +28,7 @@ struct iov_iter;		/* in uio.h */
>  #define VM_FLUSH_RESET_PERMS	0x00000100	/* reset direct map and flush TLB on unmap, can't be freed in atomic context */
>  #define VM_MAP_PUT_PAGES	0x00000200	/* put pages and free array in vfree */
>  #define VM_ALLOW_HUGE_VMAP	0x00000400      /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */
> +#define VM_XEN			0x00000800	/* xen use cases */
>  
>  #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
>  	!defined(CONFIG_KASAN_VMALLOC)

There's also VM_DEFER_KMEMLEAK a line below:

#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
	!defined(CONFIG_KASAN_VMALLOC)
#define VM_DEFER_KMEMLEAK	0x00000801	/* defer kmemleak object creation */
#else
#define VM_DEFER_KMEMLEAK	0
#endif

It should be adjusted as well.
I think it makes sense to use an enumeration for vm_flags, just like as
Suren did for GFP
(https://lore.kernel.org/linux-mm/20240224015800.2569851-1-surenb@google.com/)
Alexei Starovoitov March 5, 2024, 12:38 a.m. UTC | #3 
On Sun, Mar 3, 2024 at 11:55 PM Mike Rapoport <rppt@kernel.org> wrote:
>
> On Fri, Feb 23, 2024 at 03:57:27PM -0800, Alexei Starovoitov wrote:
> > From: Alexei Starovoitov <ast@kernel.org>
> >
> > xen grant table and xenbus ring are not ioremap the way arch specific code is using it,
> > so let's add VM_XEN flag to separate them from VM_IOREMAP users.
> > xen will not and should not be calling ioremap_page_range() on that range.
> > /proc/vmallocinfo will print such region as "xen" instead of "ioremap" as well.
> >
> > Signed-off-by: Alexei Starovoitov <ast@kernel.org>
> > ---
> >  arch/x86/xen/grant-table.c         | 2 +-
> >  drivers/xen/xenbus/xenbus_client.c | 2 +-
> >  include/linux/vmalloc.h            | 1 +
> >  mm/vmalloc.c                       | 7 +++++--
> >  4 files changed, 8 insertions(+), 4 deletions(-)
> >
> > diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
> > index 1e681bf62561..b816db0349c4 100644
> > --- a/arch/x86/xen/grant-table.c
> > +++ b/arch/x86/xen/grant-table.c
> > @@ -104,7 +104,7 @@ static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames)
> >       area->ptes = kmalloc_array(nr_frames, sizeof(*area->ptes), GFP_KERNEL);
> >       if (area->ptes == NULL)
> >               return -ENOMEM;
> > -     area->area = get_vm_area(PAGE_SIZE * nr_frames, VM_IOREMAP);
> > +     area->area = get_vm_area(PAGE_SIZE * nr_frames, VM_XEN);
> >       if (!area->area)
> >               goto out_free_ptes;
> >       if (apply_to_page_range(&init_mm, (unsigned long)area->area->addr,
> > diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
> > index 32835b4b9bc5..b9c81a2d578b 100644
> > --- a/drivers/xen/xenbus/xenbus_client.c
> > +++ b/drivers/xen/xenbus/xenbus_client.c
> > @@ -758,7 +758,7 @@ static int xenbus_map_ring_pv(struct xenbus_device *dev,
> >       bool leaked = false;
> >       int err = -ENOMEM;
> >
> > -     area = get_vm_area(XEN_PAGE_SIZE * nr_grefs, VM_IOREMAP);
> > +     area = get_vm_area(XEN_PAGE_SIZE * nr_grefs, VM_XEN);
> >       if (!area)
> >               return -ENOMEM;
> >       if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
> > diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
> > index c720be70c8dd..223e51c243bc 100644
> > --- a/include/linux/vmalloc.h
> > +++ b/include/linux/vmalloc.h
> > @@ -28,6 +28,7 @@ struct iov_iter;            /* in uio.h */
> >  #define VM_FLUSH_RESET_PERMS 0x00000100      /* reset direct map and flush TLB on unmap, can't be freed in atomic context */
> >  #define VM_MAP_PUT_PAGES     0x00000200      /* put pages and free array in vfree */
> >  #define VM_ALLOW_HUGE_VMAP   0x00000400      /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */
> > +#define VM_XEN                       0x00000800      /* xen use cases */
> >
> >  #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
> >       !defined(CONFIG_KASAN_VMALLOC)
>
> There's also VM_DEFER_KMEMLEAK a line below:

Ohh. Good catch. Will fix.

> I think it makes sense to use an enumeration for vm_flags, just like as
> Suren did for GFP
> (https://lore.kernel.org/linux-mm/20240224015800.2569851-1-surenb@google.com/)

Hmm. I'm pretty sure Christoph hates BIT macro obfuscation.
I'm not a fan of it either, though we use it in bpf in a few places.
If mm folks prefer that style they can do such conversion later.
diff mbox series

Patch

diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index 1e681bf62561..b816db0349c4 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -104,7 +104,7 @@  static int arch_gnttab_valloc(struct gnttab_vm_area *area, unsigned nr_frames)
 	area->ptes = kmalloc_array(nr_frames, sizeof(*area->ptes), GFP_KERNEL);
 	if (area->ptes == NULL)
 		return -ENOMEM;
-	area->area = get_vm_area(PAGE_SIZE * nr_frames, VM_IOREMAP);
+	area->area = get_vm_area(PAGE_SIZE * nr_frames, VM_XEN);
 	if (!area->area)
 		goto out_free_ptes;
 	if (apply_to_page_range(&init_mm, (unsigned long)area->area->addr,
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 32835b4b9bc5..b9c81a2d578b 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -758,7 +758,7 @@  static int xenbus_map_ring_pv(struct xenbus_device *dev,
 	bool leaked = false;
 	int err = -ENOMEM;
 
-	area = get_vm_area(XEN_PAGE_SIZE * nr_grefs, VM_IOREMAP);
+	area = get_vm_area(XEN_PAGE_SIZE * nr_grefs, VM_XEN);
 	if (!area)
 		return -ENOMEM;
 	if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index c720be70c8dd..223e51c243bc 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -28,6 +28,7 @@  struct iov_iter;		/* in uio.h */
 #define VM_FLUSH_RESET_PERMS	0x00000100	/* reset direct map and flush TLB on unmap, can't be freed in atomic context */
 #define VM_MAP_PUT_PAGES	0x00000200	/* put pages and free array in vfree */
 #define VM_ALLOW_HUGE_VMAP	0x00000400      /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */
+#define VM_XEN			0x00000800	/* xen use cases */
 
 #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
 	!defined(CONFIG_KASAN_VMALLOC)
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index f42f98a127d5..d769a65bddad 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3822,9 +3822,9 @@  long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
 
 		if (flags & VMAP_RAM)
 			copied = vmap_ram_vread_iter(iter, addr, n, flags);
-		else if (!(vm && (vm->flags & VM_IOREMAP)))
+		else if (!(vm && (vm->flags & (VM_IOREMAP | VM_XEN))))
 			copied = aligned_vread_iter(iter, addr, n);
-		else /* IOREMAP area is treated as memory hole */
+		else /* IOREMAP|XEN area is treated as memory hole */
 			copied = zero_iter(iter, n);
 
 		addr += copied;
@@ -4415,6 +4415,9 @@  static int s_show(struct seq_file *m, void *p)
 	if (v->flags & VM_IOREMAP)
 		seq_puts(m, " ioremap");
 
+	if (v->flags & VM_XEN)
+		seq_puts(m, " xen");
+
 	if (v->flags & VM_ALLOC)
 		seq_puts(m, " vmalloc");