* [PATCH v2 5/9] vgacon: remove screen_info dependency
From: Arnd Bergmann @ 2023-07-19 12:39 UTC (permalink / raw)
To: linux-fbdev, Thomas Zimmermann, Helge Deller,
Javier Martinez Canillas
Cc: Arnd Bergmann, David S. Miller, K. Y. Srinivasan, Ard Biesheuvel,
Borislav Petkov, Brian Cain, Catalin Marinas, Christophe Leroy,
Daniel Vetter, Dave Hansen, David Airlie, Deepak Rawat,
Dexuan Cui, Dinh Nguyen, Greg Kroah-Hartman, Guo Ren,
Haiyang Zhang, Huacai Chen, Ingo Molnar,
John Paul Adrian Glaubitz, Khalid Aziz, Linus Walleij,
Matt Turner, Max Filippov, Michael Ellerman, Nicholas Piggin,
Palmer Dabbelt, Russell King, Thomas Bogendoerfer,
Thomas Gleixner, WANG Xuerui, Wei Liu, Will Deacon, x86,
linux-alpha, linux-kernel, linux-arm-kernel, linux-efi,
linux-csky, linux-hexagon, linux-ia64, loongarch, linux-mips,
linuxppc-dev, linux-riscv, linux-sh, sparclinux, linux-hyperv,
dri-devel
In-Reply-To: <20230719123944.3438363-1-arnd@kernel.org>
From: Arnd Bergmann <arnd@arndb.de>
The vga console driver is fairly self-contained, and only used by
architectures that explicitly initialize the screen_info settings.
Chance every instance that picks the vga console by setting conswitchp
to call a function instead, and pass a reference to the screen_info
there.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
arch/alpha/kernel/setup.c | 2 +-
arch/arm/kernel/setup.c | 2 +-
arch/ia64/kernel/setup.c | 2 +-
arch/mips/kernel/setup.c | 2 +-
arch/x86/kernel/setup.c | 2 +-
drivers/firmware/pcdp.c | 2 +-
drivers/video/console/vgacon.c | 68 ++++++++++++++++++++--------------
include/linux/console.h | 7 ++++
8 files changed, 53 insertions(+), 34 deletions(-)
diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c
index b4d2297765c02..d73b685fe9852 100644
--- a/arch/alpha/kernel/setup.c
+++ b/arch/alpha/kernel/setup.c
@@ -655,7 +655,7 @@ setup_arch(char **cmdline_p)
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
- conswitchp = &vga_con;
+ vgacon_register_screen(&screen_info);
#endif
#endif
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 40326a35a179b..5d8a7fb3eba45 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -1192,7 +1192,7 @@ void __init setup_arch(char **cmdline_p)
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
- conswitchp = &vga_con;
+ vgacon_register_screen(&screen_info);
#endif
#endif
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index d2c66efdde560..2c9283fcd3759 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -619,7 +619,7 @@ setup_arch (char **cmdline_p)
* memory so we can avoid this problem.
*/
if (efi_mem_type(0xA0000) != EFI_CONVENTIONAL_MEMORY)
- conswitchp = &vga_con;
+ vgacon_register_screen(&screen_info);
# endif
}
#endif
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 1aba7dc95132c..6c3fae62a9f6b 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -794,7 +794,7 @@ void __init setup_arch(char **cmdline_p)
#if defined(CONFIG_VT)
#if defined(CONFIG_VGA_CONSOLE)
- conswitchp = &vga_con;
+ vgacon_register_screen(&screen_info);
#endif
#endif
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index fd975a4a52006..b1ea77d504615 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1293,7 +1293,7 @@ void __init setup_arch(char **cmdline_p)
#ifdef CONFIG_VT
#if defined(CONFIG_VGA_CONSOLE)
if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
- conswitchp = &vga_con;
+ vgacon_register_screen(&screen_info);
#endif
#endif
x86_init.oem.banner();
diff --git a/drivers/firmware/pcdp.c b/drivers/firmware/pcdp.c
index 715a45442d1cf..667a595373b2d 100644
--- a/drivers/firmware/pcdp.c
+++ b/drivers/firmware/pcdp.c
@@ -72,7 +72,7 @@ setup_vga_console(struct pcdp_device *dev)
return -ENODEV;
}
- conswitchp = &vga_con;
+ vgacon_register_screen(&screen_info);
printk(KERN_INFO "PCDP: VGA console\n");
return 0;
#else
diff --git a/drivers/video/console/vgacon.c b/drivers/video/console/vgacon.c
index e25ba523892e5..3d7fedf27ffc1 100644
--- a/drivers/video/console/vgacon.c
+++ b/drivers/video/console/vgacon.c
@@ -97,6 +97,8 @@ static int vga_video_font_height;
static int vga_scan_lines __read_mostly;
static unsigned int vga_rolled_over; /* last vc_origin offset before wrap */
+static struct screen_info *vga_si;
+
static bool vga_hardscroll_enabled;
static bool vga_hardscroll_user_enable = true;
@@ -161,8 +163,9 @@ static const char *vgacon_startup(void)
u16 saved1, saved2;
volatile u16 *p;
- if (screen_info.orig_video_isVGA == VIDEO_TYPE_VLFB ||
- screen_info.orig_video_isVGA == VIDEO_TYPE_EFI) {
+ if (!vga_si ||
+ vga_si->orig_video_isVGA == VIDEO_TYPE_VLFB ||
+ vga_si->orig_video_isVGA == VIDEO_TYPE_EFI) {
no_vga:
#ifdef CONFIG_DUMMY_CONSOLE
conswitchp = &dummy_con;
@@ -172,29 +175,29 @@ static const char *vgacon_startup(void)
#endif
}
- /* boot_params.screen_info reasonably initialized? */
- if ((screen_info.orig_video_lines == 0) ||
- (screen_info.orig_video_cols == 0))
+ /* vga_si reasonably initialized? */
+ if ((vga_si->orig_video_lines == 0) ||
+ (vga_si->orig_video_cols == 0))
goto no_vga;
/* VGA16 modes are not handled by VGACON */
- if ((screen_info.orig_video_mode == 0x0D) || /* 320x200/4 */
- (screen_info.orig_video_mode == 0x0E) || /* 640x200/4 */
- (screen_info.orig_video_mode == 0x10) || /* 640x350/4 */
- (screen_info.orig_video_mode == 0x12) || /* 640x480/4 */
- (screen_info.orig_video_mode == 0x6A)) /* 800x600/4 (VESA) */
+ if ((vga_si->orig_video_mode == 0x0D) || /* 320x200/4 */
+ (vga_si->orig_video_mode == 0x0E) || /* 640x200/4 */
+ (vga_si->orig_video_mode == 0x10) || /* 640x350/4 */
+ (vga_si->orig_video_mode == 0x12) || /* 640x480/4 */
+ (vga_si->orig_video_mode == 0x6A)) /* 800x600/4 (VESA) */
goto no_vga;
- vga_video_num_lines = screen_info.orig_video_lines;
- vga_video_num_columns = screen_info.orig_video_cols;
+ vga_video_num_lines = vga_si->orig_video_lines;
+ vga_video_num_columns = vga_si->orig_video_cols;
vgastate.vgabase = NULL;
- if (screen_info.orig_video_mode == 7) {
+ if (vga_si->orig_video_mode == 7) {
/* Monochrome display */
vga_vram_base = 0xb0000;
vga_video_port_reg = VGA_CRT_IM;
vga_video_port_val = VGA_CRT_DM;
- if ((screen_info.orig_video_ega_bx & 0xff) != 0x10) {
+ if ((vga_si->orig_video_ega_bx & 0xff) != 0x10) {
static struct resource ega_console_resource =
{ .name = "ega",
.flags = IORESOURCE_IO,
@@ -231,12 +234,12 @@ static const char *vgacon_startup(void)
vga_vram_base = 0xb8000;
vga_video_port_reg = VGA_CRT_IC;
vga_video_port_val = VGA_CRT_DC;
- if ((screen_info.orig_video_ega_bx & 0xff) != 0x10) {
+ if ((vga_si->orig_video_ega_bx & 0xff) != 0x10) {
int i;
vga_vram_size = 0x8000;
- if (!screen_info.orig_video_isVGA) {
+ if (!vga_si->orig_video_isVGA) {
static struct resource ega_console_resource =
{ .name = "ega",
.flags = IORESOURCE_IO,
@@ -327,14 +330,14 @@ static const char *vgacon_startup(void)
|| vga_video_type == VIDEO_TYPE_VGAC
|| vga_video_type == VIDEO_TYPE_EGAM) {
vga_hardscroll_enabled = vga_hardscroll_user_enable;
- vga_default_font_height = screen_info.orig_video_points;
- vga_video_font_height = screen_info.orig_video_points;
+ vga_default_font_height = vga_si->orig_video_points;
+ vga_video_font_height = vga_si->orig_video_points;
/* This may be suboptimal but is a safe bet - go with it */
vga_scan_lines =
vga_video_font_height * vga_video_num_lines;
}
- vgacon_xres = screen_info.orig_video_cols * VGA_FONTWIDTH;
+ vgacon_xres = vga_si->orig_video_cols * VGA_FONTWIDTH;
vgacon_yres = vga_scan_lines;
return display_desc;
@@ -379,7 +382,7 @@ static void vgacon_init(struct vc_data *c, int init)
/* Only set the default if the user didn't deliberately override it */
if (global_cursor_default == -1)
global_cursor_default =
- !(screen_info.flags & VIDEO_FLAGS_NOCURSOR);
+ !(vga_si->flags & VIDEO_FLAGS_NOCURSOR);
}
static void vgacon_deinit(struct vc_data *c)
@@ -607,7 +610,7 @@ static int vgacon_switch(struct vc_data *c)
{
int x = c->vc_cols * VGA_FONTWIDTH;
int y = c->vc_rows * c->vc_cell_height;
- int rows = screen_info.orig_video_lines * vga_default_font_height/
+ int rows = vga_si->orig_video_lines * vga_default_font_height/
c->vc_cell_height;
/*
* We need to save screen size here as it's the only way
@@ -627,7 +630,7 @@ static int vgacon_switch(struct vc_data *c)
if ((vgacon_xres != x || vgacon_yres != y) &&
(!(vga_video_num_columns % 2) &&
- vga_video_num_columns <= screen_info.orig_video_cols &&
+ vga_video_num_columns <= vga_si->orig_video_cols &&
vga_video_num_lines <= rows))
vgacon_doresize(c, c->vc_cols, c->vc_rows);
}
@@ -1074,13 +1077,13 @@ static int vgacon_resize(struct vc_data *c, unsigned int width,
* Ho ho! Someone (svgatextmode, eh?) may have reprogrammed
* the video mode! Set the new defaults then and go away.
*/
- screen_info.orig_video_cols = width;
- screen_info.orig_video_lines = height;
+ vga_si->orig_video_cols = width;
+ vga_si->orig_video_lines = height;
vga_default_font_height = c->vc_cell_height;
return 0;
}
- if (width % 2 || width > screen_info.orig_video_cols ||
- height > (screen_info.orig_video_lines * vga_default_font_height)/
+ if (width % 2 || width > vga_si->orig_video_cols ||
+ height > (vga_si->orig_video_lines * vga_default_font_height)/
c->vc_cell_height)
return -EINVAL;
@@ -1110,8 +1113,8 @@ static void vgacon_save_screen(struct vc_data *c)
* console initialization routines.
*/
vga_bootup_console = 1;
- c->state.x = screen_info.orig_x;
- c->state.y = screen_info.orig_y;
+ c->state.x = vga_si->orig_x;
+ c->state.y = vga_si->orig_y;
}
/* We can't copy in more than the size of the video buffer,
@@ -1204,4 +1207,13 @@ const struct consw vga_con = {
};
EXPORT_SYMBOL(vga_con);
+void vgacon_register_screen(struct screen_info *si)
+{
+ if (!si || vga_si)
+ return;
+
+ conswitchp = &vga_con;
+ vga_si = si;
+}
+
MODULE_LICENSE("GPL");
diff --git a/include/linux/console.h b/include/linux/console.h
index d3195664baa5a..5f900210e689e 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -101,6 +101,13 @@ extern const struct consw dummy_con; /* dummy console buffer */
extern const struct consw vga_con; /* VGA text console */
extern const struct consw newport_con; /* SGI Newport console */
+struct screen_info;
+#ifdef CONFIG_VGA_CONSOLE
+void vgacon_register_screen(struct screen_info *si);
+#else
+static inline void vgacon_register_screen(struct screen_info *si) { }
+#endif
+
int con_is_bound(const struct consw *csw);
int do_unregister_con_driver(const struct consw *csw);
int do_take_over_console(const struct consw *sw, int first, int last, int deflt);
--
2.39.2
^ permalink raw reply related
* [PATCH v2 4/9] vgacon, arch/*: remove unused screen_info definitions
From: Arnd Bergmann @ 2023-07-19 12:39 UTC (permalink / raw)
To: linux-fbdev, Thomas Zimmermann, Helge Deller,
Javier Martinez Canillas
Cc: Arnd Bergmann, David S. Miller, K. Y. Srinivasan, Ard Biesheuvel,
Borislav Petkov, Brian Cain, Catalin Marinas, Christophe Leroy,
Daniel Vetter, Dave Hansen, David Airlie, Deepak Rawat,
Dexuan Cui, Dinh Nguyen, Greg Kroah-Hartman, Guo Ren,
Haiyang Zhang, Huacai Chen, Ingo Molnar,
John Paul Adrian Glaubitz, Khalid Aziz, Linus Walleij,
Matt Turner, Max Filippov, Michael Ellerman, Nicholas Piggin,
Palmer Dabbelt, Russell King, Thomas Bogendoerfer,
Thomas Gleixner, WANG Xuerui, Wei Liu, Will Deacon, x86,
linux-alpha, linux-kernel, linux-arm-kernel, linux-efi,
linux-csky, linux-hexagon, linux-ia64, loongarch, linux-mips,
linuxppc-dev, linux-riscv, linux-sh, sparclinux, linux-hyperv,
dri-devel, Palmer Dabbelt
In-Reply-To: <20230719123944.3438363-1-arnd@kernel.org>
From: Arnd Bergmann <arnd@arndb.de>
A number of architectures either kept the screen_info definition for
historical purposes as it used to be required by the generic VT code, or
they copied it from another architecture in order to build the VGA console
driver in an allmodconfig build. The mips definition is used by some
platforms, but the initialization on jazz is not needed.
Now that vgacon no longer builds on these architectures, remove the
stale definitions and initializations.
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Acked-by: Dinh Nguyen <dinguyen@kernel.org>
Acked-by: Max Filippov <jcmvbkbc@gmail.com>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Acked-by: Guo Ren <guoren@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
arch/csky/kernel/setup.c | 12 ------------
arch/hexagon/kernel/Makefile | 2 --
arch/hexagon/kernel/screen_info.c | 3 ---
arch/mips/jazz/setup.c | 9 ---------
arch/nios2/kernel/setup.c | 5 -----
arch/sh/kernel/setup.c | 5 -----
arch/sparc/kernel/setup_32.c | 13 -------------
arch/sparc/kernel/setup_64.c | 13 -------------
arch/xtensa/kernel/setup.c | 12 ------------
9 files changed, 74 deletions(-)
delete mode 100644 arch/hexagon/kernel/screen_info.c
diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c
index 106fbf0b6f3b4..51012e90780d6 100644
--- a/arch/csky/kernel/setup.c
+++ b/arch/csky/kernel/setup.c
@@ -8,22 +8,10 @@
#include <linux/of_fdt.h>
#include <linux/start_kernel.h>
#include <linux/dma-map-ops.h>
-#include <linux/screen_info.h>
#include <asm/sections.h>
#include <asm/mmu_context.h>
#include <asm/pgalloc.h>
-#ifdef CONFIG_DUMMY_CONSOLE
-struct screen_info screen_info = {
- .orig_video_lines = 30,
- .orig_video_cols = 80,
- .orig_video_mode = 0,
- .orig_video_ega_bx = 0,
- .orig_video_isVGA = 1,
- .orig_video_points = 8
-};
-#endif
-
static void __init csky_memblock_init(void)
{
unsigned long lowmem_size = PFN_DOWN(LOWMEM_LIMIT - PHYS_OFFSET_OFFSET);
diff --git a/arch/hexagon/kernel/Makefile b/arch/hexagon/kernel/Makefile
index e73cb321630ec..3fdf937eb572e 100644
--- a/arch/hexagon/kernel/Makefile
+++ b/arch/hexagon/kernel/Makefile
@@ -17,5 +17,3 @@ obj-y += vm_vectors.o
obj-$(CONFIG_HAS_DMA) += dma.o
obj-$(CONFIG_STACKTRACE) += stacktrace.o
-
-obj-$(CONFIG_VGA_CONSOLE) += screen_info.o
diff --git a/arch/hexagon/kernel/screen_info.c b/arch/hexagon/kernel/screen_info.c
deleted file mode 100644
index 1e1ceb18bafe7..0000000000000
--- a/arch/hexagon/kernel/screen_info.c
+++ /dev/null
@@ -1,3 +0,0 @@
-#include <linux/screen_info.h>
-
-struct screen_info screen_info;
diff --git a/arch/mips/jazz/setup.c b/arch/mips/jazz/setup.c
index ee044261eb223..23059ead773fc 100644
--- a/arch/mips/jazz/setup.c
+++ b/arch/mips/jazz/setup.c
@@ -13,7 +13,6 @@
#include <linux/init.h>
#include <linux/ioport.h>
#include <linux/console.h>
-#include <linux/screen_info.h>
#include <linux/platform_device.h>
#include <linux/serial_8250.h>
#include <linux/dma-mapping.h>
@@ -76,14 +75,6 @@ void __init plat_mem_setup(void)
_machine_restart = jazz_machine_restart;
-#ifdef CONFIG_VT
- screen_info = (struct screen_info) {
- .orig_video_cols = 160,
- .orig_video_lines = 64,
- .orig_video_points = 16,
- };
-#endif
-
add_preferred_console("ttyS", 0, "9600");
}
diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c
index 8582ed9658447..da122a5fa43b2 100644
--- a/arch/nios2/kernel/setup.c
+++ b/arch/nios2/kernel/setup.c
@@ -19,7 +19,6 @@
#include <linux/memblock.h>
#include <linux/initrd.h>
#include <linux/of_fdt.h>
-#include <linux/screen_info.h>
#include <asm/mmu_context.h>
#include <asm/sections.h>
@@ -36,10 +35,6 @@ static struct pt_regs fake_regs = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
0, 0, 0, 0, 0, 0,
0};
-#ifdef CONFIG_VT
-struct screen_info screen_info;
-#endif
-
/* Copy a short hook instruction sequence to the exception address */
static inline void copy_exception_handler(unsigned int addr)
{
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index b3da2757faaf3..3d80515298d26 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -7,7 +7,6 @@
* Copyright (C) 1999 Niibe Yutaka
* Copyright (C) 2002 - 2010 Paul Mundt
*/
-#include <linux/screen_info.h>
#include <linux/ioport.h>
#include <linux/init.h>
#include <linux/initrd.h>
@@ -69,10 +68,6 @@ EXPORT_SYMBOL(cpu_data);
struct sh_machine_vector sh_mv = { .mv_name = "generic", };
EXPORT_SYMBOL(sh_mv);
-#ifdef CONFIG_VT
-struct screen_info screen_info;
-#endif
-
extern int root_mountflags;
#define RAMDISK_IMAGE_START_MASK 0x07FF
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index 34ef7febf0d56..e3b72a7b46d37 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -17,7 +17,6 @@
#include <linux/initrd.h>
#include <asm/smp.h>
#include <linux/user.h>
-#include <linux/screen_info.h>
#include <linux/delay.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
@@ -51,18 +50,6 @@
#include "kernel.h"
-struct screen_info screen_info = {
- 0, 0, /* orig-x, orig-y */
- 0, /* unused */
- 0, /* orig-video-page */
- 0, /* orig-video-mode */
- 128, /* orig-video-cols */
- 0,0,0, /* ega_ax, ega_bx, ega_cx */
- 54, /* orig-video-lines */
- 0, /* orig-video-isVGA */
- 16 /* orig-video-points */
-};
-
/* Typing sync at the prom prompt calls the function pointed to by
* romvec->pv_synchook which I set to the following function.
* This should sync all filesystems and return, for now it just
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 6546ca9d4d3f1..6a4797dec34b4 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -15,7 +15,6 @@
#include <linux/ptrace.h>
#include <asm/smp.h>
#include <linux/user.h>
-#include <linux/screen_info.h>
#include <linux/delay.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
@@ -68,18 +67,6 @@
DEFINE_SPINLOCK(ns87303_lock);
EXPORT_SYMBOL(ns87303_lock);
-struct screen_info screen_info = {
- 0, 0, /* orig-x, orig-y */
- 0, /* unused */
- 0, /* orig-video-page */
- 0, /* orig-video-mode */
- 128, /* orig-video-cols */
- 0, 0, 0, /* unused, ega_bx, unused */
- 54, /* orig-video-lines */
- 0, /* orig-video-isVGA */
- 16 /* orig-video-points */
-};
-
static void
prom_console_write(struct console *con, const char *s, unsigned int n)
{
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index aba3ff4e60d85..3f22d0537818d 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -19,7 +19,6 @@
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/proc_fs.h>
-#include <linux/screen_info.h>
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/reboot.h>
@@ -49,17 +48,6 @@
#include <asm/timex.h>
#include <asm/traps.h>
-#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE)
-struct screen_info screen_info = {
- .orig_x = 0,
- .orig_y = 24,
- .orig_video_cols = 80,
- .orig_video_lines = 24,
- .orig_video_isVGA = 1,
- .orig_video_points = 16,
-};
-#endif
-
#ifdef CONFIG_BLK_DEV_INITRD
extern unsigned long initrd_start;
extern unsigned long initrd_end;
--
2.39.2
^ permalink raw reply related
* [PATCH v2 3/9] dummycon: limit Arm console size hack to footbridge
From: Arnd Bergmann @ 2023-07-19 12:39 UTC (permalink / raw)
To: linux-fbdev, Thomas Zimmermann, Helge Deller,
Javier Martinez Canillas
Cc: Arnd Bergmann, David S. Miller, K. Y. Srinivasan, Ard Biesheuvel,
Borislav Petkov, Brian Cain, Catalin Marinas, Christophe Leroy,
Daniel Vetter, Dave Hansen, David Airlie, Deepak Rawat,
Dexuan Cui, Dinh Nguyen, Greg Kroah-Hartman, Guo Ren,
Haiyang Zhang, Huacai Chen, Ingo Molnar,
John Paul Adrian Glaubitz, Khalid Aziz, Linus Walleij,
Matt Turner, Max Filippov, Michael Ellerman, Nicholas Piggin,
Palmer Dabbelt, Russell King, Thomas Bogendoerfer,
Thomas Gleixner, WANG Xuerui, Wei Liu, Will Deacon, x86,
linux-alpha, linux-kernel, linux-arm-kernel, linux-efi,
linux-csky, linux-hexagon, linux-ia64, loongarch, linux-mips,
linuxppc-dev, linux-riscv, linux-sh, sparclinux, linux-hyperv,
dri-devel
In-Reply-To: <20230719123944.3438363-1-arnd@kernel.org>
From: Arnd Bergmann <arnd@arndb.de>
The dummycon default console size used to be determined by architecture,
but now this is a Kconfig setting on everything except ARM. Tracing this
back in the historic git trees, this was used to match the size of VGA
console or VGA framebuffer on early machines, but nowadays that code is
no longer used, except probably on the old footbridge/netwinder since
that is the only one that supports vgacon.
On machines with a framebuffer, booting with DT so far results in always
using the hardcoded 80x30 size in dummycon, while on ATAGS the setting
can come from a bootloader specific override. Both seem to be worse
choices than the Kconfig setting, since the actual text size for fbcon
also depends on the selected font.
Make this work the same way as everywhere else and use the normal
Kconfig setting, except for the footbridge with vgacon, which keeps
using the traditional code. If vgacon is disabled, footbridge can
also ignore the setting. This means the screen_info only has to be
provided when either vgacon or EFI are enabled now.
To limit the amount of surprises on Arm, change the Kconfig default
to the previously used 80x30 setting instead of the usual 80x25.
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Tested-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
arch/arm/kernel/atags_parse.c | 2 +-
arch/arm/kernel/setup.c | 3 +--
drivers/video/console/Kconfig | 5 +++--
drivers/video/console/dummycon.c | 2 +-
4 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c
index 33f6eb5213a5a..4c815da3b77b0 100644
--- a/arch/arm/kernel/atags_parse.c
+++ b/arch/arm/kernel/atags_parse.c
@@ -69,7 +69,7 @@ static int __init parse_tag_mem32(const struct tag *tag)
__tagtable(ATAG_MEM, parse_tag_mem32);
-#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE)
+#if defined(CONFIG_ARCH_FOOTBRIDGE) && defined(CONFIG_VGA_CONSOLE)
static int __init parse_tag_videotext(const struct tag *tag)
{
screen_info.orig_x = tag->u.videotext.x;
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index c66b560562b30..40326a35a179b 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -928,8 +928,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc)
request_resource(&ioport_resource, &lp2);
}
-#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE) || \
- defined(CONFIG_EFI)
+#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_EFI)
struct screen_info screen_info = {
.orig_video_lines = 30,
.orig_video_cols = 80,
diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig
index 6af90db6d2da9..b575cf54174af 100644
--- a/drivers/video/console/Kconfig
+++ b/drivers/video/console/Kconfig
@@ -52,7 +52,7 @@ config DUMMY_CONSOLE
config DUMMY_CONSOLE_COLUMNS
int "Initial number of console screen columns"
- depends on DUMMY_CONSOLE && !ARM
+ depends on DUMMY_CONSOLE && !ARCH_FOOTBRIDGE
default 160 if PARISC
default 80
help
@@ -62,8 +62,9 @@ config DUMMY_CONSOLE_COLUMNS
config DUMMY_CONSOLE_ROWS
int "Initial number of console screen rows"
- depends on DUMMY_CONSOLE && !ARM
+ depends on DUMMY_CONSOLE && !ARCH_FOOTBRIDGE
default 64 if PARISC
+ default 30 if ARM
default 25
help
On PA-RISC, the default value is 64, which should fit a 1280x1024
diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c
index f1711b2f9ff05..70549fecee12c 100644
--- a/drivers/video/console/dummycon.c
+++ b/drivers/video/console/dummycon.c
@@ -18,7 +18,7 @@
* Dummy console driver
*/
-#if defined(__arm__)
+#if defined(CONFIG_ARCH_FOOTBRIDGE) && defined(CONFIG_VGA_CONSOLE)
#define DUMMY_COLUMNS screen_info.orig_video_cols
#define DUMMY_ROWS screen_info.orig_video_lines
#else
--
2.39.2
^ permalink raw reply related
* [PATCH v2 2/9] vgacon: rework screen_info #ifdef checks
From: Arnd Bergmann @ 2023-07-19 12:39 UTC (permalink / raw)
To: linux-fbdev, Thomas Zimmermann, Helge Deller,
Javier Martinez Canillas
Cc: Arnd Bergmann, David S. Miller, K. Y. Srinivasan, Ard Biesheuvel,
Borislav Petkov, Brian Cain, Catalin Marinas, Christophe Leroy,
Daniel Vetter, Dave Hansen, David Airlie, Deepak Rawat,
Dexuan Cui, Dinh Nguyen, Greg Kroah-Hartman, Guo Ren,
Haiyang Zhang, Huacai Chen, Ingo Molnar,
John Paul Adrian Glaubitz, Khalid Aziz, Linus Walleij,
Matt Turner, Max Filippov, Michael Ellerman, Nicholas Piggin,
Palmer Dabbelt, Russell King, Thomas Bogendoerfer,
Thomas Gleixner, WANG Xuerui, Wei Liu, Will Deacon, x86,
linux-alpha, linux-kernel, linux-arm-kernel, linux-efi,
linux-csky, linux-hexagon, linux-ia64, loongarch, linux-mips,
linuxppc-dev, linux-riscv, linux-sh, sparclinux, linux-hyperv,
dri-devel
In-Reply-To: <20230719123944.3438363-1-arnd@kernel.org>
From: Arnd Bergmann <arnd@arndb.de>
On non-x86 architectures, the screen_info variable is generally only
used for the VGA console where supported, and in some cases the EFI
framebuffer or vga16fb.
Now that we have a definite list of which architectures actually use it
for what, use consistent #ifdef checks so the global variable is only
defined when it is actually used on those architectures.
Loongarch and riscv have no support for vgacon or vga16fb, but
they support EFI firmware, so only that needs to be checked, and the
initialization can be removed because that is handled by EFI.
IA64 has both vgacon and EFI, though EFI apparently never uses
a framebuffer here.
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
v2 changes:
- split out mips/jazz change
- improve ia64 #ifdef changes
---
arch/alpha/kernel/setup.c | 2 ++
arch/alpha/kernel/sys_sio.c | 2 ++
arch/ia64/kernel/setup.c | 6 ++++++
arch/loongarch/kernel/setup.c | 2 ++
arch/mips/kernel/setup.c | 2 +-
arch/mips/sibyte/swarm/setup.c | 2 +-
arch/mips/sni/setup.c | 2 +-
arch/riscv/kernel/setup.c | 11 ++---------
8 files changed, 17 insertions(+), 12 deletions(-)
diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c
index b650ff1cb022e..b4d2297765c02 100644
--- a/arch/alpha/kernel/setup.c
+++ b/arch/alpha/kernel/setup.c
@@ -131,6 +131,7 @@ static void determine_cpu_caches (unsigned int);
static char __initdata command_line[COMMAND_LINE_SIZE];
+#ifdef CONFIG_VGA_CONSOLE
/*
* The format of "screen_info" is strange, and due to early
* i386-setup code. This is just enough to make the console
@@ -147,6 +148,7 @@ struct screen_info screen_info = {
};
EXPORT_SYMBOL(screen_info);
+#endif
/*
* The direct map I/O window, if any. This should be the same
diff --git a/arch/alpha/kernel/sys_sio.c b/arch/alpha/kernel/sys_sio.c
index 7c420d8dac53d..7de8a5d2d2066 100644
--- a/arch/alpha/kernel/sys_sio.c
+++ b/arch/alpha/kernel/sys_sio.c
@@ -57,11 +57,13 @@ sio_init_irq(void)
static inline void __init
alphabook1_init_arch(void)
{
+#ifdef CONFIG_VGA_CONSOLE
/* The AlphaBook1 has LCD video fixed at 800x600,
37 rows and 100 cols. */
screen_info.orig_y = 37;
screen_info.orig_video_cols = 100;
screen_info.orig_video_lines = 37;
+#endif
lca_init_arch();
}
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 5a55ac82c13a4..d2c66efdde560 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -86,9 +86,13 @@ EXPORT_SYMBOL(local_per_cpu_offset);
#endif
unsigned long ia64_cycles_per_usec;
struct ia64_boot_param *ia64_boot_param;
+#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_EFI)
struct screen_info screen_info;
+#endif
+#ifdef CONFIG_VGA_CONSOLE
unsigned long vga_console_iobase;
unsigned long vga_console_membase;
+#endif
static struct resource data_resource = {
.name = "Kernel data",
@@ -497,6 +501,7 @@ early_console_setup (char *cmdline)
static void __init
screen_info_setup(void)
{
+#ifdef CONFIG_VGA_CONSOLE
unsigned int orig_x, orig_y, num_cols, num_rows, font_height;
memset(&screen_info, 0, sizeof(screen_info));
@@ -525,6 +530,7 @@ screen_info_setup(void)
screen_info.orig_video_mode = 3; /* XXX fake */
screen_info.orig_video_isVGA = 1; /* XXX fake */
screen_info.orig_video_ega_bx = 3; /* XXX fake */
+#endif
}
static inline void
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 95e6b579dfdd1..77e7a3722caa6 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -57,7 +57,9 @@
#define SMBIOS_CORE_PACKAGE_OFFSET 0x23
#define LOONGSON_EFI_ENABLE (1 << 3)
+#ifdef CONFIG_EFI
struct screen_info screen_info __section(".data");
+#endif
unsigned long fw_arg0, fw_arg1, fw_arg2;
DEFINE_PER_CPU(unsigned long, kernelsp);
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index cb871eb784a7c..1aba7dc95132c 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -54,7 +54,7 @@ struct cpuinfo_mips cpu_data[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(cpu_data);
-#ifdef CONFIG_VT
+#ifdef CONFIG_VGA_CONSOLE
struct screen_info screen_info;
#endif
diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c
index 76683993cdd3a..37df504d3ecbb 100644
--- a/arch/mips/sibyte/swarm/setup.c
+++ b/arch/mips/sibyte/swarm/setup.c
@@ -129,7 +129,7 @@ void __init plat_mem_setup(void)
if (m41t81_probe())
swarm_rtc_type = RTC_M41T81;
-#ifdef CONFIG_VT
+#ifdef CONFIG_VGA_CONSOLE
screen_info = (struct screen_info) {
.orig_video_page = 52,
.orig_video_mode = 3,
diff --git a/arch/mips/sni/setup.c b/arch/mips/sni/setup.c
index efad85c8c823b..9984cf91be7d0 100644
--- a/arch/mips/sni/setup.c
+++ b/arch/mips/sni/setup.c
@@ -38,7 +38,7 @@ extern void sni_machine_power_off(void);
static void __init sni_display_setup(void)
{
-#if defined(CONFIG_VT) && defined(CONFIG_VGA_CONSOLE) && defined(CONFIG_FW_ARC)
+#if defined(CONFIG_VGA_CONSOLE) && defined(CONFIG_FW_ARC)
struct screen_info *si = &screen_info;
DISPLAY_STATUS *di;
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 971fe776e2f8b..a3dbe13f45fb3 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -39,15 +39,8 @@
#include "head.h"
-#if defined(CONFIG_DUMMY_CONSOLE) || defined(CONFIG_EFI)
-struct screen_info screen_info __section(".data") = {
- .orig_video_lines = 30,
- .orig_video_cols = 80,
- .orig_video_mode = 0,
- .orig_video_ega_bx = 0,
- .orig_video_isVGA = 1,
- .orig_video_points = 8
-};
+#if defined(CONFIG_EFI)
+struct screen_info screen_info __section(".data");
#endif
/*
--
2.39.2
^ permalink raw reply related
* [PATCH v2 1/9] vgacon: rework Kconfig dependencies
From: Arnd Bergmann @ 2023-07-19 12:39 UTC (permalink / raw)
To: linux-fbdev, Thomas Zimmermann, Helge Deller,
Javier Martinez Canillas
Cc: Arnd Bergmann, David S. Miller, K. Y. Srinivasan, Ard Biesheuvel,
Borislav Petkov, Brian Cain, Catalin Marinas, Christophe Leroy,
Daniel Vetter, Dave Hansen, David Airlie, Deepak Rawat,
Dexuan Cui, Dinh Nguyen, Greg Kroah-Hartman, Guo Ren,
Haiyang Zhang, Huacai Chen, Ingo Molnar,
John Paul Adrian Glaubitz, Khalid Aziz, Linus Walleij,
Matt Turner, Max Filippov, Michael Ellerman, Nicholas Piggin,
Palmer Dabbelt, Russell King, Thomas Bogendoerfer,
Thomas Gleixner, WANG Xuerui, Wei Liu, Will Deacon, x86,
linux-alpha, linux-kernel, linux-arm-kernel, linux-efi,
linux-csky, linux-hexagon, linux-ia64, loongarch, linux-mips,
linuxppc-dev, linux-riscv, linux-sh, sparclinux, linux-hyperv,
dri-devel
In-Reply-To: <20230719123944.3438363-1-arnd@kernel.org>
From: Arnd Bergmann <arnd@arndb.de>
The list of dependencies here is phrased as an opt-out, but this is missing
a lot of architectures that don't actually support VGA consoles, and some
of the entries are stale:
- powerpc used to support VGA consoles in the old arch/ppc codebase, but
the merged arch/powerpc never did
- arm lists footbridge, integrator and netwinder, but netwinder is actually
part of footbridge, and integrator does not appear to have an actual
VGA hardware, or list it in its ATAG or DT.
- mips has a few platforms (malta, sibyte, and sni) that initialize
screen_info, on everything else the console is selected but cannot
actually work.
- csky, hexgagon, loongarch, nios2, riscv and xtensa are not listed
in the opt-out table and declare a screen_info to allow building
vga_con, but this cannot work because the console is never selected.
Replace this with an opt-in table that lists only the platforms that
remain. This is effectively x86, plus a couple of historic workstation
and server machines that reused parts of the x86 system architecture.
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
drivers/video/console/Kconfig | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig
index 1b5a319971ed0..6af90db6d2da9 100644
--- a/drivers/video/console/Kconfig
+++ b/drivers/video/console/Kconfig
@@ -7,9 +7,9 @@ menu "Console display driver support"
config VGA_CONSOLE
bool "VGA text console" if EXPERT || !X86
- depends on !4xx && !PPC_8xx && !SPARC && !M68K && !PARISC && !SUPERH && \
- (!ARM || ARCH_FOOTBRIDGE || ARCH_INTEGRATOR || ARCH_NETWINDER) && \
- !ARM64 && !ARC && !MICROBLAZE && !OPENRISC && !S390 && !UML
+ depends on ALPHA || IA64 || X86 || \
+ (ARM && ARCH_FOOTBRIDGE) || \
+ (MIPS && (MIPS_MALTA || SIBYTE_BCM112X || SIBYTE_SB1250 || SIBYTE_BCM1x80 || SNI_RM))
select APERTURE_HELPERS if (DRM || FB || VFIO_PCI_CORE)
default y
help
--
2.39.2
^ permalink raw reply related
* [PATCH v2 0/9] video: screen_info cleanups
From: Arnd Bergmann @ 2023-07-19 12:39 UTC (permalink / raw)
To: linux-fbdev, Thomas Zimmermann, Helge Deller,
Javier Martinez Canillas
Cc: Arnd Bergmann, David S. Miller, K. Y. Srinivasan, Ard Biesheuvel,
Borislav Petkov, Brian Cain, Catalin Marinas, Christophe Leroy,
Daniel Vetter, Dave Hansen, David Airlie, Deepak Rawat,
Dexuan Cui, Dinh Nguyen, Greg Kroah-Hartman, Guo Ren,
Haiyang Zhang, Huacai Chen, Ingo Molnar,
John Paul Adrian Glaubitz, Khalid Aziz, Linus Walleij,
Matt Turner, Max Filippov, Michael Ellerman, Nicholas Piggin,
Palmer Dabbelt, Russell King, Thomas Bogendoerfer,
Thomas Gleixner, WANG Xuerui, Wei Liu, Will Deacon, x86,
linux-alpha, linux-kernel, linux-arm-kernel, linux-efi,
linux-csky, linux-hexagon, linux-ia64, loongarch, linux-mips,
linuxppc-dev, linux-riscv, linux-sh, sparclinux, linux-hyperv,
dri-devel
From: Arnd Bergmann <arnd@arndb.de>
I refreshed the first four patches that I sent before with very minor
updates, and then added some more to further disaggregate the use
of screen_info:
- I found that powerpc wasn't using vga16fb any more
- vgacon can be almost entirely separated from the global
screen_info, except on x86
- similarly, the EFI framebuffer initialization can be
kept separate, except on x86.
I did extensive build testing on arm/arm64/x86 and the normal built bot
testing for the other architectures.
Which tree should this get merged through?
Link: https://lore.kernel.org/lkml/20230707095415.1449376-1-arnd@kernel.org/
Arnd Bergmann (9):
vgacon: rework Kconfig dependencies
vgacon: rework screen_info #ifdef checks
dummycon: limit Arm console size hack to footbridge
vgacon, arch/*: remove unused screen_info definitions
vgacon: remove screen_info dependency
vgacon: clean up global screen_info instances
vga16fb: drop powerpc support
hyperv: avoid dependency on screen_info
efi: move screen_info into efi init code
arch/alpha/kernel/proto.h | 2 +
arch/alpha/kernel/setup.c | 8 +--
arch/alpha/kernel/sys_sio.c | 8 ++-
arch/arm/include/asm/setup.h | 5 ++
arch/arm/kernel/atags_parse.c | 20 +++---
arch/arm/kernel/efi.c | 6 --
arch/arm/kernel/setup.c | 7 +-
arch/arm64/kernel/efi.c | 4 --
arch/arm64/kernel/image-vars.h | 2 +
arch/csky/kernel/setup.c | 12 ----
arch/hexagon/kernel/Makefile | 2 -
arch/hexagon/kernel/screen_info.c | 3 -
arch/ia64/kernel/setup.c | 51 +++++++-------
arch/loongarch/kernel/efi.c | 3 +-
arch/loongarch/kernel/image-vars.h | 2 +
arch/loongarch/kernel/setup.c | 3 -
arch/mips/jazz/setup.c | 9 ---
arch/mips/kernel/setup.c | 11 ---
arch/mips/mti-malta/malta-setup.c | 4 +-
arch/mips/sibyte/swarm/setup.c | 26 ++++---
arch/mips/sni/setup.c | 18 ++---
arch/nios2/kernel/setup.c | 5 --
arch/powerpc/kernel/setup-common.c | 16 -----
arch/riscv/kernel/setup.c | 12 ----
arch/sh/kernel/setup.c | 5 --
arch/sparc/kernel/setup_32.c | 13 ----
arch/sparc/kernel/setup_64.c | 13 ----
arch/x86/kernel/setup.c | 2 +-
arch/xtensa/kernel/setup.c | 12 ----
drivers/firmware/efi/efi-init.c | 14 +++-
drivers/firmware/efi/libstub/efi-stub-entry.c | 8 ++-
drivers/firmware/pcdp.c | 1 -
drivers/gpu/drm/hyperv/hyperv_drm_drv.c | 7 +-
drivers/hv/vmbus_drv.c | 6 +-
drivers/video/console/Kconfig | 11 +--
drivers/video/console/dummycon.c | 2 +-
drivers/video/console/vgacon.c | 68 +++++++++++--------
drivers/video/fbdev/Kconfig | 2 +-
drivers/video/fbdev/hyperv_fb.c | 8 +--
drivers/video/fbdev/vga16fb.c | 9 +--
include/linux/console.h | 7 ++
41 files changed, 178 insertions(+), 249 deletions(-)
delete mode 100644 arch/hexagon/kernel/screen_info.c
--
2.39.2
Cc: "David S. Miller" <davem@davemloft.net>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Cain <bcain@quicinc.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Airlie <airlied@gmail.com>
Cc: Deepak Rawat <drawat.floss@gmail.com>
Cc: Dexuan Cui <decui@microsoft.com>
Cc: Dinh Nguyen <dinguyen@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Guo Ren <guoren@kernel.org>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Javier Martinez Canillas <javierm@redhat.com>
Cc: John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
Cc: Khalid Aziz <khalid@gonehiking.org>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: x86@kernel.org
Cc: linux-alpha@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-efi@vger.kernel.org
Cc: linux-csky@vger.kernel.org
Cc: linux-hexagon@vger.kernel.org
Cc: linux-ia64@vger.kernel.org
Cc: loongarch@lists.linux.dev
Cc: linux-mips@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-riscv@lists.infradead.org
Cc: linux-sh@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Cc: linux-hyperv@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Cc: linux-fbdev@vger.kernel.org
^ permalink raw reply
* Re: [PATCH V4 net-next] net: mana: Configure hwc timeout from hardware
From: Leon Romanovsky @ 2023-07-19 7:08 UTC (permalink / raw)
To: Souradeep Chakrabarti
Cc: kys, haiyangz, wei.liu, decui, davem, edumazet, kuba, pabeni,
longli, sharmaajay, cai.huoqing, ssengar, vkuznets, tglx,
linux-hyperv, netdev, linux-kernel, linux-rdma, schakrabarti
In-Reply-To: <1689703232-24858-1-git-send-email-schakrabarti@linux.microsoft.com>
On Tue, Jul 18, 2023 at 11:00:32AM -0700, Souradeep Chakrabarti wrote:
> At present hwc timeout value is a fixed value. This patch sets the hwc
> timeout from the hardware. It now uses a new hardware capability
> GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG to query and set the value
> in hwc_timeout.
>
> Signed-off-by: Souradeep Chakrabarti <schakrabarti@linux.microsoft.com>
> ---
> V3 -> V4:
> * Changing branch to net-next.
> * Changed the commit message to 75 chars per line.
> ---
> .../net/ethernet/microsoft/mana/gdma_main.c | 30 ++++++++++++++++++-
> .../net/ethernet/microsoft/mana/hw_channel.c | 25 +++++++++++++++-
> include/net/mana/gdma.h | 20 ++++++++++++-
> include/net/mana/hw_channel.h | 5 ++++
> 4 files changed, 77 insertions(+), 3 deletions(-)
<...>
> gc->hwc.driver_data = NULL;
> gc->hwc.gdma_context = NULL;
> @@ -818,6 +839,7 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
> dest_vrq = hwc->pf_dest_vrq_id;
> dest_vrcq = hwc->pf_dest_vrcq_id;
> }
> + dev_err(hwc->dev, "HWC: timeout %u ms\n", hwc->hwc_timeout);
Why do you print this message every time and with error level?
Probably you should delete it.
Thanks
^ permalink raw reply
* Re: [PATCH v9 1/2] x86/tdx: Retry TDVMCALL_MAP_GPA() when needed
From: Xiaoyao Li @ 2023-07-19 2:31 UTC (permalink / raw)
To: Dexuan Cui, ak, arnd, bp, brijesh.singh, dan.j.williams,
dave.hansen, dave.hansen, haiyangz, hpa, jane.chu,
kirill.shutemov, kys, linux-arch, linux-hyperv, luto, mingo,
peterz, rostedt, sathyanarayanan.kuppuswamy, seanjc, tglx,
tony.luck, wei.liu, x86, mikelley
Cc: linux-kernel, Tianyu.Lan, rick.p.edgecombe
In-Reply-To: <20230621191317.4129-2-decui@microsoft.com>
On 6/22/2023 3:13 AM, Dexuan Cui wrote:
> GHCI spec for TDX 1.0 says that the MapGPA call may fail with the R10
> error code = TDG.VP.VMCALL_RETRY (1), and the guest must retry this
> operation for the pages in the region starting at the GPA specified
> in R11.
>
> When a fully enlightened TDX guest runs on Hyper-V, Hyper-V can return
> the retry error when set_memory_decrypted() is called to decrypt up to
> 1GB of swiotlb bounce buffers.
just out of curiosity, what size does Hyper-v handle at most in one call?
^ permalink raw reply
* Re: [PATCH net-next v5 0/2] net: mana: Fix doorbell access for receive queues
From: patchwork-bot+netdevbpf @ 2023-07-19 1:10 UTC (permalink / raw)
To: Long Li
Cc: kys, haiyangz, wei.liu, decui, davem, edumazet, kuba, pabeni,
leon, shradhagupta, sharmaajay, shacharr, stephen, linux-hyperv,
netdev, linux-kernel, linux-rdma, longli
In-Reply-To: <1689622539-5334-1-git-send-email-longli@linuxonhyperv.com>
Hello:
This series was applied to netdev/net-next.git (main)
by Jakub Kicinski <kuba@kernel.org>:
On Mon, 17 Jul 2023 12:35:37 -0700 you wrote:
> From: Long Li <longli@microsoft.com>
>
> This patchset fixes the issues discovered during 200G physical link
> tests. It fixes doorbell usage and WQE format for receive queues.
>
> Long Li (2):
> net: mana: Batch ringing RX queue doorbell on receiving packets
> net: mana: Use the correct WQE count for ringing RQ doorbell
>
> [...]
Here is the summary with links:
- [net-next,v5,1/2] net: mana: Batch ringing RX queue doorbell on receiving packets
https://git.kernel.org/netdev/net-next/c/da4e8648079e
- [net-next,v5,2/2] net: mana: Use the correct WQE count for ringing RQ doorbell
https://git.kernel.org/netdev/net-next/c/f5e39b57124f
You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html
^ permalink raw reply
* [PATCH RFC net-next v5 14/14] test/vsock: add vsock dgram tests
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman,
Jiang Wang
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
From: Jiang Wang <jiang.wang@bytedance.com>
This commit adds tests for vsock datagram.
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
Signed-off-by: Jiang Wang <jiang.wang@bytedance.com>
---
tools/testing/vsock/util.c | 141 +++++++-
tools/testing/vsock/util.h | 6 +
tools/testing/vsock/vsock_test.c | 680 +++++++++++++++++++++++++++++++++++++++
3 files changed, 826 insertions(+), 1 deletion(-)
diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c
index 01b636d3039a..811e70d7cf1e 100644
--- a/tools/testing/vsock/util.c
+++ b/tools/testing/vsock/util.c
@@ -99,7 +99,8 @@ static int vsock_connect(unsigned int cid, unsigned int port, int type)
int ret;
int fd;
- control_expectln("LISTENING");
+ if (type != SOCK_DGRAM)
+ control_expectln("LISTENING");
fd = socket(AF_VSOCK, type, 0);
@@ -130,6 +131,11 @@ int vsock_seqpacket_connect(unsigned int cid, unsigned int port)
return vsock_connect(cid, port, SOCK_SEQPACKET);
}
+int vsock_dgram_connect(unsigned int cid, unsigned int port)
+{
+ return vsock_connect(cid, port, SOCK_DGRAM);
+}
+
/* Listen on <cid, port> and return the first incoming connection. The remote
* address is stored to clientaddrp. clientaddrp may be NULL.
*/
@@ -211,6 +217,34 @@ int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
return vsock_accept(cid, port, clientaddrp, SOCK_SEQPACKET);
}
+int vsock_dgram_bind(unsigned int cid, unsigned int port)
+{
+ union {
+ struct sockaddr sa;
+ struct sockaddr_vm svm;
+ } addr = {
+ .svm = {
+ .svm_family = AF_VSOCK,
+ .svm_port = port,
+ .svm_cid = cid,
+ },
+ };
+ int fd;
+
+ fd = socket(AF_VSOCK, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ perror("socket");
+ exit(EXIT_FAILURE);
+ }
+
+ if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
+ perror("bind");
+ exit(EXIT_FAILURE);
+ }
+
+ return fd;
+}
+
/* Transmit one byte and check the return value.
*
* expected_ret:
@@ -260,6 +294,57 @@ void send_byte(int fd, int expected_ret, int flags)
}
}
+/* Transmit one byte and check the return value.
+ *
+ * expected_ret:
+ * <0 Negative errno (for testing errors)
+ * 0 End-of-file
+ * 1 Success
+ */
+void sendto_byte(int fd, const struct sockaddr *dest_addr, int len, int expected_ret,
+ int flags)
+{
+ const uint8_t byte = 'A';
+ ssize_t nwritten;
+
+ timeout_begin(TIMEOUT);
+ do {
+ nwritten = sendto(fd, &byte, sizeof(byte), flags, dest_addr,
+ len);
+ timeout_check("write");
+ } while (nwritten < 0 && errno == EINTR);
+ timeout_end();
+
+ if (expected_ret < 0) {
+ if (nwritten != -1) {
+ fprintf(stderr, "bogus sendto(2) return value %zd\n",
+ nwritten);
+ exit(EXIT_FAILURE);
+ }
+ if (errno != -expected_ret) {
+ perror("write");
+ exit(EXIT_FAILURE);
+ }
+ return;
+ }
+
+ if (nwritten < 0) {
+ perror("write");
+ exit(EXIT_FAILURE);
+ }
+ if (nwritten == 0) {
+ if (expected_ret == 0)
+ return;
+
+ fprintf(stderr, "unexpected EOF while sending byte\n");
+ exit(EXIT_FAILURE);
+ }
+ if (nwritten != sizeof(byte)) {
+ fprintf(stderr, "bogus sendto(2) return value %zd\n", nwritten);
+ exit(EXIT_FAILURE);
+ }
+}
+
/* Receive one byte and check the return value.
*
* expected_ret:
@@ -313,6 +398,60 @@ void recv_byte(int fd, int expected_ret, int flags)
}
}
+/* Receive one byte and check the return value.
+ *
+ * expected_ret:
+ * <0 Negative errno (for testing errors)
+ * 0 End-of-file
+ * 1 Success
+ */
+void recvfrom_byte(int fd, struct sockaddr *src_addr, socklen_t *addrlen,
+ int expected_ret, int flags)
+{
+ uint8_t byte;
+ ssize_t nread;
+
+ timeout_begin(TIMEOUT);
+ do {
+ nread = recvfrom(fd, &byte, sizeof(byte), flags, src_addr, addrlen);
+ timeout_check("read");
+ } while (nread < 0 && errno == EINTR);
+ timeout_end();
+
+ if (expected_ret < 0) {
+ if (nread != -1) {
+ fprintf(stderr, "bogus recvfrom(2) return value %zd\n",
+ nread);
+ exit(EXIT_FAILURE);
+ }
+ if (errno != -expected_ret) {
+ perror("read");
+ exit(EXIT_FAILURE);
+ }
+ return;
+ }
+
+ if (nread < 0) {
+ perror("read");
+ exit(EXIT_FAILURE);
+ }
+ if (nread == 0) {
+ if (expected_ret == 0)
+ return;
+
+ fprintf(stderr, "unexpected EOF while receiving byte\n");
+ exit(EXIT_FAILURE);
+ }
+ if (nread != sizeof(byte)) {
+ fprintf(stderr, "bogus recvfrom(2) return value %zd\n", nread);
+ exit(EXIT_FAILURE);
+ }
+ if (byte != 'A') {
+ fprintf(stderr, "unexpected byte read %c\n", byte);
+ exit(EXIT_FAILURE);
+ }
+}
+
/* Run test cases. The program terminates if a failure occurs. */
void run_tests(const struct test_case *test_cases,
const struct test_opts *opts)
diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h
index fb99208a95ea..a69e128d120c 100644
--- a/tools/testing/vsock/util.h
+++ b/tools/testing/vsock/util.h
@@ -37,13 +37,19 @@ void init_signals(void);
unsigned int parse_cid(const char *str);
int vsock_stream_connect(unsigned int cid, unsigned int port);
int vsock_seqpacket_connect(unsigned int cid, unsigned int port);
+int vsock_dgram_connect(unsigned int cid, unsigned int port);
int vsock_stream_accept(unsigned int cid, unsigned int port,
struct sockaddr_vm *clientaddrp);
int vsock_seqpacket_accept(unsigned int cid, unsigned int port,
struct sockaddr_vm *clientaddrp);
+int vsock_dgram_bind(unsigned int cid, unsigned int port);
void vsock_wait_remote_close(int fd);
void send_byte(int fd, int expected_ret, int flags);
+void sendto_byte(int fd, const struct sockaddr *dest_addr, int len, int expected_ret,
+ int flags);
void recv_byte(int fd, int expected_ret, int flags);
+void recvfrom_byte(int fd, struct sockaddr *src_addr, socklen_t *addrlen,
+ int expected_ret, int flags);
void run_tests(const struct test_case *test_cases,
const struct test_opts *opts);
void list_tests(const struct test_case *test_cases);
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index ac1bd3ac1533..c9904a3376ce 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -13,6 +13,7 @@
#include <string.h>
#include <errno.h>
#include <unistd.h>
+#include <linux/errqueue.h>
#include <linux/kernel.h>
#include <sys/types.h>
#include <sys/socket.h>
@@ -24,6 +25,12 @@
#include "control.h"
#include "util.h"
+#ifndef SOL_VSOCK
+#define SOL_VSOCK 287
+#endif
+
+#define DGRAM_MSG_CNT 16
+
static void test_stream_connection_reset(const struct test_opts *opts)
{
union {
@@ -1053,6 +1060,644 @@ static void test_stream_virtio_skb_merge_server(const struct test_opts *opts)
close(fd);
}
+static void test_dgram_sendto_client(const struct test_opts *opts)
+{
+ union {
+ struct sockaddr sa;
+ struct sockaddr_vm svm;
+ } addr = {
+ .svm = {
+ .svm_family = AF_VSOCK,
+ .svm_port = 1234,
+ .svm_cid = opts->peer_cid,
+ },
+ };
+ int fd;
+
+ /* Wait for the server to be ready */
+ control_expectln("BIND");
+
+ fd = socket(AF_VSOCK, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ perror("socket");
+ exit(EXIT_FAILURE);
+ }
+
+ sendto_byte(fd, &addr.sa, sizeof(addr.svm), 1, 0);
+
+ /* Notify the server that the client has finished */
+ control_writeln("DONE");
+
+ close(fd);
+}
+
+static void test_dgram_sendto_server(const struct test_opts *opts)
+{
+ union {
+ struct sockaddr sa;
+ struct sockaddr_vm svm;
+ } addr = {
+ .svm = {
+ .svm_family = AF_VSOCK,
+ .svm_port = 1234,
+ .svm_cid = VMADDR_CID_ANY,
+ },
+ };
+ unsigned long sock_buf_size;
+ int len = sizeof(addr.sa);
+ int fd;
+
+ fd = socket(AF_VSOCK, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ perror("socket");
+ exit(EXIT_FAILURE);
+ }
+
+ if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
+ perror("bind");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Set receive buffer to maximum */
+ sock_buf_size = -1;
+ if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF,
+ &sock_buf_size, sizeof(sock_buf_size))) {
+ perror("setsockopt(SO_RECVBUF)");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Notify the client that the server is ready */
+ control_writeln("BIND");
+
+ recvfrom_byte(fd, &addr.sa, &len, 1, 0);
+
+ /* Wait for the client to finish */
+ control_expectln("DONE");
+
+ close(fd);
+}
+
+static void test_dgram_connect_client(const struct test_opts *opts)
+{
+ union {
+ struct sockaddr sa;
+ struct sockaddr_vm svm;
+ } addr = {
+ .svm = {
+ .svm_family = AF_VSOCK,
+ .svm_port = 1234,
+ .svm_cid = opts->peer_cid,
+ },
+ };
+ int ret;
+ int fd;
+
+ /* Wait for the server to be ready */
+ control_expectln("BIND");
+
+ fd = socket(AF_VSOCK, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ perror("bind");
+ exit(EXIT_FAILURE);
+ }
+
+ ret = connect(fd, &addr.sa, sizeof(addr.svm));
+ if (ret < 0) {
+ perror("connect");
+ exit(EXIT_FAILURE);
+ }
+
+ send_byte(fd, 1, 0);
+
+ /* Notify the server that the client has finished */
+ control_writeln("DONE");
+
+ close(fd);
+}
+
+static void test_dgram_connect_server(const struct test_opts *opts)
+{
+ test_dgram_sendto_server(opts);
+}
+
+static void test_dgram_multiconn_sendto_client(const struct test_opts *opts)
+{
+ union {
+ struct sockaddr sa;
+ struct sockaddr_vm svm;
+ } addr = {
+ .svm = {
+ .svm_family = AF_VSOCK,
+ .svm_port = 1234,
+ .svm_cid = opts->peer_cid,
+ },
+ };
+ int fds[MULTICONN_NFDS];
+ int i;
+
+ /* Wait for the server to be ready */
+ control_expectln("BIND");
+
+ for (i = 0; i < MULTICONN_NFDS; i++) {
+ fds[i] = socket(AF_VSOCK, SOCK_DGRAM, 0);
+ if (fds[i] < 0) {
+ perror("socket");
+ exit(EXIT_FAILURE);
+ }
+ }
+
+ for (i = 0; i < MULTICONN_NFDS; i++) {
+ sendto_byte(fds[i], &addr.sa, sizeof(addr.svm), 1, 0);
+
+ /* This is here to make explicit the case of the test failing
+ * due to packet loss. The test fails when recv() times out
+ * otherwise, which is much more confusing.
+ */
+ control_expectln("PKTRECV");
+ }
+
+ /* Notify the server that the client has finished */
+ control_writeln("DONE");
+
+ for (i = 0; i < MULTICONN_NFDS; i++)
+ close(fds[i]);
+}
+
+static void test_dgram_multiconn_sendto_server(const struct test_opts *opts)
+{
+ union {
+ struct sockaddr sa;
+ struct sockaddr_vm svm;
+ } addr = {
+ .svm = {
+ .svm_family = AF_VSOCK,
+ .svm_port = 1234,
+ .svm_cid = VMADDR_CID_ANY,
+ },
+ };
+ int len = sizeof(addr.sa);
+ int fd;
+ int i;
+
+ fd = socket(AF_VSOCK, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ perror("socket");
+ exit(EXIT_FAILURE);
+ }
+
+ if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
+ perror("bind");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Notify the client that the server is ready */
+ control_writeln("BIND");
+
+ for (i = 0; i < MULTICONN_NFDS; i++) {
+ recvfrom_byte(fd, &addr.sa, &len, 1, 0);
+ control_writeln("PKTRECV");
+ }
+
+ /* Wait for the client to finish */
+ control_expectln("DONE");
+
+ close(fd);
+}
+
+static void test_dgram_multiconn_send_client(const struct test_opts *opts)
+{
+ int fds[MULTICONN_NFDS];
+ int i;
+
+ /* Wait for the server to be ready */
+ control_expectln("BIND");
+
+ for (i = 0; i < MULTICONN_NFDS; i++) {
+ fds[i] = vsock_dgram_connect(opts->peer_cid, 1234);
+ if (fds[i] < 0) {
+ perror("connect");
+ exit(EXIT_FAILURE);
+ }
+ }
+
+ for (i = 0; i < MULTICONN_NFDS; i++) {
+ send_byte(fds[i], 1, 0);
+ /* This is here to make explicit the case of the test failing
+ * due to packet loss.
+ */
+ control_expectln("PKTRECV");
+ }
+
+ /* Notify the server that the client has finished */
+ control_writeln("DONE");
+
+ for (i = 0; i < MULTICONN_NFDS; i++)
+ close(fds[i]);
+}
+
+static void test_dgram_multiconn_send_server(const struct test_opts *opts)
+{
+ union {
+ struct sockaddr sa;
+ struct sockaddr_vm svm;
+ } addr = {
+ .svm = {
+ .svm_family = AF_VSOCK,
+ .svm_port = 1234,
+ .svm_cid = VMADDR_CID_ANY,
+ },
+ };
+ unsigned long sock_buf_size;
+ int fd;
+ int i;
+
+ fd = socket(AF_VSOCK, SOCK_DGRAM, 0);
+ if (fd < 0) {
+ perror("socket");
+ exit(EXIT_FAILURE);
+ }
+
+ if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) {
+ perror("bind");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Set receive buffer to maximum */
+ sock_buf_size = -1;
+ if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF,
+ &sock_buf_size, sizeof(sock_buf_size))) {
+ perror("setsockopt(SO_RECVBUF)");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Notify the client that the server is ready */
+ control_writeln("BIND");
+
+ for (i = 0; i < MULTICONN_NFDS; i++) {
+ recv_byte(fd, 1, 0);
+ control_writeln("PKTRECV");
+ }
+
+ /* Wait for the client to finish */
+ control_expectln("DONE");
+
+ close(fd);
+}
+
+/*
+ * This test is similar to the seqpacket msg bounds tests, but it is unreliable
+ * because it may also fail in the unlikely case that packets are dropped.
+ */
+static void test_dgram_bounds_unreliable_client(const struct test_opts *opts)
+{
+ unsigned long recv_buf_size;
+ unsigned long *hashes;
+ int page_size;
+ int fd;
+ int i;
+
+ fd = vsock_dgram_connect(opts->peer_cid, 1234);
+ if (fd < 0) {
+ perror("connect");
+ exit(EXIT_FAILURE);
+ }
+
+ hashes = malloc(DGRAM_MSG_CNT * sizeof(unsigned long));
+ if (!hashes) {
+ perror("malloc");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Let the server know the client is ready */
+ control_writeln("CLNTREADY");
+
+ /* Wait, until receiver sets buffer size. */
+ control_expectln("SRVREADY");
+
+ recv_buf_size = control_readulong();
+
+ page_size = getpagesize();
+
+ for (i = 0; i < DGRAM_MSG_CNT; i++) {
+ ssize_t send_size;
+ size_t buf_size;
+ void *buf;
+
+ /* Use "small" buffers and "big" buffers. */
+ if (opts->peer_cid <= VMADDR_CID_HOST && (i & 1))
+ buf_size = page_size +
+ (rand() % (MAX_MSG_SIZE - page_size));
+ else
+ buf_size = 1 + (rand() % page_size);
+
+ buf_size = min(buf_size, recv_buf_size);
+
+ buf = malloc(buf_size);
+
+ if (!buf) {
+ perror("malloc");
+ exit(EXIT_FAILURE);
+ }
+
+ memset(buf, rand() & 0xff, buf_size);
+
+ send_size = send(fd, buf, buf_size, 0);
+ if (send_size < 0) {
+ perror("send");
+ exit(EXIT_FAILURE);
+ }
+
+ if (send_size != buf_size) {
+ fprintf(stderr, "Invalid send size\n");
+ exit(EXIT_FAILURE);
+ }
+
+ /* In theory the implementation isn't required to transmit
+ * these packets in order, so we use this PKTSENT/PKTRECV
+ * message sequence so that server and client coordinate
+ * sending and receiving one packet at a time. The client sends
+ * a packet and waits until it has been received before sending
+ * another.
+ *
+ * Also in theory these packets can be lost and the test will
+ * fail for that reason.
+ */
+ control_writeln("PKTSENT");
+ control_expectln("PKTRECV");
+
+ /* Send the server a hash of the packet */
+ hashes[i] = hash_djb2(buf, buf_size);
+ free(buf);
+ }
+
+ control_writeln("SENDDONE");
+ close(fd);
+
+ for (i = 0; i < DGRAM_MSG_CNT; i++) {
+ if (hashes[i] != control_readulong())
+ fprintf(stderr, "broken dgram message bounds or packet loss\n");
+ }
+ free(hashes);
+}
+
+static void test_dgram_bounds_unreliable_server(const struct test_opts *opts)
+{
+ unsigned long hashes[DGRAM_MSG_CNT];
+ unsigned long sock_buf_size;
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ char buf[MAX_MSG_SIZE];
+ socklen_t len;
+ int fd;
+ int i;
+
+ fd = vsock_dgram_bind(VMADDR_CID_ANY, 1234);
+ if (fd < 0) {
+ perror("bind");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Set receive buffer to maximum */
+ sock_buf_size = -1;
+ if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF,
+ &sock_buf_size, sizeof(sock_buf_size))) {
+ perror("setsockopt(SO_RECVBUF)");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Retrieve the receive buffer size */
+ len = sizeof(sock_buf_size);
+ if (getsockopt(fd, SOL_SOCKET, SO_RCVBUF,
+ &sock_buf_size, &len)) {
+ perror("getsockopt(SO_RECVBUF)");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Client ready to receive parameters */
+ control_expectln("CLNTREADY");
+
+ /* Ready to receive data. */
+ control_writeln("SRVREADY");
+
+ if (opts->peer_cid > VMADDR_CID_HOST)
+ control_writeulong(sock_buf_size);
+ else
+ control_writeulong(getpagesize());
+
+ iov.iov_base = buf;
+ iov.iov_len = sizeof(buf);
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+
+ for (i = 0; i < DGRAM_MSG_CNT; i++) {
+ ssize_t recv_size;
+
+ control_expectln("PKTSENT");
+ recv_size = recvmsg(fd, &msg, 0);
+ control_writeln("PKTRECV");
+
+ if (!recv_size)
+ break;
+
+ if (recv_size < 0) {
+ perror("recvmsg");
+ exit(EXIT_FAILURE);
+ }
+
+ hashes[i] = hash_djb2(msg.msg_iov[0].iov_base, recv_size);
+ }
+
+ control_expectln("SENDDONE");
+
+ close(fd);
+
+ for (i = 0; i < DGRAM_MSG_CNT; i++)
+ control_writeulong(hashes[i]);
+}
+
+#define POLL_TIMEOUT_MS 1000
+void vsock_recv_error(int fd)
+{
+ struct sock_extended_err *serr;
+ struct msghdr msg = { 0 };
+ struct pollfd fds = { 0 };
+ char cmsg_data[128];
+ struct cmsghdr *cm;
+ ssize_t res;
+
+ fds.fd = fd;
+ fds.events = 0;
+
+ if (poll(&fds, 1, POLL_TIMEOUT_MS) < 0) {
+ perror("poll");
+ exit(EXIT_FAILURE);
+ }
+
+ if (!(fds.revents & POLLERR)) {
+ fprintf(stderr, "POLLERR expected\n");
+ exit(EXIT_FAILURE);
+ }
+
+ msg.msg_control = cmsg_data;
+ msg.msg_controllen = sizeof(cmsg_data);
+
+ res = recvmsg(fd, &msg, MSG_ERRQUEUE);
+ if (res) {
+ fprintf(stderr, "failed to read error queue: %zi\n", res);
+ exit(EXIT_FAILURE);
+ }
+
+ cm = CMSG_FIRSTHDR(&msg);
+ if (!cm) {
+ fprintf(stderr, "cmsg: no cmsg\n");
+ exit(EXIT_FAILURE);
+ }
+
+ if (cm->cmsg_level != SOL_VSOCK) {
+ fprintf(stderr, "cmsg: unexpected 'cmsg_level'\n");
+ exit(EXIT_FAILURE);
+ }
+
+ if (cm->cmsg_type != 0) {
+ fprintf(stderr, "cmsg: unexpected 'cmsg_type'\n");
+ exit(EXIT_FAILURE);
+ }
+
+ serr = (void *)CMSG_DATA(cm);
+ if (serr->ee_origin != 0) {
+ fprintf(stderr, "serr: unexpected 'ee_origin'\n");
+ exit(EXIT_FAILURE);
+ }
+
+ if (serr->ee_errno != EHOSTUNREACH) {
+ fprintf(stderr, "serr: wrong error code: %u\n", serr->ee_errno);
+ exit(EXIT_FAILURE);
+ }
+}
+
+/*
+ * Attempt to send a packet larger than the client's RX buffer. Test that the
+ * packet was dropped and that there is an error in the error queue.
+ */
+static void test_dgram_drop_big_packets_server(const struct test_opts *opts)
+{
+ unsigned long client_rx_buf_size;
+ size_t buf_size;
+ void *buf;
+ int fd;
+
+ if (opts->peer_cid <= VMADDR_CID_HOST) {
+ printf("The server's peer must be a guest (not CID %u), skipped...\n",
+ opts->peer_cid);
+ return;
+ }
+
+ /* Wait for the server to be ready */
+ control_expectln("READY");
+
+ fd = vsock_dgram_connect(opts->peer_cid, 1234);
+ if (fd < 0) {
+ perror("connect");
+ exit(EXIT_FAILURE);
+ }
+
+ client_rx_buf_size = control_readulong();
+
+ buf_size = client_rx_buf_size + 1;
+ buf = malloc(buf_size);
+ if (!buf) {
+ perror("malloc");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Even though the buffer is exceeded, the send() should still succeed. */
+ if (send(fd, buf, buf_size, 0) < 0) {
+ perror("send");
+ exit(EXIT_FAILURE);
+ }
+
+ vsock_recv_error(fd);
+
+ /* Notify the server that the client has finished */
+ control_writeln("DONE");
+
+ close(fd);
+}
+
+static void test_dgram_drop_big_packets_client(const struct test_opts *opts)
+{
+ unsigned long buf_size = getpagesize();
+
+ if (opts->peer_cid > VMADDR_CID_HOST) {
+ printf("The client's peer must be the host (not CID %u), skipped...\n",
+ opts->peer_cid);
+ return;
+ }
+
+ control_writeln("READY");
+ control_writeulong(buf_size);
+ control_expectln("DONE");
+}
+
+static void test_stream_dgram_address_collision_client(const struct test_opts *opts)
+{
+ int dgram_fd, stream_fd;
+
+ stream_fd = vsock_stream_connect(opts->peer_cid, 1234);
+ if (stream_fd < 0) {
+ perror("connect");
+ exit(EXIT_FAILURE);
+ }
+
+ /* This simply tests if connect() causes address collision client-side.
+ * Keep in mind that there is no exchange of packets with the
+ * bound socket on the server.
+ */
+ dgram_fd = vsock_dgram_connect(opts->peer_cid, 1234);
+ if (dgram_fd < 0) {
+ perror("connect");
+ exit(EXIT_FAILURE);
+ }
+
+ close(stream_fd);
+ close(dgram_fd);
+
+ /* Notify the server that the client has finished */
+ control_writeln("DONE");
+}
+
+static void test_stream_dgram_address_collision_server(const struct test_opts *opts)
+{
+ int dgram_fd, stream_fd;
+ struct sockaddr_vm addr;
+ socklen_t addrlen;
+
+ stream_fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, 0);
+ if (stream_fd < 0) {
+ perror("accept");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Retrieve the CID/port for re-use. */
+ addrlen = sizeof(addr);
+ if (getsockname(stream_fd, (struct sockaddr *)&addr, &addrlen)) {
+ perror("getsockname");
+ exit(EXIT_FAILURE);
+ }
+
+ /* See not in the client function about the pairwise connect call. */
+ dgram_fd = vsock_dgram_bind(addr.svm_cid, addr.svm_port);
+ if (dgram_fd < 0) {
+ perror("bind");
+ exit(EXIT_FAILURE);
+ }
+
+ control_expectln("DONE");
+
+ close(stream_fd);
+ close(dgram_fd);
+}
+
static struct test_case test_cases[] = {
{
.name = "SOCK_STREAM connection reset",
@@ -1128,6 +1773,41 @@ static struct test_case test_cases[] = {
.run_client = test_stream_virtio_skb_merge_client,
.run_server = test_stream_virtio_skb_merge_server,
},
+ {
+ .name = "SOCK_DGRAM client sendto",
+ .run_client = test_dgram_sendto_client,
+ .run_server = test_dgram_sendto_server,
+ },
+ {
+ .name = "SOCK_DGRAM client connect",
+ .run_client = test_dgram_connect_client,
+ .run_server = test_dgram_connect_server,
+ },
+ {
+ .name = "SOCK_DGRAM multiple connections using sendto",
+ .run_client = test_dgram_multiconn_sendto_client,
+ .run_server = test_dgram_multiconn_sendto_server,
+ },
+ {
+ .name = "SOCK_DGRAM multiple connections using send",
+ .run_client = test_dgram_multiconn_send_client,
+ .run_server = test_dgram_multiconn_send_server,
+ },
+ {
+ .name = "SOCK_DGRAM msg bounds unreliable",
+ .run_client = test_dgram_bounds_unreliable_client,
+ .run_server = test_dgram_bounds_unreliable_server,
+ },
+ {
+ .name = "SOCK_DGRAM drop big packets",
+ .run_client = test_dgram_drop_big_packets_client,
+ .run_server = test_dgram_drop_big_packets_server,
+ },
+ {
+ .name = "SOCK_STREAM and SOCK_DGRAM address collision",
+ .run_client = test_stream_dgram_address_collision_client,
+ .run_server = test_stream_dgram_address_collision_server,
+ },
{},
};
--
2.30.2
^ permalink raw reply related
* [PATCH RFC net-next v5 11/14] vhost/vsock: implement datagram support
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
This commit implements datagram support for vhost/vsock by teaching
vhost to use the common virtio transport datagram functions.
If the virtio RX buffer is too small, then the transmission is
abandoned, the packet dropped, and EHOSTUNREACH is added to the socket's
error queue.
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
drivers/vhost/vsock.c | 62 +++++++++++++++++++++++++++++++++++++++++++++---
net/vmw_vsock/af_vsock.c | 5 +++-
2 files changed, 63 insertions(+), 4 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index d5d6a3c3f273..da14260c6654 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -8,6 +8,7 @@
*/
#include <linux/miscdevice.h>
#include <linux/atomic.h>
+#include <linux/errqueue.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/vmalloc.h>
@@ -32,7 +33,8 @@
enum {
VHOST_VSOCK_FEATURES = VHOST_FEATURES |
(1ULL << VIRTIO_F_ACCESS_PLATFORM) |
- (1ULL << VIRTIO_VSOCK_F_SEQPACKET)
+ (1ULL << VIRTIO_VSOCK_F_SEQPACKET) |
+ (1ULL << VIRTIO_VSOCK_F_DGRAM)
};
enum {
@@ -56,6 +58,7 @@ struct vhost_vsock {
atomic_t queued_replies;
u32 guest_cid;
+ bool dgram_allow;
bool seqpacket_allow;
};
@@ -86,6 +89,32 @@ static struct vhost_vsock *vhost_vsock_get(u32 guest_cid)
return NULL;
}
+/* Claims ownership of the skb, do not free the skb after calling! */
+static void
+vhost_transport_error(struct sk_buff *skb, int err)
+{
+ struct sock_exterr_skb *serr;
+ struct sock *sk = skb->sk;
+ struct sk_buff *clone;
+
+ serr = SKB_EXT_ERR(skb);
+ memset(serr, 0, sizeof(*serr));
+ serr->ee.ee_errno = err;
+ serr->ee.ee_origin = SO_EE_ORIGIN_NONE;
+
+ clone = skb_clone(skb, GFP_KERNEL);
+ if (!clone)
+ return;
+
+ if (sock_queue_err_skb(sk, clone))
+ kfree_skb(clone);
+
+ sk->sk_err = err;
+ sk_error_report(sk);
+
+ kfree_skb(skb);
+}
+
static void
vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
struct vhost_virtqueue *vq)
@@ -160,9 +189,15 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
hdr = virtio_vsock_hdr(skb);
/* If the packet is greater than the space available in the
- * buffer, we split it using multiple buffers.
+ * buffer, we split it using multiple buffers for connectible
+ * sockets and drop the packet for datagram sockets.
*/
if (payload_len > iov_len - sizeof(*hdr)) {
+ if (le16_to_cpu(hdr->type) == VIRTIO_VSOCK_TYPE_DGRAM) {
+ vhost_transport_error(skb, EHOSTUNREACH);
+ continue;
+ }
+
payload_len = iov_len - sizeof(*hdr);
/* As we are copying pieces of large packet's buffer to
@@ -394,6 +429,7 @@ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock)
return val < vq->num;
}
+static bool vhost_transport_dgram_allow(u32 cid, u32 port);
static bool vhost_transport_seqpacket_allow(u32 remote_cid);
static struct virtio_transport vhost_transport = {
@@ -410,7 +446,8 @@ static struct virtio_transport vhost_transport = {
.cancel_pkt = vhost_transport_cancel_pkt,
.dgram_enqueue = virtio_transport_dgram_enqueue,
- .dgram_allow = virtio_transport_dgram_allow,
+ .dgram_allow = vhost_transport_dgram_allow,
+ .dgram_addr_init = virtio_transport_dgram_addr_init,
.stream_enqueue = virtio_transport_stream_enqueue,
.stream_dequeue = virtio_transport_stream_dequeue,
@@ -443,6 +480,22 @@ static struct virtio_transport vhost_transport = {
.send_pkt = vhost_transport_send_pkt,
};
+static bool vhost_transport_dgram_allow(u32 cid, u32 port)
+{
+ struct vhost_vsock *vsock;
+ bool dgram_allow = false;
+
+ rcu_read_lock();
+ vsock = vhost_vsock_get(cid);
+
+ if (vsock)
+ dgram_allow = vsock->dgram_allow;
+
+ rcu_read_unlock();
+
+ return dgram_allow;
+}
+
static bool vhost_transport_seqpacket_allow(u32 remote_cid)
{
struct vhost_vsock *vsock;
@@ -799,6 +852,9 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features)
if (features & (1ULL << VIRTIO_VSOCK_F_SEQPACKET))
vsock->seqpacket_allow = true;
+ if (features & (1ULL << VIRTIO_VSOCK_F_DGRAM))
+ vsock->dgram_allow = true;
+
for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
vq = &vsock->vqs[i];
mutex_lock(&vq->mutex);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index e73f3b2c52f1..449ed63ac2b0 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1427,9 +1427,12 @@ int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
return prot->recvmsg(sk, msg, len, flags, NULL);
#endif
- if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
+ if (unlikely(flags & MSG_OOB))
return -EOPNOTSUPP;
+ if (unlikely(flags & MSG_ERRQUEUE))
+ return sock_recv_errqueue(sk, msg, len, SOL_VSOCK, 0);
+
transport = vsk->transport;
/* Retrieve the head sk_buff from the socket's receive queue. */
--
2.30.2
^ permalink raw reply related
* [PATCH RFC net-next v5 13/14] virtio/vsock: implement datagram support
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
This commit implements datagram support for virtio/vsock by teaching
virtio to use the general virtio transport ->dgram_addr_init() function
and implementation a new version of ->dgram_allow().
Additionally, it drops virtio_transport_dgram_allow() as an exported
symbol because it is no longer used in other transports.
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
include/linux/virtio_vsock.h | 1 -
net/vmw_vsock/virtio_transport.c | 24 +++++++++++++++++++++++-
net/vmw_vsock/virtio_transport_common.c | 6 ------
3 files changed, 23 insertions(+), 8 deletions(-)
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index b3856b8a42b3..d0a4f08b12c1 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -211,7 +211,6 @@ void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val);
u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk);
bool virtio_transport_stream_is_active(struct vsock_sock *vsk);
bool virtio_transport_stream_allow(u32 cid, u32 port);
-bool virtio_transport_dgram_allow(u32 cid, u32 port);
void virtio_transport_dgram_addr_init(struct sk_buff *skb,
struct sockaddr_vm *addr);
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index ac2126c7dac5..713718861bd4 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -63,6 +63,7 @@ struct virtio_vsock {
u32 guest_cid;
bool seqpacket_allow;
+ bool dgram_allow;
};
static u32 virtio_transport_get_local_cid(void)
@@ -413,6 +414,7 @@ static void virtio_vsock_rx_done(struct virtqueue *vq)
queue_work(virtio_vsock_workqueue, &vsock->rx_work);
}
+static bool virtio_transport_dgram_allow(u32 cid, u32 port);
static bool virtio_transport_seqpacket_allow(u32 remote_cid);
static struct virtio_transport virtio_transport = {
@@ -430,6 +432,7 @@ static struct virtio_transport virtio_transport = {
.dgram_enqueue = virtio_transport_dgram_enqueue,
.dgram_allow = virtio_transport_dgram_allow,
+ .dgram_addr_init = virtio_transport_dgram_addr_init,
.stream_dequeue = virtio_transport_stream_dequeue,
.stream_enqueue = virtio_transport_stream_enqueue,
@@ -462,6 +465,21 @@ static struct virtio_transport virtio_transport = {
.send_pkt = virtio_transport_send_pkt,
};
+static bool virtio_transport_dgram_allow(u32 cid, u32 port)
+{
+ struct virtio_vsock *vsock;
+ bool dgram_allow;
+
+ dgram_allow = false;
+ rcu_read_lock();
+ vsock = rcu_dereference(the_virtio_vsock);
+ if (vsock)
+ dgram_allow = vsock->dgram_allow;
+ rcu_read_unlock();
+
+ return dgram_allow;
+}
+
static bool virtio_transport_seqpacket_allow(u32 remote_cid)
{
struct virtio_vsock *vsock;
@@ -655,6 +673,9 @@ static int virtio_vsock_probe(struct virtio_device *vdev)
if (virtio_has_feature(vdev, VIRTIO_VSOCK_F_SEQPACKET))
vsock->seqpacket_allow = true;
+ if (virtio_has_feature(vdev, VIRTIO_VSOCK_F_DGRAM))
+ vsock->dgram_allow = true;
+
vdev->priv = vsock;
ret = virtio_vsock_vqs_init(vsock);
@@ -747,7 +768,8 @@ static struct virtio_device_id id_table[] = {
};
static unsigned int features[] = {
- VIRTIO_VSOCK_F_SEQPACKET
+ VIRTIO_VSOCK_F_SEQPACKET,
+ VIRTIO_VSOCK_F_DGRAM
};
static struct virtio_driver virtio_vsock_driver = {
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 96118e258097..77898f5325cd 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -783,12 +783,6 @@ bool virtio_transport_stream_allow(u32 cid, u32 port)
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_allow);
-bool virtio_transport_dgram_allow(u32 cid, u32 port)
-{
- return false;
-}
-EXPORT_SYMBOL_GPL(virtio_transport_dgram_allow);
-
int virtio_transport_connect(struct vsock_sock *vsk)
{
struct virtio_vsock_pkt_info info = {
--
2.30.2
^ permalink raw reply related
* [PATCH RFC net-next v5 10/14] virtio/vsock: add VIRTIO_VSOCK_F_DGRAM feature bit
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman,
Jiang Wang
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
This commit adds a feature bit for virtio vsock to support datagrams.
Signed-off-by: Jiang Wang <jiang.wang@bytedance.com>
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
include/uapi/linux/virtio_vsock.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h
index 331be28b1d30..27b4b2b8bf13 100644
--- a/include/uapi/linux/virtio_vsock.h
+++ b/include/uapi/linux/virtio_vsock.h
@@ -40,6 +40,7 @@
/* The feature bitmap for virtio vsock */
#define VIRTIO_VSOCK_F_SEQPACKET 1 /* SOCK_SEQPACKET supported */
+#define VIRTIO_VSOCK_F_DGRAM 3 /* SOCK_DGRAM supported */
struct virtio_vsock_config {
__le64 guest_cid;
--
2.30.2
^ permalink raw reply related
* [PATCH RFC net-next v5 07/14] virtio/vsock: add common datagram send path
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
This commit implements the common function
virtio_transport_dgram_enqueue for enqueueing datagrams. It does not add
usage in either vhost or virtio yet.
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
net/vmw_vsock/virtio_transport_common.c | 76 ++++++++++++++++++++++++++++++++-
1 file changed, 75 insertions(+), 1 deletion(-)
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index ffcbdd77feaa..3bfaff758433 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -819,7 +819,81 @@ virtio_transport_dgram_enqueue(struct vsock_sock *vsk,
struct msghdr *msg,
size_t dgram_len)
{
- return -EOPNOTSUPP;
+ /* Here we are only using the info struct to retain style uniformity
+ * and to ease future refactoring and merging.
+ */
+ struct virtio_vsock_pkt_info info_stack = {
+ .op = VIRTIO_VSOCK_OP_RW,
+ .msg = msg,
+ .vsk = vsk,
+ .type = VIRTIO_VSOCK_TYPE_DGRAM,
+ };
+ const struct virtio_transport *t_ops;
+ struct virtio_vsock_pkt_info *info;
+ struct sock *sk = sk_vsock(vsk);
+ struct virtio_vsock_hdr *hdr;
+ u32 src_cid, src_port;
+ struct sk_buff *skb;
+ void *payload;
+ int noblock;
+ int err;
+
+ info = &info_stack;
+
+ if (dgram_len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE)
+ return -EMSGSIZE;
+
+ t_ops = virtio_transport_get_ops(vsk);
+ if (unlikely(!t_ops))
+ return -EFAULT;
+
+ /* Unlike some of our other sending functions, this function is not
+ * intended for use without a msghdr.
+ */
+ if (WARN_ONCE(!msg, "vsock dgram bug: no msghdr found for dgram enqueue\n"))
+ return -EFAULT;
+
+ noblock = msg->msg_flags & MSG_DONTWAIT;
+
+ /* Use sock_alloc_send_skb to throttle by sk_sndbuf. This helps avoid
+ * triggering the OOM.
+ */
+ skb = sock_alloc_send_skb(sk, dgram_len + VIRTIO_VSOCK_SKB_HEADROOM,
+ noblock, &err);
+ if (!skb)
+ return err;
+
+ skb_reserve(skb, VIRTIO_VSOCK_SKB_HEADROOM);
+
+ src_cid = t_ops->transport.get_local_cid();
+ src_port = vsk->local_addr.svm_port;
+
+ hdr = virtio_vsock_hdr(skb);
+ hdr->type = cpu_to_le16(info->type);
+ hdr->op = cpu_to_le16(info->op);
+ hdr->src_cid = cpu_to_le64(src_cid);
+ hdr->dst_cid = cpu_to_le64(remote_addr->svm_cid);
+ hdr->src_port = cpu_to_le32(src_port);
+ hdr->dst_port = cpu_to_le32(remote_addr->svm_port);
+ hdr->flags = cpu_to_le32(info->flags);
+ hdr->len = cpu_to_le32(dgram_len);
+
+ skb_set_owner_w(skb, sk);
+
+ payload = skb_put(skb, dgram_len);
+ err = memcpy_from_msg(payload, msg, dgram_len);
+ if (err)
+ return err;
+
+ trace_virtio_transport_alloc_pkt(src_cid, src_port,
+ remote_addr->svm_cid,
+ remote_addr->svm_port,
+ dgram_len,
+ info->type,
+ info->op,
+ 0);
+
+ return t_ops->send_pkt(skb);
}
EXPORT_SYMBOL_GPL(virtio_transport_dgram_enqueue);
--
2.30.2
^ permalink raw reply related
* [PATCH RFC net-next v5 09/14] virtio/vsock: add common datagram recv path
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
This commit adds the common datagram receive functionality for virtio
transports. It does not add the vhost/virtio users of that
functionality.
This functionality includes:
- changes to the virtio_transport_recv_pkt() path for finding the
bound socket receiver for incoming packets.
- a virtio_transport_dgram_addr_init() function to be used as the
->dgram_addr_init callback for initializing sockaddr_vm inside
the generic recvmsg() caller.
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
include/linux/virtio_vsock.h | 2 +
net/vmw_vsock/virtio_transport_common.c | 92 ++++++++++++++++++++++++++++-----
2 files changed, 81 insertions(+), 13 deletions(-)
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 7632552bee58..b3856b8a42b3 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -212,6 +212,8 @@ u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk);
bool virtio_transport_stream_is_active(struct vsock_sock *vsk);
bool virtio_transport_stream_allow(u32 cid, u32 port);
bool virtio_transport_dgram_allow(u32 cid, u32 port);
+void virtio_transport_dgram_addr_init(struct sk_buff *skb,
+ struct sockaddr_vm *addr);
int virtio_transport_connect(struct vsock_sock *vsk);
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 3bfaff758433..96118e258097 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -183,7 +183,9 @@ EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt);
static u16 virtio_transport_get_type(struct sock *sk)
{
- if (sk->sk_type == SOCK_STREAM)
+ if (sk->sk_type == SOCK_DGRAM)
+ return VIRTIO_VSOCK_TYPE_DGRAM;
+ else if (sk->sk_type == SOCK_STREAM)
return VIRTIO_VSOCK_TYPE_STREAM;
else
return VIRTIO_VSOCK_TYPE_SEQPACKET;
@@ -1184,6 +1186,35 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk,
kfree_skb(skb);
}
+static void
+virtio_transport_dgram_kfree_skb(struct sk_buff *skb, int err)
+{
+ if (err == -ENOMEM)
+ kfree_skb_reason(skb, SKB_DROP_REASON_SOCKET_RCVBUFF);
+ else if (err == -ENOBUFS)
+ kfree_skb_reason(skb, SKB_DROP_REASON_PROTO_MEM);
+ else
+ kfree_skb(skb);
+}
+
+/* This function takes ownership of the skb.
+ *
+ * It either places the skb on the sk_receive_queue or frees it.
+ */
+static void
+virtio_transport_recv_dgram(struct sock *sk, struct sk_buff *skb)
+{
+ int err;
+
+ err = sock_queue_rcv_skb(sk, skb);
+ if (err) {
+ virtio_transport_dgram_kfree_skb(skb, err);
+ return;
+ }
+
+ sk->sk_data_ready(sk);
+}
+
static int
virtio_transport_recv_connected(struct sock *sk,
struct sk_buff *skb)
@@ -1347,7 +1378,8 @@ virtio_transport_recv_listen(struct sock *sk, struct sk_buff *skb,
static bool virtio_transport_valid_type(u16 type)
{
return (type == VIRTIO_VSOCK_TYPE_STREAM) ||
- (type == VIRTIO_VSOCK_TYPE_SEQPACKET);
+ (type == VIRTIO_VSOCK_TYPE_SEQPACKET) ||
+ (type == VIRTIO_VSOCK_TYPE_DGRAM);
}
/* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex
@@ -1361,40 +1393,52 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
struct vsock_sock *vsk;
struct sock *sk;
bool space_available;
+ u16 type;
vsock_addr_init(&src, le64_to_cpu(hdr->src_cid),
le32_to_cpu(hdr->src_port));
vsock_addr_init(&dst, le64_to_cpu(hdr->dst_cid),
le32_to_cpu(hdr->dst_port));
+ type = le16_to_cpu(hdr->type);
+
trace_virtio_transport_recv_pkt(src.svm_cid, src.svm_port,
dst.svm_cid, dst.svm_port,
le32_to_cpu(hdr->len),
- le16_to_cpu(hdr->type),
+ type,
le16_to_cpu(hdr->op),
le32_to_cpu(hdr->flags),
le32_to_cpu(hdr->buf_alloc),
le32_to_cpu(hdr->fwd_cnt));
- if (!virtio_transport_valid_type(le16_to_cpu(hdr->type))) {
+ if (!virtio_transport_valid_type(type)) {
(void)virtio_transport_reset_no_sock(t, skb);
goto free_pkt;
}
- /* The socket must be in connected or bound table
- * otherwise send reset back
+ /* For stream/seqpacket, the socket must be in connected or bound table
+ * otherwise send reset back.
+ *
+ * For datagrams, no reset is sent back.
*/
sk = vsock_find_connected_socket(&src, &dst);
if (!sk) {
- sk = vsock_find_bound_socket(&dst);
- if (!sk) {
- (void)virtio_transport_reset_no_sock(t, skb);
- goto free_pkt;
+ if (type == VIRTIO_VSOCK_TYPE_DGRAM) {
+ sk = vsock_find_bound_dgram_socket(&dst);
+ if (!sk)
+ goto free_pkt;
+ } else {
+ sk = vsock_find_bound_socket(&dst);
+ if (!sk) {
+ (void)virtio_transport_reset_no_sock(t, skb);
+ goto free_pkt;
+ }
}
}
- if (virtio_transport_get_type(sk) != le16_to_cpu(hdr->type)) {
- (void)virtio_transport_reset_no_sock(t, skb);
+ if (virtio_transport_get_type(sk) != type) {
+ if (type != VIRTIO_VSOCK_TYPE_DGRAM)
+ (void)virtio_transport_reset_no_sock(t, skb);
sock_put(sk);
goto free_pkt;
}
@@ -1410,12 +1454,18 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
/* Check if sk has been closed before lock_sock */
if (sock_flag(sk, SOCK_DONE)) {
- (void)virtio_transport_reset_no_sock(t, skb);
+ if (type != VIRTIO_VSOCK_TYPE_DGRAM)
+ (void)virtio_transport_reset_no_sock(t, skb);
release_sock(sk);
sock_put(sk);
goto free_pkt;
}
+ if (sk->sk_type == SOCK_DGRAM) {
+ virtio_transport_recv_dgram(sk, skb);
+ goto out;
+ }
+
space_available = virtio_transport_space_update(sk, skb);
/* Update CID in case it has changed after a transport reset event */
@@ -1447,6 +1497,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
break;
}
+out:
release_sock(sk);
/* Release refcnt obtained when we fetched this socket out of the
@@ -1515,6 +1566,21 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto
}
EXPORT_SYMBOL_GPL(virtio_transport_read_skb);
+void virtio_transport_dgram_addr_init(struct sk_buff *skb,
+ struct sockaddr_vm *addr)
+{
+ struct virtio_vsock_hdr *hdr;
+ unsigned int cid, port;
+
+ WARN_ONCE(skb->head == skb->data, "virtio vsock bug: bad dgram skb");
+
+ hdr = virtio_vsock_hdr(skb);
+ cid = le64_to_cpu(hdr->src_cid);
+ port = le32_to_cpu(hdr->src_port);
+ vsock_addr_init(addr, cid, port);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_dgram_addr_init);
+
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Asias He");
MODULE_DESCRIPTION("common code for virtio vsock");
--
2.30.2
^ permalink raw reply related
* [PATCH RFC net-next v5 08/14] af_vsock: add vsock_find_bound_dgram_socket()
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
This commit adds vsock_find_bound_dgram_socket() which allows transports
to find bound dgram sockets in the global dgram bind table. It is
intended to be used for "routing" incoming packets to the correct
sockets if the transport uses the global bind table.
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
include/net/af_vsock.h | 1 +
net/vmw_vsock/af_vsock.c | 16 ++++++++++++++++
2 files changed, 17 insertions(+)
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index f6a0ca9d7c3e..ae6b6cdf6a4d 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -215,6 +215,7 @@ void vsock_for_each_connected_socket(struct vsock_transport *transport,
void (*fn)(struct sock *sk));
int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk);
bool vsock_find_cid(unsigned int cid);
+struct sock *vsock_find_bound_dgram_socket(struct sockaddr_vm *addr);
/**** TAP ****/
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 0895f4c1d340..e73f3b2c52f1 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -264,6 +264,22 @@ static struct sock *vsock_find_bound_socket_common(struct sockaddr_vm *addr,
return NULL;
}
+struct sock *
+vsock_find_bound_dgram_socket(struct sockaddr_vm *addr)
+{
+ struct sock *sk;
+
+ spin_lock_bh(&vsock_dgram_table_lock);
+ sk = vsock_find_bound_socket_common(addr, vsock_bound_dgram_sockets(addr));
+ if (sk)
+ sock_hold(sk);
+
+ spin_unlock_bh(&vsock_dgram_table_lock);
+
+ return sk;
+}
+EXPORT_SYMBOL_GPL(vsock_find_bound_dgram_socket);
+
static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr)
{
return vsock_find_bound_socket_common(addr, vsock_bound_sockets(addr));
--
2.30.2
^ permalink raw reply related
* [PATCH RFC net-next v5 06/14] virtio/vsock: add VIRTIO_VSOCK_TYPE_DGRAM
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
This commit adds the datagram packet type for inclusion in virtio vsock
packet headers. It is included here as a standalone commit because
multiple future but distinct commits depend on it.
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
include/uapi/linux/virtio_vsock.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h
index 64738838bee5..331be28b1d30 100644
--- a/include/uapi/linux/virtio_vsock.h
+++ b/include/uapi/linux/virtio_vsock.h
@@ -69,6 +69,7 @@ struct virtio_vsock_hdr {
enum virtio_vsock_type {
VIRTIO_VSOCK_TYPE_STREAM = 1,
VIRTIO_VSOCK_TYPE_SEQPACKET = 2,
+ VIRTIO_VSOCK_TYPE_DGRAM = 3,
};
enum virtio_vsock_op {
--
2.30.2
^ permalink raw reply related
* [PATCH RFC net-next v5 04/14] af_vsock: generalize bind table functions
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
This commit makes the bind table management functions in vsock usable
for different bind tables. Future work will introduce a new table for
datagrams to avoid address collisions, and these functions will be used
there.
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
net/vmw_vsock/af_vsock.c | 34 +++++++++++++++++++++++++++-------
1 file changed, 27 insertions(+), 7 deletions(-)
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 26c97b33d55a..88100154156c 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -231,11 +231,12 @@ static void __vsock_remove_connected(struct vsock_sock *vsk)
sock_put(&vsk->sk);
}
-static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr)
+static struct sock *vsock_find_bound_socket_common(struct sockaddr_vm *addr,
+ struct list_head *bind_table)
{
struct vsock_sock *vsk;
- list_for_each_entry(vsk, vsock_bound_sockets(addr), bound_table) {
+ list_for_each_entry(vsk, bind_table, bound_table) {
if (vsock_addr_equals_addr(addr, &vsk->local_addr))
return sk_vsock(vsk);
@@ -248,6 +249,11 @@ static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr)
return NULL;
}
+static struct sock *__vsock_find_bound_socket(struct sockaddr_vm *addr)
+{
+ return vsock_find_bound_socket_common(addr, vsock_bound_sockets(addr));
+}
+
static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src,
struct sockaddr_vm *dst)
{
@@ -647,12 +653,18 @@ static void vsock_pending_work(struct work_struct *work)
/**** SOCKET OPERATIONS ****/
-static int __vsock_bind_connectible(struct vsock_sock *vsk,
- struct sockaddr_vm *addr)
+static int vsock_bind_common(struct vsock_sock *vsk,
+ struct sockaddr_vm *addr,
+ struct list_head *bind_table,
+ size_t table_size)
{
static u32 port;
struct sockaddr_vm new_addr;
+ if (WARN_ONCE(table_size < VSOCK_HASH_SIZE,
+ "table size too small, may cause overflow"))
+ return -EINVAL;
+
if (!port)
port = get_random_u32_above(LAST_RESERVED_PORT);
@@ -668,7 +680,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
new_addr.svm_port = port++;
- if (!__vsock_find_bound_socket(&new_addr)) {
+ if (!vsock_find_bound_socket_common(&new_addr,
+ &bind_table[VSOCK_HASH(addr)])) {
found = true;
break;
}
@@ -685,7 +698,8 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
return -EACCES;
}
- if (__vsock_find_bound_socket(&new_addr))
+ if (vsock_find_bound_socket_common(&new_addr,
+ &bind_table[VSOCK_HASH(addr)]))
return -EADDRINUSE;
}
@@ -697,11 +711,17 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
* by AF_UNIX.
*/
__vsock_remove_bound(vsk);
- __vsock_insert_bound(vsock_bound_sockets(&vsk->local_addr), vsk);
+ __vsock_insert_bound(&bind_table[VSOCK_HASH(&vsk->local_addr)], vsk);
return 0;
}
+static int __vsock_bind_connectible(struct vsock_sock *vsk,
+ struct sockaddr_vm *addr)
+{
+ return vsock_bind_common(vsk, addr, vsock_bind_table, VSOCK_HASH_SIZE + 1);
+}
+
static int __vsock_bind_dgram(struct vsock_sock *vsk,
struct sockaddr_vm *addr)
{
--
2.30.2
^ permalink raw reply related
* [PATCH RFC net-next v5 12/14] vsock/loopback: implement datagram support
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
This commit implements datagram support for vsock loopback.
Not much more than simply toggling on "dgram_allow" and continuing to
use the common virtio functions.
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
net/vmw_vsock/vsock_loopback.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index 278235ea06c4..0459b2bf7b15 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -46,6 +46,7 @@ static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk)
return 0;
}
+static bool vsock_loopback_dgram_allow(u32 cid, u32 port);
static bool vsock_loopback_seqpacket_allow(u32 remote_cid);
static struct virtio_transport loopback_transport = {
@@ -62,7 +63,7 @@ static struct virtio_transport loopback_transport = {
.cancel_pkt = vsock_loopback_cancel_pkt,
.dgram_enqueue = virtio_transport_dgram_enqueue,
- .dgram_allow = virtio_transport_dgram_allow,
+ .dgram_allow = vsock_loopback_dgram_allow,
.stream_dequeue = virtio_transport_stream_dequeue,
.stream_enqueue = virtio_transport_stream_enqueue,
@@ -95,6 +96,11 @@ static struct virtio_transport loopback_transport = {
.send_pkt = vsock_loopback_send_pkt,
};
+static bool vsock_loopback_dgram_allow(u32 cid, u32 port)
+{
+ return true;
+}
+
static bool vsock_loopback_seqpacket_allow(u32 remote_cid)
{
return true;
--
2.30.2
^ permalink raw reply related
* [PATCH RFC net-next v5 01/14] af_vsock: generalize vsock_dgram_recvmsg() to all transports
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
This commit drops the transport->dgram_dequeue callback and makes
vsock_dgram_recvmsg() generic to all transports.
To make this possible, two transport-level changes are introduced:
- implementation of the ->dgram_addr_init() callback to initialize
the sockaddr_vm structure with data from incoming socket buffers.
- transport implementations set the skb->data pointer to the beginning
of the payload prior to adding the skb to the socket's receive queue.
That is, they must use skb_pull() before enqueuing. This is an
agreement between the transport and the socket layer that skb->data
always points to the beginning of the payload (and not, for example,
the packet header).
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
drivers/vhost/vsock.c | 1 -
include/linux/virtio_vsock.h | 5 ---
include/net/af_vsock.h | 3 +-
net/vmw_vsock/af_vsock.c | 40 ++++++++++++++++++++++-
net/vmw_vsock/hyperv_transport.c | 7 ----
net/vmw_vsock/virtio_transport.c | 1 -
net/vmw_vsock/virtio_transport_common.c | 9 -----
net/vmw_vsock/vmci_transport.c | 58 ++++++---------------------------
net/vmw_vsock/vsock_loopback.c | 1 -
9 files changed, 50 insertions(+), 75 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 6578db78f0ae..ae8891598a48 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -410,7 +410,6 @@ static struct virtio_transport vhost_transport = {
.cancel_pkt = vhost_transport_cancel_pkt,
.dgram_enqueue = virtio_transport_dgram_enqueue,
- .dgram_dequeue = virtio_transport_dgram_dequeue,
.dgram_bind = virtio_transport_dgram_bind,
.dgram_allow = virtio_transport_dgram_allow,
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index c58453699ee9..18cbe8d37fca 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -167,11 +167,6 @@ virtio_transport_stream_dequeue(struct vsock_sock *vsk,
size_t len,
int type);
int
-virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
- struct msghdr *msg,
- size_t len, int flags);
-
-int
virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk,
struct msghdr *msg,
size_t len);
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 0e7504a42925..305d57502e89 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -120,11 +120,10 @@ struct vsock_transport {
/* DGRAM. */
int (*dgram_bind)(struct vsock_sock *, struct sockaddr_vm *);
- int (*dgram_dequeue)(struct vsock_sock *vsk, struct msghdr *msg,
- size_t len, int flags);
int (*dgram_enqueue)(struct vsock_sock *, struct sockaddr_vm *,
struct msghdr *, size_t len);
bool (*dgram_allow)(u32 cid, u32 port);
+ void (*dgram_addr_init)(struct sk_buff *skb, struct sockaddr_vm *addr);
/* STREAM. */
/* TODO: stream_bind() */
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index deb72a8c44a7..ad71e084bf2f 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1272,11 +1272,15 @@ static int vsock_dgram_connect(struct socket *sock,
int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
size_t len, int flags)
{
+ const struct vsock_transport *transport;
#ifdef CONFIG_BPF_SYSCALL
const struct proto *prot;
#endif
struct vsock_sock *vsk;
+ struct sk_buff *skb;
+ size_t payload_len;
struct sock *sk;
+ int err;
sk = sock->sk;
vsk = vsock_sk(sk);
@@ -1287,7 +1291,41 @@ int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
return prot->recvmsg(sk, msg, len, flags, NULL);
#endif
- return vsk->transport->dgram_dequeue(vsk, msg, len, flags);
+ if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
+ return -EOPNOTSUPP;
+
+ transport = vsk->transport;
+
+ /* Retrieve the head sk_buff from the socket's receive queue. */
+ err = 0;
+ skb = skb_recv_datagram(sk_vsock(vsk), flags, &err);
+ if (!skb)
+ return err;
+
+ payload_len = skb->len;
+
+ if (payload_len > len) {
+ payload_len = len;
+ msg->msg_flags |= MSG_TRUNC;
+ }
+
+ /* Place the datagram payload in the user's iovec. */
+ err = skb_copy_datagram_msg(skb, 0, msg, payload_len);
+ if (err)
+ goto out;
+
+ if (msg->msg_name) {
+ /* Provide the address of the sender. */
+ DECLARE_SOCKADDR(struct sockaddr_vm *, vm_addr, msg->msg_name);
+
+ transport->dgram_addr_init(skb, vm_addr);
+ msg->msg_namelen = sizeof(*vm_addr);
+ }
+ err = payload_len;
+
+out:
+ skb_free_datagram(&vsk->sk, skb);
+ return err;
}
EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg);
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 7cb1a9d2cdb4..7f1ea434656d 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -556,12 +556,6 @@ static int hvs_dgram_bind(struct vsock_sock *vsk, struct sockaddr_vm *addr)
return -EOPNOTSUPP;
}
-static int hvs_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg,
- size_t len, int flags)
-{
- return -EOPNOTSUPP;
-}
-
static int hvs_dgram_enqueue(struct vsock_sock *vsk,
struct sockaddr_vm *remote, struct msghdr *msg,
size_t dgram_len)
@@ -833,7 +827,6 @@ static struct vsock_transport hvs_transport = {
.shutdown = hvs_shutdown,
.dgram_bind = hvs_dgram_bind,
- .dgram_dequeue = hvs_dgram_dequeue,
.dgram_enqueue = hvs_dgram_enqueue,
.dgram_allow = hvs_dgram_allow,
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index e95df847176b..66edffdbf303 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -429,7 +429,6 @@ static struct virtio_transport virtio_transport = {
.cancel_pkt = virtio_transport_cancel_pkt,
.dgram_bind = virtio_transport_dgram_bind,
- .dgram_dequeue = virtio_transport_dgram_dequeue,
.dgram_enqueue = virtio_transport_dgram_enqueue,
.dgram_allow = virtio_transport_dgram_allow,
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index b769fc258931..01ea1402ad40 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -583,15 +583,6 @@ virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk,
}
EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_enqueue);
-int
-virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
- struct msghdr *msg,
- size_t len, int flags)
-{
- return -EOPNOTSUPP;
-}
-EXPORT_SYMBOL_GPL(virtio_transport_dgram_dequeue);
-
s64 virtio_transport_stream_has_data(struct vsock_sock *vsk)
{
struct virtio_vsock_sock *vvs = vsk->trans;
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index b370070194fa..0bbbdb222245 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -641,6 +641,7 @@ static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg)
sock_hold(sk);
skb_put(skb, size);
memcpy(skb->data, dg, size);
+ skb_pull(skb, VMCI_DG_HEADERSIZE);
sk_receive_skb(sk, skb, 0);
return VMCI_SUCCESS;
@@ -1731,57 +1732,18 @@ static int vmci_transport_dgram_enqueue(
return err - sizeof(*dg);
}
-static int vmci_transport_dgram_dequeue(struct vsock_sock *vsk,
- struct msghdr *msg, size_t len,
- int flags)
+static void vmci_transport_dgram_addr_init(struct sk_buff *skb,
+ struct sockaddr_vm *addr)
{
- int err;
struct vmci_datagram *dg;
- size_t payload_len;
- struct sk_buff *skb;
-
- if (flags & MSG_OOB || flags & MSG_ERRQUEUE)
- return -EOPNOTSUPP;
-
- /* Retrieve the head sk_buff from the socket's receive queue. */
- err = 0;
- skb = skb_recv_datagram(&vsk->sk, flags, &err);
- if (!skb)
- return err;
-
- dg = (struct vmci_datagram *)skb->data;
- if (!dg)
- /* err is 0, meaning we read zero bytes. */
- goto out;
-
- payload_len = dg->payload_size;
- /* Ensure the sk_buff matches the payload size claimed in the packet. */
- if (payload_len != skb->len - sizeof(*dg)) {
- err = -EINVAL;
- goto out;
- }
-
- if (payload_len > len) {
- payload_len = len;
- msg->msg_flags |= MSG_TRUNC;
- }
+ unsigned int cid, port;
- /* Place the datagram payload in the user's iovec. */
- err = skb_copy_datagram_msg(skb, sizeof(*dg), msg, payload_len);
- if (err)
- goto out;
-
- if (msg->msg_name) {
- /* Provide the address of the sender. */
- DECLARE_SOCKADDR(struct sockaddr_vm *, vm_addr, msg->msg_name);
- vsock_addr_init(vm_addr, dg->src.context, dg->src.resource);
- msg->msg_namelen = sizeof(*vm_addr);
- }
- err = payload_len;
+ WARN_ONCE(skb->head == skb->data, "vmci vsock bug: bad dgram skb");
-out:
- skb_free_datagram(&vsk->sk, skb);
- return err;
+ dg = (struct vmci_datagram *)skb->head;
+ cid = dg->src.context;
+ port = dg->src.resource;
+ vsock_addr_init(addr, cid, port);
}
static bool vmci_transport_dgram_allow(u32 cid, u32 port)
@@ -2040,9 +2002,9 @@ static struct vsock_transport vmci_transport = {
.release = vmci_transport_release,
.connect = vmci_transport_connect,
.dgram_bind = vmci_transport_dgram_bind,
- .dgram_dequeue = vmci_transport_dgram_dequeue,
.dgram_enqueue = vmci_transport_dgram_enqueue,
.dgram_allow = vmci_transport_dgram_allow,
+ .dgram_addr_init = vmci_transport_dgram_addr_init,
.stream_dequeue = vmci_transport_stream_dequeue,
.stream_enqueue = vmci_transport_stream_enqueue,
.stream_has_data = vmci_transport_stream_has_data,
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index 5c6360df1f31..2a59dd177c74 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -62,7 +62,6 @@ static struct virtio_transport loopback_transport = {
.cancel_pkt = vsock_loopback_cancel_pkt,
.dgram_bind = virtio_transport_dgram_bind,
- .dgram_dequeue = virtio_transport_dgram_dequeue,
.dgram_enqueue = virtio_transport_dgram_enqueue,
.dgram_allow = virtio_transport_dgram_allow,
--
2.30.2
^ permalink raw reply related
* [PATCH RFC net-next v5 00/14] virtio/vsock: support datagrams
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman,
Jiang Wang
Hey all!
This series introduces support for datagrams to virtio/vsock.
It is a spin-off (and smaller version) of this series from the summer:
https://lore.kernel.org/all/cover.1660362668.git.bobby.eshleman@bytedance.com/
Please note that this is an RFC and should not be merged until
associated changes are made to the virtio specification, which will
follow after discussion from this series.
Another aside, the v4 of the series has only been mildly tested with a
run of tools/testing/vsock/vsock_test. Some code likely needs cleaning
up, but I'm hoping to get some of the design choices agreed upon before
spending too much time making it pretty.
This series first supports datagrams in a basic form for virtio, and
then optimizes the sendpath for all datagram transports.
The result is a very fast datagram communication protocol that
outperforms even UDP on multi-queue virtio-net w/ vhost on a variety
of multi-threaded workload samples.
For those that are curious, some summary data comparing UDP and VSOCK
DGRAM (N=5):
vCPUS: 16
virtio-net queues: 16
payload size: 4KB
Setup: bare metal + vm (non-nested)
UDP: 287.59 MB/s
VSOCK DGRAM: 509.2 MB/s
Some notes about the implementation...
This datagram implementation forces datagrams to self-throttle according
to the threshold set by sk_sndbuf. It behaves similar to the credits
used by streams in its effect on throughput and memory consumption, but
it is not influenced by the receiving socket as credits are.
The device drops packets silently.
As discussed previously, this series introduces datagrams and defers
fairness to future work. See discussion in v2 for more context around
datagrams, fairness, and this implementation.
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
Changes in v5:
- teach vhost to drop dgram when a datagram exceeds the receive buffer
- now uses MSG_ERRQUEUE and depends on Arseniy's zerocopy patch:
"vsock: read from socket's error queue"
- replace multiple ->dgram_* callbacks with single ->dgram_addr_init()
callback
- refactor virtio dgram skb allocator to reduce conflicts w/ zerocopy series
- add _fallback/_FALLBACK suffix to dgram transport variables/macros
- add WARN_ONCE() for table_size / VSOCK_HASH issue
- add static to vsock_find_bound_socket_common
- dedupe code in vsock_dgram_sendmsg() using module_got var
- drop concurrent sendmsg() for dgram and defer to future series
- Add more tests
- test EHOSTUNREACH in errqueue
- test stream + dgram address collision
- improve clarity of dgram msg bounds test code
- Link to v4: https://lore.kernel.org/r/20230413-b4-vsock-dgram-v4-0-0cebbb2ae899@bytedance.com
Changes in v4:
- style changes
- vsock: use sk_vsock(vsk) in vsock_dgram_recvmsg instead of
&sk->vsk
- vsock: fix xmas tree declaration
- vsock: fix spacing issues
- virtio/vsock: virtio_transport_recv_dgram returns void because err
unused
- sparse analysis warnings/errors
- virtio/vsock: fix unitialized skerr on destroy
- virtio/vsock: fix uninitialized err var on goto out
- vsock: fix declarations that need static
- vsock: fix __rcu annotation order
- bugs
- vsock: fix null ptr in remote_info code
- vsock/dgram: make transport_dgram a fallback instead of first
priority
- vsock: remove redundant rcu read lock acquire in getname()
- tests
- add more tests (message bounds and more)
- add vsock_dgram_bind() helper
- add vsock_dgram_connect() helper
Changes in v3:
- Support multi-transport dgram, changing logic in connect/bind
to support VMCI case
- Support per-pkt transport lookup for sendto() case
- Fix dgram_allow() implementation
- Fix dgram feature bit number (now it is 3)
- Fix binding so dgram and connectible (cid,port) spaces are
non-overlapping
- RCU protect transport ptr so connect() calls never leave
a lockless read of the transport and remote_addr are always
in sync
- Link to v2: https://lore.kernel.org/r/20230413-b4-vsock-dgram-v2-0-079cc7cee62e@bytedance.com
---
Bobby Eshleman (13):
af_vsock: generalize vsock_dgram_recvmsg() to all transports
af_vsock: refactor transport lookup code
af_vsock: support multi-transport datagrams
af_vsock: generalize bind table functions
af_vsock: use a separate dgram bind table
virtio/vsock: add VIRTIO_VSOCK_TYPE_DGRAM
virtio/vsock: add common datagram send path
af_vsock: add vsock_find_bound_dgram_socket()
virtio/vsock: add common datagram recv path
virtio/vsock: add VIRTIO_VSOCK_F_DGRAM feature bit
vhost/vsock: implement datagram support
vsock/loopback: implement datagram support
virtio/vsock: implement datagram support
Jiang Wang (1):
test/vsock: add vsock dgram tests
drivers/vhost/vsock.c | 64 ++-
include/linux/virtio_vsock.h | 10 +-
include/net/af_vsock.h | 14 +-
include/uapi/linux/virtio_vsock.h | 2 +
net/vmw_vsock/af_vsock.c | 281 ++++++++++---
net/vmw_vsock/hyperv_transport.c | 13 -
net/vmw_vsock/virtio_transport.c | 26 +-
net/vmw_vsock/virtio_transport_common.c | 190 +++++++--
net/vmw_vsock/vmci_transport.c | 60 +--
net/vmw_vsock/vsock_loopback.c | 10 +-
tools/testing/vsock/util.c | 141 ++++++-
tools/testing/vsock/util.h | 6 +
tools/testing/vsock/vsock_test.c | 680 ++++++++++++++++++++++++++++++++
13 files changed, 1320 insertions(+), 177 deletions(-)
---
base-commit: 37cadc266ebdc7e3531111c2b3304fa01b2131e8
change-id: 20230413-b4-vsock-dgram-3b6eba6a64e5
Best regards,
--
Bobby Eshleman <bobby.eshleman@bytedance.com>
^ permalink raw reply
* [PATCH RFC net-next v5 05/14] af_vsock: use a separate dgram bind table
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
This commit adds support for bound dgram sockets to be tracked in a
separate bind table from connectible sockets in order to avoid address
collisions. With this commit, users can simultaneously bind a dgram
socket and connectible socket to the same CID and port.
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
net/vmw_vsock/af_vsock.c | 103 ++++++++++++++++++++++++++++++++++-------------
1 file changed, 76 insertions(+), 27 deletions(-)
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 88100154156c..0895f4c1d340 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -10,18 +10,23 @@
* - There are two kinds of sockets: those created by user action (such as
* calling socket(2)) and those created by incoming connection request packets.
*
- * - There are two "global" tables, one for bound sockets (sockets that have
- * specified an address that they are responsible for) and one for connected
- * sockets (sockets that have established a connection with another socket).
- * These tables are "global" in that all sockets on the system are placed
- * within them. - Note, though, that the bound table contains an extra entry
- * for a list of unbound sockets and SOCK_DGRAM sockets will always remain in
- * that list. The bound table is used solely for lookup of sockets when packets
- * are received and that's not necessary for SOCK_DGRAM sockets since we create
- * a datagram handle for each and need not perform a lookup. Keeping SOCK_DGRAM
- * sockets out of the bound hash buckets will reduce the chance of collisions
- * when looking for SOCK_STREAM sockets and prevents us from having to check the
- * socket type in the hash table lookups.
+ * - There are three "global" tables, one for bound connectible (stream /
+ * seqpacket) sockets, one for bound datagram sockets, and one for connected
+ * sockets. Bound sockets are sockets that have specified an address that
+ * they are responsible for. Connected sockets are sockets that have
+ * established a connection with another socket. These tables are "global" in
+ * that all sockets on the system are placed within them. - Note, though,
+ * that the bound tables contain an extra entry for a list of unbound
+ * sockets. The bound tables are used solely for lookup of sockets when packets
+ * are received.
+ *
+ * - There are separate bind tables for connectible and datagram sockets to avoid
+ * address collisions between stream/seqpacket sockets and datagram sockets.
+ *
+ * - Transports may elect to NOT use the global datagram bind table by
+ * implementing the ->dgram_bind() callback. If that callback is implemented,
+ * the global bind table is not used and the responsibility of bound datagram
+ * socket tracking is deferred to the transport.
*
* - Sockets created by user action will either be "client" sockets that
* initiate a connection or "server" sockets that listen for connections; we do
@@ -115,6 +120,7 @@
static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr);
static void vsock_sk_destruct(struct sock *sk);
static int vsock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+static bool sock_type_connectible(u16 type);
/* Protocol family. */
struct proto vsock_proto = {
@@ -151,21 +157,25 @@ static DEFINE_MUTEX(vsock_register_mutex);
* VSocket is stored in the connected hash table.
*
* Unbound sockets are all put on the same list attached to the end of the hash
- * table (vsock_unbound_sockets). Bound sockets are added to the hash table in
- * the bucket that their local address hashes to (vsock_bound_sockets(addr)
- * represents the list that addr hashes to).
+ * tables (vsock_unbound_sockets/vsock_unbound_dgram_sockets). Bound sockets
+ * are added to the hash table in the bucket that their local address hashes to
+ * (vsock_bound_sockets(addr) and vsock_bound_dgram_sockets(addr) represents
+ * the list that addr hashes to).
*
- * Specifically, we initialize the vsock_bind_table array to a size of
- * VSOCK_HASH_SIZE + 1 so that vsock_bind_table[0] through
- * vsock_bind_table[VSOCK_HASH_SIZE - 1] are for bound sockets and
- * vsock_bind_table[VSOCK_HASH_SIZE] is for unbound sockets. The hash function
- * mods with VSOCK_HASH_SIZE to ensure this.
+ * Specifically, taking connectible sockets as an example we initialize the
+ * vsock_bind_table array to a size of VSOCK_HASH_SIZE + 1 so that
+ * vsock_bind_table[0] through vsock_bind_table[VSOCK_HASH_SIZE - 1] are for
+ * bound sockets and vsock_bind_table[VSOCK_HASH_SIZE] is for unbound sockets.
+ * The hash function mods with VSOCK_HASH_SIZE to ensure this.
+ * Datagrams and vsock_dgram_bind_table operate in the same way.
*/
#define MAX_PORT_RETRIES 24
#define VSOCK_HASH(addr) ((addr)->svm_port % VSOCK_HASH_SIZE)
#define vsock_bound_sockets(addr) (&vsock_bind_table[VSOCK_HASH(addr)])
+#define vsock_bound_dgram_sockets(addr) (&vsock_dgram_bind_table[VSOCK_HASH(addr)])
#define vsock_unbound_sockets (&vsock_bind_table[VSOCK_HASH_SIZE])
+#define vsock_unbound_dgram_sockets (&vsock_dgram_bind_table[VSOCK_HASH_SIZE])
/* XXX This can probably be implemented in a better way. */
#define VSOCK_CONN_HASH(src, dst) \
@@ -181,6 +191,8 @@ struct list_head vsock_connected_table[VSOCK_HASH_SIZE];
EXPORT_SYMBOL_GPL(vsock_connected_table);
DEFINE_SPINLOCK(vsock_table_lock);
EXPORT_SYMBOL_GPL(vsock_table_lock);
+static struct list_head vsock_dgram_bind_table[VSOCK_HASH_SIZE + 1];
+static DEFINE_SPINLOCK(vsock_dgram_table_lock);
/* Autobind this socket to the local address if necessary. */
static int vsock_auto_bind(struct vsock_sock *vsk)
@@ -203,6 +215,9 @@ static void vsock_init_tables(void)
for (i = 0; i < ARRAY_SIZE(vsock_connected_table); i++)
INIT_LIST_HEAD(&vsock_connected_table[i]);
+
+ for (i = 0; i < ARRAY_SIZE(vsock_dgram_bind_table); i++)
+ INIT_LIST_HEAD(&vsock_dgram_bind_table[i]);
}
static void __vsock_insert_bound(struct list_head *list,
@@ -270,13 +285,28 @@ static struct sock *__vsock_find_connected_socket(struct sockaddr_vm *src,
return NULL;
}
-static void vsock_insert_unbound(struct vsock_sock *vsk)
+static void __vsock_insert_dgram_unbound(struct vsock_sock *vsk)
+{
+ spin_lock_bh(&vsock_dgram_table_lock);
+ __vsock_insert_bound(vsock_unbound_dgram_sockets, vsk);
+ spin_unlock_bh(&vsock_dgram_table_lock);
+}
+
+static void __vsock_insert_connectible_unbound(struct vsock_sock *vsk)
{
spin_lock_bh(&vsock_table_lock);
__vsock_insert_bound(vsock_unbound_sockets, vsk);
spin_unlock_bh(&vsock_table_lock);
}
+static void vsock_insert_unbound(struct vsock_sock *vsk)
+{
+ if (sock_type_connectible(sk_vsock(vsk)->sk_type))
+ __vsock_insert_connectible_unbound(vsk);
+ else
+ __vsock_insert_dgram_unbound(vsk);
+}
+
void vsock_insert_connected(struct vsock_sock *vsk)
{
struct list_head *list = vsock_connected_sockets(
@@ -288,6 +318,14 @@ void vsock_insert_connected(struct vsock_sock *vsk)
}
EXPORT_SYMBOL_GPL(vsock_insert_connected);
+static void vsock_remove_dgram_bound(struct vsock_sock *vsk)
+{
+ spin_lock_bh(&vsock_dgram_table_lock);
+ if (__vsock_in_bound_table(vsk))
+ __vsock_remove_bound(vsk);
+ spin_unlock_bh(&vsock_dgram_table_lock);
+}
+
void vsock_remove_bound(struct vsock_sock *vsk)
{
spin_lock_bh(&vsock_table_lock);
@@ -339,7 +377,10 @@ EXPORT_SYMBOL_GPL(vsock_find_connected_socket);
void vsock_remove_sock(struct vsock_sock *vsk)
{
- vsock_remove_bound(vsk);
+ if (sock_type_connectible(sk_vsock(vsk)->sk_type))
+ vsock_remove_bound(vsk);
+ else
+ vsock_remove_dgram_bound(vsk);
vsock_remove_connected(vsk);
}
EXPORT_SYMBOL_GPL(vsock_remove_sock);
@@ -722,11 +763,19 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
return vsock_bind_common(vsk, addr, vsock_bind_table, VSOCK_HASH_SIZE + 1);
}
-static int __vsock_bind_dgram(struct vsock_sock *vsk,
- struct sockaddr_vm *addr)
+static int vsock_bind_dgram(struct vsock_sock *vsk,
+ struct sockaddr_vm *addr)
{
- if (!vsk->transport || !vsk->transport->dgram_bind)
- return -EINVAL;
+ if (!vsk->transport || !vsk->transport->dgram_bind) {
+ int retval;
+
+ spin_lock_bh(&vsock_dgram_table_lock);
+ retval = vsock_bind_common(vsk, addr, vsock_dgram_bind_table,
+ VSOCK_HASH_SIZE);
+ spin_unlock_bh(&vsock_dgram_table_lock);
+
+ return retval;
+ }
return vsk->transport->dgram_bind(vsk, addr);
}
@@ -757,7 +806,7 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr)
break;
case SOCK_DGRAM:
- retval = __vsock_bind_dgram(vsk, addr);
+ retval = vsock_bind_dgram(vsk, addr);
break;
default:
--
2.30.2
^ permalink raw reply related
* [PATCH RFC net-next v5 03/14] af_vsock: support multi-transport datagrams
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
This patch adds support for multi-transport datagrams.
This includes:
- Per-packet lookup of transports when using sendto(sockaddr_vm)
- Selecting H2G or G2H transport using VMADDR_FLAG_TO_HOST and CID in
sockaddr_vm
- rename VSOCK_TRANSPORT_F_DGRAM to VSOCK_TRANSPORT_F_DGRAM_FALLBACK
- connect() now assigns the transport for (similar to connectible
sockets)
To preserve backwards compatibility with VMCI, some important changes
are made. The "transport_dgram" / VSOCK_TRANSPORT_F_DGRAM is changed to
be used for dgrams only if there is not yet a g2h or h2g transport that
has been registered that can transmit the packet. If there is a g2h/h2g
transport for that remote address, then that transport will be used and
not "transport_dgram". This essentially makes "transport_dgram" a
fallback transport for when h2g/g2h has not yet gone online, and so it
is renamed "transport_dgram_fallback". VMCI implements this transport.
The logic around "transport_dgram" needs to be retained to prevent
breaking VMCI:
1) VMCI datagrams existed prior to h2g/g2h and so operate under a
different paradigm. When the vmci transport comes online, it registers
itself with the DGRAM feature, but not H2G/G2H. Only later when the
transport has more information about its environment does it register
H2G or G2H. In the case that a datagram socket is created after
VSOCK_TRANSPORT_F_DGRAM registration but before G2H/H2G registration,
the "transport_dgram" transport is the only registered transport and so
needs to be used.
2) VMCI seems to require a special message be sent by the transport when a
datagram socket calls bind(). Under the h2g/g2h model, the transport
is selected using the remote_addr which is set by connect(). At
bind time there is no remote_addr because often no connect() has been
called yet: the transport is null. Therefore, with a null transport
there doesn't seem to be any good way for a datagram socket to tell the
VMCI transport that it has just had bind() called upon it.
With the new fallback logic, after H2G/G2H comes online the socket layer
will access the VMCI transport via transport_{h2g,g2h}. Prior to H2G/G2H
coming online, the socket layer will access the VMCI transport via
"transport_dgram_fallback".
Only transports with a special datagram fallback use-case such as VMCI
need to register VSOCK_TRANSPORT_F_DGRAM_FALLBACK.
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
drivers/vhost/vsock.c | 1 -
include/linux/virtio_vsock.h | 2 --
include/net/af_vsock.h | 10 +++---
net/vmw_vsock/af_vsock.c | 64 ++++++++++++++++++++++++++-------
net/vmw_vsock/hyperv_transport.c | 6 ----
net/vmw_vsock/virtio_transport.c | 1 -
net/vmw_vsock/virtio_transport_common.c | 7 ----
net/vmw_vsock/vmci_transport.c | 2 +-
net/vmw_vsock/vsock_loopback.c | 1 -
9 files changed, 58 insertions(+), 36 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index ae8891598a48..d5d6a3c3f273 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -410,7 +410,6 @@ static struct virtio_transport vhost_transport = {
.cancel_pkt = vhost_transport_cancel_pkt,
.dgram_enqueue = virtio_transport_dgram_enqueue,
- .dgram_bind = virtio_transport_dgram_bind,
.dgram_allow = virtio_transport_dgram_allow,
.stream_enqueue = virtio_transport_stream_enqueue,
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 18cbe8d37fca..7632552bee58 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -211,8 +211,6 @@ void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val);
u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk);
bool virtio_transport_stream_is_active(struct vsock_sock *vsk);
bool virtio_transport_stream_allow(u32 cid, u32 port);
-int virtio_transport_dgram_bind(struct vsock_sock *vsk,
- struct sockaddr_vm *addr);
bool virtio_transport_dgram_allow(u32 cid, u32 port);
int virtio_transport_connect(struct vsock_sock *vsk);
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index 305d57502e89..f6a0ca9d7c3e 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -96,13 +96,13 @@ struct vsock_transport_send_notify_data {
/* Transport features flags */
/* Transport provides host->guest communication */
-#define VSOCK_TRANSPORT_F_H2G 0x00000001
+#define VSOCK_TRANSPORT_F_H2G 0x00000001
/* Transport provides guest->host communication */
-#define VSOCK_TRANSPORT_F_G2H 0x00000002
-/* Transport provides DGRAM communication */
-#define VSOCK_TRANSPORT_F_DGRAM 0x00000004
+#define VSOCK_TRANSPORT_F_G2H 0x00000002
+/* Transport provides fallback for DGRAM communication */
+#define VSOCK_TRANSPORT_F_DGRAM_FALLBACK 0x00000004
/* Transport provides local (loopback) communication */
-#define VSOCK_TRANSPORT_F_LOCAL 0x00000008
+#define VSOCK_TRANSPORT_F_LOCAL 0x00000008
struct vsock_transport {
struct module *module;
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index ae5ac5531d96..26c97b33d55a 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -139,8 +139,8 @@ struct proto vsock_proto = {
static const struct vsock_transport *transport_h2g;
/* Transport used for guest->host communication */
static const struct vsock_transport *transport_g2h;
-/* Transport used for DGRAM communication */
-static const struct vsock_transport *transport_dgram;
+/* Transport used as a fallback for DGRAM communication */
+static const struct vsock_transport *transport_dgram_fallback;
/* Transport used for local communication */
static const struct vsock_transport *transport_local;
static DEFINE_MUTEX(vsock_register_mutex);
@@ -439,6 +439,18 @@ vsock_connectible_lookup_transport(unsigned int cid, __u8 flags)
return transport;
}
+static const struct vsock_transport *
+vsock_dgram_lookup_transport(unsigned int cid, __u8 flags)
+{
+ const struct vsock_transport *transport;
+
+ transport = vsock_connectible_lookup_transport(cid, flags);
+ if (transport)
+ return transport;
+
+ return transport_dgram_fallback;
+}
+
/* Assign a transport to a socket and call the .init transport callback.
*
* Note: for connection oriented socket this must be called when vsk->remote_addr
@@ -475,7 +487,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
switch (sk->sk_type) {
case SOCK_DGRAM:
- new_transport = transport_dgram;
+ new_transport = vsock_dgram_lookup_transport(remote_cid,
+ remote_flags);
break;
case SOCK_STREAM:
case SOCK_SEQPACKET:
@@ -692,6 +705,9 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
static int __vsock_bind_dgram(struct vsock_sock *vsk,
struct sockaddr_vm *addr)
{
+ if (!vsk->transport || !vsk->transport->dgram_bind)
+ return -EINVAL;
+
return vsk->transport->dgram_bind(vsk, addr);
}
@@ -1162,6 +1178,7 @@ static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
struct vsock_sock *vsk;
struct sockaddr_vm *remote_addr;
const struct vsock_transport *transport;
+ bool module_got = false;
if (msg->msg_flags & MSG_OOB)
return -EOPNOTSUPP;
@@ -1173,19 +1190,34 @@ static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
lock_sock(sk);
- transport = vsk->transport;
-
err = vsock_auto_bind(vsk);
if (err)
goto out;
-
/* If the provided message contains an address, use that. Otherwise
* fall back on the socket's remote handle (if it has been connected).
*/
if (msg->msg_name &&
vsock_addr_cast(msg->msg_name, msg->msg_namelen,
&remote_addr) == 0) {
+ transport = vsock_dgram_lookup_transport(remote_addr->svm_cid,
+ remote_addr->svm_flags);
+ if (!transport) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ if (!try_module_get(transport->module)) {
+ err = -ENODEV;
+ goto out;
+ }
+
+ /* When looking up a transport dynamically and acquiring a
+ * reference on the module, we need to remember to release the
+ * reference later.
+ */
+ module_got = true;
+
/* Ensure this address is of the right type and is a valid
* destination.
*/
@@ -1200,6 +1232,7 @@ static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
} else if (sock->state == SS_CONNECTED) {
remote_addr = &vsk->remote_addr;
+ transport = vsk->transport;
if (remote_addr->svm_cid == VMADDR_CID_ANY)
remote_addr->svm_cid = transport->get_local_cid();
@@ -1224,6 +1257,8 @@ static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
err = transport->dgram_enqueue(vsk, remote_addr, msg, len);
out:
+ if (module_got)
+ module_put(transport->module);
release_sock(sk);
return err;
}
@@ -1256,13 +1291,18 @@ static int vsock_dgram_connect(struct socket *sock,
if (err)
goto out;
+ memcpy(&vsk->remote_addr, remote_addr, sizeof(vsk->remote_addr));
+
+ err = vsock_assign_transport(vsk, NULL);
+ if (err)
+ goto out;
+
if (!vsk->transport->dgram_allow(remote_addr->svm_cid,
remote_addr->svm_port)) {
err = -EINVAL;
goto out;
}
- memcpy(&vsk->remote_addr, remote_addr, sizeof(vsk->remote_addr));
sock->state = SS_CONNECTED;
/* sock map disallows redirection of non-TCP sockets with sk_state !=
@@ -2487,7 +2527,7 @@ int vsock_core_register(const struct vsock_transport *t, int features)
t_h2g = transport_h2g;
t_g2h = transport_g2h;
- t_dgram = transport_dgram;
+ t_dgram = transport_dgram_fallback;
t_local = transport_local;
if (features & VSOCK_TRANSPORT_F_H2G) {
@@ -2506,7 +2546,7 @@ int vsock_core_register(const struct vsock_transport *t, int features)
t_g2h = t;
}
- if (features & VSOCK_TRANSPORT_F_DGRAM) {
+ if (features & VSOCK_TRANSPORT_F_DGRAM_FALLBACK) {
if (t_dgram) {
err = -EBUSY;
goto err_busy;
@@ -2524,7 +2564,7 @@ int vsock_core_register(const struct vsock_transport *t, int features)
transport_h2g = t_h2g;
transport_g2h = t_g2h;
- transport_dgram = t_dgram;
+ transport_dgram_fallback = t_dgram;
transport_local = t_local;
err_busy:
@@ -2543,8 +2583,8 @@ void vsock_core_unregister(const struct vsock_transport *t)
if (transport_g2h == t)
transport_g2h = NULL;
- if (transport_dgram == t)
- transport_dgram = NULL;
+ if (transport_dgram_fallback == t)
+ transport_dgram_fallback = NULL;
if (transport_local == t)
transport_local = NULL;
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 7f1ea434656d..c29000f2612a 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -551,11 +551,6 @@ static void hvs_destruct(struct vsock_sock *vsk)
kfree(hvs);
}
-static int hvs_dgram_bind(struct vsock_sock *vsk, struct sockaddr_vm *addr)
-{
- return -EOPNOTSUPP;
-}
-
static int hvs_dgram_enqueue(struct vsock_sock *vsk,
struct sockaddr_vm *remote, struct msghdr *msg,
size_t dgram_len)
@@ -826,7 +821,6 @@ static struct vsock_transport hvs_transport = {
.connect = hvs_connect,
.shutdown = hvs_shutdown,
- .dgram_bind = hvs_dgram_bind,
.dgram_enqueue = hvs_dgram_enqueue,
.dgram_allow = hvs_dgram_allow,
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 66edffdbf303..ac2126c7dac5 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -428,7 +428,6 @@ static struct virtio_transport virtio_transport = {
.shutdown = virtio_transport_shutdown,
.cancel_pkt = virtio_transport_cancel_pkt,
- .dgram_bind = virtio_transport_dgram_bind,
.dgram_enqueue = virtio_transport_dgram_enqueue,
.dgram_allow = virtio_transport_dgram_allow,
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 01ea1402ad40..ffcbdd77feaa 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -781,13 +781,6 @@ bool virtio_transport_stream_allow(u32 cid, u32 port)
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_allow);
-int virtio_transport_dgram_bind(struct vsock_sock *vsk,
- struct sockaddr_vm *addr)
-{
- return -EOPNOTSUPP;
-}
-EXPORT_SYMBOL_GPL(virtio_transport_dgram_bind);
-
bool virtio_transport_dgram_allow(u32 cid, u32 port)
{
return false;
diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c
index 0bbbdb222245..857b0461f856 100644
--- a/net/vmw_vsock/vmci_transport.c
+++ b/net/vmw_vsock/vmci_transport.c
@@ -2072,7 +2072,7 @@ static int __init vmci_transport_init(void)
/* Register only with dgram feature, other features (H2G, G2H) will be
* registered when the first host or guest becomes active.
*/
- err = vsock_core_register(&vmci_transport, VSOCK_TRANSPORT_F_DGRAM);
+ err = vsock_core_register(&vmci_transport, VSOCK_TRANSPORT_F_DGRAM_FALLBACK);
if (err < 0)
goto err_unsubscribe;
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index 2a59dd177c74..278235ea06c4 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -61,7 +61,6 @@ static struct virtio_transport loopback_transport = {
.shutdown = virtio_transport_shutdown,
.cancel_pkt = vsock_loopback_cancel_pkt,
- .dgram_bind = virtio_transport_dgram_bind,
.dgram_enqueue = virtio_transport_dgram_enqueue,
.dgram_allow = virtio_transport_dgram_allow,
--
2.30.2
^ permalink raw reply related
* [PATCH RFC net-next v5 02/14] af_vsock: refactor transport lookup code
From: Bobby Eshleman @ 2023-07-19 0:50 UTC (permalink / raw)
To: Stefan Hajnoczi, Stefano Garzarella, Michael S. Tsirkin,
Jason Wang, Xuan Zhuo, David S. Miller, Eric Dumazet,
Jakub Kicinski, Paolo Abeni, K. Y. Srinivasan, Haiyang Zhang,
Wei Liu, Dexuan Cui, Bryan Tan, Vishnu Dasa,
VMware PV-Drivers Reviewers
Cc: Dan Carpenter, Simon Horman, Krasnov Arseniy, kvm, virtualization,
netdev, linux-kernel, linux-hyperv, bpf, Bobby Eshleman
In-Reply-To: <20230413-b4-vsock-dgram-v5-0-581bd37fdb26@bytedance.com>
Introduce new reusable function vsock_connectible_lookup_transport()
that performs the transport lookup logic.
No functional change intended.
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Bobby Eshleman <bobby.eshleman@bytedance.com>
---
net/vmw_vsock/af_vsock.c | 25 ++++++++++++++++++-------
1 file changed, 18 insertions(+), 7 deletions(-)
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index ad71e084bf2f..ae5ac5531d96 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -423,6 +423,22 @@ static void vsock_deassign_transport(struct vsock_sock *vsk)
vsk->transport = NULL;
}
+static const struct vsock_transport *
+vsock_connectible_lookup_transport(unsigned int cid, __u8 flags)
+{
+ const struct vsock_transport *transport;
+
+ if (vsock_use_local_transport(cid))
+ transport = transport_local;
+ else if (cid <= VMADDR_CID_HOST || !transport_h2g ||
+ (flags & VMADDR_FLAG_TO_HOST))
+ transport = transport_g2h;
+ else
+ transport = transport_h2g;
+
+ return transport;
+}
+
/* Assign a transport to a socket and call the .init transport callback.
*
* Note: for connection oriented socket this must be called when vsk->remote_addr
@@ -463,13 +479,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
break;
case SOCK_STREAM:
case SOCK_SEQPACKET:
- if (vsock_use_local_transport(remote_cid))
- new_transport = transport_local;
- else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g ||
- (remote_flags & VMADDR_FLAG_TO_HOST))
- new_transport = transport_g2h;
- else
- new_transport = transport_h2g;
+ new_transport = vsock_connectible_lookup_transport(remote_cid,
+ remote_flags);
break;
default:
return -ESOCKTNOSUPPORT;
--
2.30.2
^ permalink raw reply related
* [PATCH V2,net-next] net: mana: Add page pool for RX buffers
From: Haiyang Zhang @ 2023-07-18 21:48 UTC (permalink / raw)
To: linux-hyperv@vger.kernel.org, netdev@vger.kernel.org
Cc: Haiyang Zhang, Dexuan Cui, KY Srinivasan, Paul Rosswurm,
olaf@aepfle.de, vkuznets@redhat.com, davem@davemloft.net,
wei.liu@kernel.org, edumazet@google.com, kuba@kernel.org,
pabeni@redhat.com, leon@kernel.org, Long Li,
ssengar@linux.microsoft.com, linux-rdma@vger.kernel.org,
daniel@iogearbox.net, john.fastabend@gmail.com,
bpf@vger.kernel.org, ast@kernel.org, Ajay Sharma, hawk@kernel.org,
tglx@linutronix.de, shradhagupta@linux.microsoft.com,
linux-kernel@vger.kernel.org
Add page pool for RX buffers for faster buffer cycle and reduce CPU
usage.
The standard page pool API is used.
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
---
V2:
Use the standard page pool API as suggested by Jesper Dangaard Brouer
---
drivers/net/ethernet/microsoft/mana/mana_en.c | 101 +++++++++++++++---
include/net/mana/mana.h | 3 +
2 files changed, 89 insertions(+), 15 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index a499e460594b..0b557b70cd45 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1414,8 +1414,8 @@ static struct sk_buff *mana_build_skb(struct mana_rxq *rxq, void *buf_va,
return skb;
}
-static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe,
- struct mana_rxq *rxq)
+static void mana_rx_skb(void *buf_va, bool from_pool,
+ struct mana_rxcomp_oob *cqe, struct mana_rxq *rxq)
{
struct mana_stats_rx *rx_stats = &rxq->stats;
struct net_device *ndev = rxq->ndev;
@@ -1437,8 +1437,12 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe,
act = mana_run_xdp(ndev, rxq, &xdp, buf_va, pkt_len);
- if (act == XDP_REDIRECT && !rxq->xdp_rc)
+ if (act == XDP_REDIRECT && !rxq->xdp_rc) {
+ if (from_pool)
+ page_pool_release_page(rxq->page_pool,
+ virt_to_head_page(buf_va));
return;
+ }
if (act != XDP_PASS && act != XDP_TX)
goto drop_xdp;
@@ -1448,6 +1452,9 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe,
if (!skb)
goto drop;
+ if (from_pool)
+ skb_mark_for_recycle(skb);
+
skb->dev = napi->dev;
skb->protocol = eth_type_trans(skb, ndev);
@@ -1498,9 +1505,14 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe,
u64_stats_update_end(&rx_stats->syncp);
drop:
- WARN_ON_ONCE(rxq->xdp_save_va);
- /* Save for reuse */
- rxq->xdp_save_va = buf_va;
+ if (from_pool) {
+ page_pool_recycle_direct(rxq->page_pool,
+ virt_to_head_page(buf_va));
+ } else {
+ WARN_ON_ONCE(rxq->xdp_save_va);
+ /* Save for reuse */
+ rxq->xdp_save_va = buf_va;
+ }
++ndev->stats.rx_dropped;
@@ -1508,11 +1520,13 @@ static void mana_rx_skb(void *buf_va, struct mana_rxcomp_oob *cqe,
}
static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
- dma_addr_t *da, bool is_napi)
+ dma_addr_t *da, bool *from_pool, bool is_napi)
{
struct page *page;
void *va;
+ *from_pool = false;
+
/* Reuse XDP dropped page if available */
if (rxq->xdp_save_va) {
va = rxq->xdp_save_va;
@@ -1533,7 +1547,13 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
return NULL;
}
} else {
- page = dev_alloc_page();
+ if (is_napi) {
+ page = page_pool_dev_alloc_pages(rxq->page_pool);
+ *from_pool = true;
+ } else {
+ page = dev_alloc_page();
+ }
+
if (!page)
return NULL;
@@ -1543,7 +1563,11 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
*da = dma_map_single(dev, va + rxq->headroom, rxq->datasize,
DMA_FROM_DEVICE);
if (dma_mapping_error(dev, *da)) {
- put_page(virt_to_head_page(va));
+ if (*from_pool)
+ page_pool_put_full_page(rxq->page_pool, page, true);
+ else
+ put_page(virt_to_head_page(va));
+
return NULL;
}
@@ -1552,21 +1576,25 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev,
/* Allocate frag for rx buffer, and save the old buf */
static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq,
- struct mana_recv_buf_oob *rxoob, void **old_buf)
+ struct mana_recv_buf_oob *rxoob, void **old_buf,
+ bool *old_fp)
{
+ bool from_pool;
dma_addr_t da;
void *va;
- va = mana_get_rxfrag(rxq, dev, &da, true);
+ va = mana_get_rxfrag(rxq, dev, &da, &from_pool, true);
if (!va)
return;
dma_unmap_single(dev, rxoob->sgl[0].address, rxq->datasize,
DMA_FROM_DEVICE);
*old_buf = rxoob->buf_va;
+ *old_fp = rxoob->from_pool;
rxoob->buf_va = va;
rxoob->sgl[0].address = da;
+ rxoob->from_pool = from_pool;
}
static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
@@ -1580,6 +1608,7 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
struct device *dev = gc->dev;
void *old_buf = NULL;
u32 curr, pktlen;
+ bool old_fp;
apc = netdev_priv(ndev);
@@ -1622,12 +1651,12 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
rxbuf_oob = &rxq->rx_oobs[curr];
WARN_ON_ONCE(rxbuf_oob->wqe_inf.wqe_size_in_bu != 1);
- mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf);
+ mana_refill_rx_oob(dev, rxq, rxbuf_oob, &old_buf, &old_fp);
/* Unsuccessful refill will have old_buf == NULL.
* In this case, mana_rx_skb() will drop the packet.
*/
- mana_rx_skb(old_buf, oob, rxq);
+ mana_rx_skb(old_buf, old_fp, oob, rxq);
drop:
mana_move_wq_tail(rxq->gdma_rq, rxbuf_oob->wqe_inf.wqe_size_in_bu);
@@ -1659,6 +1688,8 @@ static void mana_poll_rx_cq(struct mana_cq *cq)
if (rxq->xdp_flush)
xdp_do_flush();
+
+ page_pool_nid_changed(rxq->page_pool, numa_mem_id());
}
static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
@@ -1881,6 +1912,7 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
struct mana_recv_buf_oob *rx_oob;
struct device *dev = gc->dev;
struct napi_struct *napi;
+ struct page *page;
int i;
if (!rxq)
@@ -1913,10 +1945,18 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
dma_unmap_single(dev, rx_oob->sgl[0].address,
rx_oob->sgl[0].size, DMA_FROM_DEVICE);
- put_page(virt_to_head_page(rx_oob->buf_va));
+ page = virt_to_head_page(rx_oob->buf_va);
+
+ if (rx_oob->from_pool)
+ page_pool_put_full_page(rxq->page_pool, page, false);
+ else
+ put_page(page);
+
rx_oob->buf_va = NULL;
}
+ page_pool_destroy(rxq->page_pool);
+
if (rxq->gdma_rq)
mana_gd_destroy_queue(gc, rxq->gdma_rq);
@@ -1927,18 +1967,20 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key,
struct mana_rxq *rxq, struct device *dev)
{
struct mana_port_context *mpc = netdev_priv(rxq->ndev);
+ bool from_pool = false;
dma_addr_t da;
void *va;
if (mpc->rxbufs_pre)
va = mana_get_rxbuf_pre(rxq, &da);
else
- va = mana_get_rxfrag(rxq, dev, &da, false);
+ va = mana_get_rxfrag(rxq, dev, &da, &from_pool, false);
if (!va)
return -ENOMEM;
rx_oob->buf_va = va;
+ rx_oob->from_pool = from_pool;
rx_oob->sgl[0].address = da;
rx_oob->sgl[0].size = rxq->datasize;
@@ -2008,6 +2050,28 @@ static int mana_push_wqe(struct mana_rxq *rxq)
return 0;
}
+static int mana_create_page_pool(struct gdma_context *gc, struct mana_cq *cq,
+ struct mana_rxq *rxq)
+{
+ struct page_pool_params pprm = {};
+ int ret;
+
+ pprm.pool_size = RX_BUFFERS_PER_QUEUE;
+ pprm.napi = &cq->napi;
+ pprm.dev = gc->dev;
+ pprm.dma_dir = DMA_FROM_DEVICE;
+
+ rxq->page_pool = page_pool_create(&pprm);
+
+ if (IS_ERR(rxq->page_pool)) {
+ ret = PTR_ERR(rxq->page_pool);
+ rxq->page_pool = NULL;
+ return ret;
+ }
+
+ return 0;
+}
+
static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
u32 rxq_idx, struct mana_eq *eq,
struct net_device *ndev)
@@ -2106,6 +2170,13 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
netif_napi_add_weight(ndev, &cq->napi, mana_poll, 1);
+ /* Create page pool for RX queue */
+ err = mana_create_page_pool(gc, cq, rxq);
+ if (err) {
+ netdev_err(ndev, "Create page pool err:%d\n", err);
+ goto out;
+ }
+
WARN_ON(xdp_rxq_info_reg(&rxq->xdp_rxq, ndev, rxq_idx,
cq->napi.napi_id));
WARN_ON(xdp_rxq_info_reg_mem_model(&rxq->xdp_rxq,
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 024ad8ddb27e..b12859511839 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -280,6 +280,7 @@ struct mana_recv_buf_oob {
struct gdma_wqe_request wqe_req;
void *buf_va;
+ bool from_pool; /* allocated from a page pool */
/* SGL of the buffer going to be sent has part of the work request. */
u32 num_sge;
@@ -330,6 +331,8 @@ struct mana_rxq {
bool xdp_flush;
int xdp_rc; /* XDP redirect return code */
+ struct page_pool *page_pool;
+
/* MUST BE THE LAST MEMBER:
* Each receive buffer has an associated mana_recv_buf_oob.
*/
--
2.25.1
^ 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