On 13.01.23 03:57, Marek Marczykowski-Górecki wrote:
Hi,6.1.3 as PV dom0 crashes when attempting to suspend. 6.1.1 works. The crash: [ 348.284004] PM: suspend entry (deep) [ 348.289532] Filesystems sync: 0.005 seconds [ 348.291545] Freezing user space processes ... (elapsed 0.000 seconds) done. [ 348.292457] OOM killer disabled. [ 348.292462] Freezing remaining freezable tasks ... (elapsed 0.104 seconds) done. [ 348.396612] printk: Suspending console(s) (use no_console_suspend to debug) [ 348.749228] PM: suspend devices took 0.352 seconds [ 348.769713] ACPI: EC: interrupt blocked [ 348.816077] BUG: kernel NULL pointer dereference, address: 000000000000001c [ 348.816080] #PF: supervisor read access in kernel mode [ 348.816081] #PF: error_code(0x0000) - not-present page [ 348.816083] PGD 0 P4D 0 [ 348.816086] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 348.816089] CPU: 0 PID: 6764 Comm: systemd-sleep Not tainted 6.1.3-1.fc32.qubes.x86_64 #1 [ 348.816092] Hardware name: Star Labs StarBook/StarBook, BIOS 8.01 07/03/2022 [ 348.816093] RIP: e030:acpi_get_wakeup_address+0xc/0x20 [ 348.816100] Code: 44 00 00 48 8b 05 04 a3 82 02 c3 cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc 0f 1f 44 00 00 48 8b 05 fc 9d 82 02 <8b> 40 1c c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 90 0f 1f [ 348.816103] RSP: e02b:ffffc90042537d08 EFLAGS: 00010246 [ 348.816105] RAX: 0000000000000000 RBX: 0000000000000003 RCX: 20c49ba5e353f7cf [ 348.816106] RDX: 000000000000cd19 RSI: 000000000002ee9a RDI: 002a051ed42d7694 [ 348.816108] RBP: 0000000000000003 R08: ffffc90042537ca0 R09: ffffffff82c5e468 [ 348.816110] R10: 0000000000007ff0 R11: 0000000000000000 R12: 0000000000000000 [ 348.816111] R13: fffffffffffffff2 R14: ffff88812206e6c0 R15: ffff88812206e6e0 [ 348.816121] FS: 00007cb49b01eb80(0000) GS:ffff888189400000(0000) knlGS:0000000000000000 [ 348.816123] CS: e030 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 348.816124] CR2: 000000000000001c CR3: 000000012231a000 CR4: 0000000000050660 [ 348.816131] Call Trace: [ 348.816133] <TASK> [ 348.816134] acpi_pm_prepare+0x1a/0x50 [ 348.816141] suspend_enter+0x94/0x360 [ 348.816146] suspend_devices_and_enter+0x198/0x2b0 [ 348.816150] enter_state+0x18d/0x1f5 [ 348.816155] pm_suspend.cold+0x20/0x6b [ 348.816159] state_store+0x27/0x60 [ 348.816163] kernfs_fop_write_iter+0x125/0x1c0 [ 348.816169] new_sync_write+0x105/0x190 [ 348.816176] vfs_write+0x211/0x2a0 [ 348.816180] ksys_write+0x67/0xe0 [ 348.816183] do_syscall_64+0x59/0x90 [ 348.816188] ? do_syscall_64+0x69/0x90 [ 348.816192] ? exc_page_fault+0x76/0x170 [ 348.816195] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 348.816200] RIP: 0033:0x7cb49c1412f7 [ 348.816203] Code: 0d 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 48 89 54 24 18 48 89 74 24 [ 348.816204] RSP: 002b:00007ffc125f63f8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 348.816206] RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 00007cb49c1412f7 [ 348.816208] RDX: 0000000000000004 RSI: 00007ffc125f64e0 RDI: 0000000000000004 [ 348.816209] RBP: 00007ffc125f64e0 R08: 00005c83d772bca0 R09: 000000000000000d [ 348.816210] R10: 00005c83d7727eb0 R11: 0000000000000246 R12: 0000000000000004 [ 348.816211] R13: 00005c83d77272d0 R14: 0000000000000004 R15: 00007cb49c213700 [ 348.816213] </TASK> [ 348.816214] Modules linked in: loop vfat fat snd_hda_codec_hdmi snd_sof_pci_intel_tgl snd_sof_intel_hda_common soundwire_intel soundwire_generic_allocation soundwire_cadence snd_sof_intel_hda snd_sof_pci snd_sof_xtensa_dsp snd_sof snd_sof_utils snd_soc_hdac_hda snd_hda_ext_core snd_soc_acpi_intel_match snd_soc_acpi soundwire_bus snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio snd_soc_core snd_compress ac97_bus snd_pcm_dmaengine snd_hda_intel snd_intel_dspcfg snd_intel_sdw_acpi iTCO_wdt intel_pmc_bxt ee1004 iTCO_vendor_support intel_rapl_msr snd_hda_codec snd_hda_core snd_hwdep snd_seq snd_seq_device iwlwifi snd_pcm pcspkr joydev processor_thermal_device_pci_legacy processor_thermal_device snd_timer snd cfg80211 processor_thermal_rfim i2c_i801 processor_thermal_mbox i2c_smbus idma64 rfkill processor_thermal_rapl soundcore intel_rapl_common int340x_thermal_zone intel_soc_dts_iosf igen6_edac intel_hid intel_pmc_core intel_scu_pltdrv sparse_keymap fuse xenfs ip_tables dm_thin_pool ic#2 Part1 [ 348.816259] dm_persistent_data dm_bio_prison dm_crypt i915 crct10dif_pclmul crc32_pclmul crc32c_intel polyval_clmulni polyval_generic drm_buddy nvme video wmi drm_display_helper nvme_core xhci_pci xhci_pci_renesas ghash_clmulni_intel hid_multitouch sha512_ssse3 serio_raw nvme_common cec xhci_hcd ttm i2c_hid_acpi i2c_hid pinctrl_tigerlake xen_acpi_processor xen_privcmd xen_pciback xen_blkback xen_gntalloc xen_gntdev xen_evtchn uinput [ 348.816281] CR2: 000000000000001c [ 348.816283] ---[ end trace 0000000000000000 ]--- [ 348.867991] RIP: e030:acpi_get_wakeup_address+0xc/0x20 [ 348.867996] Code: 44 00 00 48 8b 05 04 a3 82 02 c3 cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc cc 0f 1f 44 00 00 48 8b 05 fc 9d 82 02 <8b> 40 1c c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 90 0f 1f [ 348.867998] RSP: e02b:ffffc90042537d08 EFLAGS: 00010246 [ 348.867999] RAX: 0000000000000000 RBX: 0000000000000003 RCX: 20c49ba5e353f7cf [ 348.868000] RDX: 000000000000cd19 RSI: 000000000002ee9a RDI: 002a051ed42d7694 [ 348.868001] RBP: 0000000000000003 R08: ffffc90042537ca0 R09: ffffffff82c5e468 [ 348.868001] R10: 0000000000007ff0 R11: 0000000000000000 R12: 0000000000000000 [ 348.868002] R13: fffffffffffffff2 R14: ffff88812206e6c0 R15: ffff88812206e6e0 [ 348.868008] FS: 00007cb49b01eb80(0000) GS:ffff888189400000(0000) knlGS:0000000000000000 [ 348.868009] CS: e030 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 348.868009] CR2: 000000000000001c CR3: 000000012231a000 CR4: 0000000000050660 [ 348.868014] Kernel panic - not syncing: Fatal exception [ 348.868031] Kernel Offset: disabled Looking at git log between those two versions, and the acpi_get_wakeup_address() function, I suspect it's this change (but I have _not_ tested it): commit b1898793777fe10a31c160bb8bc385d6eea640c6 Author: Juergen Gross <[email protected]> Date: Wed Nov 23 12:45:23 2022 +0100 x86/boot: Skip realmode init code when running as Xen PV guest[ Upstream commit f1e525009493cbd569e7c8dd7d58157855f8658d ]
Yes, you are right. Could you please test the attached patch? It is for upstream, but I think it should apply to 6.1.3, too. Juergen
From 40833b6701026a37243bda90bbd053c58963844d Mon Sep 17 00:00:00 2001 From: Juergen Gross <[email protected]> To: [email protected] To: [email protected] To: [email protected] Cc: Thomas Gleixner <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Borislav Petkov <[email protected]> Cc: Dave Hansen <[email protected]> Cc: "H. Peter Anvin" <[email protected]> Cc: "Rafael J. Wysocki" <[email protected]> Cc: Len Brown <[email protected]> Cc: Pavel Machek <[email protected]> Cc: Juergen Gross <[email protected]> Cc: Stefano Stabellini <[email protected]> Cc: Oleksandr Tyshchenko <[email protected]> Cc: [email protected] Date: Fri, 13 Jan 2023 08:37:45 +0100 Subject: [PATCH] x86/acpi: fix suspend with Xen MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit f1e525009493 ("x86/boot: Skip realmode init code when running as Xen PV guest") missed one code path accessing real_mode_header, leading to dereferencing NULL when suspending the system under Xen: [ 348.284004] PM: suspend entry (deep) [ 348.289532] Filesystems sync: 0.005 seconds [ 348.291545] Freezing user space processes ... (elapsed 0.000 seconds) done. [ 348.292457] OOM killer disabled. [ 348.292462] Freezing remaining freezable tasks ... (elapsed 0.104 seconds) done. [ 348.396612] printk: Suspending console(s) (use no_console_suspend to debug) [ 348.749228] PM: suspend devices took 0.352 seconds [ 348.769713] ACPI: EC: interrupt blocked [ 348.816077] BUG: kernel NULL pointer dereference, address: 000000000000001c [ 348.816080] #PF: supervisor read access in kernel mode [ 348.816081] #PF: error_code(0x0000) - not-present page [ 348.816083] PGD 0 P4D 0 [ 348.816086] Oops: 0000 [#1] PREEMPT SMP NOPTI [ 348.816089] CPU: 0 PID: 6764 Comm: systemd-sleep Not tainted 6.1.3-1.fc32.qubes.x86_64 #1 [ 348.816092] Hardware name: Star Labs StarBook/StarBook, BIOS 8.01 07/03/2022 [ 348.816093] RIP: e030:acpi_get_wakeup_address+0xc/0x20 Fix that by adding an indirection for acpi_get_wakeup_address() which Xen PV dom0 can use to return a dummy non-zero wakeup address (this address won't ever be used, as the real suspend handling is done by the hypervisor). Fixes: f1e525009493 ("x86/boot: Skip realmode init code when running as Xen PV guest") Reported-by: Marek Marczykowski-Górecki <[email protected]> Signed-off-by: Juergen Gross <[email protected]> --- arch/x86/include/asm/acpi.h | 2 +- arch/x86/kernel/acpi/sleep.c | 3 ++- include/xen/acpi.h | 9 +++++++++ 3 files changed, 12 insertions(+), 2 deletions(-) diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 65064d9f7fa6..137259ff8f03 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -61,7 +61,7 @@ static inline void acpi_disable_pci(void) extern int (*acpi_suspend_lowlevel)(void); /* Physical address to resume after wakeup */ -unsigned long acpi_get_wakeup_address(void); +extern unsigned long (*acpi_get_wakeup_address)(void); /* * Check if the CPU can handle C2 and deeper diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 3b7f4cdbf2e0..1a3cd5e24cd0 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -33,10 +33,11 @@ static char temp_stack[4096]; * Returns the physical address where the kernel should be resumed after the * system awakes from S3, e.g. for programming into the firmware waking vector. */ -unsigned long acpi_get_wakeup_address(void) +static unsigned long x86_acpi_get_wakeup_address(void) { return ((unsigned long)(real_mode_header->wakeup_start)); } +unsigned long (*acpi_get_wakeup_address)(void) = x86_acpi_get_wakeup_address; /** * x86_acpi_enter_sleep_state - enter sleep state diff --git a/include/xen/acpi.h b/include/xen/acpi.h index b1e11863144d..7e1e5dbfb77c 100644 --- a/include/xen/acpi.h +++ b/include/xen/acpi.h @@ -56,6 +56,12 @@ static inline int xen_acpi_suspend_lowlevel(void) return 0; } +static inline unsigned long xen_acpi_get_wakeup_address(void) +{ + /* Just return a dummy non-zero value, it will never be used. */ + return 1; +} + static inline void xen_acpi_sleep_register(void) { if (xen_initial_domain()) { @@ -65,6 +71,9 @@ static inline void xen_acpi_sleep_register(void) &xen_acpi_notify_hypervisor_extended_sleep); acpi_suspend_lowlevel = xen_acpi_suspend_lowlevel; +#ifdef CONFIG_ACPI_SLEEP + acpi_get_wakeup_address = xen_acpi_get_wakeup_address; +#endif } } #else -- 2.35.3
OpenPGP_0xB0DE9DD628BF132F.asc
Description: OpenPGP public key
OpenPGP_signature
Description: OpenPGP digital signature
