From 726efa92e02b460811e8bc6990dd742f03b645ea Mon Sep 17 00:00:00 2001 From: Xiaolei Wang Date: Wed, 15 Jan 2025 09:41:18 +0800 Subject: [PATCH 01/16] pmdomain: imx8mp-blk-ctrl: add missing loop break condition Currently imx8mp_blk_ctrl_remove() will continue the for loop until an out-of-bounds exception occurs. pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : dev_pm_domain_detach+0x8/0x48 lr : imx8mp_blk_ctrl_shutdown+0x58/0x90 sp : ffffffc084f8bbf0 x29: ffffffc084f8bbf0 x28: ffffff80daf32ac0 x27: 0000000000000000 x26: ffffffc081658d78 x25: 0000000000000001 x24: ffffffc08201b028 x23: ffffff80d0db9490 x22: ffffffc082340a78 x21: 00000000000005b0 x20: ffffff80d19bc180 x19: 000000000000000a x18: ffffffffffffffff x17: ffffffc080a39e08 x16: ffffffc080a39c98 x15: 4f435f464f006c72 x14: 0000000000000004 x13: ffffff80d0172110 x12: 0000000000000000 x11: ffffff80d0537740 x10: ffffff80d05376c0 x9 : ffffffc0808ed2d8 x8 : ffffffc084f8bab0 x7 : 0000000000000000 x6 : 0000000000000000 x5 : ffffff80d19b9420 x4 : fffffffe03466e60 x3 : 0000000080800077 x2 : 0000000000000000 x1 : 0000000000000001 x0 : 0000000000000000 Call trace: dev_pm_domain_detach+0x8/0x48 platform_shutdown+0x2c/0x48 device_shutdown+0x158/0x268 kernel_restart_prepare+0x40/0x58 kernel_kexec+0x58/0xe8 __do_sys_reboot+0x198/0x258 __arm64_sys_reboot+0x2c/0x40 invoke_syscall+0x5c/0x138 el0_svc_common.constprop.0+0x48/0xf0 do_el0_svc+0x24/0x38 el0_svc+0x38/0xc8 el0t_64_sync_handler+0x120/0x130 el0t_64_sync+0x190/0x198 Code: 8128c2d0 ffffffc0 aa1e03e9 d503201f Fixes: 556f5cf9568a ("soc: imx: add i.MX8MP HSIO blk-ctrl") Cc: stable@vger.kernel.org Signed-off-by: Xiaolei Wang Reviewed-by: Lucas Stach Reviewed-by: Fabio Estevam Reviewed-by: Frank Li Link: https://lore.kernel.org/r/20250115014118.4086729-1-xiaolei.wang@windriver.com Signed-off-by: Ulf Hansson --- drivers/pmdomain/imx/imx8mp-blk-ctrl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/pmdomain/imx/imx8mp-blk-ctrl.c b/drivers/pmdomain/imx/imx8mp-blk-ctrl.c index e3a0f64c144c..3668fe66b22c 100644 --- a/drivers/pmdomain/imx/imx8mp-blk-ctrl.c +++ b/drivers/pmdomain/imx/imx8mp-blk-ctrl.c @@ -770,7 +770,7 @@ static void imx8mp_blk_ctrl_remove(struct platform_device *pdev) of_genpd_del_provider(pdev->dev.of_node); - for (i = 0; bc->onecell_data.num_domains; i++) { + for (i = 0; i < bc->onecell_data.num_domains; i++) { struct imx8mp_blk_ctrl_domain *domain = &bc->domains[i]; pm_genpd_remove(&domain->genpd); -- 2.51.0 From ae02ae16b76160f0aeeae2c5fb9b15226d00a4ef Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Wed, 18 Dec 2024 11:09:18 +0100 Subject: [PATCH 02/16] x86/asm: Make serialize() always_inline In order to allow serialize() to be used from noinstr code, make it __always_inline. Fixes: 0ef8047b737d ("x86/static-call: provide a way to do very early static-call updates") Closes: https://lore.kernel.org/oe-kbuild-all/202412181756.aJvzih2K-lkp@intel.com/ Reported-by: kernel test robot Signed-off-by: Juergen Gross Signed-off-by: Borislav Petkov (AMD) Link: https://lore.kernel.org/r/20241218100918.22167-1-jgross@suse.com --- arch/x86/include/asm/special_insns.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index aec6e2d3aa1d..98bfc097389c 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -217,7 +217,7 @@ fail: #define nop() asm volatile ("nop") -static inline void serialize(void) +static __always_inline void serialize(void) { /* Instruction opcode for SERIALIZE; supported in binutils >= 2.35. */ asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory"); -- 2.51.0 From b1231ff7ea0689d04040a44864c265bc11612fa8 Mon Sep 17 00:00:00 2001 From: Matthew Brost Date: Mon, 13 Jan 2025 16:25:07 -0800 Subject: [PATCH 03/16] drm/xe: Mark ComputeCS read mode as UC on iGPU MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit RING_CMD_CCTL read index should be UC on iGPU parts due to L3 caching structure. Having this as WB blocks ULLS from being enabled. Change to UC to unblock ULLS on iGPU. v2: - Drop internal communications commnet, bspec is updated Cc: Balasubramani Vivekanandan Cc: Michal Mrozek Cc: Paulo Zanoni Cc: José Roberto de Souza Cc: stable@vger.kernel.org Fixes: 328e089bfb37 ("drm/xe: Leverage ComputeCS read L3 caching") Signed-off-by: Matthew Brost Acked-by: Michal Mrozek Reviewed-by: Stuart Summers Reviewed-by: Matt Roper Link: https://patchwork.freedesktop.org/patch/msgid/20250114002507.114087-1-matthew.brost@intel.com (cherry picked from commit 758debf35b9cda5450e40996991a6e4b222899bd) Signed-off-by: Thomas Hellström --- drivers/gpu/drm/xe/xe_hw_engine.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/xe/xe_hw_engine.c b/drivers/gpu/drm/xe/xe_hw_engine.c index 1557acee3523..eeeb98f66982 100644 --- a/drivers/gpu/drm/xe/xe_hw_engine.c +++ b/drivers/gpu/drm/xe/xe_hw_engine.c @@ -419,7 +419,7 @@ hw_engine_setup_default_state(struct xe_hw_engine *hwe) * Bspec: 72161 */ const u8 mocs_write_idx = gt->mocs.uc_index; - const u8 mocs_read_idx = hwe->class == XE_ENGINE_CLASS_COMPUTE && + const u8 mocs_read_idx = hwe->class == XE_ENGINE_CLASS_COMPUTE && IS_DGFX(xe) && (GRAPHICS_VER(xe) >= 20 || xe->info.platform == XE_PVC) ? gt->mocs.wb_index : gt->mocs.uc_index; u32 ring_cmd_cctl_val = REG_FIELD_PREP(CMD_CCTL_WRITE_OVERRIDE_MASK, mocs_write_idx) | -- 2.51.0 From 60295b944ff6805e677c48ae4178532b207d43be Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Thu, 16 Jan 2025 16:41:24 -0500 Subject: [PATCH 04/16] tracing: gfp: Fix the GFP enum values shown for user space tracing tools Tracing tools like perf and trace-cmd read the /sys/kernel/tracing/events/*/*/format files to know how to parse the data and also how to print it. For the "print fmt" portion of that file, if anything uses an enum that is not exported to the tracing system, user space will not be able to parse it. The GFP flags use to be defines, and defines get translated in the print fmt sections. But now they are converted to use enums, which is not. The mm_page_alloc trace event format use to have: print fmt: "page=%p pfn=0x%lx order=%d migratetype=%d gfp_flags=%s", REC->pfn != -1UL ? (((struct page *)vmemmap_base) + (REC->pfn)) : ((void *)0), REC->pfn != -1UL ? REC->pfn : 0, REC->order, REC->migratetype, (REC->gfp_flags) ? __print_flags(REC->gfp_flags, "|", {( unsigned long)(((((((( gfp_t)(0x400u|0x800u)) | (( gfp_t)0x40u) | (( gfp_t)0x80u) | (( gfp_t)0x100000u)) | (( gfp_t)0x02u)) | (( gfp_t)0x08u) | (( gfp_t)0)) | (( gfp_t)0x40000u) | (( gfp_t)0x80000u) | (( gfp_t)0x2000u)) & ~(( gfp_t)(0x400u|0x800u))) | (( gfp_t)0x400u)), "GFP_TRANSHUGE"}, {( unsigned long)((((((( gfp_t)(0x400u|0x800u)) | (( gfp_t)0x40u) | (( gfp_t)0x80u) | (( gfp_t)0x100000u)) | (( gfp_t)0x02u)) | (( gfp_t)0x08u) | (( gfp_t)0)) ... Where the GFP values are shown and not their names. But after the GFP flags were converted to use enums, it has: print fmt: "page=%p pfn=0x%lx order=%d migratetype=%d gfp_flags=%s", REC->pfn != -1UL ? (vmemmap + (REC->pfn)) : ((void *)0), REC->pfn != -1UL ? REC->pfn : 0, REC->order, REC->migratetype, (REC->gfp_flags) ? __print_flags(REC->gfp_flags, "|", {( unsigned long)(((((((( gfp_t)(((((1UL))) << (___GFP_DIRECT_RECLAIM_BIT))|((((1UL))) << (___GFP_KSWAPD_RECLAIM_BIT)))) | (( gfp_t)((((1UL))) << (___GFP_IO_BIT))) | (( gfp_t)((((1UL))) << (___GFP_FS_BIT))) | (( gfp_t)((((1UL))) << (___GFP_HARDWALL_BIT)))) | (( gfp_t)((((1UL))) << (___GFP_HIGHMEM_BIT)))) | (( gfp_t)((((1UL))) << (___GFP_MOVABLE_BIT))) | (( gfp_t)0)) | (( gfp_t)((((1UL))) << (___GFP_COMP_BIT))) ... Where the enums names like ___GFP_KSWAPD_RECLAIM_BIT are shown and not their values. User space has no way to convert these names to their values and the output will fail to parse. What is shown is now: mm_page_alloc: page=0xffffffff981685f3 pfn=0x1d1ac1 order=0 migratetype=1 gfp_flags=0x140cca The TRACE_DEFINE_ENUM() macro was created to handle enums in the print fmt files. This causes them to be replaced at boot up with the numbers, so that user space tooling can parse it. By using this macro, the output is back to the human readable: mm_page_alloc: page=0xffffffff981685f3 pfn=0x122233 order=0 migratetype=1 gfp_flags=GFP_HIGHUSER_MOVABLE|__GFP_COMP Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mark Rutland Cc: Mathieu Desnoyers Cc: Andrew Morton Cc: Veronika Molnarova Cc: Suren Baghdasaryan Cc: Linus Torvalds Link: https://lore.kernel.org/20250116214438.749504792@goodmis.org Reported-by: Michael Petlan Closes: https://lore.kernel.org/all/87be5f7c-1a0-dad-daa0-54e342efaea7@redhat.com/ Fixes: 772dd0342727c ("mm: enumerate all gfp flags") Signed-off-by: Steven Rostedt (Google) --- include/trace/events/mmflags.h | 63 ++++++++++++++++++++++++++++++++++ 1 file changed, 63 insertions(+) diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index bb8a59c6caa2..d36c857dd249 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -13,6 +13,69 @@ * Thus most bits set go first. */ +/* These define the values that are enums (the bits) */ +#define TRACE_GFP_FLAGS_GENERAL \ + TRACE_GFP_EM(DMA) \ + TRACE_GFP_EM(HIGHMEM) \ + TRACE_GFP_EM(DMA32) \ + TRACE_GFP_EM(MOVABLE) \ + TRACE_GFP_EM(RECLAIMABLE) \ + TRACE_GFP_EM(HIGH) \ + TRACE_GFP_EM(IO) \ + TRACE_GFP_EM(FS) \ + TRACE_GFP_EM(ZERO) \ + TRACE_GFP_EM(DIRECT_RECLAIM) \ + TRACE_GFP_EM(KSWAPD_RECLAIM) \ + TRACE_GFP_EM(WRITE) \ + TRACE_GFP_EM(NOWARN) \ + TRACE_GFP_EM(RETRY_MAYFAIL) \ + TRACE_GFP_EM(NOFAIL) \ + TRACE_GFP_EM(NORETRY) \ + TRACE_GFP_EM(MEMALLOC) \ + TRACE_GFP_EM(COMP) \ + TRACE_GFP_EM(NOMEMALLOC) \ + TRACE_GFP_EM(HARDWALL) \ + TRACE_GFP_EM(THISNODE) \ + TRACE_GFP_EM(ACCOUNT) \ + TRACE_GFP_EM(ZEROTAGS) + +#ifdef CONFIG_KASAN_HW_TAGS +# define TRACE_GFP_FLAGS_KASAN \ + TRACE_GFP_EM(SKIP_ZERO) \ + TRACE_GFP_EM(SKIP_KASAN) +#else +# define TRACE_GFP_FLAGS_KASAN +#endif + +#ifdef CONFIG_LOCKDEP +# define TRACE_GFP_FLAGS_LOCKDEP \ + TRACE_GFP_EM(NOLOCKDEP) +#else +# define TRACE_GFP_FLAGS_LOCKDEP +#endif + +#ifdef CONFIG_SLAB_OBJ_EXT +# define TRACE_GFP_FLAGS_SLAB \ + TRACE_GFP_EM(NO_OBJ_EXT) +#else +# define TRACE_GFP_FLAGS_SLAB +#endif + +#define TRACE_GFP_FLAGS \ + TRACE_GFP_FLAGS_GENERAL \ + TRACE_GFP_FLAGS_KASAN \ + TRACE_GFP_FLAGS_LOCKDEP \ + TRACE_GFP_FLAGS_SLAB + +#undef TRACE_GFP_EM +#define TRACE_GFP_EM(a) TRACE_DEFINE_ENUM(___GFP_##a##_BIT); + +TRACE_GFP_FLAGS + +/* Just in case these are ever used */ +TRACE_DEFINE_ENUM(___GFP_UNUSED_BIT); +TRACE_DEFINE_ENUM(___GFP_LAST_BIT); + #define gfpflag_string(flag) {(__force unsigned long)flag, #flag} #define __def_gfpflag_names \ -- 2.51.0 From ffd294d346d185b70e28b1a28abe367bbfe53c04 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 19 Jan 2025 15:51:45 -0800 Subject: [PATCH 05/16] Linux 6.13 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index e20a62ad397f..b9464c88ac72 100644 --- a/Makefile +++ b/Makefile @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 13 SUBLEVEL = 0 -EXTRAVERSION = -rc7 +EXTRAVERSION = NAME = Baby Opossum Posse # *DOCUMENTATION* -- 2.51.0 From f839f532c9b0f6195ac75164afab6ae15cc09091 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Sergio=20Migu=C3=A9ns=20Iglesias?= Date: Mon, 2 Dec 2024 09:59:05 +0100 Subject: [PATCH 06/16] xen: pcpu: remove unnecessary __ref annotation MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit The __ref annotation has been there since many years now, but the reason why it has been added has been removed from the code long ago. [jgross: clarify commit message] Cc: Juergen Gross Cc: Stefano Stabellini Cc: Oleksandr Tyshchenko Cc: xen-devel@lists.xenproject.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Sergio Miguéns Iglesias Reviewed-by: Juergen Gross Message-ID: <20241202085910.5539-1-sergio@lony.xyz> Signed-off-by: Juergen Gross --- drivers/xen/pcpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/pcpu.c b/drivers/xen/pcpu.c index c63f317e3df3..093ad4a08672 100644 --- a/drivers/xen/pcpu.c +++ b/drivers/xen/pcpu.c @@ -105,7 +105,7 @@ static ssize_t online_show(struct device *dev, return sprintf(buf, "%u\n", !!(cpu->flags & XEN_PCPU_FLAGS_ONLINE)); } -static ssize_t __ref online_store(struct device *dev, +static ssize_t online_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { -- 2.51.0 From 6d002348789bc16e9203e9818b7a3688787e3b29 Mon Sep 17 00:00:00 2001 From: Maksym Planeta Date: Wed, 4 Dec 2024 11:35:15 +0100 Subject: [PATCH 07/16] Grab mm lock before grabbing pt lock Function xen_pin_page calls xen_pte_lock, which in turn grab page table lock (ptlock). When locking, xen_pte_lock expect mm->page_table_lock to be held before grabbing ptlock, but this does not happen when pinning is caused by xen_mm_pin_all. This commit addresses lockdep warning below, which shows up when suspending a Xen VM. [ 3680.658422] Freezing user space processes [ 3680.660156] Freezing user space processes completed (elapsed 0.001 seconds) [ 3680.660182] OOM killer disabled. [ 3680.660192] Freezing remaining freezable tasks [ 3680.661485] Freezing remaining freezable tasks completed (elapsed 0.001 seconds) [ 3680.685254] [ 3680.685265] ================================== [ 3680.685269] WARNING: Nested lock was not taken [ 3680.685274] 6.12.0+ #16 Tainted: G W [ 3680.685279] ---------------------------------- [ 3680.685283] migration/0/19 is trying to lock: [ 3680.685288] ffff88800bac33c0 (ptlock_ptr(ptdesc)#2){+.+.}-{3:3}, at: xen_pin_page+0x175/0x1d0 [ 3680.685303] [ 3680.685303] but this task is not holding: [ 3680.685308] init_mm.page_table_lock [ 3680.685311] [ 3680.685311] stack backtrace: [ 3680.685316] CPU: 0 UID: 0 PID: 19 Comm: migration/0 Tainted: G W 6.12.0+ #16 [ 3680.685324] Tainted: [W]=WARN [ 3680.685328] Stopper: multi_cpu_stop+0x0/0x120 <- __stop_cpus.constprop.0+0x8c/0xd0 [ 3680.685339] Call Trace: [ 3680.685344] [ 3680.685347] dump_stack_lvl+0x77/0xb0 [ 3680.685356] __lock_acquire+0x917/0x2310 [ 3680.685364] lock_acquire+0xce/0x2c0 [ 3680.685369] ? xen_pin_page+0x175/0x1d0 [ 3680.685373] _raw_spin_lock_nest_lock+0x2f/0x70 [ 3680.685381] ? xen_pin_page+0x175/0x1d0 [ 3680.685386] xen_pin_page+0x175/0x1d0 [ 3680.685390] ? __pfx_xen_pin_page+0x10/0x10 [ 3680.685394] __xen_pgd_walk+0x233/0x2c0 [ 3680.685401] ? stop_one_cpu+0x91/0x100 [ 3680.685405] __xen_pgd_pin+0x5d/0x250 [ 3680.685410] xen_mm_pin_all+0x70/0xa0 [ 3680.685415] xen_pv_pre_suspend+0xf/0x280 [ 3680.685420] xen_suspend+0x57/0x1a0 [ 3680.685428] multi_cpu_stop+0x6b/0x120 [ 3680.685432] ? update_cpumasks_hier+0x7c/0xa60 [ 3680.685439] ? __pfx_multi_cpu_stop+0x10/0x10 [ 3680.685443] cpu_stopper_thread+0x8c/0x140 [ 3680.685448] ? smpboot_thread_fn+0x20/0x1f0 [ 3680.685454] ? __pfx_smpboot_thread_fn+0x10/0x10 [ 3680.685458] smpboot_thread_fn+0xed/0x1f0 [ 3680.685462] kthread+0xde/0x110 [ 3680.685467] ? __pfx_kthread+0x10/0x10 [ 3680.685471] ret_from_fork+0x2f/0x50 [ 3680.685478] ? __pfx_kthread+0x10/0x10 [ 3680.685482] ret_from_fork_asm+0x1a/0x30 [ 3680.685489] [ 3680.685491] [ 3680.685491] other info that might help us debug this: [ 3680.685497] 1 lock held by migration/0/19: [ 3680.685500] #0: ffffffff8284df38 (pgd_lock){+.+.}-{3:3}, at: xen_mm_pin_all+0x14/0xa0 [ 3680.685512] [ 3680.685512] stack backtrace: [ 3680.685518] CPU: 0 UID: 0 PID: 19 Comm: migration/0 Tainted: G W 6.12.0+ #16 [ 3680.685528] Tainted: [W]=WARN [ 3680.685531] Stopper: multi_cpu_stop+0x0/0x120 <- __stop_cpus.constprop.0+0x8c/0xd0 [ 3680.685538] Call Trace: [ 3680.685541] [ 3680.685544] dump_stack_lvl+0x77/0xb0 [ 3680.685549] __lock_acquire+0x93c/0x2310 [ 3680.685554] lock_acquire+0xce/0x2c0 [ 3680.685558] ? xen_pin_page+0x175/0x1d0 [ 3680.685562] _raw_spin_lock_nest_lock+0x2f/0x70 [ 3680.685568] ? xen_pin_page+0x175/0x1d0 [ 3680.685572] xen_pin_page+0x175/0x1d0 [ 3680.685578] ? __pfx_xen_pin_page+0x10/0x10 [ 3680.685582] __xen_pgd_walk+0x233/0x2c0 [ 3680.685588] ? stop_one_cpu+0x91/0x100 [ 3680.685592] __xen_pgd_pin+0x5d/0x250 [ 3680.685596] xen_mm_pin_all+0x70/0xa0 [ 3680.685600] xen_pv_pre_suspend+0xf/0x280 [ 3680.685607] xen_suspend+0x57/0x1a0 [ 3680.685611] multi_cpu_stop+0x6b/0x120 [ 3680.685615] ? update_cpumasks_hier+0x7c/0xa60 [ 3680.685620] ? __pfx_multi_cpu_stop+0x10/0x10 [ 3680.685625] cpu_stopper_thread+0x8c/0x140 [ 3680.685629] ? smpboot_thread_fn+0x20/0x1f0 [ 3680.685634] ? __pfx_smpboot_thread_fn+0x10/0x10 [ 3680.685638] smpboot_thread_fn+0xed/0x1f0 [ 3680.685642] kthread+0xde/0x110 [ 3680.685645] ? __pfx_kthread+0x10/0x10 [ 3680.685649] ret_from_fork+0x2f/0x50 [ 3680.685654] ? __pfx_kthread+0x10/0x10 [ 3680.685657] ret_from_fork_asm+0x1a/0x30 [ 3680.685662] [ 3680.685267] xen:grant_table: Grant tables using version 1 layout [ 3680.685921] OOM killer enabled. [ 3680.685934] Restarting tasks ... done. Signed-off-by: Maksym Planeta Reviewed-by: Juergen Gross Message-ID: <20241204103516.3309112-1-maksym@exostellar.io> Signed-off-by: Juergen Gross --- arch/x86/xen/mmu_pv.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 55a4996d0c04..2c70cd35e72c 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -781,6 +781,7 @@ void xen_mm_pin_all(void) { struct page *page; + spin_lock(&init_mm.page_table_lock); spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { @@ -791,6 +792,7 @@ void xen_mm_pin_all(void) } spin_unlock(&pgd_lock); + spin_unlock(&init_mm.page_table_lock); } static void __init xen_mark_pinned(struct mm_struct *mm, struct page *page, @@ -887,6 +889,7 @@ void xen_mm_unpin_all(void) { struct page *page; + spin_lock(&init_mm.page_table_lock); spin_lock(&pgd_lock); list_for_each_entry(page, &pgd_list, lru) { @@ -898,6 +901,7 @@ void xen_mm_unpin_all(void) } spin_unlock(&pgd_lock); + spin_unlock(&init_mm.page_table_lock); } static void xen_enter_mmap(struct mm_struct *mm) -- 2.51.0 From bda50f7770e5b8e730745e119eb6ca78570f7abf Mon Sep 17 00:00:00 2001 From: Stefano Stabellini Date: Mon, 20 Jan 2025 15:38:24 -0800 Subject: [PATCH 08/16] xen: update pvcalls_front_accept prototype While currently there are no in-tree callers of these functions, it is best to keep them up-to-date with the latest network API. In addition, add the missing EXPORT_SYMBOL_GPL to the functions listed in pvcalls-front.h. Signed-off-by: Stefano Stabellini Reviewed-by: Juergen Gross Message-ID: Signed-off-by: Juergen Gross --- drivers/xen/pvcalls-front.c | 14 ++++++++++++-- drivers/xen/pvcalls-front.h | 2 +- 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index b72ee9379d77..4926d4badc57 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -341,6 +341,7 @@ int pvcalls_front_socket(struct socket *sock) pvcalls_exit(); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_socket); static void free_active_ring(struct sock_mapping *map) { @@ -486,6 +487,7 @@ int pvcalls_front_connect(struct socket *sock, struct sockaddr *addr, pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_connect); static int __write_ring(struct pvcalls_data_intf *intf, struct pvcalls_data *data, @@ -581,6 +583,7 @@ again: pvcalls_exit_sock(sock); return tot_sent; } +EXPORT_SYMBOL_GPL(pvcalls_front_sendmsg); static int __read_ring(struct pvcalls_data_intf *intf, struct pvcalls_data *data, @@ -666,6 +669,7 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_recvmsg); int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { @@ -719,6 +723,7 @@ int pvcalls_front_bind(struct socket *sock, struct sockaddr *addr, int addr_len) pvcalls_exit_sock(sock); return 0; } +EXPORT_SYMBOL_GPL(pvcalls_front_bind); int pvcalls_front_listen(struct socket *sock, int backlog) { @@ -768,8 +773,10 @@ int pvcalls_front_listen(struct socket *sock, int backlog) pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_listen); -int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) +int pvcalls_front_accept(struct socket *sock, struct socket *newsock, + struct proto_accept_arg *arg) { struct pvcalls_bedata *bedata; struct sock_mapping *map; @@ -788,7 +795,7 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) return -EINVAL; } - nonblock = flags & SOCK_NONBLOCK; + nonblock = arg->flags & SOCK_NONBLOCK; /* * Backend only supports 1 inflight accept request, will return * errors for the others @@ -904,6 +911,7 @@ received: pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_accept); static __poll_t pvcalls_front_poll_passive(struct file *file, struct pvcalls_bedata *bedata, @@ -1004,6 +1012,7 @@ __poll_t pvcalls_front_poll(struct file *file, struct socket *sock, pvcalls_exit_sock(sock); return ret; } +EXPORT_SYMBOL_GPL(pvcalls_front_poll); int pvcalls_front_release(struct socket *sock) { @@ -1087,6 +1096,7 @@ int pvcalls_front_release(struct socket *sock) pvcalls_exit(); return 0; } +EXPORT_SYMBOL_GPL(pvcalls_front_release); static const struct xenbus_device_id pvcalls_front_ids[] = { { "pvcalls" }, diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h index f694ad77379f..881ef14660bc 100644 --- a/drivers/xen/pvcalls-front.h +++ b/drivers/xen/pvcalls-front.h @@ -12,7 +12,7 @@ int pvcalls_front_bind(struct socket *sock, int pvcalls_front_listen(struct socket *sock, int backlog); int pvcalls_front_accept(struct socket *sock, struct socket *newsock, - int flags); + struct proto_accept_arg *arg); int pvcalls_front_sendmsg(struct socket *sock, struct msghdr *msg, size_t len); -- 2.51.0 From 98a5cfd2320966f40fe049a9855f8787f0126825 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Wed, 5 Feb 2025 09:43:31 +0100 Subject: [PATCH 09/16] x86/xen: fix xen_hypercall_hvm() to not clobber %rbx xen_hypercall_hvm(), which is used when running as a Xen PVH guest at most only once during early boot, is clobbering %rbx. Depending on whether the caller relies on %rbx to be preserved across the call or not, this clobbering might result in an early crash of the system. This can be avoided by using an already saved register instead of %rbx. Fixes: b4845bb63838 ("x86/xen: add central hypercall functions") Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Reviewed-by: Andrew Cooper Signed-off-by: Juergen Gross --- arch/x86/xen/xen-head.S | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 9252652afe59..72f28d66e0e5 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -117,8 +117,8 @@ SYM_FUNC_START(xen_hypercall_hvm) pop %ebx pop %eax #else - lea xen_hypercall_amd(%rip), %rbx - cmp %rax, %rbx + lea xen_hypercall_amd(%rip), %rcx + cmp %rax, %rcx #ifdef CONFIG_FRAME_POINTER pop %rax /* Dummy pop. */ #endif -- 2.51.0 From 0bd797b801bd8ee06c822844e20d73aaea0878dd Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Wed, 5 Feb 2025 10:07:56 +0100 Subject: [PATCH 10/16] x86/xen: add FRAME_END to xen_hypercall_hvm() xen_hypercall_hvm() is missing a FRAME_END at the end, add it. Reported-by: kernel test robot Closes: https://lore.kernel.org/oe-kbuild-all/202502030848.HTNTTuo9-lkp@intel.com/ Fixes: b4845bb63838 ("x86/xen: add central hypercall functions") Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Reviewed-by: Andrew Cooper Signed-off-by: Juergen Gross --- arch/x86/xen/xen-head.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 72f28d66e0e5..4e481b0eefc9 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -132,6 +132,7 @@ SYM_FUNC_START(xen_hypercall_hvm) pop %rcx pop %rax #endif + FRAME_END /* Use correct hypercall function. */ jz xen_hypercall_amd jmp xen_hypercall_intel -- 2.51.0 From aaf5eefd374b6e006e1c224a2b37bac9d3737aa2 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Wed, 5 Feb 2025 11:24:47 +0100 Subject: [PATCH 11/16] x86/xen: remove unneeded dummy push from xen_hypercall_hvm() Stack alignment of the kernel in 64-bit mode is 8, not 16, so the dummy push in xen_hypercall_hvm() for aligning the stack to 16 bytes can be removed. Signed-off-by: Juergen Gross Reviewed-by: Jan Beulich Reviewed-by: Andrew Cooper Signed-off-by: Juergen Gross --- arch/x86/xen/xen-head.S | 6 ------ 1 file changed, 6 deletions(-) diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index 4e481b0eefc9..894edf8d6d62 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -100,9 +100,6 @@ SYM_FUNC_START(xen_hypercall_hvm) push %r10 push %r9 push %r8 -#ifdef CONFIG_FRAME_POINTER - pushq $0 /* Dummy push for stack alignment. */ -#endif #endif /* Set the vendor specific function. */ call __xen_hypercall_setfunc @@ -119,9 +116,6 @@ SYM_FUNC_START(xen_hypercall_hvm) #else lea xen_hypercall_amd(%rip), %rcx cmp %rax, %rcx -#ifdef CONFIG_FRAME_POINTER - pop %rax /* Dummy pop. */ -#endif pop %r8 pop %r9 pop %r10 -- 2.51.0 From 85fcb57c983f423180ba6ec5d0034242da05cc54 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 10 Feb 2025 08:43:39 +0100 Subject: [PATCH 12/16] xen/swiotlb: relax alignment requirements When mapping a buffer for DMA via .map_page or .map_sg DMA operations, there is no need to check the machine frames to be aligned according to the mapped areas size. All what is needed in these cases is that the buffer is contiguous at machine level. So carve out the alignment check from range_straddles_page_boundary() and move it to a helper called by xen_swiotlb_alloc_coherent() and xen_swiotlb_free_coherent() directly. Fixes: 9f40ec84a797 ("xen/swiotlb: add alignment check for dma buffers") Reported-by: Jan Vejvalka Tested-by: Jan Vejvalka Signed-off-by: Juergen Gross Reviewed-by: Stefano Stabellini Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index a337edcf8faf..26c62e0d34e9 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -74,19 +74,21 @@ static inline phys_addr_t xen_dma_to_phys(struct device *dev, return xen_bus_to_phys(dev, dma_to_phys(dev, dma_addr)); } +static inline bool range_requires_alignment(phys_addr_t p, size_t size) +{ + phys_addr_t algn = 1ULL << (get_order(size) + PAGE_SHIFT); + phys_addr_t bus_addr = pfn_to_bfn(XEN_PFN_DOWN(p)) << XEN_PAGE_SHIFT; + + return IS_ALIGNED(p, algn) && !IS_ALIGNED(bus_addr, algn); +} + static inline int range_straddles_page_boundary(phys_addr_t p, size_t size) { unsigned long next_bfn, xen_pfn = XEN_PFN_DOWN(p); unsigned int i, nr_pages = XEN_PFN_UP(xen_offset_in_page(p) + size); - phys_addr_t algn = 1ULL << (get_order(size) + PAGE_SHIFT); next_bfn = pfn_to_bfn(xen_pfn); - /* If buffer is physically aligned, ensure DMA alignment. */ - if (IS_ALIGNED(p, algn) && - !IS_ALIGNED((phys_addr_t)next_bfn << XEN_PAGE_SHIFT, algn)) - return 1; - for (i = 1; i < nr_pages; i++) if (pfn_to_bfn(++xen_pfn) != ++next_bfn) return 1; @@ -156,7 +158,8 @@ xen_swiotlb_alloc_coherent(struct device *dev, size_t size, *dma_handle = xen_phys_to_dma(dev, phys); if (*dma_handle + size - 1 > dma_mask || - range_straddles_page_boundary(phys, size)) { + range_straddles_page_boundary(phys, size) || + range_requires_alignment(phys, size)) { if (xen_create_contiguous_region(phys, order, fls64(dma_mask), dma_handle) != 0) goto out_free_pages; @@ -182,7 +185,8 @@ xen_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, size = ALIGN(size, XEN_PAGE_SIZE); if (WARN_ON_ONCE(dma_handle + size - 1 > dev->coherent_dma_mask) || - WARN_ON_ONCE(range_straddles_page_boundary(phys, size))) + WARN_ON_ONCE(range_straddles_page_boundary(phys, size) || + range_requires_alignment(phys, size))) return; if (TestClearPageXenRemapped(virt_to_page(vaddr))) -- 2.51.0 From e93ec87286bd1fd30b7389e7a387cfb259f297e3 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 11 Feb 2025 11:16:28 +0100 Subject: [PATCH 13/16] x86/xen: allow larger contiguous memory regions in PV guests Today a PV guest (including dom0) can create 2MB contiguous memory regions for DMA buffers at max. This has led to problems at least with the megaraid_sas driver, which wants to allocate a 2.3MB DMA buffer. The limiting factor is the frame array used to do the hypercall for making the memory contiguous, which has 512 entries and is just a static array in mmu_pv.c. In order to not waste memory for non-PV guests, put the initial frame array into .init.data section and dynamically allocate an array from the .init_after_bootmem hook of PV guests. In case a contiguous memory area larger than the initially supported 2MB is requested, allocate a larger buffer for the frame list. Note that such an allocation is tried only after memory management has been initialized properly, which is tested via a flag being set in the .init_after_bootmem hook. Fixes: 9f40ec84a797 ("xen/swiotlb: add alignment check for dma buffers") Signed-off-by: Juergen Gross Tested-by: Alan Robinson Reviewed-by: Jan Beulich Signed-off-by: Juergen Gross --- arch/x86/xen/mmu_pv.c | 71 +++++++++++++++++++++++++++++++++++++------ 1 file changed, 62 insertions(+), 9 deletions(-) diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 2c70cd35e72c..d078de2c952b 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -111,6 +111,51 @@ static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss; */ static DEFINE_SPINLOCK(xen_reservation_lock); +/* Protected by xen_reservation_lock. */ +#define MIN_CONTIG_ORDER 9 /* 2MB */ +static unsigned int discontig_frames_order = MIN_CONTIG_ORDER; +static unsigned long discontig_frames_early[1UL << MIN_CONTIG_ORDER] __initdata; +static unsigned long *discontig_frames __refdata = discontig_frames_early; +static bool discontig_frames_dyn; + +static int alloc_discontig_frames(unsigned int order) +{ + unsigned long *new_array, *old_array; + unsigned int old_order; + unsigned long flags; + + BUG_ON(order < MIN_CONTIG_ORDER); + BUILD_BUG_ON(sizeof(discontig_frames_early) != PAGE_SIZE); + + new_array = (unsigned long *)__get_free_pages(GFP_KERNEL, + order - MIN_CONTIG_ORDER); + if (!new_array) + return -ENOMEM; + + spin_lock_irqsave(&xen_reservation_lock, flags); + + old_order = discontig_frames_order; + + if (order > discontig_frames_order || !discontig_frames_dyn) { + if (!discontig_frames_dyn) + old_array = NULL; + else + old_array = discontig_frames; + + discontig_frames = new_array; + discontig_frames_order = order; + discontig_frames_dyn = true; + } else { + old_array = new_array; + } + + spin_unlock_irqrestore(&xen_reservation_lock, flags); + + free_pages((unsigned long)old_array, old_order - MIN_CONTIG_ORDER); + + return 0; +} + /* * Note about cr3 (pagetable base) values: * @@ -814,6 +859,9 @@ static void __init xen_after_bootmem(void) SetPagePinned(virt_to_page(level3_user_vsyscall)); #endif xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP); + + if (alloc_discontig_frames(MIN_CONTIG_ORDER)) + BUG(); } static void xen_unpin_page(struct mm_struct *mm, struct page *page, @@ -2203,10 +2251,6 @@ void __init xen_init_mmu_ops(void) memset(dummy_mapping, 0xff, PAGE_SIZE); } -/* Protected by xen_reservation_lock. */ -#define MAX_CONTIG_ORDER 9 /* 2MB */ -static unsigned long discontig_frames[1< MAX_CONTIG_ORDER)) - return -ENOMEM; + if (unlikely(order > discontig_frames_order)) { + if (!discontig_frames_dyn) + return -ENOMEM; + + if (alloc_discontig_frames(order)) + return -ENOMEM; + } memset((void *) vstart, 0, PAGE_SIZE << order); spin_lock_irqsave(&xen_reservation_lock, flags); + in_frames = discontig_frames; + /* 1. Zap current PTEs, remembering MFNs. */ xen_zap_pfn_range(vstart, order, in_frames, NULL); @@ -2358,12 +2409,12 @@ int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) { - unsigned long *out_frames = discontig_frames, in_frame; + unsigned long *out_frames, in_frame; unsigned long flags; int success; unsigned long vstart; - if (unlikely(order > MAX_CONTIG_ORDER)) + if (unlikely(order > discontig_frames_order)) return; vstart = (unsigned long)phys_to_virt(pstart); @@ -2371,6 +2422,8 @@ void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order) spin_lock_irqsave(&xen_reservation_lock, flags); + out_frames = discontig_frames; + /* 1. Find start MFN of contiguous extent. */ in_frame = virt_to_mfn((void *)vstart); -- 2.51.0 From 75ad02318af2e4ae669e26a79f001bd5e1f97472 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Wed, 12 Feb 2025 16:14:38 +0100 Subject: [PATCH 14/16] Xen/swiotlb: mark xen_swiotlb_fixup() __init It's sole user (pci_xen_swiotlb_init()) is __init, too. Signed-off-by: Jan Beulich Reviewed-by: Stefano Stabellini Message-ID: Signed-off-by: Juergen Gross --- drivers/xen/swiotlb-xen.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 26c62e0d34e9..1f65795cf5d7 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -113,7 +113,7 @@ static struct io_tlb_pool *xen_swiotlb_find_pool(struct device *dev, } #ifdef CONFIG_X86 -int xen_swiotlb_fixup(void *buf, unsigned long nslabs) +int __init xen_swiotlb_fixup(void *buf, unsigned long nslabs) { int rc; unsigned int order = get_order(IO_TLB_SEGSIZE << IO_TLB_SHIFT); -- 2.51.0 From 35bc1883733c81ff307c9c73bd00191313e651af Mon Sep 17 00:00:00 2001 From: Inochi Amaoto Date: Thu, 13 Feb 2025 08:38:45 +0800 Subject: [PATCH 15/16] dt-bindings: riscv: add bfloat16 ISA extension description Add description for the BFloat16 precision Floating-Point ISA extension, (Zfbfmin, Zvfbfmin, Zvfbfwma). which was ratified in commit 4dc23d62 ("Added Chapter title to BF16") of the riscv-isa-manual. Signed-off-by: Inochi Amaoto Acked-by: Conor Dooley Link: https://lore.kernel.org/r/20250213003849.147358-2-inochiama@gmail.com Signed-off-by: Alexandre Ghiti --- .../devicetree/bindings/riscv/extensions.yaml | 45 +++++++++++++++++++ 1 file changed, 45 insertions(+) diff --git a/Documentation/devicetree/bindings/riscv/extensions.yaml b/Documentation/devicetree/bindings/riscv/extensions.yaml index 9c7dd7e75e0c..0a1f1a76d129 100644 --- a/Documentation/devicetree/bindings/riscv/extensions.yaml +++ b/Documentation/devicetree/bindings/riscv/extensions.yaml @@ -329,6 +329,12 @@ properties: instructions, as ratified in commit 056b6ff ("Zfa is ratified") of riscv-isa-manual. + - const: zfbfmin + description: + The standard Zfbfmin extension which provides minimal support for + 16-bit half-precision brain floating-point instructions, as ratified + in commit 4dc23d62 ("Added Chapter title to BF16") of riscv-isa-manual. + - const: zfh description: The standard Zfh extension for 16-bit half-precision binary @@ -525,6 +531,18 @@ properties: in commit 6f702a2 ("Vector extensions are now ratified") of riscv-v-spec. + - const: zvfbfmin + description: + The standard Zvfbfmin extension for minimal support for vectored + 16-bit half-precision brain floating-point instructions, as ratified + in commit 4dc23d62 ("Added Chapter title to BF16") of riscv-isa-manual. + + - const: zvfbfwma + description: + The standard Zvfbfwma extension for vectored half-precision brain + floating-point widening multiply-accumulate instructions, as ratified + in commit 4dc23d62 ("Added Chapter title to BF16") of riscv-isa-manual. + - const: zvfh description: The standard Zvfh extension for vectored half-precision @@ -663,6 +681,33 @@ properties: then: contains: const: zca + # Zfbfmin depends on F + - if: + contains: + const: zfbfmin + then: + contains: + const: f + # Zvfbfmin depends on V or Zve32f + - if: + contains: + const: zvfbfmin + then: + oneOf: + - contains: + const: v + - contains: + const: zve32f + # Zvfbfwma depends on Zfbfmin and Zvfbfmin + - if: + contains: + const: zvfbfwma + then: + allOf: + - contains: + const: zfbfmin + - contains: + const: zvfbfmin allOf: # Zcf extension does not exist on rv64 -- 2.51.0 From e186c28dda11e8d6d829b08b9da2ec7c342edd78 Mon Sep 17 00:00:00 2001 From: Inochi Amaoto Date: Thu, 13 Feb 2025 08:38:46 +0800 Subject: [PATCH 16/16] riscv: add ISA extension parsing for bfloat16 ISA extension MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Add parsing for Zfbmin, Zvfbfmin, Zvfbfwma ISA extension which were ratified in 4dc23d62 ("Added Chapter title to BF16") of the riscv-isa-manual. Signed-off-by: Inochi Amaoto Reviewed-by: Clément Léger Link: https://lore.kernel.org/r/20250213003849.147358-3-inochiama@gmail.com Signed-off-by: Alexandre Ghiti --- arch/riscv/include/asm/hwcap.h | 3 +++ arch/riscv/kernel/cpufeature.c | 35 ++++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h index 869da082252a..14cc29f2a723 100644 --- a/arch/riscv/include/asm/hwcap.h +++ b/arch/riscv/include/asm/hwcap.h @@ -100,6 +100,9 @@ #define RISCV_ISA_EXT_ZICCRSE 91 #define RISCV_ISA_EXT_SVADE 92 #define RISCV_ISA_EXT_SVADU 93 +#define RISCV_ISA_EXT_ZFBFMIN 94 +#define RISCV_ISA_EXT_ZVFBFMIN 95 +#define RISCV_ISA_EXT_ZVFBFWMA 96 #define RISCV_ISA_EXT_XLINUXENVCFG 127 diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index c0916ed318c2..40021459a257 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -76,6 +76,15 @@ bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned i } EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); +static int riscv_ext_f_depends(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_f)) + return 0; + + return -EPROBE_DEFER; +} + static int riscv_ext_zicbom_validate(const struct riscv_isa_ext_data *data, const unsigned long *isa_bitmap) { @@ -136,6 +145,28 @@ static int riscv_ext_zcf_validate(const struct riscv_isa_ext_data *data, return -EPROBE_DEFER; } +static int riscv_vector_f_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_V)) + return -EINVAL; + + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVE32F)) + return 0; + + return -EPROBE_DEFER; +} + +static int riscv_ext_zvfbfwma_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZFBFMIN) && + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVFBFMIN)) + return 0; + + return -EPROBE_DEFER; +} + static int riscv_ext_svadu_validate(const struct riscv_isa_ext_data *data, const unsigned long *isa_bitmap) { @@ -341,6 +372,7 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = { __RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS), __RISCV_ISA_EXT_DATA(zawrs, RISCV_ISA_EXT_ZAWRS), __RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA), + __RISCV_ISA_EXT_DATA_VALIDATE(zfbfmin, RISCV_ISA_EXT_ZFBFMIN, riscv_ext_f_depends), __RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH), __RISCV_ISA_EXT_DATA(zfhmin, RISCV_ISA_EXT_ZFHMIN), __RISCV_ISA_EXT_DATA(zca, RISCV_ISA_EXT_ZCA), @@ -373,6 +405,9 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = { __RISCV_ISA_EXT_SUPERSET(zve64d, RISCV_ISA_EXT_ZVE64D, riscv_zve64d_exts), __RISCV_ISA_EXT_SUPERSET(zve64f, RISCV_ISA_EXT_ZVE64F, riscv_zve64f_exts), __RISCV_ISA_EXT_SUPERSET(zve64x, RISCV_ISA_EXT_ZVE64X, riscv_zve64x_exts), + __RISCV_ISA_EXT_DATA_VALIDATE(zvfbfmin, RISCV_ISA_EXT_ZVFBFMIN, riscv_vector_f_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvfbfwma, RISCV_ISA_EXT_ZVFBFWMA, + riscv_ext_zvfbfwma_validate), __RISCV_ISA_EXT_DATA(zvfh, RISCV_ISA_EXT_ZVFH), __RISCV_ISA_EXT_DATA(zvfhmin, RISCV_ISA_EXT_ZVFHMIN), __RISCV_ISA_EXT_DATA(zvkb, RISCV_ISA_EXT_ZVKB), -- 2.51.0