[PATCH 6.18.y 0/6] cBPF JIT spray hardening

[PATCH 6.18.y 0/6] cBPF JIT spray hardening

[Pawan Gupta]

Hi,

These backports harden BPF JIT against spectre-v2 class of attacks. Without
a predictor flush, execution of new BPF program may use stale prediction
left behind by the freed one.

To avoid this, issue an IBPB flush on all CPUs on JIT program allocation.
The flush is conditional to spectre-v2 mitigation applied.

Patch 1-2: Adds the predictor flush hook and enables it on x86 via IBPB.

	  bpf: Support for hardening against JIT spraying
	  x86/bugs: Enable IBPB flush on BPF JIT allocation

Patch 3-6: Narrow the flush to only unprivileged JIT allocations
	   to avoid redundant flushes. Also adds pack-selection changes
	   that minimizes flushes.

	  bpf: Restrict JIT predictor flush to cBPF
	  bpf: Skip redundant IBPB in pack allocator
	  bpf: Prefer packs that won't trigger an IBPB flush on allocation
	  bpf: Prefer dirty packs for eBPF allocations

Patches 1 & 2 had minor header conflicts. Patch 3 had a few conflicts in
bpf_int_jit_compile(), majorly loongarch bpf_int_jit_compile() doesn't use
pack allocator, dropped was_classic hunk.

x86 builds and boots fine in a VM. I don't have build infra for other
arches, relying on the bots for the builds.

---
Pawan Gupta (6):
      bpf: Support for hardening against JIT spraying
      x86/bugs: Enable IBPB flush on BPF JIT allocation
      bpf: Restrict JIT predictor flush to cBPF
      bpf: Skip redundant IBPB in pack allocator
      bpf: Prefer packs that won't trigger an IBPB flush on allocation
      bpf: Prefer dirty packs for eBPF allocations

 arch/arm64/net/bpf_jit_comp.c        |  4 +--
 arch/loongarch/net/bpf_jit.c         |  2 +-
 arch/powerpc/net/bpf_jit_comp.c      |  4 +--
 arch/riscv/net/bpf_jit_comp64.c      |  2 +-
 arch/riscv/net/bpf_jit_core.c        |  3 +-
 arch/x86/include/asm/nospec-branch.h |  4 +++
 arch/x86/kernel/cpu/bugs.c           | 50 +++++++++++++++++++++++---
 arch/x86/net/bpf_jit_comp.c          |  5 +--
 include/linux/filter.h               | 15 ++++++--
 kernel/bpf/core.c                    | 68 ++++++++++++++++++++++++++++++++----
 kernel/bpf/dispatcher.c              |  2 +-
 11 files changed, 136 insertions(+), 23 deletions(-)
---
base-commit: e46dc0adfe39724bcf52cea47b8f9c9aed86a394
change-id: 20260713-cbpf-jit-spray-hardening-6-18-y-a028879c779c

Best regards,
--  
Pawan

[PATCH 6.18.y 1/6] bpf: Support for hardening against JIT spraying

[Pawan Gupta]

commit 96cce16e26dd02a8678f1e87f88a4b5cdb63b995 upstream.

The BPF JIT allocator packs many small programs into larger executable
allocations and reuses space within those allocations as programs are
loaded and freed. When fresh code is written into space that a previous
program occupied, an indirect jump into the new program can reuse a branch
prediction left behind by the old one.

Flush the indirect branch predictors before reusing JIT memory so that
indirect jumps into a newly written program don't reuse predictions from an
old program that occupied the same space.

Introduce bpf_arch_pred_flush_enabled static key and bpf_arch_pred_flush
static call for flushing the branch predictors on JIT memory reuse.
Architectures that need a flush, can update it to a predictor flush
function. By default, its a NOP and does not emit any CALL.

Allocations larger than a pack are not covered by this flush. That is safe
because cBPF programs (the unprivileged attack surface) are bounded well
below a pack size. Issue a warning if this assumption is ever violated
while the flush is active.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/filter.h | 10 ++++++++++
 kernel/bpf/core.c      | 19 +++++++++++++++++++
 2 files changed, 29 insertions(+)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index cf7a0bce1bb6..3c4dd718bece 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -22,6 +22,7 @@
 #include <linux/vmalloc.h>
 #include <linux/sockptr.h>
 #include <crypto/sha1.h>
+#include <linux/static_call.h>
 #include <linux/u64_stats_sync.h>
 
 #include <net/sch_generic.h>
@@ -1266,6 +1267,15 @@ extern long bpf_jit_limit_max;
 
 typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
 
+/*
+ * Flush the indirect branch predictors before reusing JIT memory, so that
+ * indirect jumps into a newly written program don't reuse predictions left
+ * behind by an old program that occupied the same space.
+ */
+void bpf_arch_pred_flush(void);
+DECLARE_STATIC_CALL(bpf_arch_pred_flush, bpf_arch_pred_flush);
+DECLARE_STATIC_KEY_FALSE(bpf_pred_flush_enabled);
+
 void bpf_jit_fill_hole_with_zero(void *area, unsigned int size);
 
 struct bpf_binary_header *
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 931a4ddd8530..a043fccb917e 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -21,6 +21,7 @@
 #include <crypto/sha1.h>
 #include <linux/filter.h>
 #include <linux/skbuff.h>
+#include <linux/static_call.h>
 #include <linux/vmalloc.h>
 #include <linux/prandom.h>
 #include <linux/bpf.h>
@@ -864,6 +865,15 @@ void bpf_jit_fill_hole_with_zero(void *area, unsigned int size)
 	memset(area, 0, size);
 }
 
+DEFINE_STATIC_CALL_NULL(bpf_arch_pred_flush, bpf_arch_pred_flush);
+
+/*
+ * Enabled once bpf_arch_pred_flush points at a real flush routine. Lets the
+ * pack allocator test "is a predictor flush wired up at all" with a cheap
+ * static branch instead of repeatedly querying the static call target.
+ */
+DEFINE_STATIC_KEY_FALSE(bpf_pred_flush_enabled);
+
 #define BPF_PROG_SIZE_TO_NBITS(size)	(round_up(size, BPF_PROG_CHUNK_SIZE) / BPF_PROG_CHUNK_SIZE)
 
 static DEFINE_MUTEX(pack_mutex);
@@ -923,6 +933,14 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
 
 	mutex_lock(&pack_mutex);
 	if (size > BPF_PROG_PACK_SIZE) {
+		/*
+		 * Allocations larger than a pack get their own pages, and
+		 * predictors are not flushed for such allocation. This is only
+		 * safe because cBPF programs (the unprivileged attack surface)
+		 * are bounded well below a pack size.
+		 */
+		if (static_branch_unlikely(&bpf_pred_flush_enabled))
+			pr_warn_once("BPF: Predictors not flushed for allocations greater than BPF_PROG_PACK_SIZE\n");
 		size = round_up(size, PAGE_SIZE);
 		ptr = bpf_jit_alloc_exec(size);
 		if (ptr) {
@@ -953,6 +971,7 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
 	pos = 0;
 
 found_free_area:
+	static_call_cond(bpf_arch_pred_flush)();
 	bitmap_set(pack->bitmap, pos, nbits);
 	ptr = (void *)(pack->ptr) + (pos << BPF_PROG_CHUNK_SHIFT);
 

-- 
2.43.0

Re: [PATCH 6.18.y 1/6] bpf: Support for hardening against JIT spraying

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:

Pre-existing issues:
- [High] BPF programs larger than BPF_PROG_PACK_SIZE bypass the new predictor flush during allocation, leaving large privileged programs vulnerable to Spectre v2 JIT spraying.
--

--- Patch [1]: [PATCH 6.18.y 1/6] bpf: Support for hardening against JIT spraying ---
commit cb1a8f614dfc8fdb1bb7a2e56154f4f8e2cb7a53
Author: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>

bpf: Support for hardening against JIT spraying

This commit introduces a mechanism to flush indirect branch predictors before
reusing JIT memory. The goal is to ensure indirect jumps in a newly written
program don't reuse branch predictions left behind by an old program that
previously occupied the same space.

> --- a/kernel/bpf/core.c
> +++ b/kernel/bpf/core.c
[ ... ]
> @@ -923,6 +933,14 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
>  
>  	mutex_lock(&pack_mutex);
>  	if (size > BPF_PROG_PACK_SIZE) {
> +		/*
> +		 * Allocations larger than a pack get their own pages, and
> +		 * predictors are not flushed for such allocation. This is only
> +		 * safe because cBPF programs (the unprivileged attack surface)
> +		 * are bounded well below a pack size.
> +		 */
> +		if (static_branch_unlikely(&bpf_pred_flush_enabled))
> +			pr_warn_once("BPF: Predictors not flushed for allocations greater than BPF_PROG_PACK_SIZE\n");
>  		size = round_up(size, PAGE_SIZE);
>  		ptr = bpf_jit_alloc_exec(size);

[Severity: High]
This isn't a bug introduced by this patch, but does this logic leave large
privileged eBPF programs vulnerable to Spectre v2 attacks?

The comment here justifies skipping the flush by stating that cBPF programs
(the unprivileged attack surface) are bounded well below a pack size. However,
in a Spectre v2 attack, the newly allocated program is actually the victim,
not the attacker.

If an unprivileged attacker loads and frees a small cBPF program to mistrain
the CPU branch predictors, and a privileged user subsequently loads a large
eBPF program (> BPF_PROG_PACK_SIZE), bpf_prog_pack_alloc() allocates it via
bpf_jit_alloc_exec().

If it reuses the same virtual memory, it explicitly bypasses the new
bpf_arch_pred_flush() call, forcing the privileged eBPF program to execute
using the attacker's leftover mistrained branch predictions.

Could large allocations also receive a predictor flush to ensure privileged
programs are protected?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260713-cbpf-jit-spray-hardening-6-18-y-v1-0-755f60c55705@linux.intel.com?part=1

[PATCH 6.18.y 2/6] x86/bugs: Enable IBPB flush on BPF JIT allocation

[Pawan Gupta]

commit a3af84b0fa00ead01fcd0e28b5d773ff25990a0d upstream.

Enable hardening against JIT spraying when Spectre-v2 mitigations are in
use. Specifically, issue an IBPB flush on BPF JIT memory reuse. Skip
enabling the IBPB flush if the BPF dispatcher is already using a retpoline
sequence.

This hardening applies only when BPF-JIT is in use. Guard the enabling
under CONFIG_BPF_JIT so that bugs.c still builds with CONFIG_BPF_JIT=n.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/x86/include/asm/nospec-branch.h |  4 +++
 arch/x86/kernel/cpu/bugs.c           | 50 ++++++++++++++++++++++++++++++++----
 2 files changed, 49 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 08ed5a2e46a5..71e9861a16a8 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -386,6 +386,10 @@ extern void srso_alias_return_thunk(void);
 extern void entry_untrain_ret(void);
 extern void write_ibpb(void);
 
+#ifdef CONFIG_BPF_JIT
+extern void bpf_arch_ibpb(void);
+#endif
+
 #ifdef CONFIG_X86_64
 extern void clear_bhb_loop(void);
 #endif
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d7fa03bf51b4..fd0b7880cf7e 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -16,6 +16,7 @@
 #include <linux/sched/smt.h>
 #include <linux/pgtable.h>
 #include <linux/bpf.h>
+#include <linux/filter.h>
 
 #include <asm/spec-ctrl.h>
 #include <asm/cmdline.h>
@@ -1796,8 +1797,21 @@ static inline const char *spectre_v2_module_string(void)
 {
 	return spectre_v2_bad_module ? " - vulnerable module loaded" : "";
 }
+
+/*
+ * The "retpoline sequence" is the "call;mov;ret" sequence that
+ * replaces normal indirect branch instructions. Differentiate
+ * *the* retpoline sequence from the LFENCE-prefixed indirect
+ * branches that simply use the retpoline infrastructure.
+ */
+static inline bool retpoline_seq_enabled(void)
+{
+	return boot_cpu_has(X86_FEATURE_RETPOLINE) && !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE);
+}
+
 #else
 static inline const char *spectre_v2_module_string(void) { return ""; }
+static inline bool retpoline_seq_enabled(void) { return false; }
 #endif
 
 #define SPECTRE_V2_LFENCE_MSG "WARNING: LFENCE mitigation is not recommended for this CPU, data leaks possible!\n"
@@ -2240,8 +2254,7 @@ static void __init bhi_apply_mitigation(void)
 		return;
 
 	/* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */
-	if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
-	    !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) {
+	if (retpoline_seq_enabled()) {
 		spec_ctrl_disable_kernel_rrsba();
 		if (rrsba_disabled)
 			return;
@@ -2383,6 +2396,27 @@ static void __init spectre_v2_update_mitigation(void)
 		pr_info("%s\n", spectre_v2_strings[spectre_v2_enabled]);
 }
 
+#ifdef CONFIG_BPF_JIT
+static void __bpf_arch_ibpb(void *unused)
+{
+	write_ibpb();
+}
+
+void bpf_arch_ibpb(void)
+{
+	on_each_cpu(__bpf_arch_ibpb, NULL, 1);
+}
+
+static bool __init cpu_wants_ibpb_bpf(void)
+{
+	/* A genuine retpoline already neutralizes ring0 indirect predictions */
+	if (retpoline_seq_enabled())
+		return false;
+
+	return boot_cpu_has(X86_FEATURE_IBPB);
+}
+#endif
+
 static void __init spectre_v2_apply_mitigation(void)
 {
 	if (spectre_v2_enabled == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled())
@@ -2459,6 +2493,14 @@ static void __init spectre_v2_apply_mitigation(void)
 		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
 		pr_info("Enabling Restricted Speculation for firmware calls\n");
 	}
+
+#ifdef CONFIG_BPF_JIT
+	if (cpu_wants_ibpb_bpf()) {
+		static_call_update(bpf_arch_pred_flush, bpf_arch_ibpb);
+		static_branch_enable(&bpf_pred_flush_enabled);
+		pr_info("Enabling IBPB for BPF\n");
+	}
+#endif
 }
 
 static void update_stibp_msr(void * __unused)
@@ -3544,9 +3586,7 @@ static const char *spectre_bhi_state(void)
 		return "; BHI: BHI_DIS_S";
 	else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP))
 		return "; BHI: SW loop, KVM: SW loop";
-	else if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
-		 !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) &&
-		 rrsba_disabled)
+	else if (retpoline_seq_enabled() && rrsba_disabled)
 		return "; BHI: Retpoline";
 	else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_VMEXIT))
 		return "; BHI: Vulnerable, KVM: SW loop";

-- 
2.43.0

Re: [PATCH 6.18.y 2/6] x86/bugs: Enable IBPB flush on BPF JIT allocation

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] BPF JIT allocations trigger a system-wide IPI broadcast for IBPB flushing, allowing an attacker to cause a severe local Denial of Service (DoS) by spamming BPF program loads.
--

--- Patch [2]: [PATCH 6.18.y 2/6] x86/bugs: Enable IBPB flush on BPF JIT allocation ---
commit 6fe177facacbbf6baebd63b419b7a3255bc1668f
Author: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>

x86/bugs: Enable IBPB flush on BPF JIT allocation

This commit enables an IBPB flush on BPF JIT memory reuse to mitigate
Spectre-v2 JIT spraying attacks. It adds bpf_arch_ibpb() to broadcast the
required MSR write system-wide when BPF JIT is active.

> diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
> index d7fa03bf51b45..fd0b7880cf7e5 100644
> --- a/arch/x86/kernel/cpu/bugs.c
> +++ b/arch/x86/kernel/cpu/bugs.c
[ ... ]
> @@ -2383,6 +2396,27 @@ static void __init spectre_v2_update_mitigation(void)
>  		pr_info("%s\n", spectre_v2_strings[spectre_v2_enabled]);
>  }
>  
> +#ifdef CONFIG_BPF_JIT
> +static void __bpf_arch_ibpb(void *unused)
> +{
> +	write_ibpb();
> +}
> +
> +void bpf_arch_ibpb(void)
> +{
> +	on_each_cpu(__bpf_arch_ibpb, NULL, 1);
> +}

[Severity: High]
Does this introduce a potential local denial of service vector?

During BPF JIT compilation, bpf_prog_pack_alloc() invokes the predictor
flush unconditionally:

kernel/bpf/core.c:bpf_prog_pack_alloc() {
    ...
found_free_area:
	static_call_cond(bpf_arch_pred_flush)();
    ...
}

Since this results in calling bpf_arch_ibpb() which uses on_each_cpu() with
wait=1, won't this trigger a synchronous system-wide IPI broadcast on every
BPF program load?

If a user spams BPF program loads or unloads in a tight loop, could this
create an IPI storm that starves other tasks and locks up the system?

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260713-cbpf-jit-spray-hardening-6-18-y-v1-0-755f60c55705@linux.intel.com?part=2

[PATCH 6.18.y 3/6] bpf: Restrict JIT predictor flush to cBPF

[Pawan Gupta]

commit 0bb99f2cfaae6822d734d69722de30af823efdf3 upstream.

Currently predictor flush on memory reuse is done for all BPF JIT
allocations, but only cBPF programs can be loaded by an unprivileged user.
eBPF is privileged by default, and flushing predictors for all CPUs on
every eBPF reuse penalizes the common case for no security benefit.

eBPF allocations can be frequent on busy systems, only flush predictors
for cBPF programs. Trampoline and dispatcher allocations also skip the
flush as they are eBPF-only.

  [pawan: backport had various conflicts in arches bpf_int_jit_compile().
	  loongarch bpf_int_jit_compile() doesn't use pack allocator,
	  dropped was_classic hunk. ]

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm64/net/bpf_jit_comp.c   |  4 ++--
 arch/loongarch/net/bpf_jit.c    |  2 +-
 arch/powerpc/net/bpf_jit_comp.c |  4 ++--
 arch/riscv/net/bpf_jit_comp64.c |  2 +-
 arch/riscv/net/bpf_jit_core.c   |  3 ++-
 arch/x86/net/bpf_jit_comp.c     |  5 +++--
 include/linux/filter.h          |  5 +++--
 kernel/bpf/core.c               | 13 ++++++++-----
 kernel/bpf/dispatcher.c         |  2 +-
 9 files changed, 23 insertions(+), 17 deletions(-)

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 873c1b784a87..c563bae8fce1 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -2117,7 +2117,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 	image_size = extable_offset + extable_size;
 	ro_header = bpf_jit_binary_pack_alloc(image_size, &ro_image_ptr,
 					      sizeof(u64), &header, &image_ptr,
-					      jit_fill_hole);
+					      jit_fill_hole, was_classic);
 	if (!ro_header) {
 		prog = orig_prog;
 		goto out_off;
@@ -2754,7 +2754,7 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
 
 void *arch_alloc_bpf_trampoline(unsigned int size)
 {
-	return bpf_prog_pack_alloc(size, jit_fill_hole);
+	return bpf_prog_pack_alloc(size, jit_fill_hole, false);
 }
 
 void arch_free_bpf_trampoline(void *image, unsigned int size)
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index e9d666508ae2..a000620ca99d 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -1474,7 +1474,7 @@ static void invoke_bpf_mod_ret(struct jit_ctx *ctx, struct bpf_tramp_links *tl,
 
 void *arch_alloc_bpf_trampoline(unsigned int size)
 {
-	return bpf_prog_pack_alloc(size, jit_fill_hole);
+	return bpf_prog_pack_alloc(size, jit_fill_hole, false);
 }
 
 void arch_free_bpf_trampoline(void *image, unsigned int size)
diff --git a/arch/powerpc/net/bpf_jit_comp.c b/arch/powerpc/net/bpf_jit_comp.c
index 189ef7b72081..cedab25aa3a8 100644
--- a/arch/powerpc/net/bpf_jit_comp.c
+++ b/arch/powerpc/net/bpf_jit_comp.c
@@ -246,7 +246,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
 	alloclen = proglen + FUNCTION_DESCR_SIZE + fixup_len + extable_len;
 
 	fhdr = bpf_jit_binary_pack_alloc(alloclen, &fimage, 4, &hdr, &image,
-					      bpf_jit_fill_ill_insns);
+					 bpf_jit_fill_ill_insns, bpf_prog_was_classic(fp));
 	if (!fhdr) {
 		fp = org_fp;
 		goto out_addrs;
@@ -468,7 +468,7 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
 
 void *arch_alloc_bpf_trampoline(unsigned int size)
 {
-	return bpf_prog_pack_alloc(size, bpf_jit_fill_ill_insns);
+	return bpf_prog_pack_alloc(size, bpf_jit_fill_ill_insns, false);
 }
 
 void arch_free_bpf_trampoline(void *image, unsigned int size)
diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
index 45cbc7c6fe49..9e9e6dcfc482 100644
--- a/arch/riscv/net/bpf_jit_comp64.c
+++ b/arch/riscv/net/bpf_jit_comp64.c
@@ -1268,7 +1268,7 @@ int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
 
 void *arch_alloc_bpf_trampoline(unsigned int size)
 {
-	return bpf_prog_pack_alloc(size, bpf_fill_ill_insns);
+	return bpf_prog_pack_alloc(size, bpf_fill_ill_insns, false);
 }
 
 void arch_free_bpf_trampoline(void *image, unsigned int size)
diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c
index 191bf0e66c82..e4ab5bb9c9f6 100644
--- a/arch/riscv/net/bpf_jit_core.c
+++ b/arch/riscv/net/bpf_jit_core.c
@@ -125,7 +125,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 				bpf_jit_binary_pack_alloc(prog_size + extable_size,
 							  &jit_data->ro_image, sizeof(u32),
 							  &jit_data->header, &jit_data->image,
-							  bpf_fill_ill_insns);
+							  bpf_fill_ill_insns,
+							  bpf_prog_was_classic(prog));
 			if (!jit_data->ro_header) {
 				prog = orig_prog;
 				goto out_offset;
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 788671a32d8e..c3798cab3b7d 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -3447,7 +3447,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 
 void *arch_alloc_bpf_trampoline(unsigned int size)
 {
-	return bpf_prog_pack_alloc(size, jit_fill_hole);
+	return bpf_prog_pack_alloc(size, jit_fill_hole, false);
 }
 
 void arch_free_bpf_trampoline(void *image, unsigned int size)
@@ -3780,7 +3780,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 			/* allocate module memory for x86 insns and extable */
 			header = bpf_jit_binary_pack_alloc(roundup(proglen, align) + extable_size,
 							   &image, align, &rw_header, &rw_image,
-							   jit_fill_hole);
+							   jit_fill_hole,
+							   bpf_prog_was_classic(prog));
 			if (!header) {
 				prog = orig_prog;
 				goto out_addrs;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 3c4dd718bece..2469fd2e4015 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1290,7 +1290,7 @@ void bpf_jit_free(struct bpf_prog *fp);
 struct bpf_binary_header *
 bpf_jit_binary_pack_hdr(const struct bpf_prog *fp);
 
-void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns);
+void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns, bool was_classic);
 void bpf_prog_pack_free(void *ptr, u32 size);
 
 static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
@@ -1304,7 +1304,8 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image,
 			  unsigned int alignment,
 			  struct bpf_binary_header **rw_hdr,
 			  u8 **rw_image,
-			  bpf_jit_fill_hole_t bpf_fill_ill_insns);
+			  bpf_jit_fill_hole_t bpf_fill_ill_insns,
+			  bool was_classic);
 int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header,
 				 struct bpf_binary_header *rw_header);
 void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header,
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index a043fccb917e..338a806e25c0 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -924,7 +924,7 @@ static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_ins
 	return NULL;
 }
 
-void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
+void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns, bool was_classic)
 {
 	unsigned int nbits = BPF_PROG_SIZE_TO_NBITS(size);
 	struct bpf_prog_pack *pack;
@@ -939,7 +939,7 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
 		 * safe because cBPF programs (the unprivileged attack surface)
 		 * are bounded well below a pack size.
 		 */
-		if (static_branch_unlikely(&bpf_pred_flush_enabled))
+		if (was_classic && static_branch_unlikely(&bpf_pred_flush_enabled))
 			pr_warn_once("BPF: Predictors not flushed for allocations greater than BPF_PROG_PACK_SIZE\n");
 		size = round_up(size, PAGE_SIZE);
 		ptr = bpf_jit_alloc_exec(size);
@@ -971,7 +971,9 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
 	pos = 0;
 
 found_free_area:
-	static_call_cond(bpf_arch_pred_flush)();
+	/* Flush only for cBPF as it may contain a crafted gadget */
+	if (static_branch_unlikely(&bpf_pred_flush_enabled) && was_classic)
+		static_call_cond(bpf_arch_pred_flush)();
 	bitmap_set(pack->bitmap, pos, nbits);
 	ptr = (void *)(pack->ptr) + (pos << BPF_PROG_CHUNK_SHIFT);
 
@@ -1131,7 +1133,8 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr,
 			  unsigned int alignment,
 			  struct bpf_binary_header **rw_header,
 			  u8 **rw_image,
-			  bpf_jit_fill_hole_t bpf_fill_ill_insns)
+			  bpf_jit_fill_hole_t bpf_fill_ill_insns,
+			  bool was_classic)
 {
 	struct bpf_binary_header *ro_header;
 	u32 size, hole, start;
@@ -1144,7 +1147,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **image_ptr,
 
 	if (bpf_jit_charge_modmem(size))
 		return NULL;
-	ro_header = bpf_prog_pack_alloc(size, bpf_fill_ill_insns);
+	ro_header = bpf_prog_pack_alloc(size, bpf_fill_ill_insns, was_classic);
 	if (!ro_header) {
 		bpf_jit_uncharge_modmem(size);
 		return NULL;
diff --git a/kernel/bpf/dispatcher.c b/kernel/bpf/dispatcher.c
index b77db7413f8c..ea2d60dc1fee 100644
--- a/kernel/bpf/dispatcher.c
+++ b/kernel/bpf/dispatcher.c
@@ -145,7 +145,7 @@ void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
 
 	mutex_lock(&d->mutex);
 	if (!d->image) {
-		d->image = bpf_prog_pack_alloc(PAGE_SIZE, bpf_jit_fill_hole_with_zero);
+		d->image = bpf_prog_pack_alloc(PAGE_SIZE, bpf_jit_fill_hole_with_zero, false);
 		if (!d->image)
 			goto out;
 		d->rw_image = bpf_jit_alloc_exec(PAGE_SIZE);

-- 
2.43.0

Re: [PATCH 6.18.y 3/6] bpf: Restrict JIT predictor flush to cBPF

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Bypass of Spectre v2 / Branch History Injection (BHI) mitigation for unprivileged native eBPF programs.
--

--- Patch [3]: [PATCH 6.18.y 3/6] bpf: Restrict JIT predictor flush to cBPF ---
commit 33a895ebe7da61c93f5b498141c865b22c5d29e7
Author: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>

bpf: Restrict JIT predictor flush to cBPF

This commit modifies the BPF JIT allocator to only perform predictor flushes
on memory reuse for cBPF programs. It skips the flush for eBPF allocations
under the assumption that only cBPF programs can be loaded by unprivileged
users.

> diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
> --- a/kernel/bpf/core.c
> +++ b/kernel/bpf/core.c

[ ... ]

> @@ -939,7 +939,7 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
>  		 * safe because cBPF programs (the unprivileged attack surface)
>  		 * are bounded well below a pack size.
>  		 */
> -		if (static_branch_unlikely(&bpf_pred_flush_enabled))
> +		if (was_classic && static_branch_unlikely(&bpf_pred_flush_enabled))

[Severity: High]
Does this inadvertently suppress the warning when unprivileged eBPF is
enabled?

If an administrator sets kernel.unprivileged_bpf_disabled = 0, unprivileged
users can load native eBPF programs (like BPF_PROG_TYPE_SOCKET_FILTER). For
these native eBPF programs, was_classic evaluates to false, which seems to
improperly suppress this warning for large allocations.

>  			pr_warn_once("BPF: Predictors not flushed for allocations greater than BPF_PROG_PACK_SIZE\n");
>  		size = round_up(size, PAGE_SIZE);
>  		ptr = bpf_jit_alloc_exec(size);
> @@ -971,7 +971,9 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns)
>  	pos = 0;
>  
>  found_free_area:
> -	static_call_cond(bpf_arch_pred_flush)();
> +	/* Flush only for cBPF as it may contain a crafted gadget */
> +	if (static_branch_unlikely(&bpf_pred_flush_enabled) && was_classic)
> +		static_call_cond(bpf_arch_pred_flush)();

[Severity: High]
Can an unprivileged attacker use JIT spraying in native eBPF to execute a
speculative execution attack (Spectre v2 / BHI) here?

Since native eBPF programs loaded by an unprivileged user (when
kernel.unprivileged_bpf_disabled = 0) will have was_classic == false, the
predictor flush is entirely skipped. This appears to leave unprivileged
native eBPF exposed to JIT spraying attacks, as the mitigation is completely
bypassed.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260713-cbpf-jit-spray-hardening-6-18-y-v1-0-755f60c55705@linux.intel.com?part=3

[PATCH 6.18.y 4/6] bpf: Skip redundant IBPB in pack allocator

[Pawan Gupta]

commit a23c1c5396a91680703360d1ee28a44657c503c4 upstream.

bpf_prog_pack_alloc() issues IBPB on all CPUs on every cBPF allocation,
even when reusing chunks from an existing pack where no new memory was
touched since the last IBPB.

Since IBPB on all CPUs is heavy, Dave Hansen suggested to track allocation
since last IBPB, and only issue IBPB at reuse for the chunks that have not
seen an IBPB since they were last freed.

Track per-pack whether an IBPB is needed via arch_flush_needed. Set it when
allocating a chunk, reset on IBPB flush. On reuse, conditionally issue the
flush. Since IBPB invalidates all BTB entries, clear the flag on all packs
after flushing.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/core.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 338a806e25c0..49ca543a4111 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -857,6 +857,7 @@ int bpf_jit_add_poke_descriptor(struct bpf_prog *prog,
 struct bpf_prog_pack {
 	struct list_head list;
 	void *ptr;
+	bool arch_flush_needed;
 	unsigned long bitmap[];
 };
 
@@ -910,6 +911,8 @@ static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_ins
 	bpf_fill_ill_insns(pack->ptr, BPF_PROG_PACK_SIZE);
 	bitmap_zero(pack->bitmap, BPF_PROG_PACK_SIZE / BPF_PROG_CHUNK_SIZE);
 
+	if (static_branch_unlikely(&bpf_pred_flush_enabled))
+		pack->arch_flush_needed = true;
 	set_vm_flush_reset_perms(pack->ptr);
 	err = set_memory_rox((unsigned long)pack->ptr,
 			     BPF_PROG_PACK_SIZE / PAGE_SIZE);
@@ -972,8 +975,15 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns, bool
 
 found_free_area:
 	/* Flush only for cBPF as it may contain a crafted gadget */
-	if (static_branch_unlikely(&bpf_pred_flush_enabled) && was_classic)
+	if (static_branch_unlikely(&bpf_pred_flush_enabled) &&
+	    pack->arch_flush_needed &&
+	    was_classic) {
+		struct bpf_prog_pack *p;
+
 		static_call_cond(bpf_arch_pred_flush)();
+		list_for_each_entry(p, &pack_list, list)
+			p->arch_flush_needed = false;
+	}
 	bitmap_set(pack->bitmap, pos, nbits);
 	ptr = (void *)(pack->ptr) + (pos << BPF_PROG_CHUNK_SHIFT);
 
@@ -1011,6 +1021,9 @@ void bpf_prog_pack_free(void *ptr, u32 size)
 		  "bpf_prog_pack bug: missing bpf_arch_text_invalidate?\n");
 
 	bitmap_clear(pack->bitmap, pos, nbits);
+
+	if (static_branch_unlikely(&bpf_pred_flush_enabled))
+		pack->arch_flush_needed = true;
 	if (bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0,
 				       BPF_PROG_CHUNK_COUNT, 0) == 0) {
 		list_del(&pack->list);

-- 
2.43.0

[PATCH 6.18.y 5/6] bpf: Prefer packs that won't trigger an IBPB flush on allocation

[Pawan Gupta]

commit a9b1f19a6a673ba06820898d0f1ad02883ea1639 upstream.

Currently BPF pack allocator picks the chunks from the first available
pack. While this is okay, it naturally leads to more frequent flushes
when there are multiple packs in the system that weren't used since the
last flush.

As an optimization prefer allocating the new programs from packs that
are unused since last flush. When all packs are dirty, allocation forces
a flush and marks all packs clean.

Below are some future optimizations ideas:

  1. Currently, the "dirty" tracking is only done at the pack-level.
     Flush frequency can further be reduced with chunk-level tracking.
     This requires a new bitmap per-pack to track the dirty state.
  2. IBPB flush is done on all CPUs, even if only a single CPU ran the
     BPF program. On a system with hundreds of CPUs this could be a
     major bottleneck forcing hundreds of IPIs to deliver the flush.
     The solution is to track the CPUs where a BPF program ran, and
     issue IBPB only on those CPUs.
  3. Avoid IBPB when flush is already done at other sources (e.g.
     context switch).

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/core.c | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 49ca543a4111..e0ffdd985eb5 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -930,8 +930,8 @@ static struct bpf_prog_pack *alloc_new_pack(bpf_jit_fill_hole_t bpf_fill_ill_ins
 void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns, bool was_classic)
 {
 	unsigned int nbits = BPF_PROG_SIZE_TO_NBITS(size);
-	struct bpf_prog_pack *pack;
-	unsigned long pos;
+	struct bpf_prog_pack *pack, *fallback_pack = NULL;
+	unsigned long pos, fallback_pos = 0;
 	void *ptr = NULL;
 
 	mutex_lock(&pack_mutex);
@@ -963,8 +963,29 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns, bool
 	list_for_each_entry(pack, &pack_list, list) {
 		pos = bitmap_find_next_zero_area(pack->bitmap, BPF_PROG_CHUNK_COUNT, 0,
 						 nbits, 0);
-		if (pos < BPF_PROG_CHUNK_COUNT)
+		if (pos >= BPF_PROG_CHUNK_COUNT)
+			continue;
+		/* Flush not enabled, use any pack */
+		if (!static_branch_unlikely(&bpf_pred_flush_enabled))
 			goto found_free_area;
+		/*
+		 * cBPF reuse of a dirty pack triggers a flush, so prefer a
+		 * clean pack for cBPF. eBPF never flushes, so pick the first
+		 * free pack, dirty or clean.
+		 */
+		if (!was_classic || !pack->arch_flush_needed)
+			goto found_free_area;
+		if (!fallback_pack) {
+			fallback_pack = pack;
+			fallback_pos = pos;
+		}
+	}
+
+	/* No preferred pack found */
+	if (fallback_pack) {
+		pack = fallback_pack;
+		pos = fallback_pos;
+		goto found_free_area;
 	}
 
 	pack = alloc_new_pack(bpf_fill_ill_insns);

-- 
2.43.0

[PATCH 6.18.y 6/6] bpf: Prefer dirty packs for eBPF allocations

[Pawan Gupta]

commit b72e29e0f7ee329d89f86db8700c8ea99b4a370a upstream.

The pack allocator only flushes predictors when reusing a dirty pack for
cBPF, eBPF allocations never trigger a flush. Currently, eBPF picks the
first free pack, which could be a clean pack. As an optimization, leaving
a clean pack for cBPF can avoid flushes.

Prefer dirty packs for eBPF and keep clean packs free for cBPF. This
mirrors the existing cBPF preference for clean packs: each program kind
prefers the pack that avoids an extra flush, and falls back to the other
kind only when no preferred pack has room. eBPF reuse of a dirty pack is
harmless since eBPF being privileged does not flush.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index e0ffdd985eb5..b102704f89bc 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -970,10 +970,10 @@ void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns, bool
 			goto found_free_area;
 		/*
 		 * cBPF reuse of a dirty pack triggers a flush, so prefer a
-		 * clean pack for cBPF. eBPF never flushes, so pick the first
-		 * free pack, dirty or clean.
+		 * clean pack for cBPF. eBPF never flushes, so steer it to a
+		 * dirty pack and keep clean packs free for cBPF.
 		 */
-		if (!was_classic || !pack->arch_flush_needed)
+		if (was_classic ^ pack->arch_flush_needed)
 			goto found_free_area;
 		if (!fallback_pack) {
 			fallback_pack = pack;

-- 
2.43.0